STRONG: Spatio-Temporal Reinforcement Learning for Cross-Modal Video Moment Localization.
Da CaoYawen ZengMeng LiuXiangnan HeMeng WangZheng QinPublished in: ACM Multimedia (2020)
Keyphrases
- cross modal
- spatio temporal
- reinforcement learning
- multi modal
- visual data
- human actions
- space time
- multimedia retrieval
- video streams
- video sequences
- image sequences
- multimedia
- visual recognition
- video content
- semantic concepts
- video frames
- video data
- image retrieval
- multimedia data
- multimedia databases
- moving objects
- video retrieval
- high level
- visual similarity
- perceptual information
- visual information
- video analysis
- human motion
- machine learning
- action recognition
- search engine
- key frames
- event detection
- image data
- e learning
- computer vision
- learning algorithm