avatar

Songlin Du

Associate Professor
Southeast University, Nanjing, China
sdu (at) seu (dot) edu (dot) cn


About

Songlin Du is an associate professor with the School of Automation, Southeast University (SEU). Before joining SEU, he received a doctorate of science from Lanzhou University, Lanzhou, China, and a doctorate of engineering from Waseda University, Tokyo, Japan. His research focuses on computer vision and its applications in robotics. He is a Senior Member of the IEEE. He feels profoundly lucky to work alongside many brilliant brains.

Research Interests

Teaching

Monograph

  1. Book cover
    Human Pose Analysis: Deep Learning Meets Human Kinematics in Video
    Songlin Du and Takeshi Ikenaga
    eBook ISBN: 978-981-97-9334-1
    Springer Nature, 2024.
    Springer Amazon BibTex

    Intro: This book stands at the intersection of computer vision, artificial intelligence, and human kinematics, offering a comprehensive exploration of the principles, methodologies, and applications of analysing human pose in video data.

Recent Papers

  1. IEEE TPAMI
    Towards Free-form Local Feature Matching
    Xiaoyong Lu, Songlin Du, Yaping Yan, Xiaobo Lu and Takeshi Ikenaga
    IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE TPAMI), 2025.
    Paper BibTex

  2. CVPR
    JamMa: Ultra-lightweight Local Feature Matching with Joint Mamba
    Xiaoyong Lu and Songlin Du
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025.
    Paper Code BibTex

  3. IEEE TIP
    MambaMatch: Establishing Reliable Correspondences via Multi-Scale State Space Model
    Xiangyang Miao, Shunxing Chen, Xinyu Liu, Shiping Wang, Songlin Du, Lianghua He and Guobao Xiao
    IEEE Transactions on Image Processing (IEEE TIP), 2025.
    Paper BibTex

  4. IEEE TCSVT
    Spatially-Aware Adaptive Diffusion: Unifying Low-Resolution Image Fusion and Super-Resolution
    Jiajia Fu, Zhenni Yu, Haosheng Chen, Songlin Du, Changcai Yang, Lianghua He and Guobao Xiao
    IEEE Transactions on Circuits and Systems for Video Technology (IEEE TCSVT), 2025.
    Paper BibTex

  5. IEEE TII
    A Unified fNIRS Classification Framework Informed by Local Brain Activation Patterns
    Zenghui Wang and Songlin Du
    IEEE Transactions on Industrial Informatics (IEEE TII), 2025.
    Paper Code BibTex

  6. IEEE TCSVT
    Tex2Sem: Learning from Textures to Semantics for Robust Semantic Correspondence
    Zenghui Wang, Songlin Du, Yaping Yan, Guobao Xiao and Xiaobo Lu
    IEEE Transactions on Circuits and Systems for Video Technology (IEEE TCSVT), 2025.
    Paper Code BibTex

  7. IEEE TASE
    Skeleton-Aware Representation of Spatio-Temporal Kinematics for 3D Human Motion Prediction
    Songlin Du, Zhihan Zhuang, Zenghui Wang, Yuan Li and Takeshi Ikenaga
    IEEE Transactions on Automation Science and Engineering (IEEE TASE), 2025.
    Paper BibTex

  8. IEEE TMM
    Topology Learning for Two-view Correspondence Filtering
    Ziwei Shi, Xiangyang Miao, Guobao Xiao, Songlin Du, Zheng Wang and Heng Tao Shen
    IEEE Transactions on Multimedia (IEEE TMM), 2025.
    Paper BibTex

  9. PR
    Robust Unsupervised Visual Tracking Via Image-to-Video Identity Knowledge Transferring
    Bin Kang, Zongyu Wang, Dong Liang, Tianyu Ding and Songlin Du
    Pattern Recognition (PR), 2025.
    Paper BibTex

  10. PR
    HSENet: Hierarchical Semantic-Enriched Network for Multi-Modal Image Fusion
    Xinyu Liu, Rui Ming, Songlin Du, Lianghua He, Haibo Luo and Guobao Xiao
    Pattern Recognition (PR), 2025.
    Paper Code BibTex

  11. ECCV
    Raising the Ceiling: Conflict-Free Local Feature Matching with Dynamic View Switching
    Xiaoyong Lu and Songlin Du
    European Conference on Computer Vision (ECCV), 2024.
    Paper Code BibTex

  12. ACCV
    Contrastive Max-Correlation for Multi-view Clustering
    Yanghao Deng, Zenghui Wang and Songlin Du
    Asian Conference on Computer Vision (ACCV), 2024.
    Paper BibTex Award Finalist & Oral Presentation

