基本信息
政治面貌：中共党员
职职称称：副教授
毕业院校：哈尔滨工业大学
最后学位：博士
专专业业：计算机软件与理论
研究方向：人工智能，多模态感知学习（多模态场景理解），多模态语义通信
教学科研情况
主持辽宁省自然科学基金面上项目及“兴辽英才计划”博士后储备项目、WilliamHill中文博士启动项目、浙江省之江实验室横向项目两项，作为主要技术负责人和核心人员参与国家自然科学基金3项（包括重大联合项目）和省级重点研发项目1项，负责浙江省之江实验室纵向项目3项。中国计算机学会高级会员（CCF Senior Member），中国图像学会专业会员，在国内外学术期刊发表论文三十余篇（包括CCF-A、CCF-B、中科院1区等Top期刊和会议论文），授权专利10项，担任计算机学报、AAAI、IJCAI、ICME等审稿人；教学方面，主讲本科生《软件工程》《人工智能与大数据》及研究生《科技写作与学术规范》课程。
代表性学术成果
[1] Open-World 3D Scene Graph Generation for Retrieval-Augmented Reasoning[C] //Proceedings of the AAAI Conference on Artificial Intelligence. 2026 (CCF-A)
[2] Towards comprehensive interactive change understanding in remote sensing: A large-scale dataset and dual-granularity enhanced VLM[J]IEEE Transactions on Geoscience and Remote Sensing.2026. (中科院1区 CCF B）
[3] Exploiting Shared Adversarial Features for Dynamic Attacks in Large Vision-Language Models[J]IEEE Transactions on Information Forensics and Security. 2026. (中科院1区 CCF A）
[4] RPA: Recursive Perturbation-Based Universal Adversarial Attacks on Multimodal Generative Tasks[J]IEEE Transactions on Circuits and Systems for Video Technology.2026. (中科院1区 CCF B）
[5] Cross-modality-enhanced visual Scene Graph Generation[J]. Information Fusion, 2025: 103430.（中科院1区 TOP期刊，IF：18.6）
[6] Reliable Multimodal Semantic Communication for Audio-Visual Event Localization[J]IEEE Communications Letters.2025.(中科院3区）
[7] Task-oriented Semantic Communication via Federated Learning[C]IEEE International Performance, Computing, and Communications Conference (IPCCC). 2025: 1-7.(CCF-C)
[8] ReSeg-UNet: A Reconstruction-Guided Optimization Framework for Enhanced Medical Image Segmentation[C]//International Conference on Medical Image Computing and Computer-Assisted Intervention. Cham: Springer Nature Switzerland, 2025: 544-554(CCF-B)
[9] Temporal multi-modal knowledge graph generation for link prediction[J]. Neural Networks, 2025, 185: 107108.（CCF-B 中科院2区 TOP期刊，IF：6.3）
[10] Open-Scene Understanding-oriented 3D Scene Graph Generation [C].IEEE International Conference on Multimedia & Expo 2025. (CCF-B)
[11] Knowledge graph confidence-aware embedding for recommendation[J]. Neural Networks, 2024, 180: 106601.（CCF-B 中科院2区 TOP期刊，IF：6.3）
[12] Multimodality-guided Visual-Caption Semantic Enhancement[J]. Computer Vision and Image Understanding, 2024, 249: 104139.（CCF-B 中科院3区，IF：3.5）
[13] Os-level pmc-based runtime thermal control for arm mobile cpus[J]. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2024, 43(7): 2023-2036.（CCF-A，TOP期刊 IF：3.5）
[14] Audio-Guided Visual Knowledge Representation[C]//International Conference on Database Systems for Advanced Applications. Singapore: Springer Nature Singapore, 2024: 129-146.（CCF-B)
[15] A huber loss minimization approach to byzantine robust federated learning[C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2024, 38(19): 21806-21814.（CCF-A)
[16] Cvlue: A new benchmark dataset for chinese vision-language understanding evaluation[C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2025, 39(8): 8196-8204.（CCF-A)
联系方式
通信地址：辽宁省锦州市古塔区士英街169号 williamhill中国
电子邮箱：dxyufei@lnut.edu.cn
邮政编码：121001
