Multi-Branch Tree-based Fusion Neural Architecture Search with Zero-Cost Screen for Multi-Modal Classification

Qian Guo, Quanchen Su, Xinyan Liang, Yuhua Qian, Nan Li, Zhihua Cui

​Multi-modal classification (MMC) leverages effective fusion of information from diverse modalities to achieve superior classification performance.

IEEE Transactions on Image Processing (TIP)

Incomplete Multi-View Clustering via Neighborhood-Conditioned Diffusion

Qian Guo, Gaohui Zuo, Bingbing Jiang, Guangrui Fan, Zhihua Cui, Xinyan Liang, Jianjian Ding

​Incomplete multi-view clustering (IMVC) aims to uncover shared clustering structures from heterogeneous views with partial observations.

ICML 2026

GFD-EMVC: Evolutionary Multi-View Classification with Label Noise via Gradient and Feature Dual-Perception

Shuai Li, Xinyan Liang, Yuhua Qian, Li Lv

his paper studies a fundamental yet often overlooked premise in evolutionary multi-view classification (EMVC): the impact of label noise on EMVC, such as distorting fitness landscapes shaped by individual fitness values (e.g., test accuracy).

ICML 2026

Vertical Federated K-Means for Multi-View Data Guided by a K-Means Cost Bound after Projection

Feijiang Li, Jinhao Jiang, Jieting Wang, Liang Du, Yuhua Qian

Multi-view data is widely present in the real world. Multi-view clustering is an unsupervised method for capturing the grouping structure of such data.

KDD'26

Topology-Aware Contrastive Learning: Regulating Representation Connectivity via Persistent Homology

Jiaxin Sun, Yuhua Qian, Yang Wang

Standard contrastive learning minimizes geometric distance between positive pairs, implicitly assuming that strict compactness optimizes discrimination.

ICML 2026

Spatial Structure and Selective Text jointly Facilitate Image Clustering

Feijing Li, Zizheng Jiu, Jieting Wang, Yuhua Qian, Lu Chen.

Image clustering is a fundamental task in visual machine learning. A key research direction in this field is the incorporation of prior knowledge.

ICLR

Mining Association Patterns from Neighborhood Insight

Honghong Cheng, Yuhua Qian*, Xinyan Liang, Jiye Liang, Qingfu Zhang

Detecting and identifying complex association patterns between two variables is a fundamental task. This requires association measures that satisfy both generality (the ability to capture a wide range of association structures) and equitability (the absence of bias toward specific association types).

IEEE Transactions on Pattern Analysis and Machine Intelligence

M3D: A Benchmark Dataset and Model for Microscopic 3D Shape Reconstruction.

Tao Yan, Yingying Wang, Yuhua Qian*, Jiangfeng Zhang, Feijiang Li, Peng Wu, Lu Chen, Jieru Jia, Xiaoying Guo.

Microscopic 3D shape reconstruction using depth from focus (DFF) is crucial in precision manufacturing for 3D modeling and quality control.

IEEE Transactions on Image Processing (TIP)

分数域调制的微观三维重建方法

闫涛, 李小辉, 钱宇华*, 张江峰 , 李飞江, 王婕婷, 杜亮，徐丽云, 吴鹏， 张临垣, 翟小鹏。

微观三维重建作为现代质量控制领域的使能技术，在精密制造、集成电路和空天科技等领域具有重要应用价值。然而，当前主流的激光共聚焦三维重建与结构光三维重建等方法普遍存在硬件成本高、微米级分辨率受限等瓶颈。

中国科学信息科学