Long-Form Video-Language Pre-Training with Multimodal Temporal Contrastive Learning.
Yuchong SunHongwei XueRuihua SongBei LiuHuan YangJianlong FuPublished in: NeurIPS (2022)
Keyphrases
- learning process
- learning algorithm
- spatial and temporal
- supervised learning
- reinforcement learning
- learning tasks
- multimedia
- natural language
- learning systems
- online learning
- formal language
- real time
- language acquisition
- programming language
- active learning
- temporal information
- spatio temporal
- training process
- object oriented programming
- feedforward neural networks
- moving objects
- image sequences