Learnable Irrelevant Modality Dropout for Multimodal Action Recognition on Modality-Specific Annotated Videos.
Saghir AlfaslyJian LuChen XuYuru ZouPublished in: CVPR (2022)
Keyphrases
- action recognition
- human actions
- multi modal
- action classification
- recognition of human actions
- video dataset
- recognizing human actions
- activity recognition
- human activities
- static images
- recognizing actions
- view invariant
- spatio temporal interest points
- ucf sports
- action recognition in videos
- space time interest points
- human detection
- bag of words
- action detection
- computer vision
- bag of features
- spatial temporal
- motion history images
- body parts
- video sequences
- motion features
- high level
- action primitives
- mid level features
- event recognition
- video search
- spatio temporal
- video content
- video frames
- view invariant action recognition