I received B.A. degree from School of Internet of Things Engineering at Jiangnan University, in 2015. For two years up to 2018, I studied as a Master student in Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence, Jiangnan University. I received my Ph.D. degree at Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence, Jiangnan University, in December of 2021, supervised by Pro. Xiao-Jun Wu.

I am currently a Lecturer (home page) at the School of Artificial Intelligence and Computer Science and the International Joint Laboratory on Artificial Intelligence of Jiangsu Province, Jiangnan University, Wuxi, China. My research interests include computer vision, multi-modal image fusion, multi-modal super-resolution and multi-modal detection/tracking.

I have published several scientific papers (7 highly cited papers, 1 hot paper), including IEEE TPAMI, IEEE TIP, IJCV, Information Fusion etc. I achieved top tracking performance in several competitions, including the VOT2020 RGBT challenge (ECCV20), VOT2021 RGBD challenge (ICCV21) and Anti-UAV challenge (ICCV21). I have been chosen among the World’s Top 2% Scientists ranking in the single recent year dataset published by Stanford University (2021, 2022, 2023).

Current research:

  • Computer vision
  • Multi-modal fusion, super-resolution
  • Multi-modal detection, tracking

Email:

  • lihui.cv@jiangnan.edu.cn
  • hui_li_jnu@163.com

Github Infor

GitHub contributions GitHub contributions

Students

Mater students (Co-advised with Prof. Xiaoning Song and Prof. Xiaoqing Luo)

