3 papers
cs.CV2026
Beyond Absolute Scores: Relative Edit-induced Difference for Generalizable Image Aesthetic Assessment
Qifei Jia, Xintong Yao, Yasen Zhang +7
Traditional Image Aesthetic Assessment (IAA) methods mainly rely on regressing absolute Mean Opinion Scores (MOS). However, such a paradigm overlooks the inherently dynamic nature…
cs.LG2026
Metric-Normalized Posterior Leakage (mPL): Attacker-Aligned Privacy for Joint Consumption
Gaoyi Chen, Minghao Li, Weishi Shi +4
Metric differential privacy (mDP) strengthens local differential privacy (LDP) by scaling noise to semantic distance, but many machine learning (ML) systems are consumed under join…
cs.CV2026
Towards Visual Query Segmentation in the Wild
Bing Fan, Minghao Li, Hanzhi Zhang +6
In this paper, we introduce visual query segmentation (VQS), a new paradigm of visual query localization (VQL) that aims to segment all pixel-level occurrences of an object of inte…