Multi-Modal Multi-Action Video Recognition.
Zhensheng ShiJu LiangQianqian LiHaiyong ZhengZhaorui GuJunyu DongBing ZhengPublished in: ICCV (2021)
Keyphrases
- multi modal
- video search
- semantic concepts
- human actions
- action recognition
- action classification
- human activities
- feature extraction
- audio visual
- video data
- multi modality
- video streams
- object recognition
- multiple modalities
- cross modal
- video frames
- space time
- video sequences
- high dimensional
- multimedia
- video content
- video analysis
- motion history images
- fusing multiple
- computer vision
- video database
- visual data
- spatial and temporal
- activity recognition
- visual recognition
- image annotation
- visual features
- image processing