Tensor information for intermediate data

Abstract

Systems, methods, and tools are disclosed for encoding and decoding tensor information for intermediate data. An example apparatus for video encoding may determine tensor metadata associated with intermediate data; encoding the intermediate data and the tensor metadata associated with the intermediate data; and transmitting the encoded intermediate data and the encoded tensor metadata to the second device. An example device for video decoding may receive encoded intermediate data and encoded tensor metadata from a second device; decoding the encoded intermediate data and the encoded tensor metadata; and reconstructing a tensor based on the intermediate data and the tensor metadata.

Description

Cross-references to related applications

[0001] This application claims the benefit of U.S. Provisional Patent Application No. 63 / 527,567, filed July 18, 2023, the contents of which are incorporated herein by reference. Background Technology

[0002] Video coding systems can be used to compress digital video signals, for example, to reduce the storage and / or transmission bandwidth required for such signals. Video coding systems can include, for example, block-based, wavelet-based, and / or object-based systems. Summary of the Invention

[0003] Systems, methods, and tools for encoding and decoding tensor information of intermediate data are disclosed.

[0004] An example apparatus (e.g., for video encoding) could be a first apparatus. The first apparatus can determine tensor metadata associated with intermediate data. The first apparatus can encode the intermediate data and the tensor metadata associated with the intermediate data. The first apparatus can then transmit the encoded intermediate data and the encoded tensor metadata to a second apparatus.

[0005] The first device can be associated with a first part of an artificial intelligence (AI) model. The first part can be the initial portion of the AI ​​model. The second device can be associated with a second part of the AI ​​model. The second part can be the later portion of the AI ​​model. The first device can receive intermediate data as the output of the first part of the AI ​​model.

[0006] The intermediate data can be first intermediate data. The tensor metadata can be first tensor metadata indicating the shape of the first tensor. The first device can determine a second tensor shape associated with the second intermediate data. The second tensor shape can be different from the first tensor shape. The first device can encode the second intermediate data and the second tensor metadata. The second tensor metadata can indicate the second tensor shape. The first device can send the encoded second intermediate data and the encoded second tensor metadata to the second device.

[0007] The intermediate data can be first intermediate data. Tensor metadata can indicate the tensor shape. The first device can determine that second intermediate data is associated with the tensor shape. The first device can encode the second intermediate data and the indication that does not include tensor metadata because the tensor shape has not changed. The first device can send the encoded second intermediate data and the encoded indication to the second device.

[0008] Tensor metadata can indicate at least one of the following: tensor shape, tensor structure information, data type, or encoding algorithm.

[0009] The first device can encode intermediate data by transforming a multidimensional tensor into a one-dimensional tensor and encoding the one-dimensional tensor according to a binary structure.

[0010] The first device can transmit encoded intermediate data and encoded tensor metadata to the second device by transmitting encoded intermediate data in a first frequency band associated with the data channel and encoded tensor metadata in a second frequency band associated with the control channel.

[0011] The first device can encode intermediate data and associated tensor metadata by generating an encoded bitstream. The encoded bitstream can include the encoded intermediate data and the encoded tensor metadata. The first device can send the encoded intermediate data and the encoded tensor metadata to the second device by sending the encoded bitstream to the second device.

[0012] The first device can be a wireless transmit / receive unit (WTRU) or a network entity.

[0013] An example apparatus (e.g., for video decoding) may be a first apparatus. The first apparatus may receive encoded intermediate data and encoded tensor metadata from a second apparatus. The first apparatus may decode the encoded intermediate data and the encoded tensor metadata. The first apparatus may reconstruct the tensor based on the intermediate data and the tensor metadata.

[0014] The second device can be associated with a first part of the artificial intelligence (AI) model. The first part can be the initial part of the AI ​​model. The first device can also be associated with a second part of the AI ​​model. The second part can be the later part of the AI ​​model. The first device can input the reconstructed tensor into the second part of the AI ​​model.

[0015] The intermediate data can be first intermediate data. The tensor metadata can be first tensor metadata indicating the shape of a first tensor, where the tensor is the first tensor. The first device can receive encoded second intermediate data and encoded second tensor metadata from the second device. The first device can decode the encoded second intermediate data and the encoded second tensor metadata. The second tensor metadata can indicate the shape of a second tensor. The first device can reconstruct the second tensor based on the second intermediate data and the second tensor metadata.

[0016] The intermediate data can be first intermediate data. Tensor metadata can indicate the tensor shape. The first device can receive encoded second intermediate data and an encoded indication that does not include tensor metadata because the tensor shape has not changed. The first device can decode the encoded second intermediate data and the indication. The first device can determine the association between the second intermediate data and the tensor shape based on the indication.

[0017] Tensor metadata can indicate at least one of the following: tensor shape, tensor structure information, data type, or encoding algorithm.

[0018] The first device can decode encoded intermediate data by transforming a one-dimensional tensor into a multi-dimensional tensor and decoding the multi-dimensional tensor according to a binary structure.

[0019] The first device can receive encoded intermediate data and encoded tensor metadata from the second device by receiving encoded intermediate data in a first frequency band associated with the data channel and encoded tensor metadata in a second frequency band associated with the control channel.

[0020] The first device can receive encoded intermediate data and encoded tensor metadata from the second device by receiving an encoded bitstream from the second device. The encoded bitstream may include encoded intermediate data and encoded tensor metadata. The first device can decode the encoded intermediate data and encoded tensor metadata by decoding the encoded bitstream.

[0021] The first device can decode encoded intermediate data and encoded tensor metadata by decoding one or both of the following: decoding the encoded tensor metadata according to a tensor shape structure or algorithm to obtain a tensor shape; or encoding the encoded intermediate data according to a bitstream structure to obtain a series of intermediate data bytes.

[0022] The first device can reconstruct a tensor based on intermediate data and tensor metadata by converting binary data in intermediate data into tensor data and reshaping the tensor back to the original tensor shape based on the tensor data and tensor metadata.

[0023] The first device can be a wireless transmit / receive unit (WTRU) or a network entity.

[0024] An example apparatus for encoding intermediate data (e.g., including tensors) can receive intermediate data generated from an initial portion of an artificial intelligence (AI) model. The apparatus can encode the tensor shape associated with the intermediate data into tensor shape metadata based on a tensor shape structure or an encoding algorithm. The apparatus can also encode the intermediate data into an encoded intermediate data bitstream based on a bitstream structure. The apparatus can then transmit the tensor shape metadata and the encoded intermediate data bitstream to a second apparatus.

[0025] Encoding intermediate data can involve transforming a multidimensional tensor into a one-dimensional tensor and encoding the one-dimensional tensor according to a binary structure.

[0026] An example apparatus for decoding intermediate data can receive a data bitstream from a second apparatus, the data bitstream including encoded intermediate data and encoded tensor shape metadata associated with the encoded intermediate data. The apparatus can decode the encoded tensor shape metadata based on the tensor shape structure or an encoding algorithm to determine the tensor shape. The apparatus can decode the encoded intermediate data based on the bitstream structure to determine a series of intermediate data bytes. The apparatus can reconstruct the tensor from the series of intermediate data bytes based on the tensor shape. The apparatus can input the reconstructed tensor into the final part of an artificial intelligence (AI) model.

[0027] The tensor shape structure and bitstream structure can be pre-configured. The encoding algorithm can be a binary structure algorithm, a binary serialization algorithm, or a text serialization algorithm. Attached Figure Description

[0028] Figure 1A This is a system diagram illustrating an example communication system that can implement one or more of the disclosed embodiments.

[0029] Figure 1B This illustrates that, according to an embodiment, it is possible to Figure 1A The diagram shows a system diagram of an example wireless transmit / receive unit (WTRU) used in a communication system.

[0030] Figure 1C This illustrates that, according to an embodiment, it is possible to Figure 1A The diagram shows an example radio access network (RAN) and an example core network (CN) used in the communication system.

[0031] Figure 1D This illustrates that, according to an embodiment, it is possible to Figure 1A The system diagram shown is another example RAN and another example CN used in the communication system.

[0032] Figure 2 An example video encoder is shown.

[0033] Figure 3 An example video decoder is shown.

[0034] Figure 4 Examples of systems in which various aspects and examples can be implemented are shown.

[0035] Figure 5 This illustrates the split inference between WTRU and the network, where the media data source originates from WTRU.

[0036] Figure 6 This illustrates the split reasoning between WTRU and the network, where the media data source originates from the network.

[0037] Figure 7 An example encoded tensor shape is shown.

[0038] Figure 8 An example change pattern for encoding tensor shapes is shown.

[0039] Figure 9 An example split inference between WTRU and the network is shown, where the media data source and tensor shape metadata come from WTRU.

[0040] Figure 10 An example split inference between WTRU and the network is shown, where the media data source and tensor shape metadata come from the network.

[0041] Figure 11 An example of intermediate data access and delivery functionality is shown. Detailed Implementation

[0042] A more detailed understanding can be obtained from the following description, which is given by way of example in conjunction with the accompanying drawings.

[0043] Figure 1A This diagram illustrates an example communication system 100 that can implement one or more of the disclosed embodiments. The communication system 100 may be a multiple access system providing content such as voice, data, video, messaging, and broadcasting to multiple wireless users. The communication system 100 enables multiple wireless users to access such content through shared system resources including wireless broadband. For example, the communication system 100 may employ one or more channel access methods, such as Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), Frequency Division Multiple Access (FDMA), Orthogonal FDMA (OFDMA), Single Carrier FDMA (SC-FDMA), Zero-Tail Unique Word DFT Extended OFDM (ZT UW DTS-s OFDM), Unique Word OFDM (UW-OFDM), Resource Block Filtered OFDM, Filter Bank Multicarrier (FBMC), etc.

[0044] like Figure 1AAs shown, the communication system 100 may include wireless transmit / receive units (WTRUs) 102a, 102b, 102c, 102d, RAN 104 / 113, CN 106 / 115, public switched telephone network (PSTN) 108, Internet 110, and other networks 112. However, it will be understood that the disclosed embodiments contemplate any number of WTRUs, base stations, networks, and / or network elements. Each of the WTRUs 102a, 102b, 102c, and 102d may be any type of device configured to operate and / or communicate in a wireless environment. For example, WTRUs 102a, 102b, 102c, and 102d (any of which may be referred to as a “station” and / or “STA”) may be configured to transmit and / or receive wireless signals and may include user equipment (UE), mobile stations, fixed or mobile subscriber units, subscription-based units, pagers, cellular phones, personal digital assistants (PDAs), smartphones, laptops, netbooks, personal computers, wireless sensors, hotspots or Mi-Fi devices, Internet of Things (IoT) devices, watches or other wearable devices, head-mounted displays (HMDs), vehicles, drones, medical devices and applications (e.g., remote surgery), industrial devices and applications (e.g., robots and / or other wireless devices operating in the context of industrial and / or automated processing chains), consumer electronics devices, devices operating on commercial and / or industrial wireless networks, etc. Any of WTRUs 102a, 102b, 102c, and 102d may be interchangeably referred to as a UE.

