Reinforcement Learning for Weakly Supervised Temporal Grounding of Natural Language in Untrimmed Videos.
Jie WuGuanbin LiXiaoguang HanLiang LinPublished in: ACM Multimedia (2020)
Keyphrases
- weakly supervised
- reinforcement learning
- natural language
- weakly labeled
- relation extraction
- object class
- superpixels
- topic models
- machine learning
- named entities
- video sequences
- information extraction
- natural language processing
- semi supervised
- state space
- knowledge representation
- multiscale
- question answering
- learning algorithm
- video frames
- object detectors
- automatic extraction
- higher order