AdaFocusV3: On Unified Spatial-Temporal Dynamic Video Recognition.
Yulin WangYang YueXinhong XuAli HassaniVictor KulikovNikita OrlovShiji SongHumphrey ShiGao HuangPublished in: ECCV (4) (2022)
Keyphrases
- spatial temporal
- action recognition
- spatial and temporal
- spatio temporal
- temporal information
- video shots
- human actions
- object recognition
- activity recognition
- spatial and temporal information
- spatial information
- space time interest points
- machine learning
- video database
- space time
- video sequences
- feature extraction