Liansheng Zhuang (庄连生), PhD. School of Information Science & Technology University of Science and Technology of China Tel: +86-551-63602860 (office) Email: lszhuang_AT_ustc_DOT_edu_DOT_cn Google Profile | ResearchGate

About Me

I am an associate professor in University of Science and Technology of China (USTC). I got my PhD degree and B.S degree from USTC, respectively in 2006 and 2001. Since 2006, I have been working in School of Information Science and Technoloyg, USTC. In 2011.3-2011.11, I was nominated to join the “STARTRACKER” project of Microsoft Research of Asia (MSRA), and worked on sparse representation & object recognition in visual computing group as a vendor researcher (host by Prof. Yi Ma). During 2012.2-2013.2, I was a visiting research scholar of EECS Department in University of California at Berkeley (host by Prof. S.Shankar Sastry), and worked on object recognition in the Trust & Chess Center with Prof. S.Shankar Sastry and Dr. Allen Y. Yang.

Research topics:

My

• Computer Vision, including Object recognition, Human action location, Image Generation, etc..
• Knowledge Graph, including Knowledge graph embedding, Knowledge graph reasoning，etc.
• Computer Games, including Reinforcement learning, MCTS, etc.

Projects

In the past years, we have taken on some projects including:

• Knowledge-driven Few-shot Image Object Recogntion, supported by NSFC, 2021 - 2024.
  The past decade have witnessed the progress of object recognition with the help of deep learning (such as CNN, Transformer). However, existing mehtods rely on huge costly labeled data which are difficult to be acquired in real applications. To addres the few-shot classification, our key idea is to utilize prior knowledge learned from mass auxiliary data to do few-shot object classification. Its research topics include Knowledge Graph, AIGC, Domain Generalization, Transfer Learning, etc.

• Knowledge-based Deep Reinforcement Learning for Imperfect-information Computer Games, supported by NSFC, 2020 - 2023.
  Deep reinforcement learning has shown impressive performance in various computer games. Its paradigm of learning is by trial-and-error solely from rewards or punishments. In imperfect-information games, the policy spaces is huge and the training of deep reinforcement learning is very time-consuming and low efficient. The goal of this project is to develop new theories, algorithms and technologies to learn high performance agents for imperfect-information games, by combine the prior knowledge with deep reinforcement learning in an efficient manner. Its research topics incude Deep Reinforcment Learning, Game Theories, etc.

Teaching

I teaches three courses for undergraduate students:

• Introduction to Algorithm (2010-Now)

• Foundation of Information Security Law (2010-2020)

• Embedding System Designing (2010-2017)

Publications

Here are some selected publications.

1. EPERM: An Evidence Path Enhanced Reasoning Model for Knowledge Graph Question and Answering,
   Xiao Long, Liansheng Zhuang, Aodi Li, Minghong Yao, Shafei Wang, accepted by The 39th Annual AAAI Conference on Artificial Intelligence (AAAI-25), Feb, 2025
   

2. Progressive Neural Architecture Generation with Weaker Predictors,
   Zhengzhuo Zhang, Liansheng Zhuang, accepted by The 31st International Conference on MultiMedia Modeling (MMM 2025), Jan 8-10, 2025
   

3. Purified Policy Space Response Oracles for Symmetric Zero-Sum Games,
   Zhengdao Shao, Liansheng Zhuang, Yihong Huang, Houqiang Li, Shafei Wang, accepted by IEEE Transactions on Neural Networks and Learning Systems (TNNLS), August, 2024
   

4. COPSRO: An Offline Empirical Game Theorectic Method with Conservative Critic,
   Zhengdao Shao, Liansheng Zhuang, Houqiang Li, Shafei Wang, accepted by IEEE Transactions on Neural Networks and Learning Systems (TNNLS), August, 2024
   

5. Toward a General Transformer-Based Framework for Multi-Agent Path Finding,
   Shuqing Sun, Haonan Liu, Liansheng Zhuang, Houqiang Li, accpeted by The 29th International Conference on Neural Information Processing (ICONIP 2024), 2024
   

