Yukai Shi
 |
Associate Professor |
Biography
Currently Dr. SHI is a teacher at Guangdong University of Technology (GDUT). Before that, he graduated from Sun Yat-Sen University with a PhD degree, supervised by Prof. [Liang Lin (林倞教授)]. He was a visiting researcher in the University of Sydney and Microsoft Research Asia, worked with Prof. [Wanli Ouyang (欧阳万里教授)] and Dr. [Jingdong Wang (王井东研究员)], respectively. He serves as a Reviewer for a number of journals and conferences, such as IJCV, IEEE T-PAMI, CVPR, ICCV, etc.
Recently, almost all of my students have published top-tier conference/journal papers. In fact, all students in our group are talented, self-motivated and sometimes reliable. They own the most credit of following works which I was glad to work with.
Never stop looking for collaboration, please feel free to contact me via email. (any question/suggestion/collaboration)Research Topic
AI Generated Content (AIGC): Diffusion Model for Fantasy Generation, Vision Alignment and Augmentation.
Multimodality Sensing: Cross-sensor Cooperative Sensing, Vision-Thermal Recognition, etc.
Computer Vision and Pattern Recognition: Cross-data Vision Alignment, Data-centric Visual Learning, etc.
Selected Publications
(* indicates supervised students) [Full Paper List]CrossFuse: Learning Infrared and Visible Image Fusion by Cross-Sensor Top-K Vision Alignment and Beyond
Yukai Shi, Cidan Shi, Zhipeng Weng, Yin Tian, Xiaoyu Xian, Liang Lin
IEEE Transactions on Circuits and Systems for Video Technology (T-CSVT), 2025. [PDF] [Code]
Boosting 3D Object Detection via Self-distilling Introspective Data
Chaoqun Wang, Yiran Qin, Zijian Kang, Ningning Ma, Yukai Shi, Zhen Li, Ruimao Zhang
IEEE Transactions on Intelligent Transportation Systems (T-ITS), 2025. [PDF] [Code]
Diff-Mosaic: Augmenting Realistic Representations in Infrared Small Target Detection via Diffusion Prior
Yukai Shi, Yupei Lin, Pengxu Wei, Xiaoyu Xian, Tianshui Chen, Liang Lin
IEEE Transactions on Geoscience and Remote Sensing (T-GRS), 2024. [PDF] [Code]
The Mosaic operation is renewed with diffusion prior, click to check Diffusion-Mosaic.
SIRST-5K: Exploring Massive Negatives Synthesis with Self-supervised Learning for Robust Infrared Small Target Detection
Yahao Lu* , Yupei Lin, Han Wu, Xiaoyu Xian, Yukai Shi, Liang Lin
IEEE Transactions on Geoscience and Remote Sensing (T-GRS), 2024. [PDF] [Code][中文介绍]
NegVSR: Augmenting Negatives for Generalized Noise Modeling in Real-world Video Super-Resolution
Yexing Song* , Meilin Wang, Zhijing Yang, Xiaoyu Xian, Yukai Shi
Proc. of AAAI Conference on Artificial Intelligence (AAAI), 2024. [PDF] [Code] [Demo]
Structural Information Guided Multimodal Pre-training for Vehicle-centric Perception
Xiao Wang, Wentao Wu, Chenglong Li, Zhicheng Zhao, Zhe Chen, Yukai Shi, Jin Tang
Proc. of AAAI Conference on Artificial Intelligence (AAAI), 2024. [PDF] [Project Page]
NiteDR: Nighttime Image De-Raining with Cross-View Sensor Cooperative Learning for Dynamic Driving Scenes
Cidan Shi* , Lihuang Fang, Han Wu, Xiaoyu Xian, Yukai Shi, Liang Lin
IEEE Transactions on Multimedia (T-MM), 2024. [PDF] [Code]
Heterogeneous Semantic Transfer for Multi-label Recognition with Partial Labels
Tianshui Chen, Tao Pu, Lingbo Liu, Yukai Shi, Zhijing Yang, Liang Lin
International Journal of Computer Vision (IJCV), 2024. [PDF] [Code][Media Report]
IDF-CR: Iterative Diffusion Process for Divide-and-Conquer Cloud Removal in Remote-sensing Images
Meilin Wang, Yexing Song* , Pengxu Wei, Xiaoyu Xian,Yukai Shi, Liang Lin
