VLG: General Video Recognition with Web Textual Knowledge.
Jintao LinZhaoyang LiuWenhai WangWayne WuLimin WangPublished in: CoRR (2022)
Keyphrases
- multimedia
- special case
- knowledge base
- video streams
- textual data
- recognition rate
- multimedia information
- video data
- knowledge acquisition
- domain knowledge
- web applications
- web mining
- activity recognition
- web documents
- knowledge management
- recognition accuracy
- video clips
- computer vision
- web content
- recognition algorithm
- information overload
- textual features
- textual case based reasoning
- space time
- semantic web
- web pages
- real time
- knowledge sharing
- constantly growing
- essential information
- current web
- visual representations
- website
- user generated
- feature extraction
- video sequences
- web resources
- natural language
- object recognition
- video content
- expert systems
- information sources