A Multimodal, Multi-Task Adapting Framework for Video Action Recognition.
Mengmeng WangJiazheng XingBoyuan JiangJun ChenJianbiao MeiXingxing ZuoGuang DaiJingdong WangYong LiuPublished in: AAAI (2024)
Keyphrases
- action recognition
- multi task
- video dataset
- human actions
- action classification
- multi task learning
- action detection
- bag of words
- activity recognition
- computer vision
- learning tasks
- multi class
- multimedia
- recognition of human actions
- human activities
- space time interest points
- video frames
- video data
- spatio temporal
- video sequences
- feature selection
- space time
- learning problems
- feature vectors
- human detection
- feature space
- sparse learning
- reinforcement learning
- decision trees