巴卡漫画

2009年获巴卡漫画 博士学位

1991年获巴卡漫画 硕士学位

现为巴卡漫画 教授、博士生导师

1991-现在, 巴卡漫画 教师

2016.01—2016.07, 美国俄亥俄州立大学（OSU）计算机系高级访问学者

2005.01—2005.08, 美国伊利诺伊大学香槟分校（UIUC）计算机系访问研究

近年主要研究方向为数据挖掘、大数据管理与分析、机器学习，商务智能、社交网络分析与挖掘、个性化推荐、自然语言处理、计算机视觉、元宇宙、数字人等。

为本科生、研究生讲授包括《商务智能》、《数据挖掘》、《计算机学科前沿》、《数据库概论》、《计算机网络》、《无线网络与通信》等课程。

[1] 国家自然科学基金重点项目《面向数据要素高效共享流通的跨域数据管理关键技术研究》, 项目编号：62436010, 2025.1.1—2029.12.31，228万

[2] 国家自然科学基金面上项目《面向网络直播实时生成内容的推荐模型与算法研究》，项目编号：62172421,2021.1.1—2025.12.31，59万

[3] 国家重点研发计划项目《面向城市智能服务的数据治理体系与共享平台》，项目编号：2020YFB2104100,总经费共计3589万，其中国家专项资金1489万

[4] 深锶科技（北京）有限公司《多模态驱动的人体模型和人像生成系统》，横向项目，50万

[5] 浙江省哲学社会科学新兴(交叉)重大项目《重大突发公共卫生事件下公众风险感知、行为规律及对策研究》，项目编号：21XXJC04ZD

[6] 国家社会科学基金重大项目《我国政府数据治理与利用能力研究》，项目编号: 20&ZD161，2021.1.1-2025.12.31，80万

[7] 国家自然科学重点基金项目《深度学习支持的政府治理大数据分析与预测关键技术研究》，项目编号：U1711262，2018.1.1—2021.12.31，540万

[8] 北京市自然科学基金项目《面向用户信息需求的Web结构化信息抽取技术研究》，项目编号：4152026，2015.1.1—2017.12.31,18万

[9] 国家自然科学基金面上项目《海量RDF数据探索式搜索关键技术与系统研究》，项目编号：61472426，2015.1.1—2018.12.31，12万

[10] 国家高技术发展研究计划863项目《基于用户兴趣模型的媒体大数据内容整合与可视化技术》, 项目编号：2014AA015204，所属项目“基于媒体大数据的信息消费服务关键技术及应用示范” 

[11] 国家社科基金重大项目《中华民族伟大复兴的社会心理促进机制研究》，项目编号：13&ZD155，，80万 

[12] 国家社科基金重大项目《云计算环境下的信息资源集成与服务研究》，项目编号：12&ZD220，80万

[13] 国家重点基础研究课题973项目《海量弱可用信息上知识发现、演化与服务的理论和技术研究》, 项目编号: 2012CB316205

[14] 国家自然科学基金重点项目《网络信息融合与知识服务的理论和方法研究》，项目编号：61033010

[15] 国家核高基项目:非结构化数据管理系统之人大部分，项目编号：2010ZX01042-002-002

[16] 微软亚洲研究院IFP项目《Story-Teller: Detecting and Tracking Hot Topics to Enhance Search Engine》  

[17] 国家自然科学基金面上项目《基于数据挖掘的用户网上行为模式的发现技术与应用研究》，项目编号：70871068，2008.1.1—2011.12.31，24万 

[18] 国家自然科学基金面上项目《与信息系统紧密集成的友好的知识发现系统的理论与应用研究》，项目编号：70471006，2004.1.1—2006.12.31，16万 

[19] 国家自然科学基金重大项目《通用网上知识编辑器及示范主题语义网研究》，项目编号：60496325，2004.1.1—2008.12.31

[20] 国家自然科学基金面上项目《城市建设文件、档案信息的集成管理与集成服务研究》，项目编号：70273055，2003.1.1—2005.12.31，12万

近五年发表论文列表（自2021年以来～）

2025年

1. SyncTalk++: High-Fidelity and Efficient Synchronized Talking Heads Synthesis Using Gaussian Splatting [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence. (TPAMI, JCR Q1)，Oct. 24, 2025 received. (CCF A)

2. LEADRE: Multi-Faceted Knowledge Enhanced LLM Empowered Display Advertisement Recommender System. The 51st International Conference on Very Large Data Bases (VLDB 2025). Sep 1-5, 2025. London, United Kingdom. (CCF A)

