Multifeature fusion action recognition based on key frames.
Yuerong ZhaoHongbo GuoLing GaoHai WangJie ZhengKan ZhangYong ZhengPublished in: Concurr. Comput. Pract. Exp. (2023)
Keyphrases
- action recognition
- key frames
- video retrieval
- human actions
- visual content
- video sequences
- bag of words
- video clips
- video shots
- visual features
- video data
- feature vectors
- video content
- activity recognition
- video database
- spatial temporal
- video frames
- computer vision
- low level features
- visual cues
- action classification
- recognition of human actions
- mid level
- video summarization
- view invariant
- recognizing human actions
- action recognition in videos
- body parts
- human activities
- semantic concepts
- video segments
- bag of visual words
- bag of features
- recognizing actions
- image retrieval