Segment spatial-temporal representation and cooperative learning of convolution neural networks for multimodal-based action recognition.
Ziliang RenQieshi ZhangJun ChengFusheng HaoXiangyang GaoPublished in: Neurocomputing (2021)
Keyphrases
- spatial temporal
- action recognition
- cooperative learning
- recognizing human actions
- recognition of human actions
- human actions
- action recognition in videos
- view invariant
- bag of features
- bag of words
- activity recognition
- cooperative
- computer vision
- learning environment
- language learning
- multi modal
- spatio temporal
- problem based learning
- image representation
- space time interest points
- video shots
- learning community
- human activities
- spatial information
- co occurrence
- multimedia