[0045] The communication system 100 may also include base station 114a and / or base station 114b. Each of base stations 114a and 114b may be any type of device configured to wirelessly interface with at least one of WTRUs 102a, 102b, 102c, and 102d to facilitate access to one or more communication networks such as CN 106 / 115, Internet 110, and / or other networks 112. For example, base stations 114a and 114b may be base transceiver stations (BTS), node Bs, eNode Bs, master node Bs, master eNodeBs, gNBs, NR node Bs, site controllers, access points (APs), wireless routers, etc. Although base stations 114a and 114b are each depicted as a single element, it will be understood that base stations 114a and 114b may include any number of interconnected base stations and / or network elements.

[0046] Base station 114a may be part of RAN 104 / 113, which may also include other base stations and / or network elements (not shown), such as base station controllers (BSCs), radio network controllers (RNCs), relay nodes, etc. Base station 114a and / or base station 114b may be configured to transmit and / or receive radio signals on one or more carrier frequencies, which may be referred to as cells (not shown). These frequencies may be in licensed spectrum, unlicensed spectrum, or a combination of licensed and unlicensed spectrum. A cell may provide coverage for a specific geographic area that may be relatively fixed or may change over time. A cell may also be divided into cell sectors. For example, the cell associated with base station 114a may be divided into three sectors. Therefore, in one embodiment, base station 114a may include three transceivers, i.e., one for each sector of the cell. In embodiments, base station 114a may employ multiple-input multiple-output (MIMO) technology and may utilize multiple transceivers for each sector of the cell. For example, beamforming may be used to transmit and / or receive signals in a desired spatial direction.

[0047] Base stations 114a and 114b can communicate with one or more of WTRUs 102a, 102b, 102c, and 102d via air interface 116, which can be any suitable wireless communication link (e.g., radio frequency (RF), microwave, centimeter wave, micrometer wave, infrared (IR), ultraviolet (UV), visible light, etc.). Any suitable radio access technology (RAT) can be used to establish air interface 116.

[0048] More specifically, as described above, the communication system 100 can be a multiple access system and can employ one or more channel access schemes, such as CDMA, TDMA, FDMA, OFDMA, SC-FDMA, etc. For example, base station 114a in RAN 104 / 113 and WTRUs 102a, 102b, 102c can implement radio technologies, such as using Wideband CDMA (WCDMA) to establish Universal Mobile Telecommunications System (UMTS) Terrestrial Radio Access (UTRA) for air interfaces 115 / 116 / 117. WCDMA can include communication protocols such as High-Speed ​​Packet Access (HSPA) and / or Evolved HSPA (HSPA+). HSPA can include High-Speed ​​Downlink (DL) Packet Access (HSDPA) and / or High-Speed ​​UL Packet Access (HSUPA).

[0049] In the embodiment, base station 114a and WTRUs 102a, 102b, 102c can implement radio technologies, such as using Long Term Evolution (LTE) and / or LTE-Advanced (LTE-A) and / or LTE-Advanced Pro (LTE-A Pro) to establish Evolved UMTS Terrestrial Radio Access (E-UTRA) for air interface 116.

[0050] In the embodiments, base station 114a and WTRUs 102a, 102b, 102c can implement radio technologies, such as using New Radio (NR) to establish NR radio access for air interface 116.

[0051] In the embodiments, base station 114a and WTRUs 102a, 102b, and 102c can implement multiple radio access technologies. For example, base station 114a and WTRUs 102a, 102b, and 102c can, for instance, use the dual connectivity (DC) principle to jointly implement LTE radio access and NR radio access. Therefore, the air interface used by WTRUs 102a, 102b, and 102c can be characterized by multiple types of radio access technologies and / or transmissions sent to / from multiple types of base stations (e.g., eNBs and gNBs).

[0052] In other embodiments, base station 114a and WTRUs 102a, 102b, 102c can implement radio technologies such as IEEE 802.11 (i.e., WiFi), IEEE 802.16 (i.e., WiMAX), CDMA2000, CDMA2000 1X, CDMA2000 EV-DO, Provisional Standard 2000 (IS-2000), Provisional Standard 95 (IS-95), Provisional Standard 856 (IS-856), Global System for Mobile Communications (GSM), Enhanced Data Rate GSM Evolution (EDGE), GSMEDGE (GERAN), etc.

[0053] Figure 1ABase station 114b can be, for example, a wireless router, master node B, master eNode-B, or access point, and can utilize any suitable RAT to facilitate wireless connectivity in local areas such as commercial locations, homes, vehicles, campuses, industrial facilities, air corridors (e.g., for use by drones), roads, etc. In one embodiment, base station 114b and WTRUs 102c, 102d can implement radio technologies such as IEEE 802.11 to establish a wireless local area network (WLAN). In another embodiment, base station 114b and WTRUs 102c, 102d can implement radio technologies such as IEEE 802.15 to establish a wireless personal area network (WPAN). In yet another embodiment, base station 114b and WTRUs 102c, 102d can utilize cellular-based RATs (e.g., WCDMA, CDMA2000, GSM, LTE, LTE-a, LTE-a Pro, NR, etc.) to establish picocells or femtocells. Figure 1A As shown, base station 114b can be directly connected to Internet 110. Therefore, base station 114b does not need to access Internet 110 via CN 106 / 115.

[0054] RAN 104 / 113 can communicate with CN 106 / 115, which can be any type of network configured to provide voice, data, application, and / or Voice over Internet Protocol (VoIP) services to one or more of WTRU 102a, 102b, 102c, and 102d. Data can have different Quality of Service (QoS) requirements, such as different throughput requirements, latency requirements, fault tolerance requirements, reliability requirements, data throughput requirements, mobility requirements, etc. CN 106 / 115 can provide call control, billing services, location-based services, prepaid calling, internet connectivity, video distribution, etc., and / or perform advanced security functions such as user authentication. Although Figure 1A As not shown, but will be understood, RAN 104 / 113 and / or CN 106 / 115 can communicate directly or indirectly with other RANs using the same RAT as or a different RAT than RAN 104 / 113. For example, in addition to being connected to RAN 104 / 113, which may be utilizing NR radio technology, CN 106 / 115 can also communicate with another RAN (not shown) using GSM, UMTS, CDMA 2000, WiMAX, E-UTRA, or WiFi radio technology.

[0055] CN 106 / 115 can also serve as a gateway for WTRUs 102a, 102b, 102c, and 102d to access PSTN 108, the Internet 110, and / or other networks 112. PSTN 108 may include a circuit-switched telephone network providing Common Old-Style Telephone Service (POTS). The Internet 110 may include a global system of interconnected computer networks and devices using common communication protocols such as Transmission Control Protocol (TCP), User Datagram Protocol (UDP), and / or Internet Protocol (IP) from the TCP / IP Internet Protocol suite. Network 112 may include wired and / or wireless communication networks owned and / or operated by other service providers. For example, network 112 may include another CN connected to one or more RANs, which may use the same RAT as RAN 104 / 113 or a different RAT.

[0056] Some or all of the WTRUs 102a, 102b, 102c, and 102d in communication system 100 may include multi-mode capabilities (e.g., WTRUs 102a, 102b, 102c, and 102d may include multiple transceivers for communicating with different wireless networks via different wireless links). For example, Figure 1A The WTRU 102c shown can be configured to communicate with a base station 114a that can use cellular-based radio technology and with a base station 114b that can use IEEE 802 radio technology.

[0057] Figure 1B This is a system diagram illustrating example WTRU 102. (See diagram below.) Figure 1B As shown, WTRU 102 may include a processor 118, a transceiver 120, a transmitting / receiving element 122, a speaker / microphone 124, a keypad 126, a display / touchpad 128, non-removable memory 130, removable memory 132, a power supply 134, a Global Positioning System (GPS) chipset 136, and / or other peripheral devices 138, etc. It will be understood that, while remaining consistent with the embodiments, WTRU 102 may include any sub-combination of the foregoing elements.

[0058] Processor 118 can be a general-purpose processor, a special-purpose processor, a conventional processor, a digital signal processor (DSP), multiple microprocessors, one or more microprocessors associated with a DSP core, a controller, a microcontroller, an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) circuit, any other type of integrated circuit (IC), a state machine, etc. Processor 118 can perform signal encoding, data processing, power control, input / output processing, and / or any other functions that enable WTRU 102 to operate in a wireless environment. Processor 118 can be coupled to transceiver 120, which can be coupled to transmitting / receiving element 122. Although Figure 1B While the processor 118 and transceiver 120 are depicted as separate components, it will be understood that the processor 118 and transceiver 120 can be integrated together in an electronic package or chip.

[0059] Transmitting / receiving element 122 can be configured to transmit signals to or receive signals from a base station (e.g., base station 114a) via air interface 116. For example, in one embodiment, transmitting / receiving element 122 can be an antenna configured to transmit and / or receive RF signals. In another embodiment, transmitting / receiving element 122 can be a transmitter / detector configured to transmit and / or receive, for example, IR, UV, or visible light signals. In yet another embodiment, transmitting / receiving element 122 can be configured to transmit and / or receive both RF signals and optical signals. It will be understood that transmitting / receiving element 122 can be configured to transmit and / or receive any combination of wireless signals.

[0060] Although the transmitting / receiving element 122 is in Figure 1B While depicted as a single element, WTRU 102 may include any number of transmit / receive elements 122. More specifically, WTRU 102 may employ MIMO technology. Thus, in one embodiment, WTRU 102 may include two or more transmit / receive elements 122 (e.g., multiple antennas) for transmitting and receiving wireless signals via air interface 116.

[0061] Transceiver 120 can be configured to modulate signals transmitted by transmitting / receiving element 122 and demodulate signals received by transmitting / receiving element 122. As described above, WTRU 102 can have multi-mode capability. Therefore, transceiver 120 can include multiple transceivers for enabling WTRU 102 to communicate via various RATs (e.g., such as NR and IEEE 802.11).

[0062] The processor 118 of WTRU 102 can be coupled to and receive user input data from: a speaker / microphone 124, a keypad 126, and / or a display / touchpad 128 (e.g., a liquid crystal display (LCD) unit or an organic light-emitting diode (OLED) display unit). The processor 118 can also output user data to the speaker / microphone 124, keypad 126, and / or display / touchpad 128. Additionally, the processor 118 can access information and store data from any suitable type of memory, such as non-removable memory 130 and / or removable memory 132. Non-removable memory 130 may include random access memory (RAM), read-only memory (ROM), a hard disk, or any other type of memory storage device. Removable memory 132 may include a subscriber identity module (SIM) card, memory stick, secure digital storage (SD) card, etc. In other embodiments, the processor 118 can access information and store data from memory not actually located on WTRU 102, such as on a server or home computer (not shown).

