Adversarial Inference for Multi-Sentence Video Description.
Jae Sung ParkMarcus RohrbachTrevor DarrellAnna RohrbachPublished in: CVPR Workshops (2019)
Keyphrases
- video data
- video content
- video frames
- bayesian inference
- semantic role labeling
- video sequences
- high level
- natural language
- video streams
- video surveillance
- bayesian networks
- video database
- real time
- multimedia
- inference process
- content description
- video shots
- symbolic descriptions
- video clips
- knowledge base
- video retrieval
- key frames
- event detection
- semantic representation
- temporal information
- video images
- textual descriptions
- spatial and temporal
- real time video
- computer vision