6. Private Gradient Estimation is Useful for Generative Modeling,
   Baochao Liu, Pengju Wang, Weijia Guo, Yong Li, Liansheng Zhuang, Weiping Wang, Shiming Ge, The 32nd ACM International Conference on Multimedia (MM 24), Melbourne, Australia, 2024
   

7. Hierarchical Augmentation and Distillation for Class Incremental Audio-Visual Video Recognition,
   Yukun Zuo, Hantao Yao, Liansheng Zhuang, Changshegn Xu, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), pp.1-15, 12 April 2024
   

8. Learning Label Dependencies for Visual Information Extraction,
   Minghong Yao, Liansheng Zhuang, Houqiang Li, Jiuchang Wei, accepted by International Joint Conference on Artificial Intelligence (IJCAI), 2024
   

9. Conservative In-Distribution Q-Learning for Offline Reinforcement Learning,
   Zhengdao Shao, Liansheng Zhuang, Jie Yan, Liting Chen, 2024 International Joint Conference on Neural Networks (IJCNN), YOKOHAMA, JAPAN, June 30-July 5, 2024
   

10. Fact Embedding through Diffusion Model for Knowledge Graph Completion,
    Xiao Long, Liansheng Zhuang, Aodi, Li, Houqiang Li, Shafei Wang, accepted by The 2024 ACM Web Conference (WWW'24), 2024
    

11. A Robust Framework for One-shot Key Information Extraction via Deep Partial Graph Matching,
    Minghong Yao, Zhiguang Liu, Liansheng Zhuang, Liangwei Wang, Houqiang Li, IEEE Transactions on Image Processing (TIP), Vol.33, pp.1070-1079, 29 January 2024
    

12. KGDM: A Diffusion Model to Capture Multiple Relation Semantics for Knowledge Graph Embedding,
    Xiao Long, Liansheng Zhuang, Aodi Li, Jiuchang Wei, Houqiang Li, Shafei Wang, Thirty-Eighth AAAI Conference on Artificial Intelligence (AAAI-24), 2024
    

13. Learning a Robust Model with Pseudo Boundaries for Noisy Temporal Action Localization,
    Xinyi Yuan, Liansheng Zhuang, The 5th ACM International Conference on Multimedia in Asia (MMAsia'23), Tainan, Taiwan, China, Dec.6-8, 2023:1-7
    

14. Two-stage Content-Aware Layout Generation for Poster Designs,
    Shang Chai, Liansheng Zhuang, Fengying Yan, Zihan Zhou, The 31st ACM International Conference on Multimedia(MM'23), Ottawa, ON, Canada, Oct.29-Nov.3, 2023:8415-8423
    

15. Learning Generalized Representation for Open Set Temporal Action Localization,
    Junshan Hu, Liansheng Zhuang, Weisong Dong, Shiming Ge, Shafei Wang, The 31st ACM International Conference on Multimedia(MM'23), Ottawa, ON, Canada, Oct.29-Nov.3, 2023:1987-1996
    

16. LayoutDM: Transformer-based Diffusion Model for Conditional Layout Generation,
    Shang Chai, Liansheng Zhuang, Fengying Yan, IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR'23), Vancouver, BC, Canada, June 17-24, 2023:18349-18358
    

17. Curriculum Learning Based Multi-Agent Path Finding for Complex Enviroments,
    Cheng Zhao, Liansheng Zhuang, Yihong Huang, Haonan Liu, 2023 International Joint Conference on Neural Networks (IJCNN'23), Gold Coast, Australia, June 18-23, 2023:1-8
    

18. Bayesian Sharpness-Aware Prompt Tuning for Cross-Domain Few-Shot Learning,
    Shuo Fan, Liansheng Zhuang, Aodi Li, 2023 International Joint Conference on Neural Networks (IJCNN'23), Gold Coast, Australia, June 18-23, 2023:1-7
    

19. Dual Structural Knowledge Interaction for Domain Adaptation,
    Yukun Zuo, Hantao Yao, Liansheng Zhuang, Changsheng Xu, IEEE Transactions on Multimedia, Vol.25, pp.9057-9070, 2023
    

