Sitemap

Recommended citation: Meng Zhu, Weidong Min*, Qi Wang, et al. PFLU and FPFLU: Two novel non-monotonic activation functions in convolutional neural networks. Neurocomputing, 2021, 429: 110-117. DOI: 10.1016/j.neucom.2020.11.068.
Download Paper | Download Slides | arXiv | GitHub

Viewpoint adaptation learning with cross-view distance metric for robust vehicle re-identification

Published in Information Sciences, 2021

This paper is about vehicle re-identification.

Recommended citation: Qi Wang, Weidong Min*, Qing Han, Ziyuan Yang, Xin Xiong, Meng Zhu, Haoyu Zhao. Viewpoint adaptation learning with cross-view distance metric for robust vehicle re-identification. Information Sciences, 2021, 564: 71-84. DOI: 10.1016/j.ins.2021.02.013.
Download Paper | Download Slides | arXiv | GitHub

MSCNet: Dense vehicle counting method based on multi-scale dilated convolution channel-aware deep network

Published in GeoInformatica, 2023

This paper is about dense vehicle counting.

Recommended citation: Qiyan Fu, Weidong Min*, Chubbo Li, Haoyu Zhao, Ye Cao, Meng Zhu. MSCNet: Dense vehicle counting method based on multi-scale dilated convolution channel-aware deep network. GeoInformatica, 2024, 28 (2): 245-269. DOI: 10.1007/s10707-023-00503-7.
Download Paper | Download Slides | arXiv | GitHub

SAR ship localization method with denoising and feature refinement

Published in Engineering Applications of Artificial Intelligence, 2023

This paper is about SAR ship localization.

Recommended citation: Cheng Zha, Weidong Min*, Qing Han, Wei Li, Xin Xiong, Qi Wang, Meng Zhu. SAR ship localization method with denoising and feature refinement. Engineering Applications of Artificial Intelligence, 2023, 123: 1-13. DOI: 10.1016/j.engappai.2023.106444.
Download Paper | Download Slides | arXiv | GitHub

Structure-aware multi-view image inpainting using dual consistency attention

Published in Information Fusion, 2023

This paper is about image inpainting.

Recommended citation: Hongyue Xiang, Weidong Min*, Qing Han, Cheng Zha, Qian Liu, Meng Zhu. Structure-aware multi-view image inpainting using dual consistency attention. Information Fusion, 2024, 104: 1-11. DOI: 10.1016/j.inffus.2023.102174.
Download Paper | Download Slides | arXiv | GitHub

Spatial decomposition and aggregation for attention in convolutional neural networks

Published in International Journal of Pattern Recognition and Artificial Intelligence, 2024

This paper is about channel-spatial mixed attention.

Recommended citation: Meng Zhu, Weidong Min*, Hongyue Xiang, et al. Spatial decomposition and aggregation for attention in convolutional neural networks. International Journal of Pattern Recognition and Artificial Intelligence, 2024, 38 (1): 1-15. DOI: 10.1142/S0218001423520195.
Download Paper | Download Slides | arXiv | GitHub

Improved channel attention methods via hierarchical pooling and reducing information loss

Published in Pattern Recognition, 2024

This paper is about channel attention.

Recommended citation: Meng Zhu, Weidong Min*, Junwei Han, et al. Improved channel attention methods via hierarchical pooling and reducing information loss. Pattern Recognition, 2024, 148: 1-9. DOI: 10.1016/j.patcog.2023.110148.
Download Paper | Download Slides | arXiv | GitHub

ShuffleNeMt: Modern lightweight convolutional neural network architecture

Published in Pattern Analysis and Applications, 2024

This paper is about lightweight convolutional neural networks.

Recommended citation: Meng Zhu, Weidong Min*, Qing Han, et al. ShuffleNeMt: Modern lightweight convolutional neural network architecture. Pattern Analysis and Applications, 2024, 27 (4): 123-134. DOI: 10.1007/s10044-024-01327-3.
Download Paper | Download Slides | arXiv | GitHub

Constructing a smoothed Leaky ReLU using a linear combination of the smoothed ReLU and identity function

Published in Neural Computing and Applications, 2025

This paper is about activation functions.

Recommended citation: Meng Zhu, Weidong Min*, Jiahao Li, et al. Constructing a smoothed Leaky ReLU using a linear combination of the smoothed ReLU and identity function. Neural Computing and Applications, 2025: 1-14. DOI: 10.1007/s00521-024-10935-3.
Download Paper | Download Slides | arXiv | GitHub

Outliers Adaptation Exploration and Centroids Matching Label Refinement for Unsupervised Person Re-identification

Published in IEEE Transactions on Multimedia, 2026

This paper is about person re-identification.

Recommended citation: Li L, Han Q, Min W*, et al. Outliers Adaptation Exploration and Centroids Matching Label Refinement for Unsupervised Person Re-identification[J]. IEEE Transactions on Multimedia, 2026, 1-16. DOI: 10.1109/TMM.2026.3654461
Download Paper | Download Slides | arXiv | GitHub

Dual-Domain Balanced Channel-Spatial Mixed Attention in Convolutional Neural Networks

Published in Neural Processing Letters, 2026

This paper is about channel-spatial mixed attention methods.

Recommended citation: Meng Zhu, Weidong Min*, Qing Han, et al. Dual-domain balanced channel-spatial mixed attention in convolutional neural networks. Neural Processing Letters, 2026, 58 (4): 48-63. DOI: 10.1007/s11063-026-11855-0
Download Paper | Download Slides | arXiv | GitHub

Ada2MS: A Hybrid Optimization Algorithm Based on Exponential Mixing of Elementwise and Global Second-Moment Estimates

Published in arXiv, 2026

This paper is about optimization algorithms.

Recommended citation: Meng Zhu, Quan Xiao, Weidong Min*. Ada2MS: A Hybrid Optimization Algorithm Based on Exponential Mixing of Elementwise and Global Second-Moment Estimates. arXiv, 2026. URL https://arxiv.org/abs/2605.20533
Download Paper | Download Slides | arXiv | GitHub

AdamNX: An Adam improvement algorithm based on a novel exponential decay mechanism for the second-order moment estimate

Published in arXiv, 2026

This paper is about optimization algorithms.

Recommended citation: Meng Zhu, Quan Xiao, Weidong Min*. AdamNX: An Adam improvement algorithm based on a novel exponential decay mechanism for the second-order moment estimate. arXiv, 2026. URL https://arxiv.org/abs/2511.13465.
Download Paper | Download Slides | arXiv | GitHub

朱梦

Sitemap

Pages

Posts

portfolio

publications

talks

teaching