I am a fourth-year PhD student in the Electrical and Computer Engineering Department, Northeastern University, advised by Prof. Yun Fu. My research interests lie in machine learning and computer vision. In particular, I recently focus on learning from limited labeled data, including zero/few-shot learning, domain adaptation, unsupervised representation learning, etc. I obtained my bachelor degree (2014) and master degree (2016) both in Wuhan University, where I worked on image matching and 3D reconstruction, under the supervision of Prof. Jian Yao.

• 2020.02: Two papers are accepted by CVPR 2020.
• 2019.08: One paper is accepted by CIKM 2019.
• 2019.07: Three papers are accepted by ICCV 2019.
• 2018.12: One paper is accepted by ICLR 2019.
• 2018.09: One paper is accepted by TNNLS.
• 2018.07: One paper is accepted by ACM MM 2018 as full long paper.
• 2018.07: One paper is accepted by ECCV 2018.
• 2017.11: Two papers are accepted by AAAI18.
• 2016.09: Begin my new study journey in Northeastern University at Boston.

Zero/Few-shot Learning & Domain Adaptation

• Kai Li, Yulun Zhang, Kunpeng Li, Yun Fu. Adversarial Feature Hallucination Networks for Few-Shot Learning. IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2020. [PDF][code]
• Kai Li, C. Wigington, C. Tensmeyer, H. Zhao, N. Barmpalios, V. Morariu, V. Manjunatha, T. Sun, Yun Fu. Cross-Domain Document Object Detection: Benchmark Suite and Method. IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2020. [PDF][code]
• Kai Li, Martin Renqiang Min, Bing Bai, Yun Fu, Hans Peter Graf. On Novel Object Recognition: A Unified Framework for Discriminability and Adaptability. ACM International Conference on Information and Knowledge Management (CIKM), 2019. [PDF][code]
• Kai Li, Martin Renqiang Min, Yun Fu. Rethinking Zero-Shot Learning: A Conditional Visual Classification Perspective. International Conference on Computer Vision (ICCV), 2019. [PDF][code]
• Kunpeng Li, Yulun Zhang, Kai Li, Yuanyuan Li, Yun Fu. Attention Bridging Network for Knowledge Transfer. International Conference on Computer Vision (ICCV), 2019. [PDF][code]

Multi-view Data Analysis

• Kunpeng Li, Yulun Zhang, Kai Li, Yuanyuan Li, Yun Fu. Visual Semantic Reasoning for Image-Text Matching. International Conference on Computer Vision (ICCV), 2019. [PDF][code]
• Kai Li, Zhengming Ding, Sheng Li, and Yun Fu. Towards Resolution-Invariant Person Re-identification via Projective Dictionary Learning.. IEEE Transactions on Neural Networks and Learning Systems (TNNLS), vol: , pages: , 2018. [PDF][code]
• Kai Li, Zhengming Ding, Kunpeng Li, Yulun Zhang, Yun Fu. Support Neighbor Loss for Person Re-Identification. ACM Multimedia (ACM MM), 2018. [PDF] [code]
• Kai Li, Zhengming Ding, Sheng Li, and Yun Fu. Discriminative Semi-coupled Projective Dictionary Learning for Low-Resolution Person Re-Identification. AAAI, 2018. [PDF][code]
• Kai Li, Sheng Li, Zhengming Ding, Weidong Zhang, and Yun Fu. Latent Discriminant Subspace Representations for Multi-view Outlier Detection. AAAI, 2018. [PDF][code]

Low-Level Vision

• Yulun Zhang, Kunpeng Li, Kai Li, Bineng Zhong, Yun Fu. Residual Non-local Attention Networks for Image Restoration. International Conference on Learning Representations (ICLR), 2019. [PDF][code]
• Yulun Zhang, Kunpeng Li, Kai Li, Lichen Wang, Bineng Zhong, Yun Fu. Image Super-Resolution Using Very Deep Residual Channel Attention Networks. European Conference on Computer Vision (ECCV), 2018. [PDF][code]
• Kai Li and Jian Yao. Line Segment Matching and Reconstruction via Exploiting Coplanar Cues.. ISPRS Journal of Photogrammetry and Remote Sensing (ISPRS), vol: 125, pages: 33-49, 2017. [PDF][Demo]
• Kai Li, Jian Yao, Xiaohu Lu, Li Li, and Zhichao Zhang. Hierarchical Line Matching Based on Line-Junction-Line Structure Descriptor and Local Homography Estimation.. Neurocomputing, vol: 186, pages: 207-220, 2016.[PDF][code]
• Kai Li, Jian Yao. 3D Line Segment Reconstruction in Structured Scenes via Coplanar Line Segment Clustering. ACCV Workshop on 3D modelling and applications (ACCV-W), 2016. [PDF][Demo]
• Kai Li, Jian Yao, Mengsheng Lu, Heng Yuan, Teng Wu, and YinXuan Li. Line Segment Matching: A Benchmark. IEEE Winter Conference of Applications of Computer Vision (WACV), 2016.[PDF][Project]
• Kai Li and Jian Yao. Joint Point and Line Segment Matching on Wide-Baseline Stereo Images. IEEE Winter Conference of Applications of Computer Vision (WACV), 2016. [PDF][Executable Binaries]
• Mi Zhang, Jian Yao, Menghan Xia, Kai Li, Yi Zhang, and Yaping Liu. Line-Based Multiple Label Energy Optimization for Fisheye Image Rectification and Calibration. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015. [PDF]
• Kai Li, Jian Yao, and Xiaohu Lu. Robust Line Matching Based on Ray-Point-Ray Structure Descriptor. Asian Conference on Computer Vision Workshop on Robust Local Descriptors for Computer Vision (ACCV-W), 2014. [PDF]

• Dean's Fellowship, College of Engineering, Northeastern University, 2016.
• Wang Zhizhou Scholarship, Wuhan University, 2015.
• Excellent Graduate Student, Wuhan University, 2015.
• Outstanding Undergraduate Thesis, Hubei Province, 2015.
• Best Undergraduate Thesis, School of Remote Sensing and Information Engineering, Wuhan University, 2014.

• Reviewer for TIP, TNNLS, TKDD, IET Image Processing, JEI, Neurocomputing
• Reviewer for CVPR, ECCV, ICCV, IJCAI, AAAI, WACV.
• IEEE student member, AAAI student member.