李军侠

招生信息： 今年拟招收硕士研究生5-7名，欢迎对计算机视觉、深度学习、模式识别等方向感兴趣的同学与我联系，可发送个人简历至邮箱：junxiali99@163.com 学习与工作经历： 工作经历 2021年7月-至今 南京信息工程大学 计算机与软件学院 副教授 2021年2月-2021年7月 南京信息工程大学 计算机与软件学院 讲师 2017年3月-2021年2月 南京信息工程大学 自动化学院 讲师 研究领域： 主要研究领域为：计算机视觉、深度学习、模式识别等。具体研究方向包括：图像/视频显著性检测、弱监督语义分割、3D人体姿态估计、单目图像深度估计等。 科研成果： 1.  Junxia Li, Ziyang Wang, Zefeng Pan, Qingshan Liu, and Dongyan Guo.  Looking at boundary: siamese densely cooperative fusion for salient object detection. IEEE Transactions on Neural Networks and Learning Systems, online, DOI: 10.1109/TNNLS.2021.3113657. 2.  Junxia Li, Zefeng Pan, Qingshan Liu, and Ziyang Wang. Stacked U-shape network with channel-wise attention for salient object detection. IEEE Transactions on Multimedia, 23: 1397-1409, 2021. 3.  Junxia Li, Zefeng Pan, Qingshan Liu, Ying Cui, and Yubao Sun. Complementarity-aware attention network for salient object detection. IEEE Transactions on Cybernetics, 52(2): 873-886, 2022. 4.  Luhui Yue, Junxia Li, Qingshan Liu. Body parts relevance learning via expectation-maximization for human pose estimation. Multimedia Systems, 27(5): 927-939, 2021. 5.  Zefeng Pan, Junxia Li*, and Ziyang Wang. Local bi-directional funnel network for salient object detection. Electronics Letters,  57(4): 187-189, 2021. 6. Quan Yuan, Junxia Li*, Lingwei Zhang, Zhefu Wu, and Guangyu Liu. Blind motion deblurring with cycle generative adversarial networks. The Visual Computer, 36, 1591-1601, 2020.  7.  Mingyuan Pan, Huihui Song*, Junxia Li, Kaihua Zhang, and Qingshan Liu. Top-down fusing multi-level contextual features for salient object detection. Pattern Recognition and Computer Vision (PRCV), 2020. 8.  Junxia Li, Lingzhang Dai, Yu Ding, and Qingshan Liu. Local context embedding neural network for scene semantic segmentation. Pattern Recognition and Computer Vision (PRCV), 2019. 9.  Junxia Li, Jian Yang, Chen Gong, Qingshan Liu, Saliency Fusion via Sparse and Double Low Rank Decomposition, Pattern Recognition Letters, 2018,107:114-122. 10.  Junxia Li, Deepu Rajan*, and Jian Yang. Locality and context-aware top-down saliency. IET Image Processing, 2018,12(3): 400-407. 11. Junxia Li, Lei Luo, Fanlong Zhang, Jian Yang* and Deepu Rajan. Double Low Rank Matrix Recovery for Saliency Fusion. IEEE Transactions on Image Processing, 25(9), 4421-4432, 2016.   12. Junxia Li, Jundi Ding, Jian Yang and Lingzheng Dai. Object Segmentation by Saliency-seeded and Spatial-weighted Region Merging. Applied Informatics, 3(1), 1-25, 2016. 13. Junxia Li, Deepu Rajan and Jian Yang. Local feature embedding for weakly supervised image classification. IEEE International Conference on Image Processing (ICIP), pp. 1300-1304, 2015. Oral Presentation (Top 10% paper award) 14. Junxia Li, Jundi Ding and Jian Yang. Visual Salience Learning via Low Rank Matrix Recovery. Asian Conference on Computer Vision (ACCV), pp. 112-117, 2014. 15.  Junxia Li, Runing Ma, Jundi Ding. Saliency-Seeded Region Merging: Automatic Object Segmentation. Asian Conference on Pattern Recognition (ACPR), pp. 691-695, 2011, Oral Presentation.   学生指导： 1. 指导本科生获得大学生创新创业训练计划项目国家级项目1项，省级项目1项。 2. 指导研究生获得“互联网”校级银奖1项。 3. 指导研究生获得2020年研究生实践创新项目1项。