SBAT: Video Captioning with Sparse Boundary-Aware Transformer.
Tao JinSiyu HuangMing ChenYingming LiZhongfei ZhangPublished in: IJCAI (2020)
Keyphrases
- video content
- video data
- multimedia
- real time face tracking
- video sequences
- video streams
- fault diagnosis
- high dimensional
- real time
- sparse representation
- video frames
- space time
- real time video
- event recognition
- object boundaries
- video analysis
- video shots
- compressed sensing
- video retrieval
- video database
- fuzzy logic
- video processing
- video clips
- image quality
- key frames
- temporal information
- multimedia data