Ground-A-Video: Zero-shot Grounded Video Editing using Text-to-image Diffusion Models.
Hyeonho JeongJong Chul YePublished in: ICLR (2024)
Keyphrases
- video editing
- video data
- input image
- multiscale
- video segmentation
- video database
- image analysis
- image data
- image features
- image retrieval
- video camera
- image classification
- image representation
- high resolution
- multimedia
- visual data
- segmentation method
- low level
- video retrieval
- edge detection
- object recognition
- video analysis
- video clips
- temporal information
- video streams
- video frames
- visual information
- segmentation algorithm