Name：Junliang XING

Professor

Email：jlxing@tsinghua.edu.cn

Homepage：https://pi.cs.tsinghua.edu.cn/people/#faculty

Education Background:

2003.09-2007.07 Bachelor of Computer Science and Technology Xi'an Jiaotong University

2003.09-2007.07 Bachelor of Mathematics and Applied Mathematics (Dual Degree) Xi'an Jiaotong University

2007.09-2012.07 Ph.D. in Department of Computer Science and Technology Tsinghua University

Work Experience:

2012.07-2015.10 Assistant Researcher National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences

2012.12-2013.11 Visiting Researcher, National University of Singapore

2015.04-2015.10 Visiting Professor, Microsoft Research Asia

2015.11-2018.10 Associate Researcher National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences

2018.11-2022.01 Researcher National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences

2022.02~now: Professor, Department of Computer Science and Technology, Tsinghua University

Research Fields: Computer Vision, Computer Gaming, Human-Computer Interactive Learning

Research Overview:

My research work mainly centers on the field of intelligent perception and decision-making. In the direction of intelligent perception, my early research focused on core visual tasks under unconstrained conditions, including object detection, registration, tracking, segmentation and recognition. In recent years, I have extended my research to the perception and analysis of complex situational information via the fusion of multi-modal data. In the direction of intelligent decision-making, targeting the challenges of difficult modeling, intractable computation and poor interpretability in complex system decision problems, I have gradually established a research route of game-interactive learning by integrating traditional game theory for problem representation and modeling, state-of-the-art machine learning algorithms for approximate model solving, and human-computer interaction for model analysis and interpretation. Relevant research outcomes have led to the publication of over 100 papers in CCF-A international conferences and journals, with more than 24,000 citations on Google Scholar. Notably, the algorithm for human attribute relationship perception received the Best Paper Award at ACM Multimedia 2013, the anchor-free single-stage online multi-object tracking algorithm won the Best Paper Award at PRCV 2020, the AlphaHoldem algorithm for large-scale imperfect information games won the Distinguished Paper Award at AAAI 2022, and the algorithm for semantic transfer and synthesis of gesture motion won the Brave New Idea Paper Award at ACM Multimedia 2023.

Teaching Courses:

Computer Vision: Tsinghua University, graduate course, 48 credits, since spring semester 2024

Programming Fundamentals: Tsinghua University, undergraduate course, 48 credits, since fall semester 2023.

Game Theory: University of Chinese Academy of Sciences, graduate course, 20 credits, spring semester 2024.

Principles and Applications of Computational Game Theory: University of Chinese Academy of Sciences, graduate course, 40 credits, fall semester 2019 to fall semester 2023.

Game Theory: University of Chinese Academy of Sciences, graduate course, 20 credits, spring semester 2017 to spring semester 2019.

Publications:

Selected Journal Papers（* indicates the corresponding author, # indicates a co-first author）:

[1] Junliang Xing#, Zhe Wu#, Zhaoke Yu, Renye Yan, Zhipeng Ji, Pin Tao, Yuanchun Shi*. Game Interactive Learning: A New Paradigm towards Intelligent Decision-Making. CAAI Artificial Intelligence Research (AIR), vol. 2, no. 9150027, 2023.

[2] Junliang Xing, Zhiheng Niu, Junshi Huang, Weiming Hu*, Xi Zhou, and Shuicheng Yan. Towards Robust and Accurate Multi-view and Partially-occluded Face Alignment. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), vol. 40, no. 4, pp. 987-1001, 2018.

[3] Junliang Xing, Weiming Hu, Haizhou Ai, and Shuicheng Yan. FatRegion: A Fast, Adaptive, Tree-structured Region Extraction Approach. IEEE Transactions on Circuits, System and Video Technology (TCSVT), vol. 28, no. 3, pp. 601-615, 2018.

[4] Junliang Xing, Kai Li, Weiming Hu, Chunfeng Yuan, and Haibin Ling. Diagnosing Deep Learning Models for High Accuracy Age Estimation from A Single Image. Pattern Recognition (PR), vol. 66, pp. 95-105, 2017.

