BiST: Bi-directional Spatio-Temporal Reasoning for Video-Grounded Dialogues.
Hung LeDoyen SahooNancy F. ChenSteven C. H. HoiPublished in: EMNLP (1) (2020)
Keyphrases
- bi directional
- spatio temporal
- spatial and temporal
- space time
- spatial temporal
- video representation
- human actions
- video data
- video content
- temporal domain
- video sequences
- moving objects
- temporal segmentation
- real time
- video frames
- spatio temporally
- knowledge representation
- dynamic textures
- associative memory
- knowledge base
- video database
- video analysis
- human activities
- video streams
- english chinese
- video surveillance
- computer vision
- neural network
- spatial and temporal relationships
- temporal consistency
- temporal correlation
- video shots
- video clips
- human motion
- event detection
- high dimensional
- image sequences
- information retrieval