Incorporating granularity bias as the margin into contrastive loss for video captioning.
Jiayang GuFengming YaoPublished in: CoRR (2023)
Keyphrases
- video content
- video data
- video clips
- multimedia
- video streams
- real time video
- video database
- video frames
- support vector
- video sequences
- video analysis
- event recognition
- real time
- training set
- video retrieval
- video images
- space time
- image sequences
- computer vision
- dynamic scenes
- neural network
- video segmentation
- compressed video