Research
My general research interests lie in object re-identification, image retrieval, and deep metric learning, with a particular emphasis on the following topics:
Theory:
Analysis and understanding of the generalization ability of various loss functions.
Algorithm:
Development of effective deep learning algorithms for object re-identification and image retrieval.
Application:
Application of learning algorithms in object re-identification, image retrieval, and deep metric learning.
Feel free to drop me an email if you are interested in collaborating with me on the above research topics.
Publications
(* Corresponding author; † Equal contribution)
Kun Qian, Wei Liu, Minshi Chen, Xiao Wang, Xin Yuan.
RPUDet: Learning Relational Prior and Uncertainty for Robust Aerial Object Detection.
Proceedings of the ACM International Conference on Multimedia Retrieval (ICMR'25), Accepted, 2025.
Xin Yuan, Ying He, Guozhu Hao.
Identity Hides in Darkness: Learning Feature Discovery Transformer for Nighttime Person Re-identification.
Sensors, Accepted, 2025.
Wei Liu, Xin Xu, Hua Chang, Xin Yuan, Zheng Wang.
Mix-Modality Person Re-Identification: A New and Practical Paradigm.
ACM Transactions on Multimedia Computing, Communications, and Applications, Accepted, 2025.
Zhongyang Li, Xin Yuan*, Wei Liu, Xin Xu.
VAGeo: View-specific Attention for Cross-View Object Geo-Localization.
Proceedings of the International Conference on Acoustics, Speech and Signal Processing (ICASSP'25), Accepted, 2025.
Renkai Li, Xin Yuan*, Wei Liu, Xin Xu.
Event-based Video Person Re-identification via Cross-Modality and Temporal Collaboration.
Proceedings of the International Conference on Acoustics, Speech and Signal Processing (ICASSP'25), Accepted, 2025.
Jialin Zhang, Xiao Wang, Xin Yuan, Nan Mu, Zheng Wang.
Spatial Bi-Exploration for Robust Camouflaged Object Detection.
IEEE Signal Processing Letters, Accepted, 2024.
Yiru Zheng, Wei Wang, Xiao Wang, Xin Yuan.
RLUNet: Overexposure-Content-Recovery-Based Single HDR Image Reconstruction with the Imaging Pipeline Principle.
Applied Sciences, Accepted, 2024.
Xiaopan Li, Shiqian Wu, Xin Yuan, Shoulie Xie, Sos Agaian.
Hierarchical Wavelet-Guided Diffusion Model for Single Image Deblurring.
The Visual Computer, Accepted, 2024.
Hengwei Li, Wei Wang, Xiao Wang, Xin Yuan, Xin Xu.
Blind 3D Video Stabilization with Spatio-Temporally Varying Motion Blur.
ACM Transactions on Multimedia Computing, Communications, and Applications, Accepted, 2024.
Wanyu Wu, Wei Wang, Xin Yuan, Xin Xu.
LIMPID: A Lightweight Image-to-Curve MaPpIng moDel for Extremely Low-Light Image Enhancement.
Photonics, vol. 10, no. 3, p. 273, 2023.
Xin Yuan, Xin Xu, Zheng Wang, Kai Zhang, Wei Liu, Ruimin Hu.
Searching Parameterized Retrieval & Verification Loss for Re-identification.
IEEE Journal of Selected Topics in Signal Processing, vol. 17, no. 3, pp. 560-574, 2023.
Xin Yuan, Xin Xu, Xiao Wang, Liang Liao, Kai Zhang, Zheng Wang, Chia-Wen Lin.
OSAP-Loss: Efficient Optimization of Average Precision via Involving Samples after Positive Ones Towards Remote Sensing Image Retrieval.
CAAI Transactions on Intelligence Technology, vol. 8, no. 4, pp. 1191-1212, 2023.
Xin Xu, Xin Yuan, Zheng Wang, Kai Zhang, Ruimin Hu.
Rank-in-Rank Loss for Person Re-identification.
ACM Transactions on Multimedia Computing, Communications, and Applications, vol. 18, no. 2s, art. no. 130, pp. 1-21, 2022.
Xiang Shuai, Xiao Wang, Wei Wang, Xin Yuan, Xin Xu.
SAM: Self Attention Mechanism for Scene Text Recognition based on Swin Transformer.
Proceedings of the International Conference on Multimedia Modeling (MMM'22), pp. 443–454, 2022.
|