20. Neural-based Mixture Probabilistic Query Embedding for Answering FOL queries on Knowledge Graphs,
    Xiao Long, Liansheng Zhuang, Aodi Li, Shafei Wang, Houqiang Li, The 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP 2022), Abu Dhabi, United Arab Emirates, Dec.7-11, 2022:3001-3013
    

21. Learning Common and Specific Visual Prompts for Domain Generalization,
    Aodi Li, Liansheng Zhuang, Shuo Fan, Shafei Wang, The 16th Asian Conference on Computer Vision (ACCV 2022), Dec.4-8, Macau SAR, China, 2022:578-593
    

22. HaViT: Hybrid-attention based Vision Transformer for Video Classification,
    Li Li, Liansheng Zhuang, Shenghua Gao, Shafei Wang, The 16th Asian Conference on Computer Vision (ACCV 2022), Dec.4-8, Macau SAR, China, 2022:502-517
    

23. Efficient Double Oracle for Extensive-Form Two-Player Zero-Sum Games,
    Yihong Huang, Liansheng Zhuang, Cheng Zhao, Haonan Liu, The 27th International Conference on Neural Information Processing (ICONIP 2022), Nov.22-26, IIT Indore, India, 2022:414-424
    

24. VAAC: V-value Attention Actor-Critic for Cooperative Multi-agent Reinforcement Learning,
    Haonan Liu, Liansheng Zhuang, Yihong Huang, Cheng Zhao, The 27th International Conference on Neural Information Processing (ICONIP 2022), Nov.22-26, IIT Indore, India, 2022:562-573
    

25. Estimation of Reliable Proposal Quality for Temporal Action Detection,
    Junshan Hu, Chaoxu Guo, Liansheng Zhuang, Biao Wang, Tiezheng Ge, Yuning Jiang, Houqiang Li, The 30th ACM International Conference on Multimedia (MM'22), Lisboa, Portugal, October 10-14, 2022:6685-6695
    

26. PMIVec: A Word Embedding Model Guided by Point-wise Mutual Information Criterion,
    Minghong Yao, Liansheng Zhuang , Shafei Wang, Houqiang Li, accepted by Multimedia Systems, 2022
    

27. MEViT: Motion Enhanced Video Transformer for Video Classification,
    Li Li, Liansheng Zhuang , The 28th International Conference on MultiMedia Modeling (MMM 2022), Phu Quoc, Vietnam, June 6-10, 2022: 419-430
    

28. Seek Common Ground While Reserving Differences: A Model-Agnostic Module for Noisy Domain Adaptation,
    Yukun Zuo, Hantan Yao, Liansheng Zhuang , Changsheng Xu, IEEE Transactions on Multimedia (TMM), Vol.24, July 16, 2021:1020-1030
    

29. Margin-based Adversarial Joint Alignment Domain Adaptation,
    Yukun Zuo, Hantan Yao, Liansheng Zhuang , Changsheng Xu, IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), Vol.32, No.4, April 2022:2057-2067
    

30. Path Ranking Model for Entity Prediction,
    Xiao Long, Minghong Yao, Liansheng Zhuang , Houqiang Li, Shafei Wang, IEEE International Conference on Multimedia and Expo (ICME 2021), Shenzhen, China, July 5-9, 2021
    

31. Learn the Approximation Distribution of Sparse Coding with Mixture Sparsity Network,
    Li Li, Xiao Long, Liansheng Zhuang , Shafei Wang, accpted to The 4th Chinese Conference on Pattern Recognition and Computer Vision (PRCV 2021), Beijing, China, October 29-November 1, 2021
    

32. Question-relationship guided graph attention network for visual question answer,
    Rui Liu, Liansheng Zhuang , Zhou Yu, Zhihao Jiang, Tian Bai, Multimedia Systems, Vol.28, pp.445-446, 2022.
    

