Conditional Video Diffusion Network for Fine-Grained Temporal Sentence Grounding.
Daizong LiuJiahao ZhuXiang FangZeyu XiongHuan WangRenfu LiPan ZhouPublished in: IEEE Trans. Multim. (2024)
Keyphrases
- fine grained
- coarse grained
- spatial and temporal
- space time
- temporal information
- access control
- temporal consistency
- spatio temporal
- video sequences
- tightly coupled
- video data
- network structure
- network traffic
- massively parallel
- natural language
- multimedia
- video frames
- diffusion process
- information diffusion
- text classification
- peer to peer
- video content
- markov random field
- data lineage