AIM: Adapting Image Models for Efficient Video Action Recognition.
Taojiannan YangYi ZhuYusheng XieAston ZhangChen ChenMu LiPublished in: CoRR (2023)
Keyphrases
- action recognition
- static images
- human actions
- spatial temporal
- mid level
- action classification
- recognizing human actions
- video dataset
- bag of words
- random fields
- image retrieval
- computer vision
- bag of features
- action detection
- recognition of human actions
- human activities
- image representation
- image content
- motion features
- image classification
- input image
- human pose
- low level descriptors
- space time interest points
- image features
- high resolution
- human detection
- video frames
- multiscale
- key frames
- video images
- activity recognition
- video sequences
- low level
- view invariant
- object recognition
- machine learning