SLVP: Self-Supervised Language-Video Pre-Training for Referring Video Object Segmentation.
Jie MeiA. J. PiergiovanniJenq-Neng HwangWei LiPublished in: WACV (Workshops) (2024)
Keyphrases
- video sequences
- video streams
- video content
- training examples
- video data
- training process
- language learning
- programming language
- natural language
- multimedia
- real time
- online learning
- training phase
- video analysis
- space time
- real time video
- video segmentation
- training algorithm
- change detection
- video surveillance
- online video
- dynamic scenes
- human activities
- spatial and temporal
- test set
- training samples
- image quality
- active learning
- training set
- high level
- metadata