Min Meng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Min Meng has a total of 51 co-authors. Here are the top co-authors by number of shared publications:
- Jigang Wu
School of Computer Science and Technology, Guangdong University of Technology, Guangzhou, China
27 shared publications - Jun Yu
Harbin Institute of Technology
13 shared publications Jigang Wu
11 shared publicationsJigang Liu
8 shared publications- Mengcheng Lan
Department of Computer Science, Guangdong University of Technology, Guangzhou, China
4 shared publications - Jigang Liu
Ping An Life Insurance of China, Shenzhen, China
3 shared publications
Latest Publications
- 12 August 2026
- Published by Springer Nature in The Visual Computer
- Vol. 42 (10) , 468
Dynamic concept memory and contrastive feature generation for robust generalized zero-shot learning
- 12 August 2026
- Published by Springer Nature in The Visual Computer
- Vol. 42 (10) , 468
Dynamic concept memory and contrastive feature generation for robust generalized zero-shot learning
- 12 August 2026
- Published by Elsevier in Signal Processing
- Vol. 251
Source-free domain adaptation with class relationship transfer
- 12 August 2026
- Published by Elsevier in Signal Processing
- Vol. 251
Source-free domain adaptation with class relationship transfer
- 8 July 2026
- Published by Elsevier in Applied Soft Computing
- Vol. 202
HKD: Hybrid knowledge distillation for zero-shot anomaly detection
- 8 July 2026
- Published by Elsevier in Applied Soft Computing
- Vol. 202
HKD: Hybrid knowledge distillation for zero-shot anomaly detection
- 22 March 2026
- Published by Springer Nature in The Visual Computer
- Vol. 42 (5) , 217
Recurrent semantic disentanglement: enhancing zero-shot learning through dynamic feature refinement
- 22 March 2026
- Published by Springer Nature in The Visual Computer
- Vol. 42 (5) , 217
Recurrent semantic disentanglement: enhancing zero-shot learning through dynamic feature refinement
- 21 March 2026
- Published by Springer Nature in International Journal of Machine Learning and Cybernetics
- Vol. 17 (5) , 218
Multi-level consistency learning for multi-view clustering
- 21 March 2026
- Published by Springer Nature in International Journal of Machine Learning and Cybernetics
- Vol. 17 (5) , 218
Multi-level consistency learning for multi-view clustering
- 5 March 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 318
Adaptive Pseudo-labeling for Causal-driven Cross-Modal hashing
- 5 March 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 318
Adaptive Pseudo-labeling for Causal-driven Cross-Modal hashing
- 2 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (7) , 9349-9362
DKGZSL: Leveraging Dynamic Visual-Semantic Knowledge for Generative Zero-Shot Learning
Generative Zero-Shot Learning (GZSL) methods address the challenge of recognizing unseen classes by synthesizing visual features, thereby converting ZSL into a supervised learning task. However, existing approaches are predominantly constrained to two multi-stage strategies: pre-generation prior knowledge enhancement and post-generation feature refinement. These paradigms often suffer from error propagation across stages, ultimately limiting generation quality and representational fidelity. To overcome these limitations, we propose DKGZSL, a novel generative framework that injects dynamic visual-semantic knowledge directly into the feature synthesis process, effectively unifying generation and refinement into a single cohesive stage. Specifically, a Knowledge Transfer Network (KTN) is introduced to convert semantic information into hierarchical visual knowledge representations. To ensure accurate semanticvisual alignment, we further design a Semantic-Oriented Visual Refinement (SOVR) module that reshapes real visual features into semantically aligned and noise-suppressed representations, providing precise guidance for the KTN. Moreover, hierarchical knowledge extracted from each KTN layer is progressively transmitted to the generator via Meta-Fusion Units (MFUs), enabling dynamic semantic guidance and improving generation quality. Extensive experiments on three benchmark datasets demonstrate that DKGZSL achieves consistent state-of-the-art performance with both ResNet-101 and ViT-B/16 feature extractors. Comprehensive ablation studies further confirm the effectiveness and complementarity of each proposed component. The code is available at https://github.com/JingHu-gdut/DKGZSL.
- 2 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (7) , 9349-9362
DKGZSL: Leveraging Dynamic Visual-Semantic Knowledge for Generative Zero-Shot Learning
Generative Zero-Shot Learning (GZSL) methods address the challenge of recognizing unseen classes by synthesizing visual features, thereby converting ZSL into a supervised learning task. However, existing approaches are predominantly constrained to two multi-stage strategies: pre-generation prior knowledge enhancement and post-generation feature refinement. These paradigms often suffer from error propagation across stages, ultimately limiting generation quality and representational fidelity. To overcome these limitations, we propose DKGZSL, a novel generative framework that injects dynamic visual-semantic knowledge directly into the feature synthesis process, effectively unifying generation and refinement into a single cohesive stage. Specifically, a Knowledge Transfer Network (KTN) is introduced to convert semantic information into hierarchical visual knowledge representations. To ensure accurate semanticvisual alignment, we further design a Semantic-Oriented Visual Refinement (SOVR) module that reshapes real visual features into semantically aligned and noise-suppressed representations, providing precise guidance for the KTN. Moreover, hierarchical knowledge extracted from each KTN layer is progressively transmitted to the generator via Meta-Fusion Units (MFUs), enabling dynamic semantic guidance and improving generation quality. Extensive experiments on three benchmark datasets demonstrate that DKGZSL achieves consistent state-of-the-art performance with both ResNet-101 and ViT-B/16 feature extractors. Comprehensive ablation studies further confirm the effectiveness and complementarity of each proposed component. The code is available at https://github.com/JingHu-gdut/DKGZSL.
- 9 February 2026
- Published by Elsevier in Neurocomputing
- Vol. 676
Dynamic patch selection and dual-granularity alignment for cross-modal retrieval
- 9 February 2026
- Published by Elsevier in Neurocomputing
- Vol. 676
Dynamic patch selection and dual-granularity alignment for cross-modal retrieval
- Top Cited Papers
- 2 February 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 312
AnomalyLVM:Vision-language models for zero-shot anomaly detection
- 2 February 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 312
Top Cited PapersAnomalyLVM:Vision-language models for zero-shot anomaly detection
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 35, 8804-8818
UAD: A Unified Model for Zero-Shot Anomaly Detection
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 35, 8804-8818
UAD: A Unified Model for Zero-Shot Anomaly Detection