IEEE Transactions on Geoscience and Remote Sensing (T-GRS), 2024. [PDF] [Code]
MirrorDiffusion: Stabilizing Diffusion Process in Zero-shot Image Translation by Prompts Redescription and Beyond
Yupei Lin* , Xiaoyu Xian, Yukai Shi, Liang Lin
IEEE Signal Processing Letters (SPL), 2024. [PDF] [Project Page] [Code]
CROSE: Low-light Enhancement by CROss-SEnsor Interaction for Nighttime Driving Scenes
Xiaoyu Xian*, Qi Zhou*, Jinghui Qin, Xiaojun Yang, Yin Tian, Yukai Shi, Daxin Tian
Expert Systems with Applications (ESWA), 2024. [PDF]
OccluMix: Towards De-Occlusion Virtual Try-on by Semantically-Guided Mixup
Zhijing Yang, Junyang Chen* , Yukai Shi, Hao Li, Tianshui Chen, Liang Lin
IEEE Transactions on Multimedia (T-MM), 2023. [PDF] [Code]
Reference-free Low-light Image Enhancement by Associating Hierarchical Wavelet Representations
Xiaojun Yang, Junhong Gong, Lianpei Wu, Zhijing Yang, Yukai Shi, Feiping Nie
Expert Systems with Applications (ESWA), 2023. [PDF]
DnSwin: Toward Real-World Denoising via Continuous Wavelet Sliding-Transformer
Hao Li* , Zhijing Yang, Xiaobin Hong, Ziying Zhao, Junyang Chen, Yukai Shi, Jinshan Pan
Knowledge-Based Systems (KBS), 2022. [PDF] [Code]
Criteria Comparative Learning for Real-scene Image Super-Resolution
Yukai Shi, Hao Li, Sen Zhang, Zhijing Yang, Xiao Wang
IEEE Transactions on Circuits and Systems for Video Technology (T-CSVT), 2022. [PDF][Code][RealSR-Zero]
Exploring Negatives in Contrastive Learning for Unpaired Image-to-Image Translation
Yupei Lin* , Sen Zhang, Tianshui Chen, Yongyi Lu, Guangping Li, Yukai Shi
ACM International Conference on Multimedia (ACM MM), 2022. [PDF][Code]
Real-World Image Super-Resolution by Exclusionary Dual-Learning
Hao Li* , Jinghui Qin, Zhijing Yang, Pengxu Wei, Jinshan Pan, Liang Lin, Yukai Shi
IEEE Transactions on Multimedia (T-MM), 2022. [PDF][Code]
Unsupervised Multi-view Clustering by Squeezing Hybrid Knowledge from Cross View and Each View
Junpeng Tan*, Yukai Shi, Zhijing Yang, Caizhen Wen, Liang Lin
IEEE Transactions on Multimedia (T-MM), 2021. [PDF]
GTAE: Graph Transformer–Based Auto-Encoders for Linguistic-Constrained Text Style Transfer
Yukai Shi, Sen Zhang, Chenxing Zhou, Xiaodan Liang, Xiaojun Yang, Liang Lin
ACM Transactions on Intelligent Systems and Technology (ACM T-IST), 2021. [PDF][Code][Benchmark]
Face Hallucination by Attentive Sequence Optimization with Reinforcement Learning
Yukai Shi, Guanbin Li, Qingxing Cao, Keze Wang, Liang Lin
IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 2020. [PDF][Code]
Structure-preserving Image Super-resolution via Contextualized Multitask Learning
Yukai Shi, Keze Wang, Chongyu Chen, Li Xu, Liang Lin
IEEE Transactions on Multimedia (T-MM), 2017. [PDF][Code]
Students' Achievements
[2024] National Scholarship (+1) : Yupei Lin, Cidan Shi and Yexing Song, congrats!
[2023] National Scholarship (Highest Scholarship in China) : Junyang Chen.
Alumni
* This is a partial list.
| Name | Year | Thesis/Project | Graduation TO |
|---|---|---|---|
| Yupei Lin | 2025 | Controlled Content Generation | Ph.D@SYSU |
| Yexing Song | 2025 | Video Super-Resolution | Tencent |
| Junyang Chen | 2024 | Semantically-Guided Virtual Try-on | Ph.D@NJUST |
| Lihuang Fang | 2024 | Hyperspectral Data Fusion | Master@SUSTech |
| Junhong Gong | 2024 | Reference-free Low-light Enhancement | Digital Guangdong Co., Ltd. |
| Haoyu Zhong | 2023 | Real-world Image Super-Resolution | Xiaomi Corporation |
| Hao Li | 2023 | Real-world Image Processing | Ph.D@NJUST |