activity
20242026
collaborators

5 papers

cs.CV2026

PRISM: Progressive Reasoning through Iterative Slot Memory for Vision

Ziyu Wang, Shuangpeng Han, Mengmi Zhang

Modern vision models process images in a single feed-forward pass, which limits their ability to recover missing evidence or refine uncertain representations under incomplete obser…

cs.CV2026

Pose Prior Learner: Unsupervised Categorical Prior Learning for Pose Estimation

Ziyu Wang, Shuangpeng Han, Mengmi Zhang

A prior represents a set of beliefs or assumptions about a system, aiding inference and decision-making. In this paper, we introduce the challenge of unsupervised categorical prior…

cs.CV2025

Unforgettable Lessons from Forgettable Images: Intra-Class Memorability Matters in Computer Vision

Jie Jing, Yongjian Huang, Serena J. -W. Wang +5

We introduce intra-class memorability, where certain images within the same class are more memorable than others despite shared category characteristics. To investigate what featur…

cs.LG2025

Unveiling AI's Blind Spots: An Oracle for In-Domain, Out-of-Domain, and Adversarial Errors

Shuangpeng Han, Mengmi Zhang

AI models make mistakes when recognizing images-whether in-domain, out-of-domain, or adversarial. Predicting these errors is critical for improving system reliability, reducing cos…

cs.CV2024

Flow Snapshot Neurons in Action: Deep Neural Networks Generalize to Biological Motion Perception

Shuangpeng Han, Ziyu Wang, Mengmi Zhang

Biological motion perception (BMP) refers to humans' ability to perceive and recognize the actions of living beings solely from their motion patterns, sometimes as minimal as those…