A Survey on Backbones for Deep Video Action Recognition.
Zixuan TangYoujun ZhaoYuhang WenMengyuan LiuPublished in: CoRR (2024)
Keyphrases
- action recognition
- human actions
- action classification
- spatial temporal
- video dataset
- action detection
- recognizing human actions
- recognition of human actions
- motion features
- human activities
- static images
- space time interest points
- spatio temporal interest points
- bag of words
- activity recognition
- human detection
- computer vision
- mid level
- body parts
- recognizing actions
- video sequences
- video data
- multimedia
- human pose
- motion history images
- bag of features
- three dimensional
- human activity recognition
- view invariant
- space time
- video frames
- motion capture data
- spatio temporal
- depth sensors
- max margin
- video streams
- machine learning
- action recognition in videos
- video surveillance
- video analysis