杜飞｜云南大学｜学者主页

2026

R2-MER: Micro-Expression Recognition Via Region-Aware Reconstruction and Modality-Aware Fusion

Hanyuan Wang, Zhiqi Li, Zongfa Wang, Fei Du, Yun Yang

IEEE Transactions on Affective Computing

2026

Lumos-Nexus: Efficient Frequency Bridging with Homogeneous Latent Space for Video Unified Models

Jiazheng Xing, Hang-Jie Yuan, Lingling Cai, Xinyu Liu, Yujie Wei, Fei Du, Hai Ci, Tao Feng, Jiasheng Tang, Weihua Chen, Fan Wang, Yong Liu

arXiv.org

DOI

2026

HiPrune: Training-Free Visual Token Pruning via Hierarchical Attention in Vision-Language Models (Student Abstract)

Jizhihui Liu, Guang-Dao Zhu, Fei Du

AAAI Conference on Artificial Intelligence

DOI

2026

LumosX: Relate Any Identities with Their Attributes for Personalized Video Generation

Jiazheng Xing, Fei Du, Hangjie Yuan, Peng Liu, Hongbin Xu, Hai Ci, Ruigang Niu, Weihua Chen, Fan Wang, Yong Liu

arXiv.org

DOI

2026

Ensemble Image and Text for Unsupervised Domain Adaptation Using Vision Language Models

Qi Jia, Fei Du, Zulong Lin, Jing Guo, Yun Yang

IEEE Transactions on Image Processing

DOI

2025

PLZero: placeholder based approach to generalized zero-shot learning for multi-label recognition in chest radiographs

Chengrong Yang, Qiwen Jin, Fei Du, Jing Guo, Yujue Zhou

Complex & Intelligent Systems

DOI

2025

HiPrune: Hierarchical Attention for Efficient Token Pruning in Vision-Language Models

Jizhihui Liu, Guang-Dao Zhu, Fei Du, Niu Lian, Jun Li, Bin Chen, Weili Guan, Yaowei Wang

Annual Meeting of the Association for Computational Linguistics

DOI

2025

Patient teacher can impart locality to improve lightweight vision transformer on small dataset

Jun Ling, Xuan Zhang, Fei Du, Linyu Li, Wei-Yi Shang, Chen Gao, Tong Li

Pattern Recognition

DOI

2024

RealisID: Scale-Robust and Fine-Controllable Identity Customization via Local and Global Complementation

Zhaoyang Sun, Fei Du, Weihua Chen, Fan Wang, Ya-Xiong Chen, Yi Rong, Shengwu Xiong

AAAI Conference on Artificial Intelligence

DOI

2024

SHMT: Self-supervised Hierarchical Makeup Transfer via Latent Diffusion Models

Zhaoyang Sun, Shengwu Xiong, Ya-Xiong Chen, Fei Du, Weihua Chen, Fan Wang, Yi Rong

Neural Information Processing Systems

DOI

2023

持续学习：研究综述

林钰尧，杜飞，杨云

《云南大学学报(自然科学版)》

2023

面向持续学习的自适应增长神经网络研究

杜飞

《云南大学》

2023

Global and Local Mixture Consistency Cumulative Learning for Long-tailed Visual Recognitions

Fei Du, Peng Yang, Qi Jia, Fengtao Nan, X. Chen, Yun Yang

IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings

DOI

2022

A Fast Texture-to-Stain Adversarial Stain Normalization Network for Histopathological Images

Qi Jia, Jing Ming Guo, Fei Du, Peng Yang, Yun Yang

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

DOI

2022

Efficient Perturbation Inference and Expandable Network for continual learning

Fei Du, Yun Yang, Ziyuan Zhao, Zeng Zeng

Neural Networks

DOI

杜飞

精选作品

期刊论文

R2-MER: Micro-Expression Recognition Via Region-Aware Reconstruction and Modality-Aware Fusion

Lumos-Nexus: Efficient Frequency Bridging with Homogeneous Latent Space for Video Unified Models

HiPrune: Training-Free Visual Token Pruning via Hierarchical Attention in Vision-Language Models (Student Abstract)

LumosX: Relate Any Identities with Their Attributes for Personalized Video Generation

Ensemble Image and Text for Unsupervised Domain Adaptation Using Vision Language Models

PLZero: placeholder based approach to generalized zero-shot learning for multi-label recognition in chest radiographs

HiPrune: Hierarchical Attention for Efficient Token Pruning in Vision-Language Models

Patient teacher can impart locality to improve lightweight vision transformer on small dataset

RealisID: Scale-Robust and Fine-Controllable Identity Customization via Local and Global Complementation

SHMT: Self-supervised Hierarchical Makeup Transfer via Latent Diffusion Models

持续学习：研究综述

面向持续学习的自适应增长神经网络研究

Global and Local Mixture Consistency Cumulative Learning for Long-tailed Visual Recognitions

A Fast Texture-to-Stain Adversarial Stain Normalization Network for Histopathological Images

Efficient Perturbation Inference and Expandable Network for continual learning

研究方向