Learning Unified Video-Language Representations via Joint Modeling and Contrastive Learning for Natural Language Video Localization.
Chenhao CuiXinnian LiangShuangzhi WuZhoujun LiPublished in: IJCNN (2023)
Keyphrases
- natural language
- learning algorithm
- learning tasks
- interactive video
- learning process
- knowledge acquisition
- learning systems
- unsupervised learning
- machine learning
- programming language
- reinforcement learning
- knowledge base
- supervised learning
- spatio temporal
- video data
- event detection
- metadata
- learning analytics
- learning community
- hybrid learning
- external representations