A Micro Video Classification Method and System Based on Missing Data Completion
A technology of missing data and classification methods, applied in neural learning methods, instruments, biological neural network models, etc., can solve problems such as reducing the accuracy of micro-video classification tasks, achieve strong semantic representation capabilities, and ensure accuracy
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0059] like figure 1 As shown, this embodiment provides a micro-video classification method based on missing data completion. This embodiment uses the method applied to the server as an example for illustration. It can be understood that the method can also be applied to the terminal, and can also be applied to It includes terminals, servers and systems, and is realized through the interaction of terminals and servers. The server can be an independent physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud service, cloud database, cloud computing, cloud function, cloud storage, network server, cloud communication, intermediate Cloud servers for basic cloud computing services such as software services, domain name services, security service CDNs, and big data and artificial intelligence platforms. The terminal may be a smart phone, a tablet computer, a notebook computer, a desktop computer, a smart speaker, a smart watch, etc...
Embodiment approach
[0064] As one or more implementations, the bidirectional recurrent generative adversarial network includes: three recurrent generative adversarial networks, each recurrent generative adversarial network includes two directions, generating a second modality from a first modality and generating a second modality from a second modality The modality generates a first modality, wherein the first modality is a visual modality or a sound modality or a text modality, the second modality is a visual modality or a sound modality or a text modality, and the first modality is the same as the The second mode is not the same.
[0065] Specifically, as image 3 Shown: The features of the three modalities of the micro-video go through three groups of recurrent generative adversarial networks to generate the feature representations of other modalities respectively. Each set of recurrent generative adversarial networks includes two directions, generating modality B from modality A and generati...
Embodiment 2
[0092] This embodiment provides a micro-video classification system based on missing data completion.
[0093] A micro-video classification system based on missing data completion, including:
[0094] A classification module, which is configured to: obtain a classification result of the micro-videos with partial modal data missing based on the micro-videos with partial modal data missing, using the trained micro-video classification network;
[0095] The model building module is configured as follows: the micro-video classification network includes: based on the micro-videos with missing partial modal data, a bidirectional loop is used to generate an adversarial network to obtain the missing modalities of the micro-videos; The missing modalities of the micro-videos with modalities and complements go through the common subspace learning module to extract the visual modal semantic feature representation vector, the voice modal semantic feature representation vector and the text ...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap