A hybrid attention-guided ConvNeXt-GRU network for action recognition.
Yiyuan AnYingmin YiXiaoyong HanLi WuChun-Yi SuBojun LiuXianghong XueYankai LiPublished in: Eng. Appl. Artif. Intell. (2024)
Keyphrases
- action recognition
- human actions
- bag of words
- computer vision
- activity recognition
- body parts
- human detection
- action classification
- depth sensors
- spatial temporal
- independent subspace analysis
- static images
- recognizing human actions
- recognizing actions
- depth cameras
- recognition of human actions
- space time interest points
- action recognition in videos
- action primitives
- bag of features
- image representation