A Closer Look at Debiased Temporal Sentence Grounding in Videos: Dataset, Metric, and Approach.
Xiaohan LanYitian YuanXin WangLong ChenZhi WangLin MaWenwu ZhuPublished in: CoRR (2022)
Keyphrases
- human actions
- temporal coherence
- spatio temporal
- temporal relationships
- natural language
- temporal domain
- video sequences
- temporal information
- video dataset
- temporal constraints
- spatial and temporal
- benchmark datasets
- event recognition
- temporal order
- temporal segmentation
- human activities
- metric space
- video data
- temporal databases
- web videos
- video search
- trecvid multimedia event detection
- temporal consistency
- temporal structure
- synthetic datasets
- temporal data
- video analysis
- video frames
- action recognition
- distance function
- text summarization
- temporal relations
- temporal patterns
- metric learning
- evaluation metrics
- dynamic scenes
- video clips
- key frames
- weakly labeled
- knn