Scholar
Xiao Zhang
Google Scholar ID: xImPgj4AAAAJ
University of Pennsylvania
Citations & Impact
Citations
1,109
H-index
6
i10-index
6
Publications
7
Co-authors
0
Publications
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
- - Falcon: Fractional Alternating Cut with Overcoming Minima in Unsupervised Segmentation, 2025 Preprint
- - Rhythm Gate: Invisible Conversations in the Elevator, 2025 ACM International Conference on Multimedia (MM)
- - Refining Pseudo Labels with Clustering Consensus over Generations for Unsupervised Object Re-Identification, 2021 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- - RBF-Softmax: Learning Deep Representative Prototypes with Radial Basis Function Softmax, 2020 European Conference on Computer Vision (ECCV)
- - Adacos: Adaptively Scaling Cosine Logits for effectively Learning Deep Face Representations, 2019 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) [Oral]
- - P2SGrad: Refined Gradients for Optimizing Deep Face Models, 2019 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- - Range Loss for Deep Face Recognition with Long-tailed Training Data, 2017 IEEE International Conference on Computer Vision (ICCV)
Research Experience
- - Research Intern at Nvidia (Jul. 2021 to Jul. 2022), worked on self-supervised representation learning with Dr. Charles Cheung
- - Computer Vision Research Intern at SenseTime Research (Jul. 2017 to Jul. 2019), worked on large-scale smart city projects with Dr. Rui Zhao and Dr. Junjie Yan
- - Visiting student at MMLab, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences (Jul. 2016 to Jul. 2017), Advisor: Prof. Yu Qiao
Education
- - Postdoc, University of Pennsylvania, Advisor: Prof. Konrad Kording
- - Ph.D., Multimedia Lab (MMLab), The Chinese University of Hong Kong, Supervisors: Prof. Xiaogang Wang and Prof. Hongsheng Li
- - B.Eng, College of Intelligence and Computing, Tianjin University, Minor in Finance
Background
- - Research Interests: Representation learning and theory in foundation vision, language, and multi-modal data and their applications; human movement and cognition modeling; eye-movement analysis in medical areas; real-time scalable AI systems and infrastructures; AI systems empowered creative industries and contemporary arts research.
- - Professional Field: Advancing scalable AI systems that address diverse machine learning challenges in real-world environments.
- - Introduction: Dedicated to developing robust, scalable, and flexible representation learning methods, employing optimization, statistics, and high-performance computing systems to overcome challenges in large-scale, uncurated, and even ill-posed data.
Co-authors