2531 results about "Decoding methods" patented technology

The invention relates to the technical field of streaming media decoding, and discloses a streaming media decoding method and device for a network high-definition player and a storage medium, and the method comprises the steps: carrying out the multi-thread parallel collection and storage of real-time temperature data, network bandwidth jitter data and video code rate fluctuation data of a decoding chip in the network high-definition player; obtaining a streaming media dynamic feature data set; performing classification training to obtain an inter-frame correlation prediction model; constructing a multi-stage streaming media caching system based on the inter-frame correlation prediction model; monitoring a cache state, a network state and a chip state in the multi-stage streaming media cache system in real time to obtain a decoding event sequence; according to the decoding event sequence, the decoding parameter is adjusted in real time, and the streaming media decoding control instruction is obtained.The collaborative optimization of a network layer, a decoding layer and a display layer is achieved, the playing starting delay is reduced, and the overall stability of a network high-definition player is improved.

The invention relates to the technical field of voice processing, can be applied to business scenes of financial science and technology, medical health and the like, and discloses an audio coding and decoding method, device, equipment and medium, and the method comprises the steps: carrying out the sliding window segmentation processing of an input audio signal, and generating signal segments; processing the signal segments through an encoder containing a multi-layer self-attention mechanism to generate continuous potential representations; performing decomposition vector quantization processing on the continuous potential representation to generate a discrete code; the discrete codes are processed through a decoder comprising a multi-layer self-attention mechanism, and reconstructed signal segments are generated; and splicing the reconstructed signal segments to generate a complete audio signal. According to the method, a traditional convolution structure is replaced by a multi-layer self-attention mechanism, global time sequence dependence modeling is carried out on the audio signals after sliding window segmentation, effective compression of potential representation is realized in combination with decomposition vector quantization, and continuity and fidelity of audio reconstruction are improved on the premise that calculation complexity is not increased.

The invention provides a decoding and coding method, device and equipment, and the decoding method comprises the steps: decoding a first code stream of a current image block, and obtaining a coefficient hyper-parameter feature of the current image block; for each stage sub-block of the current image block, determining a probability distribution parameter of the stage sub-block based on the coefficient hyper-parameter feature, and decoding a second code stream of the current image block based on the probability distribution parameter to obtain a residual feature of the stage sub-block; based on a mean value prediction network, determining mean value features of the sub-blocks in the stage; determining a reconstruction feature of the stage sub-block based on the mean feature of the stage sub-block and the residual feature of the stage sub-block; performing feature aggregation on the reconstruction features of the sub-blocks in each stage to obtain the reconstruction features of the current image block; a reconstructed image block of the current image block is determined based on the reconstruction feature of the current image block. Through the scheme of the invention, the coding performance and the decoding performance are improved.

The invention discloses an audio and video joint coding and decoding method based on generative artificial intelligence. The coding comprises the following steps: extracting various modal features from an audio signal and a video; fusion is carried out in cross-modal attention; task identification: firstly identifying a current task type, determining the task type, and analyzing specific requirements of the task by a system; dynamic self-adaptive weight distribution is carried out; and fusing the features, namely fusing the multi-modal features distributed with different weights. The audio and video joint coding method has the advantages that audio and video feature extraction, video feature extraction and AI-based generation technologies are applied to audio and video joint coding for the first time, and the problems that when video coding and decoding are conducted through a traditional method, compression efficiency is low, and the pursuit of higher quality cannot be met are solved. Meanwhile, on the basis of a generation type coding and decoding mode, the style and quality can be flexibly adjusted according to the personal requirements of the user.

Disclosed are an encoding / decoding method, apparatus, and system. In an implementation, the encoding method includes: encoding video information, where the video information includes M frames, the M frames include a first frame, a second frame, and a third frame, the second frame refers to the first frame, and the third frame refers to the second frame or the first frame, storing the first frame, the second frame, and the third frame in a buffer to obtain candidates of a long-term reference frame, and selecting a subset from the candidates based on a feedback signal as a long-term reference frame.

Embodiments of the present disclosure provide a decoding method, an encoding method, and a storage medium. In the decoding method provided in embodiments of the present disclosure, first transform is performed on first transform coefficients of a current block based on a transform set corresponding to a first intra prediction mode, and the first intra prediction mode is designed to be any one of: an intra prediction mode derived from a decoder side intra mode derivation (DIMD) mode for a prediction block of the current block, an intra prediction mode derived from the DIMD mode for an output vector of an optimal matrix based intra prediction (MIP) mode for predicting the current block, an intra prediction mode derived from the DIMD mode for reconstructed samples in a first template region adjacent to the current block, and an intra prediction mode derived from a template based intra mode derivation (TIMD) mode.

