Yiyang Su
I am a Ph.D. student in Computer Vision Lab (CVLab) at Michigan State University advised by Dr. Xiaoming Liu. My research is mostly focused on open-set recognition and video understanding. In summer 2025, I worked as an Applied Scientist Intern at AWS AI Labs with Drs. Xiang Xu, Zheng Zhang, Chang Liu, Zhuowen Tu, Anil Jain, and Jon Wu. Prior to joining MSU, I received my Bachelor of Science degrees from the University of Rochester, where I also had the opportunity to work with Dr. Chenliang Xu and Dr. Yapeng Tian on audio-visual sound separation.
News
| Jun, 2025 | Two papers are accepted to ICCV 2025. |
|---|---|
| Feb, 2025 | Our paper on human recognition foundation model is accepted to CVPR 2025. |
| Jul, 2024 | Our paper on open-set biometrics is accepted to ECCV 2024. |
| Mar, 2024 | Our paper on keypoint relative position encoding is accepted to CVPR 2024. |
| Sep, 2023 | Our paper on ChatGPT-powered hierarchical comparisons for image classification is accepted to NeurIPS 2023. |
Publications
2025
-
A Quality-Guided Mixture of Score-fusion Experts Framework for Human RecognitionIn Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2025 -
HAMoBE: Hierarchical and Adaptive Mixture of Biometric Experts for Video-based Person ReIDIn Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2025 -
SapiensID: Foundation for Human RecognitionIn Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025
2024
-
Open-Set Biometrics: Beyond Good Closed-Set ModelsIn European Conference on Computer Vision (ECCV), 2024 -
KeyPoint Relative Position Encoding for Face RecognitionIn Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024 -
FarSight: A Physics-Driven Whole-Body Biometric System at Large Distance and AltitudeIn Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2024
2023
-
ChatGPT-Powered Hierarchical Comparisons for Image ClassificationIn Advances in Neural Information Processing Systems (NeurIPS), 2023 -
Separating Invisible Sounds Toward Universal Audio-Visual Scene-Aware Sound SeparationIn Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops, 2023