3 papers
cs.CV2024
Spatial-Semantic Collaborative Cropping for User Generated Content
Yukun Su, Yiwen Cao, Jingliang Deng +2
A large amount of User Generated Content (UGC) is uploaded to the Internet daily and displayed to people world-widely through the client side (e.g., mobile and PC). This requires t…
cs.CV2023
Dual-Augmented Transformer Network for Weakly Supervised Semantic Segmentation
Jingliang Deng, Zonghan Li
Weakly supervised semantic segmentation (WSSS), a fundamental computer vision task, which aims to segment out the object within only class-level labels. The traditional methods ado…
cs.CV2023
COMNet: Co-Occurrent Matching for Weakly Supervised Semantic Segmentation
Yukun Su, Jingliang Deng, Zonghan Li
Image-level weakly supervised semantic segmentation is a challenging task that has been deeply studied in recent years. Most of the common solutions exploit class activation map (C…