AdaFocusV3: On Unified Spatial-temporal Dynamic Video Recognition.
Yulin WangYang YueXinhong XuAli HassaniVictor KulikovNikita OrlovShiji SongHumphrey ShiGao HuangPublished in: CoRR (2022)
Keyphrases
- spatial temporal
- action recognition
- video shots
- temporal information
- spatio temporal
- spatial and temporal
- human actions
- human activities
- activity recognition
- spatial information
- video frames
- object recognition
- video sequences
- video database
- image sequences
- computer vision
- bag of words
- search engine
- video data
- visual features
- video content
- video retrieval