Multi-Modal Domain Adaptation Across Video Scenes for Temporal Video Grounding.
Haifeng HuangYang ZhaoZehan WangYan XiaZhou ZhaoPublished in: CoRR (2023)
Keyphrases
- multi modal
- video scene
- domain adaptation
- audio visual
- video data
- scene analysis
- video analysis
- video sequences
- video shots
- dynamic scenes
- semantic concepts
- cross domain
- video clips
- temporal information
- labeled data
- semi supervised
- space time
- video frames
- transfer learning
- news video
- moving objects
- unlabeled data
- semi supervised learning
- three dimensional
- high dimensional
- optical flow
- multimedia
- supervised learning
- video database
- event detection
- video streams
- low level
- multi view
- model selection
- video content
- feature space