avatar

ZHANG Xiao

Postdoc, The University of Pennsylvania.

About

I am currently a postdoc scholar at the University of Pennsylvania, advised by Prof. Konrad Kording. Perviously I obtained my Ph.D. degree from Multimedia Lab (MMLab) at the Chinese University of Hong Kong, supervised by Prof. Xiaogang Wang and Prof. Hongsheng Li. I have also collaborated with researchers in Nvidia, SenseTime, the Chinese Academy of Sciences (CAS), and Shanghai AI Lab. Prior to CUHK, I received my B.Eng degree from College of Intelligence and Computing, Tianjin University (TJU) in 2017. At that time, I also minored in Finance.

My research is dedicated to advancing scalable AI perception systems that address diverse machine learning challenges in real-world environments. I’m particularly interested in developing robust, flexible representation learning pipelines. My work explores general representation techniques, employing optimization, statistics, and high-performance computing systems to overcome challenges in large-scale, unlabeled, and ill-posed data.

My current research interests include:

  • Representation learning and theory in foundation vision, language, and multi-modal data;
  • Alignment learning and parameter-efficient adaptation;
  • Human vision and human behavior/motion modeling;
  • Eye-movement behavior modeling and analysis in medical areas;
  • Real-time AI systems.

Before joining UPenn as a postdoc, I co-founded a startup focused on AI-driven fitness and exercise safety. I led an AI R&D team, developing a scalable, real-time system for motion capture and human-object interaction using multi-view sparse 3D reconstruction. I introduced key optimizations, including Asynchronous Tolerant Multi-View Reconstruction, Multiview-guided NMS, and advancements in scalable AI systems and infrastructures.

Publications

Refining Pseudo Labels with Clustering Consensus over Generations for Unsupervised Object Re-Identification
Xiao Zhang, Yixiao Ge, Yu Qiao, Hongsheng Li
2021 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

RBF-Softmax: Learning Deep Representative Prototypes with Radial Basis Function Softmax
Xiao Zhang, Rui Zhao, Yu Qiao, Hongsheng Li
2020 European Conference on Computer Vision (ECCV)

Adacos: Adaptively Scaling Cosine Logits for effectively Learning Deep Face Representations
Xiao Zhang, Rui Zhao, Yu Qiao, Xiaogang Wang, Hongsheng Li
2019 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) [Oral]

P2SGrad: Refined Gradients for Optimizing Deep Face Models
Xiao Zhang, Rui Zhao, Junjie Yan, Mengya Gao, Yu Qiao, Xiaogang Wang, Hongsheng Li
2019 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Range Loss for Deep Face Recognition with Long-tailed Training Data
Xiao Zhang, Zhiyuan Fang, Yandong Wen, Zhifeng Li, Yu Qiao
2017 IEEE International Conference on Computer Vision (ICCV)

Services

I have served as a reviewer for the following conferences:

Computer Vision

  • ICCV: 2023, 2021, 2019
  • CVPR: 2023, 2022, 2021, 2019, 2018
  • ECCV: 2022, 2020

Machine Learning and AI

  • ICLR: 2025, 2024
  • NeurIPS: 2024, 2023
  • AISTATS: 2025

Robotics

  • ICRA: 2019

Journal Reviewing

I have contributed as a reviewer for the following journals:

  • IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI)
  • International Journal of Computer Vision (IJCV)
  • Neurocomputing
  • Computer Vision and Image Understanding (CVIU)

Teaching

Teaching Assistant of the following courses in CUHK:

  • CUHK ENGG 5202, Pattern Recognition, Spring 2022
  • CUHK ELEG 5760, Machine Learning for Signal Processing Applications, Fall 2019.
  • CUHK ENGG 2030, Signals and Systems, Fall 2022, Fall 2021, Spring 2021, Fall 2020, Spring 2020, Fall 2019