Matching video net: Memory-based embedding for video action recognition.
Daesik KimMyunggi LeeNojun KwakPublished in: IJCNN (2017)
Keyphrases
- action recognition
- human actions
- action classification
- spatial temporal
- action detection
- video dataset
- video data
- recognition of human actions
- recognizing human actions
- static images
- human activities
- video sequences
- motion features
- video content
- multimedia
- video analysis
- bag of words
- video streams
- activity recognition
- motion history images
- mid level
- video images
- spatio temporal interest points
- video clips
- video shots
- body parts
- computer vision
- video frames
- event recognition
- video retrieval
- space time
- feature points
- spatio temporal
- image sequences
- space time interest points