[0063] The processor 118 may receive power from the power supply 134 and may be configured to distribute power to other components in the WTRU 102 and / or control power to those other components. The power supply 134 may be any suitable device for powering the WTRU 102. For example, the power supply 134 may include one or more dry cell batteries (e.g., nickel-cadmium (NiCd), nickel-zinc (NiZn), nickel metal hydride (NiMH), lithium-ion (Li-ion), etc.), solar cells, fuel cells, etc.

[0064] The processor 118 may also be coupled to a GPS chipset 136, which may be configured to provide location information (e.g., longitude and latitude) about the current location of the WTRU 102. In addition to or instead of information from the GPS chipset 136, the WTRU 102 may receive location information from base stations (e.g., base stations 114a, 114b) via air interface 116 and / or determine its location based on the timing of signals received from two or more nearby base stations. It will be understood that, while remaining consistent with the embodiments, the WTRU 102 may acquire location information using any suitable location determination method.

[0065] The processor 118 can also be connected to other peripheral devices 138, which may include one or more software and / or hardware modules that provide additional features, functions, and / or wired or wireless connectivity. For example, peripheral devices 138 may include accelerometers, electronic compasses, satellite transceivers, digital cameras (for photos and / or videos), Universal Serial Bus (USB) ports, vibration devices, television transceivers, hands-free headsets, Bluetooth® modules, FM radio units, digital music players, media players, video game player modules, internet browsers, virtual reality and / or augmented reality (VR / AR) devices, activity trackers, etc. Peripheral devices 138 may include one or more sensors, which may be one or more of the following: gyroscopes, accelerometers, Hall effect sensors, magnetometers, orientation sensors, proximity sensors, temperature sensors, time sensors; geolocation sensors; altimeters, light sensors, touch sensors, magnetometers, barometers, gesture sensors, biometric sensors, and / or humidity sensors.

[0066] WTRU 102 may include a full-duplex radio, wherein some or all of the transmission and reception of signals (e.g., associated with a specific subframe of both UL (e.g., for transmission) and downlink (e.g., for reception)) may be concurrent and / or simultaneous. The full-duplex radio may include an interference management unit to reduce and / or substantially eliminate self-interference via hardware (e.g., a choke) or signal processing via a processor (e.g., a separate processor (not shown) or via processor 118). In embodiments, WTRU 102 may include a half-duplex radio, wherein some or all of the transmission and reception of signals (e.g., associated with a specific subframe of both UL (e.g., for transmission) or downlink (e.g., for reception)) may be concurrent and / or simultaneous.

[0067] Figure 1C This is a system diagram illustrating RAN 104 and CN 106 according to an embodiment. As described above, RAN 104 can employ E-UTRA radio technology to communicate with WTRUs 102a, 102b, and 102c via air interface 116. RAN 104 can also communicate with CN 106.

[0068] RAN 104 may include eNode-Bs 160a, 160b, and 160c, but it will be understood that RAN 104 may include any number of eNode-Bs while remaining consistent with the embodiments. eNode-Bs 160a, 160b, and 160c may each include one or more transceivers for communicating with WTRUs 102a, 102b, and 102c via air interface 116. In one embodiment, eNode-Bs 160a, 160b, and 160c may implement MIMO technology. Therefore, for example, eNode-B 160a may use multiple antennas to transmit radio signals to and / or receive radio signals from WTRU 102a.

[0069] Each of the eNode-B 160a, 160b, and 160c can be associated with a specific cell (not shown) and can be configured to handle radio resource management decisions, handover decisions, user scheduling in UL and / or DL, etc. Figure 1C As shown, eNode-B 160a, 160b, and 160c can communicate with each other via the X2 interface.

[0070] Figure 1C The CN 106 shown may include a Mobility Management Entity (MME) 162, a Serving Gateway (SGW) 164, and a Packet Data Network (PDN) Gateway (or PGW) 166. While each of the foregoing elements is described as part of CN 106, it will be understood that any of these elements may be owned and / or operated by an entity other than a CN operator.

[0071] The MME 162 can connect to each of the eNode-Bs 162a, 162b, and 162c in RAN 104 via the S1 interface and can act as a control node. For example, the MME 162 can be responsible for authenticating users of WTRUs 102a, 102b, and 102c, activating / deactivating bearers, selecting a specific serving gateway during the initial attachment of WTRUs 102a, 102b, and 102c, etc. The MME 162 can provide control plane functions for handover between RAN 104 and other RANs (not shown) employing other radio technologies such as GSM and / or WCDMA.

[0072] The SGW 164 can connect to each of the eNode Bs 160a, 160b, and 160c in RAN 104 via the S1 interface. The SGW 164 can typically route and forward user data packets to or from WTRUs 102a, 102b, and 102c. The SGW 164 can perform other functions such as anchoring the user plane during eNode-B handover, triggering paging when DL data is available to WTRUs 102a, 102b, and 102c, and managing and storing the context of WTRUs 102a, 102b, and 102c.

[0073] SGW 164 can be connected to PGW 166, which can provide WTRU 102a, 102b, 102c with access to packet-switched networks (such as Internet 110) to facilitate communication between WTRU 102a, 102b, 102c and IP-enabled devices.

[0074] CN 106 can facilitate communication with other networks. For example, CN 106 can provide WTRUs 102a, 102b, and 102c with access to circuit-switched networks (such as PSTN 108) to facilitate communication between WTRUs 102a, 102b, and 102c and conventional terrestrial line communication devices. For example, CN 106 may include an IP gateway (e.g., an IP Multimedia Subsystem (IMS) server) or be able to communicate with it, serving as an interface between CN 106 and PSTN 108. Additionally, CN 106 can provide WTRUs 102a, 102b, and 102c with access to other networks 112, which may include other wired and / or wireless networks owned and / or operated by other service providers.

[0075] Despite WTRU in Figures 1A to 1D While described as a wireless terminal, it is envisioned that, in some representative embodiments, such a terminal may (e.g., temporarily or permanently) use a wired communication interface with a communication network.

[0076] In a representative embodiment, the other network 112 may be a WLAN.

[0077] A WLAN in Infrastructure Basic Services Set (BSS) mode may have an access point (AP) for the BSS and one or more stations (STAs) associated with the AP. The AP may access a distribution system (DS) or another type of wired / wireless network that loads traffic into and / or loads traffic out of the BSS, or have an interface to it. Traffic originating outside the BSS destined for a STA can be delivered to the AP via it. Traffic from a STA destined for a destination outside the BSS can be sent to the AP for delivery to the appropriate destination. Traffic between STAs within the BSS can be sent via the AP, for example, where a source STA can send traffic to the AP, and the AP can deliver the traffic to the destination STA. Traffic between STAs within the BSS can be considered and / or referred to as point-to-point traffic. Point-to-point traffic can be sent between a source STA and a destination STA using a direct link setup (DLS) (e.g., directly between them). In some representative embodiments, the DLS may use 802.11e DLS or 802.11z Tunneled DLS (TDLS). A WLAN using the Standalone BSS (IBSS) mode may not have an access point (AP), and STAs within the IBSS or using the IBSS (e.g., all STAs) can communicate directly with each other. The IBSS communication mode may sometimes be referred to as a "self-organizing" communication mode in this document.

[0078] When operating in 802.11ac infrastructure mode or a similar mode, the AP can transmit beacons on a fixed channel, such as the primary channel. The primary channel can be of fixed width (e.g., a 20 MHz bandwidth) or dynamically set via signaling. The primary channel can be the operating channel of the BSS and can be used by the STA to establish a connection with the AP. In some representative embodiments, Carrier Sense Multiple Access - Collision Avoidance (CSMA / CA) can be implemented, for example, in an 802.11 system. For CSMA / CA, each STA (e.g., every STA), including the AP, can sense the primary channel. If a particular STA senses / detects that the primary signal is busy and / or determines that the primary signal is busy, that STA can back off. In a given BSS, at any given time, only one STA (e.g., only one station) can transmit.

[0079] High-throughput (HT) STAs can communicate using a 40 MHz wide channel, for example, by combining a primary 20 MHz channel with adjacent or non-adjacent 20 MHz channels.

[0080] Very High Throughput (VHT) STAs can support channels with widths of 20 MHz, 40 MHz, 80 MHz, and / or 160 MHz. 40 MHz and / or 80 MHz channels can be formed by combining consecutive 20 MHz channels. A 160 MHz channel can be formed by combining eight consecutive 20 MHz channels, or by combining two non-consecutive 80 MHz channels, which can be referred to as an 80+80 configuration. In the 80+80 configuration, data, after channel coding, can be passed through a fragment parser that splits the data into two streams. Inverse Fast Fourier Transform (IFFT) processing and time-domain processing can be performed on each stream separately. The streams can be mapped onto the two 80 MHz channels, and the data can be transmitted by the transmitting STA. At the receiver of the receiving STA, the above operations of the 80+80 configuration can be reversed, and the combined data can be sent to the Media Access Control (MAC).

[0081] 802.11af and 802.11ah support operating modes below 1 GHz. The channel operating bandwidth and carrier are reduced in 802.11af and 802.11ah compared to those used in 802.11n and 802.11ac. 802.11af supports 5 MHz, 10 MHz, and 20 MHz bandwidths in the TV Blank (TVWS) spectrum, and 802.11ah supports 1 MHz, 2 MHz, 4 MHz, 8 MHz, and 16 MHz bandwidths using non-TVWS spectrum. According to a representative embodiment, 802.11ah may support instrument-type control / machine-type communication (MTC), such as MTC devices in macro coverage areas. MTC devices may have certain capabilities, such as limited capabilities, including support (e.g., only support) certain and / or limited bandwidths. MTC devices may include batteries with a battery life exceeding a threshold (e.g., to maintain a very long battery life).

[0082] WLAN systems that can support multiple channels and channel bandwidths (such as 802.11n, 802.11ac, 802.11af, and 802.11ah) include a channel that can be designated as the primary channel. The primary channel can have a bandwidth equal to the maximum common operating bandwidth supported by all STAs in the BSS. The bandwidth of the primary channel can be set and / or limited by the STAs operating in the BSS that support the minimum bandwidth operating mode. In the 802.11ah example, for STAs that support (e.g., only support) the 1 MHz mode (e.g., MTC type devices), the primary channel can be 1 MHz wide, even if the AP and other STAs in the BSS support 2 MHz, 4 MHz, 8 MHz, 16 MHz, and / or other channel bandwidth operating modes. Carrier Sense and / or Network Allocation Vector (NAV) settings can depend on the status of the primary channel. If the primary channel is busy, for example, due to STAs (which only support the 1 MHz operating mode) transmitting to the AP, the entire available band can be considered busy even if most of the band remains idle and potentially available.