The present invention provides a method for real-time parsing and dynamic decoding of audio and video streams in 5G enhanced calls, and relates to the field of new generation communication telephone technology. The first method is to perform audio and video media negotiation after the 5G enhanced call starts, read the SDP description information to separate the media description control information and the RTP data packet, separate the audio and video media stream data according to the media load type, parse the load data according to the RTP data protocol format, and parse the load data of the data packet in the call in real time. The second method is to retain the effective frame data, rearrange the frame data and compensate for the silent frame of the extracted AMR-WB voice data, parse the complete AMR-WB audio stream, and then determine the decoding parameters according to the obtained audio clock frequency, and transcode the AMR-WB audio stream into the PCM encoding format. This method can solve the problem that the existing technology cannot perform real-time parsing of audio and video streams under the 5G enhanced call network. Under the premise of ensuring the quality of 5G enhanced calls, recognizable transcoded audio is provided for intelligent interaction in calls.

Provided herein is a novel method named Knowledge-Constrained Tree Search Decoding (KCTS) is provided, which is a first discriminator-guided constrained decoding approach to knowledge-grounded generation. The KCTS method also employs a Monte-Carlo Tree Search decoding (MCTS) instead of conventional LM decoding methods, which re-orders each token's importance based on the estimated future faithfulness starting from that token with multiple simulations. Coupled with a novel token-level hallucination detection method, RIPA (Reward Inflection Point Approximation), trained to predict the starting point of the hallucinating token, enabling effective adaptation of the knowledge classifier defined on the sequence level to the token level, this novel method is able to greatly mitigate hallucination problems of LLMs without the need of fine-tuning, thereby preventing the incurrence of high computational costs.

A system related to tactile reproduction is made more efficient by achieving a data amount reduction of a tactile signal while ensuring reproducibility of a tactile sense.An encoding apparatus according to the present technology includes an encoding unit configured to encode tactile signals using different data formats between different regions of a human body. Therefore, for example, a data amount reduction of a tactile signal can be performed considering difficulty in perceiving tactile stimulation of a region, by reducing a data distribution of a tactile signal for a region with low tactile sensitivity using a difference in tactile sensitivity between regions of a human body, and the like.

The invention provides a cosine convolution multichannel group decoding method and system for electroencephalogram classification, and relates to the technical field of artificial intelligence, and the method comprises the steps: obtaining different types of to-be-classified motor imagery electroencephalogram signals, inputting the motor imagery electroencephalogram signals into an electroencephalogram signal classification model, and outputting the classification results of the different types of motor imagery electroencephalogram signals; wherein through the cosine convolution time-frequency feature extraction module, cosine convolution kernels with different frequencies are adopted to decompose and reconstruct different frequency components, and multi-scale time-frequency features are obtained; inputting the multi-scale time-frequency features into a multi-channel group spatial feature extraction module, and carrying out convolution on data of each channel subgroup in a channel dimension by adopting an independent separable convolution branch network to obtain time-frequency-space features of electroencephalogram signals of each channel subgroup; and splicing the time-frequency-space features of the electroencephalogram signals of each channel subgroup into a fusion feature vector, and outputting the probability of the electroencephalogram signals of the motor imagery corresponding to each category of the motor imagery through a full connection layer.

Encoding and decoding methods are employed for toggleable overlays in a video. An encoding method comprises receiving a plurality of image frames; determining one or more overlay image frames each comprising a plurality of toggleable overlays, each toggleable overlay being associated with an identifier. An image frame is associated with an overlay image frame of the one or more overlay image frames. Metadata is added to a header of the image frame, wherein the metadata comprises, for each toggleable overlay of the plurality of toggleable overlays: position data identifying a position of the toggleable overlay in the overlay image frame, size data identifying a size of the toggleable overlay in the overlay image frame, and identification data corresponding to the identifier of the toggleable overlay.

