Affordance Grounding from Demonstration Video to Target Image.
Joya ChenDifei GaoKevin Qinghong LinMike Zheng ShouPublished in: CVPR (2023)
Keyphrases
- object detection
- pre trained
- computer vision
- object recognition
- image data
- target images
- multiscale
- image retrieval
- image segmentation
- image content
- image analysis
- image frames
- single image
- multimedia
- template matching
- image representation
- image features
- image classification
- images and video sequences
- input image
- target object
- video files
- static images
- region of interest
- spatial information
- image regions
- feature points
- image matching
- background subtraction
- visual cues
- video images
- high resolution
- motion estimation
- key frames
- low level
- segmentation method
- similarity measure
- edge detection