Affordance Grounding from Demonstration Video to Target Image.
Joya ChenDifei GaoKevin Qinghong LinMike Zheng ShouPublished in: CoRR (2023)
Keyphrases
- pre trained
- target images
- input image
- template matching
- image content
- image retrieval
- image analysis
- image data
- image frames
- image features
- test images
- key frames
- visual data
- image segmentation
- static images
- video streams
- video images
- image regions
- single image
- similarity measure
- video sequences
- image classification
- video analysis
- multimedia
- high resolution
- visual cues
- segmentation method
- edge detection
- image representation
- pixel values
- target object
- image collections
- color histogram
- low level
- video content
- object motion
- low resolution
- face recognition
- segmentation algorithm
- video files