33. Time-Sensitive Collaborative Interest Aware Model for Session-Based Recommendation,
    Yang Lv, Liansheng Zhuang , Pengyu Luo, Houqiang Li, Zheng-jun Zha, IEEE International Conference on Multimedia and Expo (ICME 2020), London, United Kingdom, July 6-10, 2020
    

34. Phrase-Level Global-local Hybrid Model for Sentence Embedding,
    Mingyu Tang, Liansheng Zhuang , Houqiang Li, Jian Yang, Yanqun Guo, IEEE International Conference on Multimedia and Expo (ICME 2020), London, United Kingdom, July 6-10, 2020
    

35. Quantile Regression Hindsight Experience Replay,
    Qiwei He, Liansheng Zhuang , Wei Zhang, Houqiang Li, Neural Information Processing - 27th International Conference (ICONIP 2020), Bangkok, Thailand, November 18-22, 2020
    

36. Continuous Sign Language Recognition via Reinforcement Learning,
    Zhihao Zhang, Junfu Pu, Liansheng Zhuang, Wengang Zhou, Houqiang Li, 2019 IEEE International Conference on Image Processing (ICIP 2019), Taipei, Taiwan, September 22-25, 2019: 285-289
    

37. Dynamic Cascaded Regression Network with Reinforcement Learning for Robust Face Alignment,
    Zhihao Zhang, Liansheng Zhuang, Wengang Zhou, Houqiang Li, IEEE International Conference on Multimedia and Expo (ICME 2019), Shanghai, China, July 8-12, 2019: 598-603
    

38. Learning Motion-Aware Policies for Robust Visual Tracking,
    Qianqian Wang, Liansheng Zhuang , Ning Wang, Wengang Zhou, Houqiang Li, IEEE International Conference on Multimedia and Expo (ICME 2019), Shanghai, China, July 8-12, 2019: 1786-1791
    

39. CCNet: Cluster-Coordinated Net for Learning Multi-agent Communication Protocols with Reinforcement Learning,
    Xin Wen, Zheng-Jun Zha, Zilei Wang, Liansheng Zhuang , Houqiang Li, Proceedings of The 10th Asian Conference on Machine Learning (ACML 2018), Beijing, China, November 14-16, 2018: 582-597
    

40. A Feature-Adaptive Semi-Supervised Framework for Co-saliency Detection,
    Xiaoju Zheng, Zheng-Jun Zha, Liansheng Zhuang, 2018 ACM Multimedia Conference on Multimedia Conference (MM 2018), Seoul, Republic of Korea, October 22-26, 2018: 959-966
    

41. Label Information Guided Graph Construction for Semi-supervised Learning,
    Liansheng Zhuang, Zihan Zhou, Shenghua Gao, Jingwen Yin, Zhouchen Lin, Yi Ma, IEEE Transactions on Image Processing (TIP), Vol.26, No.9, Sept. 2017:4182-4192.
    

42. Multi-level visual tracking with hierarchical tree structural constraint,
    Jingjing Wang, Nenghai Yu, Feng Zhu, Liansheng Zhuang, Neurocomputing, Vol.202, August 2016:1-11.
    

43. Locality-Preserving Low-Rank Representation for Graph Construction from Nonlinear Manifolds,
    Liansheng Zhuang, Jingjing Wang, Zhouchen Lin, Allen Y. Yang, Yi Ma, Nenghai Yu, Neurocomputing, Vol.175, January 2016:715-722;
    

44. Constructing a Non-Negative Low-Rank and Sparse Graph with Data-Adaptive Features,
    Liansheng ZHUANG, Shenghua GAO, Jinhui TANG, Jingjing WANG, Zhouchen LIN, Yi MA, Nenghai YU, IEEE Transactions on Image Processing (T-IP), Vol.24, No.11, November 2015:3717-3727.
    

45. Online Shared Dictionary Learning for Visual Tracking,
    Jingjing Wang, Liansheng Zhuang, Nenghai Yu, Proceedings of the 7th International Conference on Internet Multimedia Computing and Service (ICIMCS), 2015:22:1-22:5.
    

