No frame left behind: Full Video Action Recognition.
Xin LiuSilvia L. PinteaFatemeh Karimi NejadaslOlaf BooijJan C. van GemertPublished in: CoRR (2021)
Keyphrases
- action recognition
- human actions
- action classification
- spatial temporal
- video dataset
- video frames
- action detection
- recognition of human actions
- motion features
- bag of words
- recognizing human actions
- human activities
- key frames
- static images
- activity recognition
- human detection
- space time interest points
- computer vision
- video data
- video sequences
- temporal coherence
- motion history images
- body parts
- video streams
- video analysis
- mid level
- bag of features
- view invariant
- human pose
- space time
- action primitives
- recognizing actions
- video images
- video content
- atomic actions
- visual features
- multimedia
- video shots
- max margin
- human activity recognition