Convolutional Gated Recurrent Units Fusion for Video Action Recognition.
Bo HuangHualong HuangHongtao LuPublished in: ICONIP (3) (2017)
Keyphrases
- action recognition
- human actions
- action classification
- video dataset
- spatial temporal
- action detection
- recognizing human actions
- motion features
- human activities
- recognition of human actions
- bag of words
- spatio temporal interest points
- space time interest points
- static images
- activity recognition
- human detection
- computer vision
- video sequences
- motion history images
- video frames
- video data
- mid level
- multimedia
- human pose
- bag of features
- key frames
- spatio temporal
- body parts
- motion capture data
- action primitives
- video streams
- recognizing actions
- space time
- video analysis
- video clips
- video content
- action recognition in videos
- optical flow
- view invariant action recognition