Zeze Tao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Zeze Tao has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Jinjia Peng
School of Cyber Security and Computer, Hebei University, Baoding, Hebei, China
6 shared publications - Hui Li
Hebei University
2 shared publications - Huibing Wang
Dalian Martime University, Dalian, Liaoning, China and University of Illinois Chicago, Chicago, Illinois, USA
2 shared publications - Huibing Wang
Dalian Maritime University, Dalian, China
2 shared publications - Junyu Liu
School of Cyber Security and Computer, Hebei University, Hebei, China
2 shared publications - Cheng Peng
School of Cyber Security and Computer, Hebei University, Hebei, China
1 shared publication
Latest Publications
- 5 November 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 334
Loss-gap guided adaptive sampling for transferable adversarial attacks
- 5 November 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 334
Loss-gap guided adaptive sampling for transferable adversarial attacks
- 30 June 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 332
Transferable adversarial queries on person re-identification via dynamic bilateral tuning
- 30 June 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 332
Transferable adversarial queries on person re-identification via dynamic bilateral tuning
- Top Cited Papers
- 5 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 21 (15566013) , 2652-2667
Bi-Level Inter-Modality Modulation for Unsupervised Visible-Infrared Person Re-Identification
The task of unsupervised visible–infrared person re-identification (USL-VI-ReID) aims to retrieve cross-modal pedestrian images without manual annotations. The key challenge lies in achieving semantic alignment to resolve modality bias in the absence of real labels. However, existing methods overly rely on single-modal information in the process of pseudo-label generation without considering cross-modal associations, making it difficult to bridge the modality gap between visible and infrared images. To address these issues, this paper proposes a Bi-level Inter-Modal Modulation Network (BIMM-Net), which employs multi-level cluster structure optimization as a core strategy to drive the establishment of cross-modal semantic associations, ultimately achieving cross-modal alignment at the feature representation level. Specifically, we construct a novel intermediary modality GrayMix from visible images to enhance model robustness against color variations and alleviate modality gaps. To filter out noise in cross-modal matching and establish a shared semantic space between visible and infrared modalities, we further develop a Ternary Pairs Calibration-Convergence module designed for filtering noise from visible-infrared cluster matching, on this basis constructing fused mixture clusters. Building on this mixture cluster space, an Heterogeneous-Isomorphic Alignment Loss is also designed to align the feature distributions of the three modalities, reinforcing cross-modal semantic consistency. In addition, we present a Cross-modal Neighborhood Consistency Clustering method, which facilitates the formation and propagation of cross-modal clusters by selecting high-confidence cross-modal neighbor pairs and refining feature distances. Ultimately, BIMM-Net through the joint modeling of bi-level clustering enables multiple levels to guide each other in refining cross-modal structures, thereby effectively establishing the semantic associations between visible and infrared modalities. Extensive experiments validate the superior performance of the proposed framework, achieving state-of-the-art results in USL-VI-ReID. The source code of this paper is available at: https://github.com/liujuny5920/DIMM-Net.
- 5 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 21 (15566013) , 2652-2667
Top Cited PapersBi-Level Inter-Modality Modulation for Unsupervised Visible-Infrared Person Re-Identification
The task of unsupervised visible–infrared person re-identification (USL-VI-ReID) aims to retrieve cross-modal pedestrian images without manual annotations. The key challenge lies in achieving semantic alignment to resolve modality bias in the absence of real labels. However, existing methods overly rely on single-modal information in the process of pseudo-label generation without considering cross-modal associations, making it difficult to bridge the modality gap between visible and infrared images. To address these issues, this paper proposes a Bi-level Inter-Modal Modulation Network (BIMM-Net), which employs multi-level cluster structure optimization as a core strategy to drive the establishment of cross-modal semantic associations, ultimately achieving cross-modal alignment at the feature representation level. Specifically, we construct a novel intermediary modality GrayMix from visible images to enhance model robustness against color variations and alleviate modality gaps. To filter out noise in cross-modal matching and establish a shared semantic space between visible and infrared modalities, we further develop a Ternary Pairs Calibration-Convergence module designed for filtering noise from visible-infrared cluster matching, on this basis constructing fused mixture clusters. Building on this mixture cluster space, an Heterogeneous-Isomorphic Alignment Loss is also designed to align the feature distributions of the three modalities, reinforcing cross-modal semantic consistency. In addition, we present a Cross-modal Neighborhood Consistency Clustering method, which facilitates the formation and propagation of cross-modal clusters by selecting high-confidence cross-modal neighbor pairs and refining feature distances. Ultimately, BIMM-Net through the joint modeling of bi-level clustering enables multiple levels to guide each other in refining cross-modal structures, thereby effectively establishing the semantic associations between visible and infrared modalities. Extensive experiments validate the superior performance of the proposed framework, achieving state-of-the-art results in USL-VI-ReID. The source code of this paper is available at: https://github.com/liujuny5920/DIMM-Net.
- 29 January 2026
- Published by Elsevier in Neural Networks
- Vol. 199, 108665
Enhancing adversarial transferability via curvature-aware penalization
- 29 January 2026
- Published by Elsevier in Neural Networks
- Vol. 199, 108665
Enhancing adversarial transferability via curvature-aware penalization
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 28, 1-11
Transferable Adversarial Attack on Person Re-Identification via Direction-Aware Attack
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 28, 1-11
Transferable Adversarial Attack on Person Re-Identification via Direction-Aware Attack
- 21 November 2025
- Published by Elsevier in Pattern Recognition
- Vol. 172
Global aggregated gradient-guided adversarial attacks for person re-identification
- 21 November 2025
- Published by Elsevier in Pattern Recognition
- Vol. 172
Global aggregated gradient-guided adversarial attacks for person re-identification