Spatial attention based visual semantic learning for action recognition in still images.
Yunpeng ZhengXiangtao ZhengXiaoqiang LuSiyuan WuPublished in: Neurocomputing (2020)
Keyphrases
- action recognition
- mid level
- spatial temporal
- spatial information
- image classification
- bag of words
- static images
- computer vision
- three dimensional
- semantic content
- input image
- object recognition
- human actions
- bag of features
- human detection
- high level
- space time
- image representation
- image collections
- web images
- relevance feedback
- image features
- high level semantics
- recognition of human actions