Aichun Zhu — accepted AI-conference papers

2025

Unveiling Local Well-posedness Influence for Cross-modal Person Re-Identification

Yumeng Yang, Guannan Dong, Aichun Zhu, Mingcheng Ni, Yifeng Li

ICASSP 2025accepted

The existing cross-modal retrieval methods trend toward the conventional multi-modal alignment while ignoring the localization bias caused by visual hallucination, including color pollution and appearance-like occlusion due to uncontrollable factors such as weather, illumination, and occlusion. This…

Cited by 0 Source ↗Scholar ↗

2022

Bi-Level Doubly Variational Learning for Energy-Based Latent Variable Models

Ge Kan, Jinhu Lü, Tian Wang, Baochang Zhang, Aichun Zhu, Lei Huang +2

CVPR 2022poster

Energy-based latent variable models (EBLVMs) are more expressive than conventional energy-based models. However, its potential on visual tasks are limited by its training process based on maximum likelihood estimate that requires sampling from two intractable distributions. In this paper, we propose…

Cited by 7 PDF ↗Scholar ↗