Deep Image-to-Video Adaptation and Fusion Networks for Action Recognition.
Yang LiuZhaoyang LuJing LiTao YangChao YaoPublished in: IEEE Trans. Image Process. (2020)
Keyphrases
- action recognition
- static images
- human actions
- mid level
- action classification
- spatial temporal
- bag of features
- recognizing human actions
- computer vision
- action detection
- video dataset
- input image
- bag of words
- recognition of human actions
- image classification
- video sequences
- image features
- activity recognition
- human activities
- motion features
- image content
- video frames
- image retrieval
- image representation
- human detection
- multiscale
- view invariant
- spatio temporal
- human pose
- visual cues
- video images
- space time
- video data
- low level descriptors
- class specific
- body parts
- video content
- keypoints
- visual features
- space time interest points