LOCATE: Localize and Transfer Object Parts for Weakly Supervised Affordance Grounding.
Gen LiVarun JampaniDeqing SunLaura Sevilla-LaraPublished in: CVPR (2023)
Keyphrases
- weakly supervised
- object class
- object categories
- object classes
- object detection
- object recognition
- object localization
- viewpoint
- superpixels
- bounding box
- partial occlusion
- object segmentation
- image features
- generative model
- training examples
- d objects
- object detectors
- appearance model
- image patches
- visual words
- target object
- computer vision
- test images
- machine learning
- image content
- co occurrence
- small number
- multi class
- training set