A component-based video content representation for action recognition.
Vida AdeliEhsan Fazl ErsiAhad HaratiPublished in: Image Vis. Comput. (2019)
Keyphrases
- action recognition
- video content
- recognizing human actions
- recognition of human actions
- video database
- action recognition in videos
- human actions
- bag of features
- view invariant
- video data
- bag of words
- activity recognition
- video streams
- video sequences
- computer vision
- action classification
- video retrieval
- video shots
- mid level
- body parts
- video frames
- video dataset
- human activities
- key frames
- video search
- bag of visual words
- image representation