TVT: Two-View Transformer Network for Video Captioning.
Ming ChenYingming LiZhongfei ZhangSiyu HuangPublished in: ACML (2018)
Keyphrases
- video sequences
- distribution network
- real time
- peer to peer
- network structure
- video surveillance
- computer networks
- video data
- network model
- network traffic
- neural network
- online video
- network architecture
- video analysis
- video content
- spatial and temporal
- video streams
- fault diagnosis
- wireless sensor networks
- multimedia
- traveling salesman problem
- communication networks
- temporal information
- video clips
- video images
- network conditions