Skimming, Locating, then Perusing: A Human-Like Framework for Natural Language Video Localization.
Daizong LiuWei HuPublished in: ACM Multimedia (2022)
Keyphrases
- natural language
- video classification
- main contribution
- activity detection
- conceptual framework
- video content
- video streams
- neural network
- digital video
- human robot interaction
- natural language processing
- video sequences
- theoretical framework
- video frames
- lightweight
- spatio temporal
- computer vision
- bdi agents
- machine learning
- real time