collaborators

5 papers

cs.CV2026

Dual-level Modality Debiasing Learning for Unsupervised Visible-Infrared Person Re-Identification

Jiaze Li, Yan Lu, Bin Liu +2

Two-stage learning pipeline has achieved promising results in unsupervised visible-infrared person re-identification (USL-VI-ReID). It first performs single-modality learning and t…

cs.CV2026

Scalable and Generalizable Correspondence Pruning via Geometry-Consistent Pre-training

Tangfei Liao, Xiaoqin Zhang, Tao Wang +4

Two-view correspondence pruning aims to identify reliable correspondences for camera pose estimation, serving as a fundamental step in many 3D vision tasks. Existing methods rely o…

cs.IR2025

MUSE: A Simple Yet Effective Multimodal Search-Based Framework for Lifelong User Interest Modeling

Bin Wu, Feifan Yang, Zhangming Chan +8

Lifelong user interest modeling is crucial for industrial recommender systems, yet existing approaches rely predominantly on ID-based features, suffering from poor generalization o…

cs.LG2025

FedThief: Harming Others to Benefit Oneself in Self-Centered Federated Learning

Xiangyu Zhang, Mang Ye

In federated learning, participants' uploaded model updates cannot be directly verified, leaving the system vulnerable to malicious attacks. Existing attack strategies have adversa…

cs.CV2025

Pose-Star: Anatomy-Aware Editing for Open-World Fashion Images

Yuran Dong, Mang Ye

To advance real-world fashion image editing, we analyze existing two-stage pipelines(mask generation followed by diffusion-based editing)which overly prioritize generator optimizat…