A Closer Look at Temporal Sentence Grounding in Videos: Dataset and Metric.
Yitian YuanXiaohan LanXin WangLong ChenZhi WangWenwu ZhuPublished in: HUMA @ ACM Multimedia (2021)
Keyphrases
- human actions
- spatio temporal
- temporal coherence
- temporal relationships
- video sequences
- temporal information
- temporal databases
- temporal domain
- benchmark datasets
- metric space
- video analysis
- video dataset
- spatial and temporal
- video frames
- temporal structure
- trecvid multimedia event detection
- natural language
- temporal relations
- dynamic textures
- temporal data
- temporal constraints
- distance metric
- temporal reasoning
- video surveillance
- temporal order
- event detection
- human activities
- multimedia event detection
- keywords
- moving objects
- weakly labeled
- web videos
- distance measure
- distance function
- event recognition
- temporal sequences
- sentence level
- video summarization
- user generated
- text summarization