[0083] In the United States, the available frequency band for 802.11ah is 902 MHz to 928 MHz. In South Korea, the available frequency band is 917.5 MHz to 923.5 MHz. In Japan, the available frequency band is 916.5 MHz to 927.5 MHz. The total available bandwidth for 802.11ah is 6 MHz to 26 MHz, depending on the country code.

[0084] Figure 1D This is a system diagram illustrating RAN 113 and CN 115 according to an embodiment. As described above, RAN 113 may employ NR radio technology to communicate with WTRUs 102a, 102b, and 102c via air interface 116. RAN 113 may also communicate with CN 115.

[0085] RAN 113 may include gNBs 180a, 180b, and 180c, but it will be understood that RAN 113 may include any number of gNBs while remaining consistent with the embodiments. gNBs 180a, 180b, and 180c may each include one or more transceivers for communicating with WTRUs 102a, 102b, and 102c via air interface 116. In one embodiment, gNBs 180a, 180b, and 180c may implement MIMO technology. For example, gNBs 180a and 180b may utilize beamforming to transmit signals to and / or receive signals from gNBs 180a, 180b, and 180c. Thus, for example, gNB 180a may use multiple antennas to transmit radio signals to and / or receive radio signals from WTRU 102a. In embodiments, gNBs 180a, 180b, and 180c may implement carrier aggregation technology. For example, gNB 180a can transmit multiple component carriers to WTRU 102a (not shown). A subset of these component carriers may be located on unlicensed spectrum, while the remaining component carriers may be located on licensed spectrum. In embodiments, gNBs 180a, 180b, and 180c can implement Coordinated Multipoint (CoMP) technology. For example, WTRU 102a can receive coordinated transmissions from gNBs 180a and 180b (and / or gNB 180c).

[0086] WTRUs 102a, 102b, and 102c can communicate with gNBs 180a, 180b, and 180c using transmissions associated with scalable parameter sets. For example, the OFDM symbol spacing and / or OFDM subcarrier spacing can be varied for different transmissions, different cells, and / or different portions of the radio transmission spectrum. WTRUs 102a, 102b, and 102c can communicate with gNBs 180a, 180b, and 180c using subframes of various or scalable lengths or transmission time intervals (TTIs) (e.g., containing different numbers of OFDM symbols and / or absolute times of varying durations).

[0087] gNBs 180a, 180b, and 180c can be configured to communicate with WTRUs 102a, 102b, and 102c in standalone and / or non-standalone configurations. In standalone configuration, WTRUs 102a, 102b, and 102c can communicate with gNBs 180a, 180b, and 180c without accessing other RANs (e.g., eNodeBs 160a, 160b, and 160c). In standalone configuration, WTRUs 102a, 102b, and 102c can use one or more of gNBs 180a, 180b, and 180c as mobile anchors. In standalone configuration, WTRUs 102a, 102b, and 102c can communicate with gNBs 180a, 180b, and 180c using signals in unlicensed frequency bands. In a non-standalone configuration, WTRUs 102a, 102b, and 102c can communicate / connect with gNBs 180a, 180b, and 180c while also communicating / connecting with another RAN (such as eNode-Bs 160a, 160b, and 160c). For example, WTRUs 102a, 102b, and 102c can implement DC principles to communicate substantially simultaneously with one or more gNBs 180a, 180b, and 180c and one or more eNode-Bs 160a, 160b, and 160c. In a non-standalone configuration, eNode-Bs 160a, 160b, and 160c can act as mobile anchors for WTRUs 102a, 102b, and 102c, and gNBs 180a, 180b, and 180c can provide additional coverage and / or throughput to serve WTRUs 102a, 102b, and 102c.

[0088] Each of gNBs 180a, 180b, and 180c can be associated with a specific cell (not shown) and can be configured to handle radio resource management decisions, handover decisions, user scheduling in UL and / or DL, support for network slicing, dual connectivity, interoperability between NR and E-UTRA, routing of user plane data to User Plane Functions (UPF) 184a and 184b, routing of control plane information to Access and Mobility Management Functions (AMF) 182a and 182b, etc. Figure 1D As shown, gNB180a, 180b, and 180c can communicate with each other via the Xn interface.

[0089] Figure 1DThe CN 115 shown may include at least one AMF 182a, 182b, at least one UPF 184a, 184b, at least one Session Management Function (SMF) 183a, 183b, and possibly a Data Network (DN) 185a, 185b. While each of the foregoing elements is described as part of the CN 115, it will be understood that any of these elements may be owned and / or operated by an entity other than a CN operator.

[0090] AMF 182a and 182b can connect to one or more of the gNBs 180a, 180b, and 180c in RAN 113 via the N2 interface and can act as control nodes. For example, AMF 182a and 182b can be responsible for authenticating users of WTRU 102a, 102b, and 102c, supporting network slicing (e.g., handling different PDU sessions with different requirements), selecting specific SMFs 183a and 183b, managing registration areas, terminating NAS signaling, mobility management, etc. AMF 182a and 182b can use network slicing to customize CN support for WTRU 102a, 102b, and 102c based on the service types being used by WTRU 102a, 102b, and 102c. For example, different network slices can be established for different use cases, such as services relying on Ultra Reliable Low Latency (URLLC) access, services relying on Enhanced Massive Mobile Broadband (eMBB) access, and services for Machine Type Communication (MTC) access. AMF 162 can provide control plane functions for handover between RAN 113 and other RANs (not shown) that employ other radio technologies (such as LTE, LTE-A, LTE-A Pro) and / or non-3GPP access technologies (such as WiFi).

[0091] SMFs 183a and 183b can connect to AMFs 182a and 182b in CN 115 via the N11 interface. SMFs 183a and 183b can also connect to UPFs 184a and 184b in CN 115 via the N4 interface. SMFs 183a and 183b can select and control UPFs 184a and 184b, and configure traffic routing through UPFs 184a and 184b. SMFs 183a and 183b can perform other functions, such as managing and allocating UE IP addresses, managing PDU sessions, controlling policy enforcement and QoS, and providing downlink data notifications. PDU session types can be IP-based, non-IP-based, or Ethernet-based.

[0092] UPF 184a and 184b can be connected via the N3 interface to one or more of the gNBs 180a, 180b, and 180c in RAN 113. These gNBs can provide WTRU 102a, 102b, and 102c with access to packet-switched networks (such as the Internet 110) to facilitate communication between WTRU 102a, 102b, and 102c and IP-enabled devices. UPF 184 and 184b can perform other functions such as routing and forwarding packets, enforcing user plane policies, supporting multihomed PDU sessions, handling user plane QoS, buffering downlink packets, and providing mobility anchoring.

[0093] CN 115 can facilitate communication with other networks. For example, CN 115 may include or be able to communicate with an IP gateway (e.g., an IP Multimedia Subsystem (IMS) server) that serves as an interface between CN 115 and PSTN 108. Additionally, CN 115 can provide WTRUs 102a, 102b, and 102c with access to other networks 112, which may include other wired and / or wireless networks owned and / or operated by other service providers. In one embodiment, WTRUs 102a, 102b, and 102c can be connected to DN 185a and 185b via UPF 184a and 184b through the N3 interface to UPF 184a and 184b and the N6 interface between UPF 184a and 184b and local data networks (DNs) 185a and 185b.

[0094] Given Figures 1A to 1D and Figures 1A to 1D The corresponding descriptions can be performed by one or more emulation devices (not shown) that perform one or more of the functions described herein with respect to: WTRU 102a to 102d, base stations 114a to 114b, eNode-B 160a to 160c, MME 162, SGW 164, PGW 166, gNB 180a to 180c, AMF 182a to 182b, UPF 184a to 184b, SMF 183a to 183b, DN 185a to 185b, and / or any other devices described herein. An emulation device can be one or more devices configured to emulate one or more of the functions described herein. For example, an emulation device can be used to test other devices and / or simulate network and / or WTRU functions.

[0095] Simulation devices can be designed to perform one or more tests on other devices in laboratory and / or carrier network environments. For example, one or more simulation devices may perform one or more functions when fully or partially implemented and / or deployed as part of a wired and / or wireless communication network to test other devices within the communication network. One or more simulation devices may perform one or more functions when temporarily implemented / deployed as part of a wired and / or wireless communication network. Simulation devices may be directly coupled to another device for testing purposes and / or use over-the-air wireless communication to perform tests.

[0096] One or more simulation devices may perform one or more functions without being implemented / deployed as part of a wired and / or wireless communication network. For example, a simulation device may be used to test scenarios in a laboratory and / or undeployed (e.g., under test) wired and / or wireless communication networks to enable testing of one or more components. One or more simulation devices may be test equipment. The simulation device may transmit and / or receive data using direct RF connection and / or wireless communication via an RF circuit system (e.g., which may include one or more antennas).

[0097] This application describes various aspects, including tools, features, examples, models, methods, etc. Many of these aspects are described in a specific manner, and are generally described in a way that may sound restrictive, at least to illustrate the individual features. However, this is for the purpose of clarity of description and does not limit the application or scope of these aspects. In fact, all the different aspects can be combined and interchanged to provide other aspects. Furthermore, these aspects can also be combined and interchanged with those described in previous documents.

[0098] The aspects described and envisioned in this application can be implemented in many different forms. Figures 5 to 2 7 can provide some examples, but other examples are envisioned. (Regarding...) Figures 5 to 2 The discussion in section 7 does not limit the breadth of implementations. At least one aspect generally relates to video encoding and decoding, and at least one other aspect generally relates to transmitting the generated or encoded bitstream. These and other aspects can be implemented as methods, apparatus, computer-readable storage media having instructions thereon stored thereon for encoding or decoding video data according to any of the methods, and / or computer-readable storage media having bitstreams generated according to any of the methods stored thereon.

[0099] In this application, the terms “reconstruction” and “decoding” are used interchangeably, the terms “pixel” and “sample” are used interchangeably, and the terms “image”, “picture” and “frame” are used interchangeably.

[0100] This document describes various methods, each of which includes one or more steps or actions to implement the described method. Unless the correct operation of the method requires a specific order of steps or actions, the order and / or use of specific steps and / or actions can be modified or combined. Additionally, in various examples, terms such as "first," "second," etc., may be used to modify elements, components, steps, operations, etc., such as, for example, "first decoding" and "second decoding." Unless specifically required, the use of such terms does not imply a sequence of operations. Therefore, in this example, the first decoding does not need to be performed before the second decoding, but can occur, for example, before, during, or in a time period overlapping with the second decoding.

