Temporal Modeling Approach for Video Action Recognition Based on Vision-language Models.
Yue HuangXiaodong GuPublished in: ICONIP (3) (2023)
Keyphrases
- action recognition
- language model
- spatial temporal
- human actions
- action classification
- motion history images
- computer vision
- language modeling
- video dataset
- action detection
- video database
- bag of words
- recognition of human actions
- recognizing human actions
- probabilistic model
- activity recognition
- human activities
- spatio temporal
- n gram
- static images
- retrieval model
- information retrieval
- atomic actions
- motion features
- query expansion
- space time interest points
- spatial and temporal
- statistical language modeling
- human object interactions
- test collection
- space time
- temporal information
- context sensitive
- multimedia
- language models for information retrieval
- temporal structure
- video sequences
- video data
- visual features
- multi view
- feature vectors
- smoothing methods
- video frames
- relevance model
- human pose
- video shots
- feature selection