  13. PR
    AnatPose: Bidirectionally Learning Anatomy-Aware Heatmaps for Human Pose Estimation
    Songlin Du, Zhiwen Zhang and Takeshi Ikenaga
    Pattern Recognition (PR), 2024.
    Paper BibTex

  14. PR
    Fine-Grained Recognition via Submodular Optimization Regulated Progressive Training
    Bin Kang, Songlin Du, Dong Liang, Fan Wu and Xin Li
    Pattern Recognition (PR), 2024.
    Paper BibTex

  15. IEEE TIM
    Towards Better Generalization: Shape Feature-Enhanced Fastener Defect Detection with Diffusion Model
    Shixiang Su, Songlin Du, Dezhou Wang and Xiaobo Lu
    IEEE Transactions on Instrumentation and Measurement (IEEE TIM), 2024.
    Paper BibTex

  16. IEEE TCSVT
    ContextMatcher: Detector-Free Feature Matching with Cross-Modality Context
    Dongyue Li and Songlin Du
    IEEE Transactions on Circuits and Systems for Video Technology (IEEE TCSVT), 2024.
    Paper BibTex

  17. PR
    Kinematics-Aware Spatial-Temporal Feature Transform for 3D Human Pose Estimation
    Songlin Du, Zhiwei Yuan and Takeshi Ikenaga
    Pattern Recognition (PR), 2024.
    Paper BibTex

  18. PR
    JoyPose: Jointly Learning Evolutionary Data Augmentation and Anatomy-Aware Global-Local Representation for 3D Human Pose Estimation
    Songlin Du, Zhiwei Yuan, Peifu Lai and Takeshi Ikenaga
    Pattern Recognition (PR), 2024.
    Paper BibTex

  19. IEEE TASE
    Bi-Pose: Bidirectional 2D-3D Transformation for Human Pose Estimation from a Monocular Camera
    Songlin Du, Hao Wang, Zhiwei Yuan and Takeshi Ikenaga
    IEEE Transactions on Automation Science and Engineering (IEEE TASE), 2024.
    Paper BibTex

  20. ICCV
    Scene-Aware Feature Matching
    Xiaoyong Lu, Yaping Yan, Tong Wei and Songlin Du
    IEEE/CVF International Conference on Computer Vision (ICCV), 2023.
    Paper BibTex

  21. AAAI
    ParaFormer: Parallel Attention Transformer for Efficient Feature Matching
    Xiaoyong Lu, Yaping Yan, Bin Kang and Songlin Du
    AAAI Conference on Artificial Intelligence (AAAI), 2023.
    Paper BibTex Oral Presentation

  22. IEEE TII
    Straight-Line Detection Within 1 Millisecond Per Frame for Ultrahigh-Speed Industrial Automation
    Songlin Du, Ziwei Dong, Yuan Li and Takeshi Ikenaga
    IEEE Transactions on Industrial Informatics (IEEE TII), 2023.
    Paper BibTex

  23. IEEE TCSVT
    RFS-Net: Railway Track Fastener Segmentation Network with Shape Guidance
    Shixiang Su, Songlin Du, Xuan Wei and Xiaobo Lu
    IEEE Transactions on Circuits and Systems for Video Technology (IEEE TCSVT), 2023.
    Paper BibTex

  24. IEEE TITS
    Geometric Constraint and Image Inpainting Based Railway Track Fastener Sample Generation for Improving Defect Inspection
    Shixiang Su, Songlin Du and Xiaobo Lu
    IEEE Transactions on Intelligent Transportation Systems (IEEE TITS), 2022.
    Paper BibTex

  25. IEEE TIM
    Subpixel Displacement Measurement at 784 FPS: From Algorithm to Hardware System
    Songlin Du, Kaidong Gu and Takeshi Ikenaga
    IEEE Transactions on Instrumentation and Measurement (IEEE TIM), 2022.
    Paper BibTex

  26. IEEE TASE
    Automatic Foreground Detection at 784 FPS for Ultra-High-Speed Human-Machine Interactions
    Songlin Du, Peikun Cai, Tingting Hu and Takeshi Ikenaga
    IEEE Transactions on Automation Science and Engineering (IEEE TASE), 2022.
    Paper Demo BibTex

  27. IEEE TCSVT
    Highly-Parallel Hardwired Deep Convolutional Neural Network for 1-ms Dual-Hand Tracking
    Peiqi Zhang, Tingting Hu, Dingli Luo, Songlin Du and Takeshi Ikenaga
    IEEE Transactions on Circuits and Systems for Video Technology (IEEE TCSVT), 2022.
    Paper Demo BibTex


Powered by Jekyll and Minimal Light theme.