[0101] The various methods and other aspects described in this application can be used to modify, for example... Figure 2 and Figure 3 The illustrated video encoder 200 and decoder 300 modules include, for example, a decoding module. Furthermore, the subject matter disclosed herein can be applied to, for example, any type, format, or version of video encoding, whether described in standards or recommendations (whether pre-existing or future-developed) and any extensions to such standards and recommendations. Unless otherwise stated or technically excluded, these aspects described in this application may be used alone or in combination.

[0102] Various numerical values, such as 1, 2, 4, 7, 8, 16, 32, 64, etc., are used in the examples described in this application. These and other specific values ​​are for illustrative purposes only, and the aspects described are not limited to these specific values.

[0103] Figure 2 This is a diagram illustrating an example video encoder 200. Variations of the example encoder 200 are envisioned, but for clarity, encoder 200 is described below without depicting all anticipated variations.

[0104] Before being encoded, the video sequence may undergo pre-coding processing 201, such as applying a color transformation to the input color image (e.g., a conversion from RGB 4:4:4 to YCbCr 4:2:0), or performing a remapping of the input image components to obtain a signal distribution that is more resilient to compression (e.g., using histogram equalization of one of the color components). Metadata (e.g., which may include film grain parameters determined through pre-processing as described herein) may be associated with the pre-processing and appended to the bitstream.

[0105] In encoder 200, the image is encoded by encoder elements as described below. The image to be encoded is partitioned (202) and processed in units such as coding units (CUs). Each unit is encoded using, for example, an intra-frame or inter-frame mode. When a unit is encoded in intra-frame mode, intra-frame prediction (260) is performed. In inter-frame mode, motion estimation (275) and compensation (270) are performed. The encoder determines (205) which mode, intra-frame or inter-frame, to use to encode the unit, and indicates the intra-frame / inter-frame decision by, for example, a prediction mode flag. For example, the prediction residual is calculated by subtracting (210) the prediction block from the original image block.

[0106] The predicted residual is then transformed (225) and quantized (230). The quantized transform coefficients, motion vectors, and other syntactic elements are entropy encoded (245) to output a bitstream. The encoder can skip the transform and apply quantization directly to the untransformed residual signal. The encoder can bypass both the transform and quantization, i.e., directly encode the residual without applying either the transform or quantization process.

[0107] The encoder decodes the coded block to provide a reference for further prediction. The quantized transform coefficients are dequantized (240) and inverse transformed (250) to decode the prediction residual. The decoded prediction residual and the prediction block are combined (255) to reconstruct the image block. An in-loop filter (265) is applied to the reconstructed image to perform, for example, deblocking / SAO (Sample Adaptive Shift) filtering, thereby reducing coding artifacts. The filtered image is stored in a reference image buffer (280).

[0108] Figure 3 This is a diagram illustrating an example video decoder. In the example decoder 300, the bitstream is decoded by decoder elements, as described below. The video decoder 300 typically performs operations similar to... Figure 2 The encoding process shown is the reverse of the decoding process. Encoder 200 typically also performs video decoding as part of the encoded video data.

[0109] Specifically, the decoder's input includes a video bitstream, which can be generated by the video encoder 200. First, entropy decoding (330) is performed on the bitstream to obtain transform coefficients, motion vectors, and other encoded information. Image partitioning information indicates how the image is partitioned. Therefore, the decoder can partition (335) the image based on the decoded image partitioning information. The transform coefficients are dequantized (340) and inverse transformed (350) to decode the prediction residuals. The decoded prediction residuals and prediction blocks are combined (355) to reconstruct the image blocks. Prediction blocks (370) can be obtained from intra-frame prediction (360) or motion-compensated prediction (i.e., inter-frame prediction) (375). An in-loop filter (365) is applied to the reconstructed image. The filtered image is stored in a reference image buffer (380).

[0110] The decoded image can also undergo post-decoding processing (385), such as inverse color transformation (e.g., conversion from YCbCr 4:2:0 to RGB 4:4:4) or inverse remapping, which is the inverse of the remapping process performed in the pre-encoding process (201). Post-decoding processing can use metadata derived in the pre-encoding process and signaled in the bitstream. In the example, the decoded image (e.g., after applying an in-loop filter (365) and / or, in the case of post-decoding processing, after post-decoding processing (385)) can be sent to a display device for presentation to the user.

[0111] Figure 4 This is a diagram illustrating examples of systems in which the various aspects and examples described herein can be implemented. System 400 may be embodied as an apparatus including the various components described below and configured to perform one or more aspects described in this document. Examples of such apparatus include, but are not limited to, various electronic devices such as personal computers, laptop computers, smartphones, tablet computers, digital multimedia set-top boxes, digital television receivers, personal video recording systems, connected home appliances, and servers. Elements of system 400 may be embodied individually or in combination in a single integrated circuit (IC), multiple ICs, and / or discrete components. For example, in at least one example, the processing elements and encoder / decoder elements of system 400 are distributed across multiple ICs and / or discrete components. In various examples, system 400 is communicatively coupled to one or more other systems or other electronic devices via, for example, a communication bus or through dedicated input and / or output ports. In various examples, system 400 is configured to implement one or more aspects described in this document.

[0112] System 400 includes at least one processor 410 configured to execute instructions loaded thereon to implement various aspects described herein, such as those described. Processor 410 may include embedded memory, input / output interfaces, and various other circuitry known in the art. System 400 includes at least one memory 420 (e.g., a volatile memory device and / or a non-volatile memory device). System 400 includes a storage device 440 that may include non-volatile memory and / or volatile memory, including but not limited to electrically erasable programmable read-only memory (EEPROM), read-only memory (ROM), programmable read-only memory (PROM), random access memory (RAM), dynamic random access memory (DRAM), static random access memory (SRAM), flash memory, disk drives, and / or optical disk drives. As a non-limiting example, storage device 440 may include internal storage, attached storage (including removable and non-removable storage devices), and / or network-accessible storage devices.

[0113] System 400 includes an encoder / decoder module 430 configured to, for example, process data to provide encoded or decoded video, and the encoder / decoder module 430 may include its own processor and memory. The encoder / decoder module 430 represents a module that can be included in a device to perform encoding and / or decoding functions. It is well known that a device can include one or both encoding and decoding modules. Alternatively, the encoder / decoder module 430 may be implemented as a separate element of system 400, or it may be incorporated within processor 410 as a combination of hardware and software known to those skilled in the art.

[0114] Program code to be loaded onto processor 410 or encoder / decoder 430 to execute the various aspects described in this document may be stored in storage device 440 and subsequently loaded onto memory 420 for execution by processor 410. According to various examples, one or more of processor 410, memory 420, storage device 440, and encoder / decoder module 430 may store one or more of various items during the execution of the processes described in this document. Such stored items may include, but are not limited to, input video, decoded video or portions of decoded video, bitstreams, matrices, variables, and intermediate or final results from equations, formulas, operations, and operational logic processing.

[0115] In some examples, the memory within processor 410 and / or encoder / decoder module 430 is used to store instructions and provide working memory for processing required during encoding or decoding. However, in other examples, external memory (e.g., the processing device may be processor 410 or encoder / decoder module 430) is used for one or more of these functions. External memory may be memory 420 and / or storage device 440, such as volatile memory and / or non-volatile flash memory. In several examples, external non-volatile flash memory is used to store, for example, the operating system of a television. In at least one example, fast external volatile memory such as RAM is used as working memory for video encoding and decoding operations.

[0116] Input to the components of system 400 can be provided through various input devices, as indicated in box 445. Such input devices include, but are not limited to, (i) a radio frequency (RF) section that receives, for example, RF signals transmitted over the air by a broadcaster, (ii) a component (COMP) input terminal (or a set of COMP input terminals), (iii) a universal serial bus (USB) input terminal, and / or (iv) a high-definition multimedia interface (HDMI) input terminal. Figure 4 Other examples not shown include composite video.

[0117] In various examples, the input device of block 445 has corresponding input processing elements known in the art. For example, the RF section may be associated with elements suitable for: (i) selecting a desired frequency (also known as selecting a signal, or limiting the signal band to a band), (ii) down-converting the selected signal, (iii) further band-limiting to a narrower band to select (e.g.,) a signal band that may be referred to as a channel in some examples), (iv) demodulating the down-converted and band-limited signal, (v) performing error correction, and / or (vi) demultiplexing to select the desired data packet stream. The RF section of various examples includes one or more elements performing these functions, such as frequency selectors, signal selectors, band limiters, channel selectors, filters, downconverters, demodulators, error correctors, and demultiplexers. The RF section may include tuners performing various of these functions, including, for example, down-converting a received signal to a lower frequency (e.g., intermediate frequency or near-baseband frequency) or baseband. In one set-top box example, the RF section and its associated input processing elements receive RF signals transmitted via a wired (e.g., cable) medium and perform frequency selection by filtering, down-converting, and filtering again to the desired frequency band. Various examples rearrange the above (and other) components, remove some of them, and / or add other components that perform similar or different functions. Adding components may include inserting components between existing components, such as inserting amplifiers and analog-to-digital converters. In various examples, the RF section includes an antenna.

[0118] USB and / or HDMI terminals may include corresponding interface processors for connecting system 400 to other electronic devices via USB and / or HDMI connections. It should be understood that aspects of input processing (e.g., Reed-Solomon error correction) may be implemented, for example, within a separate input processing IC or within processor 410 as needed. Similarly, aspects of USB or HDMI interface processing may be implemented, as needed, within a separate interface IC or within processor 410. The demodulated, error-corrected, and demultiplexed stream is provided to various processing elements, including, for example, processor 410 and an encoder / decoder 430 operating in conjunction with memory and storage elements, to process the data stream as needed for presentation on an output device.

[0119] Various components of system 400 can be housed within an integrated housing. Within the integrated housing, the various components can be interconnected and transmit data between them using suitable connection means 425 (e.g., internal buses known in the art, including inter-IC (I2C) buses, wiring, and printed circuit boards).

[0120] System 400 includes a communication interface 450 that enables communication with other devices via a communication channel 460. The communication interface 450 may include, but is not limited to, a transceiver configured to send and receive data via the communication channel 460. The communication interface 450 may include, but is not limited to, a modem or network interface card (NIC), and the communication channel 460 may be implemented, for example, within a wired and / or wireless medium.

[0121] In various examples, wireless networks, such as Wi-Fi networks (e.g., IEEE 802.11, where IEEE refers to the Institute of Electrical and Electronics Engineers), are used to stream or otherwise provide data to system 400. In these examples, the Wi-Fi signal is received via a communication channel 460 and a communication interface 450 adapted for Wi-Fi communication. The communication channel 460 in these examples is typically connected to an access point or router that provides access to external networks, including the Internet, to allow streaming applications and other top-level communications. Other examples use a set-top box to provide streaming data to system 400, delivering data via an HDMI connection to input block 445. Still other examples use an RF connection to input block 445 to provide streaming data to system 400. As indicated above, various examples provide data in non-streaming modes. Additionally, various examples use wireless networks other than Wi-Fi, such as cellular networks or Bluetooth® networks.

