2026 Tong Zhang: Computer Science Researcher – H-Index, Publications & Awards

Overview

Tong Zhang is a researcher affiliated with the University of Illinois at Urbana-Champaign in the United States. Their work primarily focuses on the field of Computer Science, with an emphasis on Computer Vision and Pattern Recognition, Artificial Intelligence, and related subfields.

The research topics covered by Tong Zhang include advanced image and video retrieval techniques, visual attention and saliency detection, topic modeling, natural language processing techniques, advanced vision and imaging, advanced neural network applications, and machine learning and data classification.

The scientist has contributed significantly to the literature, with recent papers including:

Optimal Feature Transport for Cross-View Image Geo-Localization, 2020, Proceedings of the AAAI Conference on Artificial Intelligence
UC-Net: Uncertainty Inspired RGB-D Saliency Detection via Conditional Variational Autoencoders, 2020, arXiv (Cornell University)
Semi-supervised Active Salient Object Detection, 2021, Pattern Recognition
Learning Saliency From Single Noisy Labelling: A Robust Model Fitting Perspective, 2020, IEEE Transactions on Pattern Analysis and Machine Intelligence
RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment, 2023, arXiv (Cornell University)

Frequent coauthors of Tong Zhang include Sabine Süsstrunk, Yuchao Dai, Mathieu Salzmann, Jipeng Zhang, and Shizhe Diao. These collaborations reflect ongoing work across multiple projects and topics within their research areas.

Tong Zhang has published extensively in several venues, notably:

arXiv (Cornell University)
Proceedings of the AAAI Conference on Artificial Intelligence
IEEE Transactions on Pattern Analysis and Machine Intelligence
SSRN Electronic Journal
Pattern Recognition

The concentration of publications in these venues indicates a focus on sharing research findings related to artificial intelligence, pattern recognition, and computer vision for academic and professional audiences.

Best Publications

Solving large scale linear prediction problems using stochastic gradient descent algorithms

