Exploring multimodal video representation for action recognition.
Cheng WangHaojin YangChristoph MeinelPublished in: IJCNN (2016)
Keyphrases
- action recognition
- video representation
- video database
- spatio temporal
- human actions
- space time
- video analysis
- bag of words
- video streams
- activity recognition
- video content
- generative model
- body parts
- computer vision
- dynamic textures
- human activities
- key frames
- motion patterns
- video data
- video processing
- mid level
- mean shift
- bag of features
- video sequences
- multiscale
- bag of visual words
- multimedia