[0122] System 400 can provide output signals to various output devices, including display 475, speaker 485, and other peripheral devices 495. Various examples of display 475 include one or more of, for example, a touchscreen display, an organic light-emitting diode (OLED) display, a curved display, and / or a foldable display. The display (475) can be used in a television, tablet computer, laptop computer, mobile phone, or another device. Display 475 can also be integrated with other components (e.g., in a smartphone) or standalone (e.g., an external monitor for a laptop computer). In various examples, other peripheral devices 495 include one or more of a standalone digital video disc (or digital multifunction disc) (DVD, for both terms), an optical disc player, a stereo system, and / or a lighting system. Various examples utilize one or more peripheral devices 495 that provide functionality based on the output of system 400. For example, an optical disc player performs the function of playing the output of system 400.

[0123] In various examples, signaling (such as AV.Link, Consumer Electronics Control (CEC), or other communication protocols that enable device-to-device control with or without user intervention) is used to transmit control signals between system 400 and display 475, speaker 485, or other peripheral devices 495. Output devices may be communicatively coupled to system 400 via dedicated connections through corresponding interfaces 470, 480, and 490. Alternatively, output devices may be connected to system 400 via communication interface 450 using communication channel 460. Display 475 and speaker 485 may be integrated into a single unit along with other components of system 400 in electronic devices such as televisions. In various examples, display interface 470 includes a display driver, such as a timing controller (TCon) chip.

[0124] For example, if the RF input section 445 is part of a separate set-top box, the display 475 and speaker 485 can alternatively be separate from one or more of the other components. In various examples where the display 475 and speaker 485 are external components, the output signal can be provided via a dedicated output connection, including, for example, an HDMI port, a USB port, or a COMP output.

[0125] The example can be executed by processor 410 or by computer software implemented by hardware or a combination of hardware and software. As a non-limiting example, the example can be implemented by one or more integrated circuits. As a non-limiting example, memory 420 can be of any type suitable for the technical environment and can be implemented using any suitable data storage technology, such as optical memory devices, magnetic memory devices, semiconductor-based memory devices, fixed memory, and removable memory. As a non-limiting example, processor 410 can be of any type suitable for the technical environment and can encompass one or more microprocessors, general-purpose computers, special-purpose computers, and processors based on multi-core architectures.

[0126] Various implementations involve decoding. As used herein, "decoding" can encompass all or part of a process performed, for example, on a received encoded sequence to produce a final output suitable for display. In various examples, such a process includes one or more processes typically performed by a decoder, such as entropy decoding, inverse quantization, inverse transform, and differential decoding. In various examples, such a process also includes, or alternatively includes, processes performed by a decoder of the various implementations described herein, such as receiving encoded intermediate data and encoded tensor metadata from a second device; decoding the encoded intermediate data and encoded tensor metadata; reconstructing a tensor based on the intermediate data and tensor metadata, etc.

[0127] As further examples, in one example, "decoding" refers only to entropy decoding; in another example, "decoding" refers only to differential decoding; and in yet another example, "decoding" refers to a combination of entropy decoding and differential decoding. Based on the specific context of the description, it will be clear whether the phrase "decoding process" is intended to specifically refer to a subset of operations or to refer to a broader decoding process, and it is believed that those skilled in the art will readily understand this.

[0128] Various implementations involve encoding. Similar to the discussion of "decoding" above, "encoding" as used in this application can include, for example, all or part of the processing performed on an input video sequence to produce an encoded bitstream. In various examples, such processes include one or more processes typically performed by an encoder, such as partitioning, differential coding, transform, quantization, and entropy coding. In various examples, such processes also include, or alternatively include, processes performed by an encoder of the various implementations described in this application, such as determining tensor metadata associated with intermediate data; encoding the intermediate data and the tensor metadata associated with the intermediate data; and sending the encoded intermediate data and the encoded tensor metadata to a second device, etc.

[0129] As further examples, in one example, "encoding" refers only to entropy encoding; in another example, "encoding" refers only to differential encoding; and in yet another example, "encoding" refers to a combination of entropy encoding and differential encoding. Based on the specific context of the description, it will be clear whether the phrase "encoding process" is intended to specifically refer to a subset of operations or to refer to a broader encoding process, and it is believed that those skilled in the art will readily understand this.

[0130] It should be noted that the syntactic elements used in this article are descriptive terms. Therefore, the use of other syntactic element names is not excluded.

[0131] When a diagram is presented as a flowchart, it should be understood that it also provides a block diagram of the corresponding device. Similarly, when a diagram is presented as a block diagram, it should be understood that it also provides a flowchart of the corresponding method / device.

[0132] The implementations and aspects described herein can be implemented, for example, in methods or processes, devices, software programs, data streams, or signals. Even if discussed only in the context of a single implementation (e.g., discussed only as a method), the implementation of the features in question can also be implemented in other forms (e.g., devices or programs). Devices can be implemented, for example, with appropriate hardware, software, and firmware. Methods can be implemented, for example, in a processor, which generally refers to a processing device, including, for example, a computer, microprocessor, integrated circuit, or programmable logic device. Processors also include communication devices, such as computers, cellular phones, portable / personal digital assistants (“PDAs”), and other devices that facilitate information communication between end users.

[0133] The reference to “an example” or “an example” or “an implementation” or “an implementation”, and their variations, means that the specific features, structures, characteristics, etc., described in connection with the example are included in at least one example. Therefore, the phrases “in an example” or “in the example” or “in an implementation” or “in the implementation”, and any other variations, appearing throughout this application, do not necessarily refer to the same example.

[0134] Additionally, this application may relate to "determining" various types of information. Determining information may include one or more of the following: for example, estimated information, calculated information, predicted information, or information retrieved from memory. Obtaining may include receiving, retrieving, constructing, generating, and / or determining.

[0135] Furthermore, this application may involve "accessing" various types of information. Accessing information may include one or more of the following: for example, receiving information, retrieving information (e.g., retrieving from memory), storing information, moving information, copying information, calculating information, determining information, predicting information, or estimating information.

[0136] Additionally, this application may relate to "receiving" various types of information. Like "access," the intent to receive is a broad term. Receiving information may include one or more of the following: for example, accessing information or retrieving information (e.g., retrieving from memory). Furthermore, "receiving" is generally referred to in one or more ways during operation, such as storing information, processing information, transmitting information, moving information, copying information, erasing information, calculating information, determining information, predicting information, or estimating information.

[0137] It should be understood that, for example, in the cases of “A / B,” “A and / or B,” and “at least one of A and B,” the use of any of the following “ / ,” “and / or,” and “at least one” is intended to cover selecting only the first listed option (A), or only the second listed option (B), or selecting both options (A and B). As yet another example, in the cases of “A, B, and / or C” and “at least one of A, B, and C,” this wording is intended to include selecting only the first listed option (A), or only the second listed option (B), or only the third listed option (C), or only the first and second listed options (A and B), or only the first and third listed options (A and C), or only the second and third listed options (B and C), or selecting all three options (A, B, and C). As will be apparent to those skilled in the art and related fields, this can be extended to a large number of listed items.

[0138] Furthermore, as used herein, the term "signaling" specifically refers to instructing the corresponding decoder to do something. Encoder signals may include, for example, the number of intensity intervals, the number of model values, particle parameters, particle identification, scaling factors, etc. In this way, in the example, the same parameters are used on both the encoder and decoder sides. Thus, for example, the encoder can send (explicit signaling) specific parameters to the decoder so that the decoder can use the same specific parameters. Conversely, if the decoder already has specific parameters as well as other parameters, signaling can be used without sending (implicit signaling) to simply allow the decoder to know and select specific parameters. Bit savings are achieved in various embodiments by avoiding the transmission of any actual functionality. It should be understood that signaling can be implemented in various ways. For example, in various examples, one or more syntactic elements, flags, etc., are used to send information to the corresponding decoder. Although the verb form of the word "signal" was mentioned above, the word "signal" can also be used as a noun in this document.

[0139] As will be apparent to those skilled in the art, implementations can produce various signals formatted to carry, for example, signals that can be stored or transmitted. Information may include, for example, instructions for performing a method, or data generated by one of the described implementations. For example, a signal may be formatted to carry a bitstream of the described example. Such a signal may be formatted as, for example, an electromagnetic wave (e.g., using the radio frequency portion of a spectrum) or a baseband signal. Formatting may include, for example, encoding a data stream and modulating a carrier wave with the encoded data stream. The information carried by the signal may be, for example, analog or digital information. It is well known that signals can be transmitted via a variety of different wired or wireless links. Signals may be stored on, or accessed or received from, a processor-readable medium.

[0140] This document describes numerous examples. Features of the examples may be provided individually or in any combination across various claim classes and types. Furthermore, examples may include one or more of the features, apparatuses, or aspects described herein, individually or in any combination across various claim classes and types. For example, the features described herein may be implemented in a bitstream or signal that includes information generated as described herein. This information may allow a decoder to decode the bitstream, the encoder, bitstream, and / or decoder being any of the embodiments described. For example, the features described herein may be implemented by creating and / or transmitting and / or receiving and / or decoding a bitstream or signal. For example, the features described herein may be implemented by a method, process, apparatus, medium storing instructions, medium storing data, or signal. For example, the features described herein may be implemented by a TV, set-top box, mobile phone, tablet computer, or other electronic device performing decoding. The TV, set-top box, mobile phone, tablet computer, or other electronic device may display (e.g., using a monitor, screen, or other type of display) a resulting image (e.g., an image reconstructed from the residual of a video bitstream). The TV, set-top box, mobile phone, tablet computer, or other electronic device may receive a signal including an encoded image and perform decoding.

[0141] Figure 5 and Figure 6 An example architecture for split inference between the network and WTRU, consisting of an n-layer model (e.g., layer 1…n), is shown. The first inference can process the first part of the AI ​​model (e.g., layer 1…k). The second inference can process the second part of the AI ​​model (e.g., layer k+1…n).

[0142] Figure 5 and Figure 6 The architecture illustrates the delivery and access capabilities of intermediate data between the WTRU and the network in different scenarios (e.g., two different scenarios). For example, if the media data source originates from the WTRU, the first part of the inference can be executed within the WTRU. In this case, the second part can be executed within the network. The resulting output data can be sent back to the WTRU. If the media data source originates from the network or comes from the network via the WTRU, the first part of the AI ​​model can be executed on the network side. In this case, the second part of the AI ​​model can be executed within the WTRU.

