Fine-grained Knowledge Graph-driven Video-Language Learning for Action Recognition.
Rui ZhangYafen LuPengli JiJunxiao XueXiaoran YanPublished in: CoRR (2024)
Keyphrases
- fine grained
- action recognition
- language learning
- human actions
- action classification
- coarse grained
- spatial temporal
- video dataset
- action detection
- recognizing human actions
- recognition of human actions
- static images
- motion features
- mobile language learning
- computer assisted language learning
- human activities
- access control
- computer vision
- foreign language
- human pose
- activity recognition
- space time interest points
- multimedia
- view invariant
- mobile learning
- space time
- data lineage
- motion history images
- video content
- recognizing actions
- video sequences
- video data
- learning systems
- bag of words
- spatio temporal
- video clips