Attentional Fused Temporal Transformation Network for Video Action Recognition.
Ke YangZhiyuan WangHuadong DaiTianlong ShenPeng QiaoXin NiuJie JiangDongsheng LiYong DouPublished in: ICASSP (2020)
Keyphrases
- action recognition
- spatial temporal
- human actions
- action classification
- motion history images
- video dataset
- recognition of human actions
- bag of words
- action detection
- spatio temporal
- spatial and temporal
- human activities
- recognizing human actions
- static images
- computer vision
- activity recognition
- motion features
- temporal information
- mid level
- space time
- human detection
- human pose
- video sequences
- space time interest points
- multimedia
- atomic actions
- body parts
- video frames
- depth sensors
- video data
- temporal structure
- temporal resolution
- view invariant
- video content
- video streams
- recognizing actions
- action recognition in videos
- motion trajectories
- bag of features
- view invariant action recognition