Human-Object Relation Network For Action Recognition In Still Images.
Wentao MaShuang LiangPublished in: ICME (2020)
Keyphrases
- action recognition
- static images
- bag of words
- mid level
- human actions
- bag of features
- three dimensional
- human object interactions
- image classification
- image features
- lighting conditions
- human movements
- input image
- video dataset
- activity recognition
- object recognition
- action classification
- object segmentation
- computer vision
- human activities
- bounding box
- low level descriptors
- recognition of human actions
- multiple objects
- human detection
- keypoints
- spatio temporal
- class specific
- intensity images
- partial occlusion
- recognizing human actions
- viewpoint
- moving objects