轩诗宇

(1) 2020-09 至 2024-06, 北京大学, 计算机应用技术, 博士 

(2) 2017-09 至 2020-06, 中国科学院大学, 电子与通信工程, 硕士 

(3) 2013-09 至 2017-06, 华中科技大学, 电子信息工程, 学士

2024-07 至 今, 南京理工大学, 计算机科学与工程学院, 副教授

研究方向：多模态大模型、多媒体检索、具身智能。

本课题组隶属于，由国家杰青唐金辉教授领导的智能媒体分析实验室（Intelligent Media Analysis Group, IMAG）。

* 全年招收多名硕士生

要求：有一定的自驱力，希望做出厉害的工作。

提供：

1）1对1的科研指导，从idea产生、实验进行到论文发表；

2）优秀者可推荐至本团队或国内外顶尖团队深造/访学/交流，亦可推荐至华为、阿里、微软、百度、腾讯等企业实习/工作；

3）充足的助研补贴 + 丰富的团建活动（春/秋游、运动、聚餐等）；

* 全年招收本科实习生（若干）

要求：面向本校计算机、机械、控制类专业本科生，对人工智能、大模型相关应用有浓厚兴趣。

提供：

1）进组学习 + 项目实践机会；

2）一对一的硕/博指导；

3）全方位指导参加挑战杯、互联网+ 等竞赛；

4）优秀者可推荐至本团队或国内外顶尖团队深造（具体同上）。

研究方向：计算机视觉、多模态信号处理，专注于多模态大模型及相关应用。

1. 中国图像图形学会多媒体专业委员会委员

2. 中国计算机学会多媒体技术专业委员会执行委员

3. 计算机视觉及人工智能领域顶级期刊审稿人TPAMI, ISPRS, TMM, TIP, TNNLS, TCSVT, TGRS, ToMM, CVIU, GRSL, KBS

4. 计算机视觉及人工智能领域顶级会议审稿人ICCV, ECCV, CVPR, AAAI, ACM MM

1. Shiyu Xuan, Shiliang Zhang, Intra-inter Domain Similarity for Unsupervised Person Re-Identification, IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024, 46(3): 1711-1726.  

2. Shiyu Xuan, Ming Yang, Shiliang Zhang, Incremental Model Enhancement via Memory-based Contrastive Learning, International Journal of Computer Vision, 2025, 133: 65-83.  

3. Shiyu Xuan, Qinepei Guo, Ming Yang, Shiliang Zhang, Pink: Unveiling the Power of Referential Comprehension for Multi-modal LLMs, IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024.  

4. Shiyu Xuan, Ming Yang, Shiliang Zhang, Adapting Vision-Language Models via Learning to Inject Knowledge, IEEE Transactions on Image Processing, 2024, 33: 5798-5809.  

5. Shiyu Xuan, Shiliang Zhang, Intra-inter Camera Similarity for Unsupervised Person Re-Identification, IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021.  

6. Shiyu Xuan, Ming Yang, Shiliang Zhang, Decoupled Contrastive Learning for Long-Tailed Recognition, AAAI Conference on Artificial Intelligence, 2024.  

7. Shiyu Xuan, Shengyang Li, Mingfei Han, Xue Wan and Guisong Xia, Object Tracking in Satellite Videos by Improved Correlation Filters with Motion Estimations, IEEE Transactions on Geoscience and Remote Sensing, 2020, 58(2): 1074-1086.  

8. Shiyu Xuan, Shengyang Li, Zifei Zhao, Longxuan Kou, Zhuang Zhou and Guisong Xia, Siamese Networks with Distractor-reduction Method for Long-term Visual Object Tracking, Pattern Recognition, 2021, 112: 107698.  

9. Shiyu Xuan, Shengyang Li, Zifei Zhao, Zhuang Zhou, Wanfeng Zhang, Hong Tan, Guisong Xia and Yanfeng Gu, Rotation Adaptive Correlation Filter for Moving Object Tracking in Satellite Videos. Neurocomputing, 2021, 438: 94-106.  

10. Dongkai Wang, Shiyu Xuan, Shiliang Zhang. LocLLM: Exploiting Generalizable Human Keypoint  Localization via Large Language Model, IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024.  

11. Cong Cong, Shiyu Xuan, Sidong Liu, Shiliang Zhang, Maurice Pagnucco, Yang Song, Decoupled Optimisation for Long-tailed Visual Recognition, AAAI Conference on Artificial Intelligence, 2024.  

12. Manqi Zhao, Shengyang Li, Shiyu Xuan, Longxuan Kou, Shuai Gong and Zhuang Zhou, SatSOT: A Benchmark Dataset for Satellite Video Single Object Tracking, IEEE Transactions on Geoscience and Remote Sensing, 2022, 60: 1-11.