3. Topic Guided Multi-faceted Semantic Disentanglement for CTR prediction. the 33st ACM International Conference on Multimedia (ACM Multimedia 2025)，Oct. 27-31, 2025, Dublin, Ireland. (CCF A)

4. DualTalk: Dual-Speaker Interaction for 3D Talking Head Conversations. The IEEE/CV Computer Vision and Pattern Recognition Conference (CVPR 2025). June 10th–17th, Nashville, Tennessee. USA. (CCF A)

5. CoheDancers: Enhancing Interactive Group Dance Generation through Music-Driven Coherence Decomposition. the 33st ACM International Conference on Multimedia (ACM Multimedia 2025)，Oct. 27-31, 2025, Dublin, Ireland. (CCF A)

6. Ziqiao Peng, Jiwen Liu, Haoxian Zhang, Xiaoqiang Liu, Songlin Tang, Pengfei Wan, Di ZHANG, Hongyan Liu, Jun He. OmniSync: Towards Universal Lip Synchronization via Diffusion Transformers. the Thirty-Ninth Annual Conference on Neural Information Processing Systems (NeurIPS 2025), Dec. 2-7, 2025. San Diego, California, USA. (Spotlight, CCF A)

7. Kaixing Yang, XulongTang, Ziqiao Peng, Yuxuan Hu, Jun He, Hongyan Liu. MEGADance: Mixture-of-Experts Architecture for Genre-Aware 3D Dance Generation. the Thirty-Ninth Annual Conference on Neural Information Processing Systems (NeurIPS 2025), Dec. 2-7, 2025. San Diego, California, USA. (CCF A)

8. Offline Reinforcement Learning via Conservative Smoothing and Dynamics Controlling. ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Hyderabad, India, 2025, pp. 1-5, (CCF B)

9. Debiased Estimation for Cross-Domain Cold Start Recommendation. ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Hyderabad, India, 2025, pp. 1-5, doi: 10.1109/ICASSP49660.2025.10889985. (CCF B)

10. KAN v.s. MLP for Offline Reinforcement Learning. ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Hyderabad, India, 2025, pp. 1-5, doi: 10.1109/ICASSP49660.2025.10888327. (CCF B)

11. Meta-Learning Empowered Meta-Face: Personalized Speaking Style Adaptation for Audio-Driven 3D Talking Face Animation. IEEE International Conference on Multimedia & Expo (ICME) 2025. June 30-July 4, 2025. Nantes, France. (CCF B)

2024年

12. SyncTalk: The Devil is in the Synchronization for Talking Head Synthesis. 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (CVPR 2024). pp. 666-676. Jun 16-22, 2024, Seattle, Washington, USA. ISBN: 979-8-3503-5300-6, (CCF A)

13. CoDancers: Music-Driven Coherent Group Dance Generation with Choreographic Unit. The proceedings of 2024 ACM International Conference on Multimedia Retrieval (ACM ICMR-2024).  Pages 675-683. Published: June 07, 2024. June 9-14, 2024, Thailand. (CCF B)

14. BeatDance: A Beat-Based Model-Agnostic Contrastive Learning Framework for Music-Dance Retrieval.  The proceedings of 2024 ACM International Conference on Multimedia Retrieval (ACM ICMR-2024).  Pages 11-19. Published: June 07, 2024. June 9-14, 2024, Thailand. (CCF B)

15. PoseRec: 3D Human Pose Driven Online Advertisement Recommendation for Micro-videos. The proceedings of 2024 ACM International Conference on Multimedia Retrieval (ACM ICMR-2024). Pages 37–45.  Published: June 07, 2024. June 9-14 2024, Thailand, (CCF B)

16. STDG: Semi-Teacher-Student Training Paradigm for Depth-guided One-stage Scene Graph Generation. The proceedings of 2024 ACM International Conference on Multimedia Retrieval (ACM ICMR-2024). Pages 915-924. Published: June 07, 2024. June 9-14, 2024, Thailand. (CCF B)

17. ACR-Pose: Adversarial Canonical Representation Reconstruction Network for Category Level 6D Object Pose Estimation. The proceedings of 2024 ACM International Conference on Multimedia Retrieval (ACM ICMR-2024). Pages 55-63. Published: June 07, 2024. June 9-14, 2024, Thailand. (CCF B)

