Learning to Combine the Modalities of Language and Video for Temporal Moment Localization.
Jungkyoo ShinJinyoung MoonPublished in: CoRR (2021)
Keyphrases
- supervised learning
- knowledge acquisition
- learning systems
- spatial and temporal
- learning process
- online learning
- learning algorithm
- temporal reasoning
- language learning
- pattern languages
- language acquisition
- active learning
- video sequences
- reinforcement learning
- machine learning
- interactive video
- combining multiple
- inductive inference
- temporal constraints
- key frames
- video frames
- e learning