Skeletal Spatial-Temporal Semantics Guided Homogeneous-Heterogeneous Multimodal Network for Action Recognition.
Chenwei ZhangYuxuan HuMin YangChengming LiXiping HuPublished in: ACM Multimedia (2023)
Keyphrases
- spatial temporal
- action recognition
- human actions
- bag of words
- computer vision
- activity recognition
- recognition of human actions
- view invariant
- action classification
- bag of features
- temporal information
- recognizing human actions
- video database
- video shots
- human motion
- semantic information
- multi modal
- image classification
- wireless sensor networks
- recognizing actions
- multiscale