Embodiments of the present disclosure provide an encoding and decoding method, apparatus and device. The method includes: obtaining a weight prediction angle and weight configuration parameters; configuring reference weight values for surrounding positions outside the current block; determining a surrounding matching position to which the pixel position points; determining a target weight value of the pixel position based on a reference weight value associated with the surrounding matching position, and determining an associated weight value of the pixel position based on the target weight value of the pixel position; determining a first prediction value of the pixel position and a second prediction value; determining a weighted prediction value of the pixel position based on the first prediction value, target weight value, second prediction value and associated weight value; determining weighted prediction values of the current block based on the weighted prediction value of each pixel position of the current block.

An electronic device performs sub-band decomposition on a to-be-coded audio to obtain a to-be-coded low frequency signal corresponding to a low frequency band and a to-be-coded high frequency signal corresponding to a high frequency band. The device performs compression coding on the to-be-coded low frequency signal to obtain low frequency coded data of the to-be-coded low frequency signal. The device determines high frequency prediction information according to the to-be-coded low frequency signal. The device performs feature extraction on the to-be-coded high frequency signal to obtain high frequency feature information. The device determines high frequency compensation information of the to-be-coded high frequency signal according to a difference between the high frequency feature information and the high frequency prediction information. The device also performs encapsulation processing on the low frequency coded data and the high frequency compensation information to obtain audio coded data of the to-be-coded audio.

The invention discloses a voice decoding method, system and device based on electroencephalogram signals and a medium, and relates to the technical field of electroencephalogram signal processing.The method comprises the steps that reading electroencephalogram signals and voice signals in the reading process of a to-be-tested person and imagination electroencephalogram signals in the imagination reading process of the to-be-tested person are collected; inputting the reading electroencephalogram signals and the voice signals into the DRCL to generate electroencephalogram characteristics containing voice information; training the DBM by using the electroencephalogram characteristics as input and using the voice signals as output, and adjusting the DBM by using imaginary electroencephalogram signals to construct a voice synthesizer; a mapping relation between the imaginary electroencephalogram signals and the voice signals is generated through the voice synthesizer, and decoding from the electroencephalogram signals to the voice signals is completed; according to the method, a deep representation correlation learning method is provided, potential correlation between electroencephalogram and voice signals can be deeply mined through a multi-layer network structure, a complex mode which is difficult to recognize by a traditional model is captured, and the voice decoding process is more accurate.

The invention provides a Chinese quintessence art gene decoding method and system based on cross-modal AI, and belongs to the crossing field of artificial intelligence and digital media art, and the method comprises the steps: S1, constructing a Chinese painting-music-text multi-modal data set; s2, inputting the traditional Chinese painting image into a visual encoder improved based on CLIP-ViT, and outputting a 512-dimensional visual Token sequence through a normalization module, a position encoding module and a Transform encoder; s3, inputting the visual Token sequence and the emotion label into a cross-modal adapter, and directly mapping the visual Token to a music hidden space by adopting a self-attention mechanism to obtain a music embedding vector; and S4, inputting the user parameters into the improved high-frequency fidelity generative adversarial network to generate Chinese traditional music audio conforming to five sound orders. According to the method, intelligent semantic communication between visual art and auditory art is realized.

An image decoding / encoding method and apparatus are discussed. The image decoding method can include decoding candidate mode set selecting information, selecting a candidate mode set based on the candidate mode set selecting information, decoding, in case the selected candidate mode set comprises two or more candidate modes, candidate mode selecting information, and selecting one candidate mode among at least one candidate mode included in the candidate mode set based on the candidate mode selecting information as an intra prediction mode of a current block.

The embodiment of the invention provides a coding and decoding method and an end-cloud cooperation system. The coding and decoding method is realized based on the end-cloud collaborative system, and the total code rate of the end-cloud can be reduced under the condition of ensuring the end-side rendering picture. The encoding method comprises the steps that rendering processing is carried out on a three-dimensional scene to obtain a rendered image, a rendering intermediate result is generated in the rendering processing process, and the rendering intermediate result comprises a first rendering intermediate result. And performing target operation on the reconstructed image based on the first rendering intermediate result to generate a virtual reference block. And predicting the rendered image based on the virtual reference block to obtain a predicted image. And encoding a residual image between the predicted image and the rendered image to obtain a code stream. Wherein the target operation comprises at least one of reprojection, validity check, weighted averaging, hole filling or intra-frame noise reduction.

