SViTT: Temporal Learning of Sparse Video-Text Transformers.
Yi LiKyle MinSubarna TripathiNuno VasconcelosPublished in: CVPR (2023)
Keyphrases
- learning algorithm
- interactive video
- learning systems
- information retrieval
- temporal consistency
- high dimensional
- supervised learning
- video search
- feature selection
- spatial and temporal
- learning tasks
- video streams
- temporal analysis
- dictionary learning
- video content
- text retrieval
- e learning
- text documents
- video data
- online learning
- learning process
- video sequences
- reinforcement learning