18. CausalCDR: Causal Embedding Learning for Cross-domain Recommendation. SIAM International Conference on Data Mining (SDM24). pp. 553-561. April 18-20, 2024. Houston, TX, USA. (CCF B)

19. Backdoor Attacks with Input-unique Triggers in NLP. European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases. Research Track (ECML PKDD 2024). First Online: 22 August 2024. pp 296–312. September 9-13. Vilnius, Lithuania. LNAI, volume 14941, (CCF B)

2023年

20. SelfTalk: A Self-Supervised Commutative Training Diagram to Comprehend 3D Talking Face，the 31st ACM International Conference on Multimedia (ACM MM)，October 29, 2023 – November 3, 2023. Ottawa, Canada. (CCF A)

21. Reconstruction-Aware Prior Distillation for Semi-supervised Point Cloud Completion. Proceedings of the 32nd International Joint Conference on Artificial Intelligence (IJCAI 2023). p726-735, August 19-25, 2023, Macao. (CCF A)

22. EmoTalk: Speech-driven emotional disentanglement for 3D face animation. The 2023 International Conference on Computer Vision (ICCV 2023), October 2-6, 2023. Paris, France. (CCF A)

23. GIDP: Learning a Good Initialization and Inducing Descriptor Post-enhancing for Largescale. the 2023 IEEE International Conference on Robotics and Automation (ICRA), May 29 - June 2, 2023, London, United Kingdom. (CCF B)

24. Deep Learning on Monocular Object Pose Detection and Tracking: A Comprehensive Overview [J]. ACM Computing Surveys (SCI, JCR Q1). Volume 55, Issue 4, May 2023, pp 1–40, //doi.org/10.1145/3524496

2022年

25. SVT-Net: Super Light-Weight Sparse Voxel Transformer for Large Scale Place Recognition. The Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI-22). Vancouver, BC, Canada. February 22-March 1, 2022. PP. 551-560, (CCF A)

26. Object Level Depth Reconstruction for Category Level 6D Object Pose Estimation from Monocular RGB Image. European Conference on Computer Vision (ECCV) 2022. October 23-27, 2022. Tel-Aviv, Israel. (CCF B)

27. An MRC Framework for Semantic Role Labeling. The 29th International Conference on Computational Linguistics (Coling 2022). October 12-17, 2022. Gyeongju, Korea. (CCF B)

28. Learning dynamic treatment strategies for coronary heart diseases by artificial intelligence: real-world data-driven study[J]. BMC Medical Informatics and Decision Making (SCI). 2022. 22-39, //doi.org/10.1186/s12911-022-01774-0

29. Predicting viewer’s watching behavior and live streaming content change for anchor recommendation[J]. Applied Intelligence (SCI, JCR Q2), 2022, 52(3): 2480-2495. (CCF C) 

2021年

30. MPDNet: A 3D Missing Part Detection Network Based on Point Cloud Segmentation. 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2021). June 6-11, 2021, Toronto, Ontario, Canada. (CCF B)

31. A Deep Bi-Directional Prediction Model for Live Streaming Recommendation. Information Processing and Management. Volume 58, Issue 2, March 2021, pp 1-15 (CCF B, JCR Q1)

32. Deep sequential model for anchor recommendation on live streaming platforms [J]. Big Data Mining and Analytics, 2021, 4(3): 173-182.（Excellent Paper Award 2023）

中国计算机学会杰出会员 

中国计算机学会大数据专家委员会委员 

中国计算机学会数据库专家委员会委员 

获五次国际会议及期刊最佳论文奖：

[1] 第13届知识科学、工程与管理国际会议（The 13th International Conference on Knowledge Science, Engineering and Management，KSEM 2020）Best Paper Runner-Up award, 2020. 

[2] 第14届Web信息系统工程国际会议（The 14th International Conference on Web Information System Engineering）最佳竞赛论文奖（Best Challenge paper award), 2013. 

[3] 第十届美国工业与应用数学学会数据挖掘国际会议（ SIAM International conference on Data Mining, SDM 2010）最佳论文奖（Best Paper Award）, 2010. 

[4] 第五届高级数据挖掘及其应用国际会议(The International Conference on Advanced Data Mining and Applications)最佳研究论文奖（Best Research Paper Award）, 2009. 

[5] Deep sequential model for anchor recommendation on live streaming platforms[J]. Big Data Mining and Analytics, 2021, 4(3): 173-182. （Excellent Paper Award 2023 ）