[5] Junliang Xing, Haizhou Ai, Liwei Liu, and Shihong Lao, Multiple Players Tracking in Sports Video: A Dual-Mode Two-Way Bayesian Inference Approach with Progressive Observation Modeling, IEEE Transactions on Image Processing (TIP), vol. 20, no. 6, pp. 1652-67, 2011.

[6] Wenhan Luo, Junliang Xing*, Anton Milan, Xiaoqin Zhang, Wei Liu, Tae-Kyun Kim. Multiple Object Tracking: A Literature Review. Artificial Intelligence (AI), vol. 293, pp. 1–23, 2021.

[7] Kai Li, Hang Xu, Haobo Fu, Qiang Fu, Junliang Xing*: Automatically designing counterfactual regret minimization algorithms for solving imperfect-information games. Artificial Intelligence (AI), vol.337, no.104232 , pp.1-18, 2024.

[8]Kai Li, Hang Xu, Enmin Zhao, Zhe Wu, Junliang Xing*: OpenHoldem: A Benchmark for Large-Scale Imperfect-Information Game Research. IEEE Transactions on Neural Networks and Learning System (TNNLS), vol. 35, no.10, pp.14618-14632, 2024.

[9] Xiaoshu Shao#, Junliang Xing#, Jiangjing Lv, Xiangdong Zhou, Yu Shi, Steve Maybank. Robust Face Alignment via Deep Progressive Reinitialization and Adaptive Error-driven Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 10.1109/TPAMI.2021.3073593, 2021.

[10] Jian Zhao, Junliang Xing*, Lin Xiong, Shuicheng Yan, Jiashi Feng. Recognizing Profile Faces by Imagining Frontal View. International Journal of Computer Vision (IJCV), vol. 128, pp. 460–478, 2020.

Selected Conference Papers（* indicates the corresponding author, # indicates a co-first author）:

[1] Junliang Xing, Zhiheng Niu, Junshi Huang, Weiming Hu, Shuicheng Yan. Towards Multi-view and Partially-occluded Face Alignment. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014.

[2] Junliang Xing, Jin Gao, Bin Li, Weiming Hu, Shuicheng Yan. Robust Object Tracking with Online Multi-lifespan Dictionary Learning. In IEEE International Conference on Computer Vision (ICCV), 2013.

[3] Junliang Xing, Haizhou Ai and Shihong Lao, Multi-Object Tracking through Occlusions by Local Tracklets Filtering and Global Tracklets Association with Detection Responses. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2009.

[4] Zijie Ye, Jia Jia, Junliang Xing, Semantics2Hands: Transferring Hand Motion Semantics between Avatars. In ACM Multimedia Conference (ACM MM), 2023: 9282-9290.（Brave New Idea Award）

[5] Enmin Zhao, Renye Yan, Jinqiu Li, Kai Li, and Junliang Xing*. AlphaHoldem: High-Performance Artificial Intelligence for Heads-Up No-Limit Poker from End-to-End Reinforcement Learning. In AAAI Annual Conference on Artificial Intelligence (AAAI), 2022. （Distinguished Paper Award）

[6] Hang Xu, Kai Li, Haobo Fu, Qiang Fu, and Junliang Xing*. AutoCFR: Learning to Design Counterfactual Regret Minimization Algorithms. In AAAI Annual Conference on Artificial Intelligence (AAAI), 2022.

[7] Yongxin Kang, Enmin Zhao, Kai Li, and Junliang Xing*. Exploration via State Influence Modeling. In AAAI Annual Conference on Artificial Intelligence (AAAI), 2021.

[8] Peixi Peng, Junliang Xing*, and Lili Cao. Hybrid Learning for Multi-agent Cooperation with Sub-optimal Demonstrations. In International Joint Conferences on Artificial Intelligence (IJCAI), 2020.

[9] Zongwei Zhou, Yangxi Li, Jin Gao, Junliang Xing, Liang Li, and Weiming Hu. Anchor-Free One-Stage Online Multi-object Tracking. In Chinese Conference on Pattern Recognition and Computer Vision (PRCV), 2020.（Best Paper Award）

[10] Luoqi Liu, Hui Xu, Junliang Xing, Si Liu, Xi Zhou, Shuicheng Yan. “Wow! You Are So Beautiful Today!” In ACM International Conference on Multimedia (ACM MM), 2013.（Best Paper Award）