MLENet: Multi-Level Extraction Network for video action recognition.
Fan WangXinke LiHan XiongHaofan MoYongming LiPublished in: Pattern Recognit. (2024)
Keyphrases
- action recognition
- human actions
- action classification
- spatial temporal
- video dataset
- action detection
- recognition of human actions
- motion features
- static images
- recognizing human actions
- human detection
- activity recognition
- bag of words
- human activities
- spatio temporal interest points
- space time interest points
- computer vision
- recognizing actions
- motion history images
- bag of features
- mid level
- video sequences
- wireless sensor networks
- multimedia
- view invariant
- body parts
- video streams
- space time
- video data
- atomic actions
- video surveillance
- video frames
- spatio temporal
- view invariant action recognition