[0143] Figure 5 This illustrates the split inference between WTRU and the network, where the media data source originates from WTRU. Figure 6 This illustrates the split reasoning between WTRU and the network, where the media data source originates from the network.

[0144] In different functions, intermediate data delivery functions can apply serialization techniques (e.g., to encode intermediate data output). Intermediate data access functions can apply corresponding deserialization techniques (e.g., to obtain intermediate data). Binary serialization can transform a data structure into a series of bytes of intermediate data.

[0145] Intermediate data obtained from the first part of the AI ​​model (e.g., from a WTRU to the network) may include multidimensional arrays or tensors. The transmitted tensors may be fed into second inference (e.g., occurring in the network or in a WTRU on another device).

[0146] Tensor shapes can be tuples of positive integers. The size of the tuple can represent the dimensions of the tensor. A value (e.g., each value) can represent the size in one dimension (e.g., each dimension). For example, a tensor of shape (1, 64, 112, 112) can describe a four-dimensional array with 1, 64, 112, and 112 elements in each dimension, respectively.

[0147] Intermediate data dimensions may be lost in the output. The tensor shape may vary depending on the split point. If the data is encoded as a binary bitstream, tensor dimensions may be lost.

[0148] Efficient delivery may be desired. The device can receive and process intermediate data bitstreams. The speed at which the device processes intermediate data bitstreams can depend on a given frame rate (e.g., it may be fast if processing high frame rate inputs).

[0149] Metadata can be transmitted. Metadata can include the tensor shape of the intermediate data. This allows the intermediate tensor to be reconstructed from the decoded bitstream (e.g., with the appropriate original intermediate data shape). Metadata can be transmitted in the frequency band along with the intermediate data bitstream. Metadata can also be transmitted out of band. For example, metadata can be carried in a specific control channel or through the same data channel as the intermediate data.

[0150] This paper provides features associated with tensor shape metadata of encoded intermediate data.

[0151] The first device can process a first part of splitting the AI ​​model. The first device can encode the output intermediate data. The first device can encode the tensor shape into metadata (e.g., along with the bitstream of the intermediate data). The first device can send the combined encoded bitstream to the second device.

[0152] The second device can receive an encoded bitstream. The second device can decode intermediate data and metadata. The second device can extract the tensor shape from the metadata. The second device can reconstruct the intermediate data bitstream back to its original tensor shape (e.g., before feeding the intermediate data into the second part of the AI ​​model).

[0153] Tensor shapes can be encoded using one or more encoding techniques or algorithms.

[0154] The encoding type indicates which encoding technique / algorithm or tensor-shaped encoding structure is used to encode intermediate data and / or metadata. The encoding type can be a Boolean value (e.g., if there are only two possible encoding types).

[0155] The encoded shape may include an indication of the total length of the encoded structure (e.g., 4, such as...). Figure 7 The total length indication (as shown). The encoded shape may include a payload having a list comprising a sequence of unsigned integers (e.g., Figure 7 The encoded shape can include a list of unsigned integers [number of dimensions, value dimension 1, value dimension 2, ...] (e.g., for 4 four-dimensional arrays, 4, 1, 64, 62, 112, where there are 1, 64, 64, and 112 elements in the corresponding dimensions).

[0156] Figure 7 An example encoded tensor shape is shown. Figure 7 In this context, encoding type "X" indicates that the tensor shape is encoded using bytes. Encoding type "Y" indicates that the tensor shape is encoded using strings. Figure 7 In the example shown, the tensor shape is [1, 64, 64, 64] (e.g., indicated by the payload portion of the encoded shape).

[0157] An encoding technique or algorithm instruction can be sent from the first device to the second device. For example, the encoding technique or algorithm instruction can be sent as metadata along with encoded intermediate data.

[0158] In some examples, the encoded tensor can be sent along with the intermediate bitstream (e.g., each time intermediate data is sent). In some examples, the encoded tensor can be sent if the shape changes (e.g., only when the shape changes). For example, some neural network models (e.g., the ResNet family of deep neural network models) can have (e.g., starting with) several layers (e.g., conv2d, BatchNorm2d_2, Relu_3). For example, the first layer can provide intermediate data with a shape (e.g., the same shape S1). Another layer (e.g., the next layer, such as maxPoll_4) can provide intermediate data with a different shape (e.g., S2). In some examples, the encoded shape S1 can be sent using conv2d. In some examples, the encoded shape may not be possible to send using (BatchNorm2d_2, Relu_3). In some examples, the encoded shape S2 can be sent before processing the maxPoll_4 layer.

[0159] Figure 8 An example changing pattern for encoding tensor shapes is shown. For example... Figure 8 As shown, the encoding type "C" can indicate whether the tensor shape is provided (e.g., only provided) if the tensor shape changes. This can save bandwidth and improve computational efficiency. The device receiving intermediate data can track the current shape of the tensor.

[0160] In some examples, metadata may include tensor information (e.g., detailed tensor information). For example, metadata may include tensor structure identifiers. Tensor structure identifiers can identify tensor structures in use (e.g., precise tensor structures) (e.g., including the version of the tensor structure). Tensor structure identification tables may be shared and known by devices (e.g., transmitting and receiving devices). Tensor structure identification tables may be sent during the setup phase (e.g., by sending control data between devices). Table 1 shows examples of tensor tables with identifiers and associated descriptions.

[0161]

[0162] Table 1. Example Tensor Tables Metadata can include tensor names. Tensor names can identify the tensor structure in use based on a string representation (e.g., an exact tensor structure). For example, tensor names could be "Pytorch.Tensor2.0", "TensorStream v2.13.0", or "numpy v1.25".

[0163] In the example, the first device can transmit tensor shape metadata out of band. The tensor shape metadata can be carried in a control channel (e.g., a specific control channel). The tensor shape metadata can also be carried as intermediate data via a data channel (e.g., the same data channel). The metadata can be carried together with the intermediate data without synchronization.

[0164] Figure 9 An example split inference between WTRU and the network is shown. Figure 9 An example of a media data source (e.g., one with tensor shape metadata) in WTRU is shown. In this case, WTRU can provide tensor shape metadata to the network.

[0165] Figure 10 An example split inference between WTRU and the network is shown, where the media data source (e.g., with tensor shape metadata) is in the network. Figure 10 An example is shown of the network providing tensor shape metadata to the WTRU. Figure 11 An example of intermediate data access and delivery functionality is shown.

[0166] Intermediate data delivery functionality can be implemented in a first device. The first device can receive output intermediate data (e.g., inference from a first part of the AI ​​model, such as the head). The first device can encode the tensor shape into metadata (e.g., based on a tensor shape structure or algorithm). The encoding algorithm can be a binary structure, binary serialization, or text serialization (e.g., suitable for small data sizes). The first device can encode the intermediate data into a bitstream (e.g., based on a bitstream structure). For example, the intermediate data can be encoded as a bitstream of floating-point numbers or integers (e.g., int). Encoding a tensor can involve reshaping and / or flattening an input multidimensional tensor into a one-dimensional tensor. The tensor can be encoded according to a binary structure (e.g., a predefined binary structure) (e.g., encoding can then be performed). Binary serialization can be used for large chunks of data (e.g., intermediate data that may be several megabytes in size).

[0167] Binary serialization (e.g., a single binary serialization) can include both data and metadata. Serialization can be based on a composite structure of both data and metadata (e.g., a predefined composite structure).

[0168] The first device can send an encoded bitstream (e.g., data and metadata) to the second device. In some examples, the data and metadata bitstreams can be combined. In some examples, the metadata can be separated and sent independently (e.g., out-of-band transmission).

[0169] The structure may be known to both the first and second devices (e.g., on the transmitter and receiver sides). The structure may be distributed or shared during the configuration phase. The structure may be sent from one device to another (e.g., at least before encoding begins and the encoded data and metadata are sent).

[0170] Intermediate data access functionality can be located in a second device (e.g., a receiver device). The second device can receive a data bitstream and metadata. The metadata can include at least a tensor shape. The second device can decode the tensor shape metadata (e.g., according to a tensor shape structure or algorithm) to obtain the tensor shape. The second device can decode the intermediate data bitstream (e.g., according to a bitstream structure) to obtain a series of intermediate data bytes. The second device can reconstruct the original tensor from this series of intermediate data bytes. Reconstruction can involve converting binary data into a tensor (e.g., reshaping the tensor into the indicated tensor shape). The second device can provide the reshaped (e.g., original) intermediate data to inference processing in the second part of the AI ​​model (e.g., the final part of the AI ​​model, sometimes referred to as the tail portion of the AI ​​model).

[0171] The size of the tensor shape can be used to compute / reconstruct / decode the received intermediate data. Sending the tensor shape along with the intermediate data bitstream avoids providing and / or updating the static tensor shape configuration of the trained models (e.g., all trained models to be used). One or more trained models (e.g., having the same name) may include a modified layer shape. In this case, inference may not produce errors.

[0172] Although some of the features described herein can be performed by video codecs, those skilled in the art will understand that these features are not limited to the use of video codecs.

[0173] Although the features and elements have been described above in specific combinations, those skilled in the art will understand that each feature or element can be used alone or in any combination with other features and elements. Furthermore, the methods described herein can be implemented in a computer program, software, or firmware incorporated into a computer-readable medium for execution by a computer or processor. Examples of computer-readable media include electronic signals (transmitted via a wired or wireless connection) and computer-readable storage media. Examples of non-transitory computer-readable storage media include, but are not limited to, read-only memory (ROM), random access memory (RAM), registers, cache memory, semiconductor memory devices, magnetic media such as internal hard disks and removable disks, magneto-optical media, and optical media such as CD-ROM discs and digital multifunction disks (DVDs). The processor associated with the software can be used to implement a radio frequency transceiver for a WTRU, UE, terminal, base station, RNC, or any host computer.

Claims

1. A first apparatus, comprising: a processor configured to: determine tensor metadata associated with intermediate data; encode the intermediate data and the tensor metadata associated with the intermediate data; and transmit encoded intermediate data and encoded tensor metadata to a second apparatus. the first apparatus is associated with a first portion of an artificial intelligence (AI) model, wherein the first portion is an initial portion of the AI model, the second apparatus is associated with a second portion of the AI model, wherein the second portion is a subsequent portion of the AI model, and the processor is further configured to receive the intermediate data as an output of the first portion of the AI model.

