DCT-net: A deep co-interactive transformer network for video temporal grounding.
Wen WangJian ChengSiyu LiuPublished in: Image Vis. Comput. (2021)
Keyphrases
- spatial and temporal
- temporal information
- spatio temporal
- video sequences
- spatial temporal
- temporal consistency
- space time
- peer to peer
- video frames
- fuzzy logic
- network structure
- multimedia
- interactive video
- temporal coherence
- temporal correlation
- temporal analysis
- distribution network
- temporal domain
- jpeg images
- complex networks
- temporal reasoning
- user interaction
- video retrieval
- key frames
- video streams
- filter bank
- action recognition
- temporal structure
- image compression
- wireless sensor networks
- high voltage