The invention discloses a sleep real-time staging modeling method, a sleep real-time encoding and decoding method and a sleep real-time staging modeling system. EEG, EOG and EMG signals of a subject are collected, statistics, frequency domain and frequency domain characteristics and other characteristics are extracted after preprocessing, sleep stages marked by experts serve as real labels, a model is trained in a supervised learning mode, and real-time classification of the sleep stages is achieved. Furthermore, high-precision encoding and decoding of sleep content are realized by applying stimulation prompt during sleep, collecting and preprocessing whole-brain EEG signals, distinguishing NREM and REM stages, training encoding and decoding models respectively, and aligning nerve characterization during waking and sleep by utilizing comparative learning.

A cross-component dependent tool to be used for a chroma block of a picture is enabled responsive to a size of said chroma block and to a size of at least one luma block co-located with the chroma block. Then, the chroma block is decoded responsive to said enablement of said cross-component dependent tool. A encoding and decoding methods are presented as well as encoding and decoding devices.

A method for decoding includes: reference information of a current block is determined; a filtering process is performed on at least partial information in the reference information of the current block, to determine target information of the current block; a respective one of weighting coefficients is determined according to each of reference sample values of a first color component in the target information; a prediction block of a second color component of the current block is determined according to the weighting coefficients and reference sample values of a second color component in the target information; and reconstructed values of second color component samples of the current block are determined according to the prediction block.

A radar system may include transmitter modules configured to transmit multiple transmit signals in accordance with a Doppler Domain Multiplexing (DDM) scheme, receiver modules configured to receive reflections from the plurality of transmit signals reflected off an object and to generate corresponding digital signals, and a signal processor configured to generate a range-Doppler antenna cube representing the digital signals, and, for each of range bin of the cube, to generate a decoded range-Doppler bit map (RDBM) from the range-Doppler antenna cube by generating decoded RDBM rows by extracting a range bin matrix, performing a Discrete Fourier Transform on range bin matrix to generate an output matrix, determining peak locations in the output matrix, comparing associated peak locations across transmit channels of the output matrix to identify location-matched peaks associated with the Doppler bin, and generating a decoded RDBM row based on the location-matched peaks.

The embodiment of the invention provides a voice coding method and decoding method based on time sequence modeling and a related device. The voice coding method comprises the following steps: acquiring target voice; extracting voice features corresponding to the voice waveform of the target voice through an input cavity convolution extraction module; performing down-sampling processing on the voice features through a down-sampling module to obtain a down-sampling sequence; performing long time sequence modeling on the down-sampling sequence through a long and short time memory neural network added with exponential activation and matrix operation to obtain a coding sequence; and converting the feature dimension of the coding sequence into 128 dimensions through the first convolutional layer to obtain a target code stream. According to the embodiment of the invention, the feature extraction module, the down-sampling module, the long and short term memory neural network and the output cavity convolution layer code the target voice, so that the compression of the voice with the extremely low bit rate can be realized, and the reconstruction of the voice with the extremely low bit rate and high quality under 150bps is realized.

The invention discloses a natural statement decoding method and device based on high-density electrocorticogram. The method comprises the following steps: acquiring an electroencephalogram signal acquired based on the high-density electrocorticogram; different frequency band signals are extracted from the electroencephalogram signals; the signals of different frequency bands comprise high gamma frequency band signals and at least one frequency band signal with the frequency lower than that of the high gamma frequency band signals; acquiring a voice starting point corresponding to each frequency band signal, and determining a target voice starting point based on the voice starting point corresponding to each frequency band signal; after the target voice starting point, acquiring a syllable classification result and a tone decoding result corresponding to each frequency band signal, determining a target syllable classification result based on the syllable classification result corresponding to each frequency band signal, and determining a target tone decoding result based on the tone decoding result corresponding to each frequency band signal; and determining a target tone language corresponding to the electroencephalogram signal based on the target syllable classification result and the target tone decoding result. According to the scheme, the natural statement decoding accuracy can be improved.

The embodiment of the invention discloses a coding and decoding method and device, relates to the technical field of media, and can perform spatial dimension quality adjustment on image content through JPEGAI. The method comprises the following steps: acquiring a target quality matrix; and scaling the first residual image and / or the first Gaussian distribution parameter information according to the target quality matrix to obtain a second residual image and / or second Gaussian distribution parameter information. And generating a code stream according to the target quality matrix, the second residual image and / or the second Gaussian distribution parameter information. Wherein the target quality matrix is used for representing image quality of each region in a residual image of a feature domain, the first residual image is the residual image of the feature domain, and the first Gaussian distribution parameter information is Gaussian distribution parameter information of the residual image of the feature domain.

