SBAT: Video Captioning with Sparse Boundary-Aware Transformer.
Tao JinSiyu HuangMing ChenYingming LiZhongfei ZhangPublished in: CoRR (2020)
Keyphrases
- real time face tracking
- video streams
- video sequences
- video frames
- video content
- high dimensional
- video data
- fuzzy logic
- real time
- real time video
- digital video
- multimedia
- video retrieval
- video surveillance
- sparse data
- video images
- fault diagnosis
- dynamic scenes
- video shots
- video segmentation
- video database
- video processing
- key frames
- power system
- data sets
- sparse matrix
- spatio temporal
- medial axis
- visual data
- video analysis
- video clips
- human actions
- event detection
- temporal information
- spatial and temporal
- active contours
- control system