Publications

Journal papers

29. OCCO: LVM-guided Infrared and Visible Image Fusion Framework based on Object-aware and Contextual COntrastive Learning
Hui Li*, Congcong Bian, Zeyang Zhang, Xiaoning Song, Xi Li, Xiao-Jun Wu
International Journal of Computer Vision (IJCV, IF: 9.3), Published: 17 June 2025.
[paper][arxiv][code]
28. Visual complexity guided diffusion defender for video object tracking and recognition
Shaochuan Zhao, Tianyang Xu, Hui Li, Xiao-Jun Wu*, Josef Kittler
Pattern Recognition (PR, IF: 7.5), available online 31 May 2025, 111867.
[paper][arxiv][code]
27. ISFPN: A medical detection model for ischemic stroke based on feature pyramid network and Swin Transformer
Zhi Wang, Ao Dong, Junli Zhao, Zhenkuan Pan, Hui Li, Yi Li*
Biomedical Signal Processing and Control (IF: 4.9), 17 May 2025, 109: 108064.
[paper][arxiv][code]
26. Deep Discriminative Multi-view Clustering
Zhe Chen, Xiao-Jun Wu*, Tianyang Xu, Hui Li, Josef Kittler
IEEE Transactions on Circuits and Systems for Video Technology (TCSVT, IF: 8.3), 13 February 2025, Early Access.
[paper][arxiv][code]
25. APMG: 3D Molecule Generation Driven by Atomic Chemical Properties
Yang Hua, Zhenhua Feng, Xiaoning Song*, Hui Li, Tianyang Xu, Xiao-Jun Wu, Dong-Jun Yu
IEEE/ACM Transactions on Computational Biology and Bioinformatics (TCBB, IF: 3.4), Volume: 21, Issue: 6, Nov.-Dec. 2024.
[paper][arxiv][code]
24. UUD-Fusion: An unsupervised universal image fusion approach via generative diffusion model
Xiangxiang Wang, Lixing Fang, Junli Zhao, Zhenkuan Pan, Hui Li, Yi Li*
Computer Vision and Image Understanding (CVIU, IF: 3.5), Volume: 249, December 2024, 104218.
[paper][arxiv][code]
23. Conti-Fuse: A Novel Continuous Decomposition-based Fusion Framework for Infrared and Visible Images
Hui Li*, Haolong Ma, Chunyang Cheng, Zhongwei Shen, Xiaoning Song, Xiao-Jun Wu
Information Fusion (InfFus, IF: 15.5), Volume 117, May 2025, 102839.
[paper][arxiv][code]
22. Multi-layer multi-level comprehensive learning for deep multi-view clustering
Zhe Chen, Xiao-Jun Wu*, Tianyang Xu, Hui Li, Josef Kittler
Information Fusion (InfFus, IF: 15.5), Volume 116, April 2025, 102785.
[paper][arxiv][code]
21. EDMF: A New Benchmark for Multi-Focus Images with the Challenge of Exposure Difference
Hui Li*, Tianyu Shen, Zeyang Zhang, Xuefeng Zhu, Xiaoning Song
Sensors (IF: 3.5), 2024, 24(22), 7287.
[paper][arxiv][code]
20. TextFusion: Unveiling the Power of Textual Semantics for Controllable Image Fusion
Chunyang Cheng, Tianyang Xu, Xiao-Jun Wu*, Hui Li, Xi Li, Zhangyong Tang, Josef Kittler
Information Fusion (InfFus, IF: 15.5), Volume 117, May 2025, 102790.
[paper][arxiv][code]
19. FusionBooster: A Unified Image Fusion Boosting Paradigm
Chunyang Cheng, Tianyang Xu, Xiao-Jun Wu*, Hui Li, Xi Li, Josef Kittler
International Journal of Computer Vision (IJCV, IF: 9.3), 2024: 1-18.
[paper][arxiv][code]
18. MMAE: A universal image fusion method via mask attention mechanism
Xiangxiang Wang, Lixing Fang, Junli Zhao, Zhenkuan Pan, Hui Li, Yi Li*
Pattern Recognition (PR, IF: 7.5), available online 26 September 2024, 111041.
[paper][arxiv][code]
17. DDBFusion: An unified image decomposition and fusion framework based on dual decomposition and Bézier curves
Zeyang Zhang, Hui Li, Tianyang Xu, Xiao-Jun Wu*, Josef Kittler
Information Fusion (InfFus, IF: 15.5), Volume 114, February 2025, 102655.
[paper][arxiv][code]
16. An unsupervised multi-focus image fusion method via dual-channel convolutional network and discriminator
Lixing Fang, Xiangxiang Wang, Junli Zhao, Zhenkuan Pan, Hui Li*, Yi Li*
Computer Vision and Image Understanding (CVIU, IF: 3.5), Volume: 244, July 2024, 104029.
[paper][arxiv][code]
15. CrossFuse: A Novel Cross Attention Mechanism based Infrared and Visible Image Fusion Approach
Hui Li*, Xiao-Jun Wu
Information Fusion (InfFus, IF: 15.5), Volume: 103, March 2024, 102147.
