Temporal cues enhanced multimodal learning for action recognition in RGB-D videos.
Dan LiuFanrong MengQing XiaZhiyuan MaJinpeng MiYan GanMao YeJianwei ZhangPublished in: Neurocomputing (2024)
Keyphrases
- action recognition
- human actions
- action classification
- recognizing human actions
- static images
- computer vision
- human activities
- spatial temporal
- recognition of human actions
- depth cameras
- video surveillance
- mid level
- max margin
- motion features
- action recognition in videos
- ucf sports
- space time interest points
- action detection
- video dataset
- visual cues
- bag of words
- text classification
- low level
- spatio temporal