Spatial-Temporal Information Aggregation and Cross-Modality Interactive Learning for RGB-D-Based Human Action Recognition.
Qin ChengZhen LiuZiliang RenJun ChengJianming LiuPublished in: IEEE Access (2022)
Keyphrases
- spatial temporal
- action recognition
- human actions
- temporal information
- interactive learning
- bag of words
- spatio temporal
- human activities
- contextual information
- video database
- higher level
- wireless sensor networks
- action classification
- activity recognition
- computer vision
- spatial information
- video shots
- depth cameras