(Highly Cited Paper)
[paper][arxiv][code]
14. GuideFuse: A novel guided auto-encoder fusion network for infrared and visible images
Zeyang Zhang, Hui Li, Tianyang Xu, Xiao-Jun Wu*, Yu Fu
IEEE Transactions on Instrumentation and Measurement (TIM, IF: 5.9), 2023, Volume: 73, 5011211.
[paper][arxiv][code]
13. DePF: A Novel Fusion Approach based on Decomposition Pooling for Infrared and Visible Images
Hui Li*, Yongbiao Xiao, Chunyang Cheng, Zhongwei Shen, Xiaoning Song
IEEE Transactions on Instrumentation and Measurement (TIM, IF: 5.9), 2023, Volume: 72, 5031014.
[paper][arxiv][code]
12. SFPFusion: An Improved Vision Transformer Combining Super Feature Attention and Wavelet-Guided Pooling for Infrared and Visible Images Fusion
Hui Li*, Yongbiao Xiao, Chunyang Cheng, Xiaoning Song
Sensors (IF: 3.5), 2023, volume: 23, number: 18, 2023: 7870
[paper][arxiv][code]
11. Exploring fusion strategies for accurate RGBT visual object tracking
Zhangyong Tang, Tianyang Xu, Hui Li, Xiao-Jun Wu*, Xue-Feng Zhu, Josef Kittler
Information Fusion (InfFus, IF: 15.5), Volume: 99, November 2023, 101881.
[paper][arxiv][code]
10. LRRNet: A novel representation learning guided fusion framework for infrared and visible images
Hui Li, Tianyang Xu, Xiao-Jun Wu*, Jiwen Lu, Josef Kittler
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI, IF: 18.6), Volume: 45, Issue: 9, pp. 11040-11052, April 2023
(Highly Cited Paper, *Hot Paper*)
[paper][arxiv][code]
9. I Know How You Move: Explicit Motion Estimation for Human Action Recognition
Zhongwei Shen, Xiao-Jun Wu*, Hui Li, Tianyang Xu, Cong Wu
IEEE Transactions on Multimedia (TMM, IF: 9.7), 2022, Early Access.
[paper][code]
8. SwinFuse: A Residual Swin Transformer Fusion Network for Infrared and Visible Images
Zhishe Wang*, Yanlin Chen, Wenyu Shao, Hui Li, Lei Zhang
IEEE Transactions on Instrumentation and Measurement (TIM, IF: 5.9), 2022, vol: 71.
(Highly Cited Paper)
[paper][code]
7. Generalized n-Dimensional Rigid Registration: Theory and Applications
Jin Wu, Miaomiao Wang, Hassen Fourati, Hui Li, Yilong Zhu, Chengxi Zhang, Yi Jiang, Xiangcheng Hu, Ming Liu*
IEEE Transactions on Cybernetics (TCYB, IF: 10.5), Volume: 53, Issue: 2, February 2023.
[paper][code][video]
6. RFN-Nest: An end-to-end residual fusion network for infrared and visible images
Hui Li, Xiao-Jun Wu* , Josef Kittler
Information Fusion (InfFus, IF: 15.5), Volume: 73, Pages: 72-86, September 2021.
(Highly Cited Paper)
[paper][arxiv][code][Supplementary Material]
5. UMFA: a photorealistic style transfer method based on U-Net and multi-layer feature aggregation
Dongyu Rao, Xiao-Jun Wu*, Hui Li, Josef Kittler, Tianyang Xu
Journal of Electronic Imaging (JEI, IF: 1.0), Volume: 30, Issue: 5, pp. 053013, September 2021.
[paper][arxiv][code]
4. NestFuse: An Infrared and Visible Image Fusion Architecture based on Nest Connection and Spatial/Channel Attention Models
Hui Li, Xiao-Jun Wu* , Tariq S. Durrani
IEEE Transactions on Instrumentation and Measurement (TIM, IF: 5.9), Volume: 69, Issue: 12, pp. 9645–9656, Dec. 2020.
(Highly Cited Paper)
[paper][arxiv][code]
3. MDLatLRR: A novel decomposition method for infrared and visible image fusion
Hui Li, Xiao-Jun Wu* , Josef Kittler
IEEE Transactions on Image Processing (TIP, IF: 13.7), Volume: 29, pp. 4733-4746, February, 2020.
(Highly Cited Paper)
[paper][arxiv][code]
2. Infrared and Visible Image Fusion with ResNet and zero-phase component analysis
Hui Li, Xiao-Jun Wu* , Tariq S. Durrani
Infrared Physics & Technology (JIPT, IF: 3.4), Volume 102, November 2019, 103039.
(Highly Cited Paper)
[paper][arxiv][code]
1. DenseFuse: A Fusion Approach to Infrared and Visible Images
Hui Li, Xiao-Jun Wu*
IEEE Transactions on Image Processing (TIP, IF: 13.7), Volume: 28, Issue: 5, pp. 2614–2623, May. 2019.
(Highly Cited Paper)
[paper][arxiv][code]

