本人为天津理工大学计算机科学与工程学院副教授、硕士生导师。近年来在ACM TOIS、IEEE TMM、WWW、ACM MM等国际期刊和会议发表学术论文十余篇。研究方向主要包括：推荐系统、多模态学习、生成式模型、图神经网络、计算机视觉与多媒体分析检索。欢迎对推荐系统、多模态学习、生成式模型或计算机视觉感兴趣、具有良好编程与科研基础的同学报考或联系加入课题组攻读硕士研究生。 
（1）2025.01-2027.12 国家自然科学基金青年科学基金：面向开放域的短视频增量话题检测。主持人 （2）2021.01-2025.12 国家自然科学基金重点项目:面向领域大数据的跨媒体可解释分析与推理。参与人 （3）2015.01-2019.12 国家自然科学基金重点项目:大数据环境下复杂多媒体内容分析、推送与展示。参与人 （4）2019.06 - 2021.08 快手科技公司:多模态短视频冷启动推荐研究。执行人 （5）2021.04-2022.04 腾讯微信犀牛鸟专项:推荐场景中结合视频多模态用户行为的主题模型。执行人 
[1] Ying He, Desheng Cai*, Shengsheng Qian, Quan Fang, Yinwei Wei and Changsheng Xu. “Multi- modal Bipartite Graph Structure Learning with Information Bottleneck for Micro-video Recommendation.” The Web Conference (WWW), 2026.(CCF-A类会议论文). [2] Desheng Cai, Shengsheng Qian, Quan Fang, Jun Hu, Changsheng Xu. “User Cold-Start Recommendation via Inductive Heterogeneous Graph Neural Network.” ACM Transactions on Information Systems (TOIS), vol.41, pp.1-27, 2023. (CCF-A类期刊论文). [3] Desheng Cai, Shengsheng Qian, Quan Fang, Jun Hu, Changsheng Xu. “Adaptive Anti-Bottleneck Multi-Modal Graph Learning Network for Personalized Micro-video Recommendation.” ACM Multimedia (MM) 2022: 581-590.(CCF-A类会议论文). [4] Desheng Cai, Shengsheng Qian, Quan Fang, Jun Hu, Changsheng Xu. “Heterogeneous Graph Contrastive Learning Network for Personalized Micro-Video Recommendation.” EEE Transactions on Multimedia (TMM), vol.25, pp.2761-2773, 2023.(CCF-A类期刊论文). [5] Desheng Cai, Shengsheng Qian, Quan Fang, Changsheng Xu. “Heterogeneous Hierarchical Feature Aggregation Network for Personalized Micro-Video Recommendation.” IEEE Transactions on Multimedia (TMM), vol.24, pp.805-818, 2022.(CCF-A类期刊论文). [6] Desheng Cai, Gongqing Wu. “Content-aware Attributed Entity Embedding for Synonymous Named Entity Discovery.” Neurocomputing, vol.329, pp.237-247, 2019. [7] Junwei Lv, Ying He, Xuegang Hu, Desheng Cai, Yuqi Chu, Jun Hu. “Dual Confidence Learning Network for Open-World Time Series Classification.”. Database Systems for Advanced Applications (DASFAA) 2022:574-589. [8] Ying He, Gongqing Wu, Desheng Cai, Xuegang Hu. Meta-path Based Graph Contrastive Learning for Micro-video Recommendation[J]. Expert Systems with Application, 2023. [9] Ying He, Gongqing Wu, Desheng Cai, Xuegang Hu. “Cross-View Sample-Enriched Graph Contrastive Learning Network for Personalized Micro-video Recommendation.” ACM International Conference on Multimedia Retrieval (ICMR) 2023:48-56. [10] Ying He, Gongqing Wu, Desheng Cai, Shengjie Hu, Xianyu Bao, Xuegang Hu:Attentive Interaction-driven Entity Resolution over Multi-source Web Information. Neurocomputing 425: 266-277 (2021). 
2023.6 安徽省优秀毕业生 |