The invention belongs to the related technical field of workshop scheduling, and discloses a flexible workshop production scheduling method and system with a double-track type guide vehicle, and the method comprises the steps: building a flexible workshop production scheduling model with the double-track type guide vehicle in consideration of the machine constraint of a flexible workshop machining process and the carrying constraint of the track type guide vehicle; performing iterative solution on the flexible workshop production scheduling model through an optimization algorithm to obtain a flexible workshop production scheduling method; during iterative solution, the procedure processing sequence, the procedure processing machine selection and the procedure guide vehicle selection are coded respectively to form chromosomes, and the three chromosomes correspond to one solution; and a decoding operator based on motion conflict repair is executed on a solution generated by each iteration. According to the method, processing machine constraints and track guided vehicle constraints of processes are considered, a three-layer coding structure is provided, and a decoding mode based on motion conflict repair is designed, so that collaborative optimization scheduling of a flexible manufacturing system with double RGVs can be realized.

The invention relates to the technical field of audio encoding and decoding, in particular to a fast encoding and decoding method and system for real-time audio. The method comprises the following steps: acquiring real-time sampling data of an input audio stream, and performing multi-time-point sliding window division and coding preprocessing to generate a coding preprocessing enhanced audio; carrying out adaptive quantization strategy analysis on the coding preprocessing enhanced audio, carrying out multi-level residual quantization modeling, and constructing a real-time increment coding mapping table; performing multi-module decomposition execution based on the real-time incremental coding mapping table, performing multi-thread parallel coding optimization, and constructing a real-time audio parallel coding strategy; and carrying out real-time coding processing according to a real-time audio parallel coding strategy, and carrying out task-by-task code rate distortion optimization to obtain an optimal coding parameter of each coding task. According to the invention, high-fidelity and low-delay audio coding and decoding are realized, and the auditory experience of a user is improved.

A mesh decoding device, including: a circuit, wherein the circuit: acquires a decoded motion vector of a vertex connected to a vertex to be decoded from a motion vector buffer; and outputs a motion vector of the vertex to be decoded using all or a part of the acquired decoded motion vector.

The invention provides an electroencephalogram text cross-modal brain intention decoding method based on generative text prompt. International public motor imagery data sets BCI IV 2a and BCI IV 2b are adopted for validity verification, and the method comprises the steps that firstly, a public data set is preprocessed, and a training set and a test set are established; secondly, constructing an electroencephalogram text cross-modal brain intention decoding model based on generative text prompt; inputting the preprocessed training set into a model, and carrying out model training; and finally, inputting the test set into the trained model, and carrying out model performance test. The method has the advantages that the motor imagery task text description is generated by utilizing the generative language model, and the model is guided to understand the correlation between the motor imagery task context and the electroencephalogram text data; an electroencephalogram text multi-scale cross-modal attention feature fusion strategy is designed, and effective complementation of multi-modal brain intention information is achieved. Effectiveness verification is carried out on the method on BCI IV 2a and BCI IV 2b, the average recognition accuracy rate reaches 85.32% and 87.69% respectively, and both the average recognition accuracy rate and the average recognition accuracy rate are superior to those of an existing optimal method.

An image decoding method according to the present invention may comprise the steps of: deriving a merge candidate from a candidate block; generating a first merge candidate list including the merge candidate; specifying any one of a plurality of merge candidates included in the first merge candidate list; deriving affine vectors of a current block on the basis of motion information of the specified merge candidate; deriving a motion vector of a sub-block in the current block on the basis of the affine vectors; and performing motion compensation on the sub-block on the basis of the motion vector.

The invention relates to a decoding method and device, electronic equipment and a computer program product, and belongs to the technical field of computers. The method comprises the following steps: inputting each decoding frame to be decoded into a decoder in sequence; for each input decoding frame, acquiring a decoding reference relationship of the decoding frame through a main thread, and judging whether the decoding frame meets a decoding condition or not according to the decoding reference relationship; and if the decoded frame satisfies the decoding condition, sending a decoding task corresponding to the decoded frame to a sub-thread so as to decode the decoded frame through the sub-thread. The decoding reference relation of the decoding frame is acquired and analyzed through the main thread, the decoding frame meeting the decoding condition is sent to the branch threads for decoding, the upper limit of the decoding parallelism degree can be improved, and the decoding speed is increased.