Conference papers

13. One Model for ALL: Low-Level Task Interaction Is a Key to Task-Agnostic Image Fusion
Chunyang Cheng, Tianyang Xu, Zhenhua Feng, Xiaojun Wu*, Zhangyong Tang, Hui Li, Zeyang Zhang, Sara Atito, Muhammad Awais, Josef Kittler
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2025), 2025.
[paper][arxiv][code]
12. SMFuse: Two-Stage Structural Map Aware Network for Multi-focus Image Fusion
Tianyu Shen, Hui Li*, Chunyang Cheng, Zhongwei Shen, and Xiaoning Song
The 27th International Conference on Pattern Recognition (ICPR 2024), December 01-05, 2024, Kolkata, India.
[paper][arxiv][code]
11. IFFusion: Illumination-free Fusion Network for Infrared and Visible Images
Chengcheng Song, Hui Li, Tianyang Xu, Zeyang Zhang, and Xiao-Jun Wu*
The 27th International Conference on Pattern Recognition (ICPR 2024), December 01-05, 2024, Kolkata, India.
[paper][arxiv][code]
10. CoMoFusion: Fast and High-quality Fusion of Infrared and Visible Image with Consistency Model
Zhiming Meng, Hui Li*, Zeyang Zhang, Zhongwei Shen, Yunlong Yu, Xiaoning Song, Xiaojun Wu
The 7th Chinese Conference on Pattern Recognition and Computer Vision (PRCV 2024), October 18-20, 2024, Urumqi, China.
[paper][arxiv][code]
9. TandemFuse: An Intra-and Inter-Modal Fusion Strategy for RGB-T Tracking
Xinyang Zhou, Hui Li*
The 2024 2nd Asia Conference on Computer Vision, Image Processing and Pattern Recognition (CVIPPR 2024), Apirl 26-28, 2024, Xiamen, China.
[paper][arxiv][code]
8. LE2Fusion: A novel local edge enhancement module for infrared and visible image fusion
Yongbiao Xiao, Hui Li*, Chunyang Cheng, Xiaoning Song
International Conference on Image and Graphics (ICIG 2023), 29 October 2023, Nanjing, China.
[paper][arxiv][code]
7. D2-LRR: A Medical Image Fusion Method based on Dual-decomposed MDLatLRR
Xu Song, Tianyu Shen, Hui Li*, Xiao-Jun Wu
International Conference on Machine Vision, Image Processing & Imaging Technology (MVIPIT 2023), 24 September 2023, Hangzhou, Zhejiang, China.
[paper][arxiv][code]
6. Res2NetFuse: A Fusion Method for Infrared and Visible Images
Xu Song, Yongbiao Xiao, Hui Li*, Xiao-Jun Wu, Jun Sun, Valsile Palade
International Conference on Machine Vision, Image Processing & Imaging Technology (MVIPIT 2023), 24 September 2023, Hangzhou, Zhejiang, China.
[paper][arxiv][code]
5. MSC-Fuse: An Unsupervised Multi-scale Convolutional Fusion Framework for Infrared and Visible Image
Guo-Yang Chen, Xiao-Jun Wu* , Hui Li, Tian-Yang Xu
International Conference on Image and Graphics (ICIG 2021), 30 September 2021, Haikou, China. Lecture Notes in Computer Science, vol 12888. Springer, Cham.
[paper][code]
4. Subspace Clustering via Joint Unsupervised Feature Selection
Wenhua Dong, Xiao-Jun Wu* , Hui Li, Zhen-Hua Feng, Josef Kittler
IEEE International Conference on Pattern Recognition (ICPR 2020), 2021, Page(s): 3892 - 3898. Beijing, China.
[paper][code]
3. MSDNet for Medical Image Fusion
Xu Song, Xiao-Jun Wu* , Hui Li
International Conference on Image and Graphics (ICIG 2019), 28 November 2019, Beijing, China. Lecture Notes in Computer Science, vol 11902. Springer, Cham.
[paper][code]
2. Infrared and Visible Image Fusion using a Deep Learning Framework
Hui Li, Xiao-Jun Wu* , Josef Kittler
IEEE International Conference on Pattern Recognition (ICPR 2018), 2018, Page(s):2705 - 2710. Beijing, China.
(Google citation: 556)
[paper][arxiv][code]
1. Multi-focus Image Fusion Using Dictionary Learning and Low-Rank Representation
Hui Li, Xiao-Jun Wu*
International Conference on Image and Graphics (ICIG 2017), Shanghai, China. Springer, Cham, 2017: 675 - 686.
(Google citation: 116)
[paper][arxiv][code]