46. Sparse Illumination Learning and Transfer for Single-Sample Face Recognition with Image Corruption and Misalignment,
    Liansheng ZHUANG, Tsung-Han Chan, Allen Y. Yang, S. Shankar Sastry, Yi Ma, International Journal of Computer Vision (IJCV), Vol.114, 2015:272-287.
    (A preliminary version was published in CVPR 2013)

47. Neither Global Nor Local: Regularized Patch-Based Representation for Single Sample Per Person Face Recognition,
    Shenghua Gao, Kui Jia, Liansheng Zhuang, Yi Ma, International Journal of Computer Vision (IJCV), Vol.111, 2015:365-383;

48. D-SIFT: An Extended SIFT Feature in DCT Domain (in Chinese),
    Liansheng ZHUANG, Chi Fei, Hangshi Zhong, Nenghai Yu, Journal of Computer-Aided Design & Computer Graphics, Vol.27, No.10, 2015:1859-1864.
    (This paper won the Best Paper Award in HHME 2014.)

49. Unsupervised Feature Learning for RGB-D Image Classification,
    I-Hong Jhuo, Shenghua Gao, Liansheng Zhuang, D.T. Lee, Yi Ma, Proceedings of the 12th Asian Conference on Computer Vision (ACCV), September 2014:276-289.
    

50. Single-Sample Face Recognition with Image Corruption and Misalignment via Sparse Illumination Transfer,
    Liansheng ZHUANG, Allen Yang, S. Shankar Sastry, Zihan Zhou, Yi Ma, in Proceedings of CVPR 2013, 2013;

51. Regularized Semi-supervised Latent Dirichlet Allocation via Low Rank Graph,
    Liansheng ZHUANG, Haoyuan Gao, Jiebo LUO, Zhouchen LIN, Neurocomputing, Vol. 119, November 2013: 26-32.
    (A preliminary version was published in MMM 2011)

52. Non-negative Low Rank and Sparse Graph for Semi-supervised Learning,
    Liansheng ZHUANG, Haoyuan Gao, Zhouchen LIN, Yi MA, Nenghai YU, in Proceedings of CVPR 2012, 2012;

53. Patch-based Face Recognition in Large Pose Variation (in Chinese),
    Qiang Ping, Liansheng ZHUANG, Nenghai YU, in Chinese Journal of Electronics, 2012.

54. Non-negative Sparse Locally Linear Coding (in Chinese),
    Liansheng ZHUANG, Haoyuan GAO, Chao LIU, Nenghai YU, The 7th Joint Conference on Harmonious Human Machine Environment (HHME2011), Beijing, Sept. 17-18, 2011;
    (Excellent Paper Prize, 1/2)

55. A New Graph Constructor for Semi-supervised Discriminant Analysis via Group Sparsity,
    Haoyuan GAO, Liansheng ZHUANG, Nenghai YU, in ICIG2011, Aug. 12-15, 2011;

56. Pose-robust Face Recognition via Part based Sparse Representation (in Chinese),
    Qiang PING, Liansheng ZHUANG, Nenghai YU, Journal of Univerisity of Science and Technology of China, vol.41, Nov. 2011.

57. SVD Based Linear Filtering in DCT Domain,
    Liansheng ZHUANG, Rui ZHAO, Nenghai YU, ICIP2010, Sept. 26-29, 2010, Hong Kong;

58. A Robust Part-based Tracker,
    Wei ZHOU, Liansheng ZHUANG, Nenghai YU, 2010 IEEE International Conference on Multimedia & Expo (ICME2010), July 19 to 23, 2010, Singapore;

59. Low-Resolution Face Recognition via Sparse Representation of Patches,
    Liansheng ZHUANG, MengLiao WANG, Nenghai YU, ICIG2009, Sep.21-24, 2009;

60. Image classification via Semi-Supervised pLSA,
    Liansheng ZHUANG, Lanbo SHE, Yuning JIANG, Nenghai YU, Ketan TANG, ICIG2009, Sep.21-24, 2009;

61. Fast Way to Detect Salient Object based on Segments,
    Liansheng ZHUANG, Ketan TANG, Nenghai YU, Yangchun QIAN, 2009 International Conference on Measuring Technology and Mechatronics Automation (ICMTMA2009), April 11-12, 2009;

62. Learning Object from Small and Imbalanced Dataset with Boost-BFKO,
    Liansheng ZHUANG, Wei ZHOU, Qi Tian, Nenghai YU, 2008 IEEE International Conference on Multimedia & Expo (ICME2008), June 23-26, 2008, Hannover, Germany;

Software

Coming soon ……

Useful Resource

Coming soon ……