• 其他栏目

    金泰松

    • 电子邮箱:
    • 学历:博士研究生毕业
    • 联系方式:jintaisong@xmu.edu.cn
    • 学位:工学博士学位
    • 毕业院校:北京理工大学

    访问量:

    开通时间:..

    最后更新时间:..

    个人简介

    金泰松,厦门大学信息学院副教授、厦门大学挂职厦门二中副校长、中国计算机学会多媒体专委会执行委员,中国计算机学会计算机应用专委会执行委员。研究方向为计算机视觉、甲骨文信息处理,智慧海洋和人工智能赋能教育教学。承担国家自然科学基金面上项目、国家重点研发子课题、甲骨文智能破译与活化等10多个纵向和横向项目。近几年,以第一作者或通讯作者在TIP、TNNLS、TCY、PR等人工智能期刊和NeurIPS、CVPR、ICCV、AAAI 和IJCAI等学术会议上发表了20多篇学术论文。


    作为厦门大学甲骨文研究团队负责人,联合腾讯及安阳师范学院,发布全球首个甲骨文多模态数据集与甲骨文智能体“殷契行止”。研究成果获中国商业联合会科技进步一等奖、河南省科技进步二等奖,三等奖和福建省科技进步三等奖等多项科技奖励。


    【代表性论文】

     

    [NeurIPS 2025]DAMamba: Vision State Space Model with Dynamic Adaptive Scan. Conference on Neural Information Processing Systems 2025. 通讯作者

    [CVPR 2025] DVHGNN: Multi-Scale Dilated Vision HGNN for Efficient Vision Recognition.IEEE/CVF Conference on Computer Vision and Pattern Recognition 2025.  通讯作者

    [CVPR 2025]  VTON-HandFit: Virtual Try-on for Arbitrary Hand Pose Guided by Hand Priors Embedding. IEEE/CVF Conference on Computer Vision and Pattern Recognition 2025 共同通讯作者

    [AAAI 2025] Dynamic Clustering Convolutional Neural Network. AAAI Conference of Artificial Intelligence 2025: 18448-18456 通讯作者

    [AAAI 2025] K-hop Hypergraph Neural Network: A Comprehensive Aggregation Approach. AAAI Conference of Artificial Intelligence 2025: 21679-21687 通讯作者

    [TNNLS 2024 WalkGAN: Network Representation Learning With Sequence-Based Generative Adversarial Networks. IEEE Trans. Neural Networks Learn. Syst. 35(4): 5684-5694 (2024) 第一作者  

    [AAAI 2024] Hypergraph Neural Architecture Search.AAAI Conference of Artificial Intelligence 2024: 13837-13845 通讯作者

    [CVPR 2024] PortraitBooth: A Versatile Portrait Model for Fast Identity-preserved Personalization. IEEE/CVF Conference on Computer Vision and Pattern Recognition 2024 通讯作者

    [TCY 2023 Ridge-Regression-Induced Robust Graph Relational Network. IEEE Trans. Cybern. 53(9): 5631-5640 (2023)

    [AAAI 2023]  OMPQ: Orthogonal Mixed Precision Quantization. AAAI Conference of Artificial Intelligence 2023: 9029-9037  通讯作者

    [InForation Science 2020Link-aware semi-supervised hypergraph. Information Sciences, Volume 507, January 2020, Pages 339-355

    [InForation Science 2019] Robust ℓ2-Hypergraph and its applications. Information Sciences, 501: 708-723 (2019) 第一作者

    [TIP 2019] Correntropy-Induced robust low-rank hypergraph. IEEE Transactions On Image Processing. 28(6): 2755-2769, 2019. 第一作者

    [IJCAI 2019Hypergraph induced convolutional manifold networks. International Joint Conference on Artificial Intelligence, Macao, 2019. 第一作者

    [PR 2015 Low-rank matrix factorization with multiple hypergraph regularizer, Pattern Recognition, 48(3): 1011-1022, 2015. 第一作者

    [Neurocomputing] Multiple graph regularized sparse coding and multiple hypergraph regularized sparse coding for image representation, Neurocomputing, 154(4): 245~256, 2015.  第一作者