Preprint

3. S4Fusion: Saliency-aware Selective State Space Model for Infrared Visible Image Fusion
Haolong Ma, Hui Li*, Chunyang Cheng, Gaoang Wang, Xiaoning Song, Xiaojun Wu
arXiv 2024
[arxiv][code]
2. Infrared and visible image fusion using Latent Low-Rank Representation
Hui Li, Xiao-Jun Wu*
arXiv 2017
(Google citation: 208)
[arxiv][code]
1. Multi-focus Noisy Image Fusion using Low-Rank Representation
Hui Li, Xiao-Jun Wu*, Tariq Durrani
arXiv 2017
[arxiv][code]

Contest

The Tenth Visual Object Tracking VOT2022 Challenge Results
Zhangyong Tang, Xuefeng Zhu, Tianyang Xu, Jiaye Chen, Ze Kang, Hui Li, Shaochuan Zhao, Xiao-Jun Wu, Josef Kittler, Xi Li
VOT-D 2022 subchallenge (RSDiMP, 2nd place)
[home page][VOT report]
The Ninth Visual Object Tracking VOT2021 Challenge Results
Xuefeng Zhu, Zhangyong Tang, Tianyang Xu, Hui Li, Shaochuan Zhao, Xiao-Jun Wu, Josef Kittler
VOT2021 RGBD subchallenge (TALGD, 2nd place)
[home page][VOT report]
Detection and tracking of UAV in the wild ICCV Workshop 2021
Xuefeng Zhu, Zhangyong Tang, Hui Li, Tianyang Xu, Xiao-Jun Wu, Josef Kittler
The Second Anti-UAV Workshop & Challenge 2021 (3rd place award)
[home page]
The Eighth Visual Object Tracking VOT2020 Challenge Results
Hui Li, Wu Xiao-Jun, Josef Kittler, Tianyang Xu, Xuefeng Zhu, Yunkun Li
VOT2020 RGB thermal and infrared subchallenge (DFAT, The winning tracker award)
[home page][VOT report][code]
The Seventh Visual Object Tracking VOT2019 Challenge Results
Hui Li, Zhangyong Tang, Tianyang Xu, Xuefeng Zhu, Xiao-Jun Wu, Josef Kittler
VOT2019 RGB thermal and infrared subchallenge (FSRPN, 4th in public dataset)
[home page][VOT report][code]

Experience

2022.01 ~ now: Lecturer, School of Artificial Intelligence and Computer Science, Jiangnan University, China.
2018.09 ~ 2021.12: Ph.D candidate in Control Science and Engineering in school of IoT, Jiangnan University, China.
2016.09 ~ 2018.06: Master in Computer science and technology in Jiangnan University, China.
2015.06 ~ 2016.08: Software engineer in Nanjing, China.
2011.09 ~ 2015.06: Bachelor in Computer science and technology in school of IoT, Jiangnan University, China.

Activities

Associate Editor: Springer Nature (SN) Computer Science
Reviewer: CVPR, ICCV, NeurIPS, ECCV, AAAI, IEEE TPAMI, IJCV, IEEE TIP, Information Fusion, IEEE TMM, IEEE TCSVT, …