Stacked Temporal Attention: Improving First-person Action Recognition by Emphasizing Discriminative Clips.
Lijin YangYifei HuangYusuke SuganoYoichi SatoPublished in: BMVC (2021)
Keyphrases
- action recognition
- action classification
- spatial temporal
- video database
- mid level
- human actions
- motion history images
- bag of words
- recognizing actions
- max margin
- human detection
- deformable part models
- activity recognition
- computer vision
- spatio temporal
- recognizing human actions
- spatial and temporal
- body parts
- static images
- mid level features
- bag of features
- temporal information
- depth sensors
- action recognition in videos
- recognition of human actions
- video dataset
- action detection
- low level
- view invariant
- space time
- semi supervised
- video clips
- human pose