Distilling Vision-Language Pre-Training to Collaborate with Weakly-Supervised Temporal Action Localization.
Chen JuKunhao ZhengJinxiang LiuPeisen ZhaoYa ZhangJianlong ChangQi TianYanfeng WangPublished in: CVPR (2023)
Keyphrases
- weakly supervised
- object localization
- object detectors
- object class
- topic models
- computer vision
- relation extraction
- superpixels
- named entities
- semi supervised
- object detection
- supervised learning
- information extraction
- natural language
- training samples
- segmentation method
- viewpoint
- training set
- graph cuts
- object segmentation
- automatic extraction
- object recognition