2. The first apparatus of claim 1, wherein, the intermediate data is first intermediate data, the tensor metadata is first tensor metadata that indicates a first tensor shape, and the processor is further configured to:

3. The first apparatus of claim 1 or 2, wherein, determine a second tensor shape associated with second intermediate data, wherein the second tensor shape is different from the first tensor shape; encode the second intermediate data and second tensor metadata, wherein the second tensor metadata indicates the second tensor shape; and transmit encoded second intermediate data and encoded second tensor metadata to the second apparatus. the intermediate data is first intermediate data, the tensor metadata indicates a tensor shape, and the processor is further configured to:

4. The first apparatus according to claim 1 or 2, wherein, determine that second intermediate data is associated with the tensor shape; encode the second intermediate data and an indication that the tensor metadata is not included due to the tensor shape not changing; and transmit the encoded second intermediate data and the encoded indication to the second apparatus. the tensor metadata indicates at least one of: a tensor shape, tensor structure information, a data type, or an encoding algorithm. the processor being configured to encode the intermediate data includes the processor being configured to:

5. The first apparatus of one of claims 1 to 4, wherein, transform a multi-dimensional tensor into a one-dimensional tensor; and 6. The first apparatus according to any one of claims 1 to 5, wherein, encode the one-dimensional tensor according to a binary structure. the processor being configured to transmit the encoded intermediate data and the encoded tensor metadata to the second apparatus includes the processor being configured to: transmit the encoded intermediate data in a first frequency band associated with a data channel; and transmit the encoded tensor metadata in a second frequency band associated with a control channel.

7. The first apparatus according to any one of claims 1 to 6, wherein, the processor being configured to encode the intermediate data and the tensor metadata associated with the intermediate data includes the processor being configured to generate an encoded bitstream, wherein the encoded bitstream includes the encoded intermediate data and the encoded tensor metadata, and the processor being configured to transmit the encoded intermediate data and the encoded tensor metadata to the second apparatus includes the processor being configured to transmit the encoded bitstream to the second apparatus. the first apparatus is a wireless transmit / receive unit (WTRU) or a network entity.

10. A first apparatus, comprising:

8. The first apparatus according to any one of claims 1 to 7, wherein, a processor configured to:

9. The first apparatus according to any one of claims 1 to 8, wherein, ​ ​ ​ receive encoded intermediate data and encoded tensor metadata from a second device; decode the encoded intermediate data and the encoded tensor metadata; and reconstruct a tensor based on the intermediate data and the tensor metadata.

11. The first apparatus of claim 10, wherein, the second device is associated with a first portion of an artificial intelligence (AI) model, where the first portion is an initial portion of the AI model, the first device is associated with a second portion of the AI model, where the second portion is a subsequent portion of the AI model, and the processor is further configured to input the reconstructed tensor to the second portion of the AI model.

12. The first apparatus of claim 10 or 11, wherein, the intermediate data is first intermediate data, the tensor metadata is first tensor metadata that indicates a first tensor shape, the tensor is a first tensor, and the processor is further configured to: receive encoded second intermediate data and encoded second tensor metadata from the second device; decode the encoded second intermediate data and the encoded second tensor metadata, where the second tensor metadata indicates a second tensor shape; and reconstruct a second tensor based on the second intermediate data and the second tensor metadata.

13. The first apparatus of claim 10 or 11, wherein, the intermediate data is first intermediate data, the tensor metadata indicates a tensor shape, and the processor is further configured to: receive encoded second intermediate data and an encoded indication that the tensor metadata is not included because the tensor shape has not changed; decode the encoded second intermediate data and the indication; and determine, based on the indication, that the second intermediate data is associated with the tensor shape.

14. The first apparatus of one of claims 10 to 13, wherein, the tensor metadata indicates at least one of: a tensor shape, tensor structure information, a data type, or an encoding algorithm.

15. The first apparatus according to any one of claims 10 to 14, wherein, the processor being configured to decode the encoded intermediate data includes the processor being configured to: transform a one-dimensional tensor into a multi-dimensional tensor; and decode the multi-dimensional tensor according to a binary structure.

16. The first apparatus according to any one of claims 10 to 15, wherein, the processor being configured to receive the encoded intermediate data and the encoded tensor metadata from the second device includes the processor being configured to: receive the encoded intermediate data in a first frequency band associated with a data channel; and receive the encoded tensor metadata in a second frequency band associated with a control channel.

17. The first apparatus according to any one of claims 10 to 16, wherein, the processor being configured to receive the encoded intermediate data and the encoded tensor metadata from the second device includes the processor being configured to receive an encoded bitstream from the second device, where the encoded bitstream includes the encoded intermediate data and the encoded tensor metadata, and the processor being configured to decode the encoded intermediate data and the encoded tensor metadata includes the processor being configured to decode the encoded bitstream.

18. The first apparatus according to any one of claims 10 to 17, wherein, the processor being configured to decode the encoded intermediate data and the encoded tensor metadata includes the processor being configured to decode one or both of: decoding the encoded tensor metadata according to a tensor shape structure or algorithm to obtain the tensor shape; or encoding the encoded intermediate data according to a bitstream structure to obtain a series of intermediate data bytes.

19. The first apparatus according to any one of claims 10 to 18, wherein, the processor being configured to reconstruct the tensor based on the intermediate data and the tensor metadata includes the processor being configured to: convert binary data in the intermediate data to tensor data; and reshape the tensor to an original tensor shape based on the tensor data and the tensor metadata.

20. The first apparatus according to any one of claims 10 to 19, wherein, the first apparatus is a wireless transmit / receive unit (WTRU) or a network entity.

21. A method performed by a first apparatus, comprising: determining tensor metadata associated with intermediate data; encoding the intermediate data and the tensor metadata associated with the intermediate data; and sending encoded intermediate data and encoded tensor metadata to a second apparatus.

22. The method of claim 21, wherein, the first apparatus is associated with a first portion of an artificial intelligence (AI) model, wherein the first portion is an initial portion of the AI model, the second apparatus is associated with a second portion of the AI model, wherein the second portion is a subsequent portion of the AI model, and the method further comprises receiving the intermediate data as an output of the first portion of the AI model.

23. The method of claim 21 or 22, wherein, the intermediate data is first intermediate data, the tensor metadata is first tensor metadata indicating a first tensor shape, and the method further comprises: determining a second tensor shape associated with second intermediate data, wherein the second tensor shape is different from the first tensor shape; encoding the second intermediate data and second tensor metadata, wherein the second tensor metadata indicates the second tensor shape; and sending encoded second intermediate data and encoded second tensor metadata to the second apparatus.

24. The method of claim 21 or 22, wherein, the intermediate data is first intermediate data, the tensor metadata indicates a tensor shape, and the method further comprises: determining that second intermediate data is associated with the tensor shape; encoding the second intermediate data and an indication that the tensor metadata is not included because the tensor shape has not changed; and sending the encoded second intermediate data and the encoded indication to the second apparatus.

25. The method of one of claims 21 to 24, wherein, the tensor metadata indicates at least one of: a tensor shape, tensor structure information, a data type, or an encoding algorithm.

26. The method of any one of claims 21 to 25, wherein, encoding the intermediate data includes: transforming a multi-dimensional tensor to a one-dimensional tensor; and encoding the one-dimensional tensor according to a binary structure.

27. The method of any one of claims 21 to 26, wherein, sending the encoded intermediate data and the encoded tensor metadata to the second apparatus includes: sending the encoded intermediate data in a first frequency band associated with a data channel; and sending the encoded tensor metadata in a second frequency band associated with a control channel.

28. The method of any one of claims 21 to 27, wherein, Encoding the intermediate data and the tensor metadata associated with the intermediate data comprises generating an encoded bitstream, wherein the encoded bitstream comprises the encoded intermediate data and the encoded tensor metadata, and transmitting the encoded intermediate data and the encoded tensor metadata to the second apparatus comprises transmitting the encoded bitstream to the second apparatus.

29. The method of any one of claims 21 to 28, wherein, The first apparatus is a wireless transmit / receive unit (WTRU) or a network entity.

30. A method performed by a first apparatus, comprising: receiving, from a second apparatus, encoded intermediate data and encoded tensor metadata; decoding the encoded intermediate data and the encoded tensor metadata; and reconstructing a tensor based on the intermediate data and the tensor metadata.

31. The method of claim 30, wherein, The second apparatus is associated with a first portion of an artificial intelligence (AI) model, wherein the first portion is an initial portion of the AI model, the first apparatus is associated with a second portion of the AI model, wherein the second portion is a subsequent portion of the AI model, and the method further comprises inputting the reconstructed tensor to the second portion of the AI model.

32. The method of claim 30 or 31, wherein, The intermediate data is first intermediate data, the tensor metadata is first tensor metadata that indicates a first tensor shape, the tensor is a first tensor, and the method further comprises: receiving, from the second apparatus, encoded second intermediate data and encoded second tensor metadata; decoding the encoded second intermediate data and the encoded second tensor metadata, wherein the second tensor metadata indicates a second tensor shape; and reconstructing a second tensor based on the second intermediate data and the second tensor metadata.

33. The method of claim 30 or 31, wherein, The intermediate data is first intermediate data, the tensor metadata indicates a tensor shape, and the method further comprises: receiving encoded second intermediate data and an encoded indication that the tensor metadata is not included because the tensor shape has not changed; decoding the encoded second intermediate data and the indication; and determining, based on the indication, that the second intermediate data is associated with the tensor shape.

34. The method of one of claims 30 to 33, wherein, The tensor metadata indicates at least one of: a tensor shape, tensor structure information, a data type, or an encoding algorithm.

35. The method of any one of claims 30-34, wherein, Decoding the encoded intermediate data comprises: transforming a one-dimensional tensor into a multi-dimensional tensor; and decoding the multi-dimensional tensor according to a binary structure.

36. The method of any one of claims 30 to 35, wherein, Receiving the encoded intermediate data and the encoded tensor metadata from the second apparatus comprises: receiving the encoded intermediate data in a first frequency band associated with a data channel; and receiving the encoded tensor metadata in a second frequency band associated with a control channel.

37. The method of any one of claims 30 to 36, wherein, Receiving the encoded intermediate data and the encoded tensor metadata from the second apparatus comprises receiving an encoded bitstream from the second apparatus, wherein the encoded bitstream comprises the encoded intermediate data and the encoded tensor metadata, and decoding the encoded intermediate data and the encoded tensor metadata comprises decoding the encoded bitstream.

38. The method of any one of claims 30 to 37, wherein, Decoding the encoded intermediate data and the encoded tensor metadata comprises decoding one or both of: the encoded intermediate data according to a bitstream structure to obtain a series of intermediate data bytes; and the encoded tensor metadata according to a tensor shape structure or algorithm to obtain the tensor shape. or 39. The method of any one of claims 30 to 38, wherein, Encoding the encoded intermediate data according to a bitstream structure to obtain a series of intermediate data bytes. Reconstructing the tensor based on the intermediate data and the tensor metadata comprises: converting binary data in the intermediate data to tensor data; and 40. The method of any one of claims 30 to 39, wherein, based on the tensor data and the tensor metadata, reshaping the tensor to an original tensor shape. The first apparatus is a wireless transmit / receive unit (WTRU) or a network entity.

Images