Collaborative three-stream transformers for video captioning.
Hao WangLibo ZhangHeng FanTiejian LuoPublished in: Comput. Vis. Image Underst. (2023)
Keyphrases
- video data
- video sequences
- real time
- video streams
- video database
- video content
- video frames
- data streams
- collaborative learning
- multimedia
- real time video
- video clips
- space time
- video surveillance
- multimedia data
- multi user
- digital video
- video images
- spatial and temporal
- sliding window
- geographically dispersed
- online video
- audio stream
- collaborative environment
- temporal information
- compressed video
- video search
- video processing
- motion estimation
- feature vectors
- cooperative
- computer vision