Tong Zhang

1449
Citations
Efficient mini-batch training for stochastic optimization

Mu Li;Tong Zhang;Yuqiang Chen;Alexander J. Smola

899
Citations
The Benefit of Group Sparsity

Junzhou Huang;Tong Zhang

612
Citations
Learning with Structured Sparsity

Junzhou Huang;Tong Zhang;Dimitris Metaxas

601
Citations
Analysis of Multi-stage Convex Relaxation for Sparse Regularization

Tong Zhang

559
Citations
Spatial–Temporal Recurrent Neural Network for Emotion Recognition

Tong Zhang;Wenming Zheng;Zhen Cui;Yuan Zong

556
Citations
Multi-Label Prediction via Compressed Sensing

John Langford;Tong Zhang;Daniel J. Hsu;Sham M Kakade

481
Citations
Sparse Recovery With Orthogonal Matching Pursuit Under RIP

Tong Zhang

435
Citations
UC-Net: Uncertainty Inspired RGB-D Saliency Detection via Conditional Variational Autoencoders

Jing Zhang;Deng-Ping Fan;Yuchao Dai;Saeed Anwar

408
Citations
Deep Subspace Clustering Networks

Pan Ji;Tong Zhang;Hongdong Li;Mathieu Salzmann

406
Citations
Involution: Inverting the Inherence of Convolution for Visual Recognition

Duo Li;Jie Hu;Changhu Wang;Xiangtai Li

385
Citations
The Epoch-Greedy algorithm for contextual multi-armed bandits

John Langford;Tong Zhang

359
Citations
Adaptive Sampling Towards Fast Graph Representation Learning

Wenbing Huang;Tong Zhang;Yu Rong;Junzhou Huang

358
Citations
Adaptive Forward-Backward Greedy Algorithm for Learning Sparse Representations

Tong Zhang

345
Citations
A Deep Neural Network-Driven Feature Learning Method for Multi-view Facial Expression Recognition

Tong Zhang;Wenming Zheng;Zhen Cui;Yuan Zong

344
Citations
Uncertainty-aware Joint Salient Object and Camouflaged Object Detection

Aixuan Li;Jing Zhang;Yunqiu Lv;Bowen Liu

269
Citations
Adaptive Forward-Backward Greedy Algorithm for Sparse Learning with Linear Models

Tong Zhang

224
Citations
On the Consistency of Feature Selection using Greedy Least Squares Regression

Tong Zhang

222
Citations
Learning with structured sparsity

Junzhou Huang;Tong Zhang;Dimitris Metaxas

206
Citations
Modeling Localness for Self-Attention Networks

Baosong Yang;Zhaopeng Tu;Derek F. Wong;Fandong Meng

205
Citations
Deep Unsupervised Saliency Detection: A Multiple Noisy Labeling Perspective

Jing Zhang;Tong Zhang;Yuchao Daf;Mehrtash Harandi

194
Citations
Multi-Head Attention with Disagreement Regularization

Jian Li;Zhaopeng Tu;Baosong Yang;Michael R. Lyu

189
Citations
Design of Highly Nonlinear Substitution Boxes Based on I-Ching Operators

Tong Zhang;C. L. Philip Chen;Long Chen;Xiangmin Xu

187
Citations
Improved Local Coordinate Coding using Local Tangents

Kai Yu;Tong Zhang

185
Citations
Error Compensated Quantized SGD and its Applications to Large-scale Distributed Optimization

Jiaxiang Wu;Weidong Huang;Junzhou Huang;Tong Zhang

155
Citations
Optimal Feature Transport for Cross-View Image Geo-Localization

Yujiao Shi;Xin Yu;Liu Liu;Tong Zhang

148
Citations
Efficient Optimal Learning for Contextual Bandits

Miroslav Dudik;Daniel Hsu;Satyen Kale;Nikos Karampatziakis

134
Citations
Gradient Hard Thresholding Pursuit for Sparsity-Constrained Optimization

Xiaotong Yuan;Xiaotong Yuan;Ping Li;Tong Zhang

134
Citations
End-to-End Active Object Tracking and Its Real-World Deployment via Reinforcement Learning

Wenhan Luo;Peng Sun;Fangwei Zhong;Wei Liu

132
Citations
Multi-cue fusion for emotion recognition in the wild

Jingwei Yan;Wenming Zheng;Zhen Cui;Chuangao Tang

131
Citations
A robust risk minimization based named entity recognition system

Tong Zhang;David Johnson

127
Citations
A Novel Neural Network Model based on Cerebral Hemispheric Asymmetry for EEG Emotion Recognition.

Yang Li;Wenming Zheng;Zhen Cui;Tong Zhang

123
Citations
Cross-Corpus Speech Emotion Recognition Based on Domain-Adaptive Least-Squares Regression

Yuan Zong;Wenming Zheng;Tong Zhang;Xiaohua Huang

107
Citations
Exploiting Deep Representations for Neural Machine Translation

Zi-Yi Dou;Zhaopeng Tu;Xing Wang;Shuming Shi

99
Citations
Unsupervised Image-to-Image Translation with Stacked Cycle-Consistent Adversarial Networks

Minjun Li;Haozhi Huang;Lin Ma;Wei Liu

97
Citations
Sparse Online Learning via Truncated Gradient

John Langford;Lihong Li;Tong Zhang

73
Citations
Deep Unsupervised Saliency Detection: A Multiple Noisy Labeling Perspective

Jing Zhang;Tong Zhang;Yuchao Dai;Mehrtash Harandi

72
Citations

Frequent Co-Authors

Wenbing Huang Renmin University of China

Hongdong Li Australian National University

Yuchao Dai Northwestern Polytechnical University

Mehrtash Harandi Monash University

Richard Hartley Australian National University

Ian Reid University of Adelaide

Junzhou Huang The University of Texas at Arlington

Mathieu Salzmann École Polytechnique Fédérale de Lausanne

Lars Petersson Commonwealth Scientific and Industrial Research Organisation

Fatih Porikli Australian National University

External Links

Personal website of Tong Zhang

If you think any of the details on this page are incorrect, let us know.

Related Online Degrees & Career Pathways

Studying Computer Science in the USA opens the door to a wide range of educational paths and career options. Many students start with an associate degree online, an affordable option that can be completed quickly to help you enter the tech field or continue on to a bachelor’s program.

If you're considering advanced studies, there are several graduate degrees that are worth it, especially those in high-demand technology areas like data science, cybersecurity, and artificial intelligence. These programs can lead to specialized and higher-paying roles in the industry.

Cost is often a concern, but you’ll find many cheap online college classes offered by accredited institutions. These programs provide flexibility and affordability, allowing you to learn at your own pace without a heavy financial burden.

Don’t worry if your academic record isn’t perfect. There are also online colleges that accept 2.0 gpa, making it possible for more students to pursue their interests in computer science or related fields. With so many pathways, starting your tech career is more accessible than ever.