Kai Han

韩 锴

Assistant Professor

Visual AI Lab
Division of Statistics and Actuarial Science
School of Computing and Data Science
The University of Hong Kong

    Pokfulam Road, Hong Kong
    Room 220, Run Run Shaw Building
    kaihanx at hku.hk

@inproceedings{Roberts2024SciFIBench,
 author    = {Jonathan Roberts and Kai Han and Neil Houlsby and Samuel Albanie},
 title     = {SciFIBench: Benchmarking Large Multimodal Models for Scientific Figure Interpretation},
 booktitle = {Conference on Neural Information Processing Systems},
 year      = {2024},
}

@article{wang2024dissect,
    author    = {Wang, Hongjun and Vaze, Sagar and Han, Kai},
    title     = {Dissecting Out-of-Distribution Detection and Open-Set Recognition: A Critical Analysis of Methods and Benchmarks},
    journal   = {International Journal of Computer Vision (IJCV)},
    year      = {2024}
}

@inproceedings{lu2024regiondrag,
    author    = {Jingyi Lu and Xinghui Li and Kai Han},
    title     = {RegionDrag: Fast Region-Based Image Editing with Diffusion Models},
    booktitle = {European Conference on Computer Vision (ECCV)},
    year      = {2024},
}

 @inproceedings{cendra2024promptccd,
  author    = {Fernando Julio Cendra and Bingchen Zhao and Kai Han},
  title     = {PromptCCD: Learning Gaussian Mixture Prompt Pool for Continual Category Discovery},
  booktitle = {European Conference on Computer Vision},
  year      = {2024}
}

 @inproceedings{hao2024conceptexpress,
  author    = {Shaozhe Hao and Kai Han and Zhengyao Lv and Shihao Zhao and Kwan-Yee~K. Wong},
  title     = {Concept{E}xpress: Harnessing Diffusion Models for Single-image Unsupervised Concept Extraction},
  booktitle = {European Conference on Computer Vision},
  year      = {2024}
}

@inproceedings{yin2024ibdslam,
 author    = {Minghao Yin and Shangzhe Wu and Kai Han},
 title     = {IBD-SLAM: Learning Image-Based Depth Fusion for Generalizable SLAM},
 booktitle  = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
 year      = {2024},
}

@inproceedings{cao24dream,
 author    = {Yukang Cao and Yan-Pei Cao and Kai Han and Ying Shan and Kwan-Yee K. Wong},
 title     = {DreamAvatar: Text-and-Shape Guided 3D Human Avatar Generation via Diffusion Models},
 booktitle  = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
 year      = {2024},
}

@inproceedings{li2024sd4match,
 author    = {Xinghui Li and Jingyi Lu and Kai Han and Victor Prisacariu},
 title     = {SD4Match: Learning to Prompt Stable Diffusion Model for Semantic Matching},
 booktitle  = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
 year      = {2024},
}

@inproceedings{han23scd,
 author    = {Kai Han and Yandong Li and Sagar Vaze and Jie Li and Xuhui Jia},
 title     = {What's in a Name? Beyond Class Indices for Image Recognition},
 booktitle = {CVPR Workshop on Computer Vision in the Wild},
 year      = {2024},
}

@inproceedings{Roberts2024NewTerri,
 author    = {Roberts, Jonathan and L\"uddecke, Timo and Sheikh, Rehan and Han, Kai and Albanie, Samuel},
 title     = {Charting New Territories: Exploring the Geographic and Geospatial Capabilities of Multimodal LLMs},
 booktitle = {CVPR Workshop on EarthVision},
 year      = {2024},
}

@article{hao24cipr,
  title    = {CiPR: An Efficient Framework with Cross-instance Positive Relations for Generalized Category Discovery},
  author   = {Shaozhe Hao and Kai Han and Kwan-Yee K. Wong},
  journal  = {Transactions on Machine Learning Research},
  year     = {2024},
}

@inproceedings{wang2024sptnet,
 author    = {Hongjun Wang and Sagar Vaze and Kai Han},
 title     = {SPTNet: An Efficient Alternative Framework for Generalized Category Discovery with Spatial Prompt Tuning},
 booktitle  = {International Conference on Learning Representations (ICLR)},
 year      = {2024},
}

@inproceedings{huang2024froster,
 author    = {Xiaohu Huang and Hao Zhou and Kun Yao and Kai Han},
 title     = {FROSTER: Frozen CLIP is a Strong Teacher for Open-Vocabulary Action Recognition},
 booktitle  = {International Conference on Learning Representations (ICLR)},
 year      = {2024},
}

@inproceedings{han2023headsculpt,
 author    = {Xiao Han and Yukang Cao and Kai Han and Xiatian Zhu and Jiankang Deng and Yi-Zhe Song and Tao Xiang and Kwan-Yee K. Wong},
 title     = {HeadSculpt: Crafting 3D Head Avatars with Text},
 booktitle  = {Conference on Neural Information Processing Systems (NeurIPS)},
 year      = {2023},
}

@inproceedings{roberts2023GPT4GEO,
 author = {Roberts, Jonathan and L{\"u}ddecke, Timo and Das, Sowmen and Han, Kai and Albanie, Samuel},
 title     = {GPT4GEO: How a Language Model Sees the World's Geography},
 booktitle  = {NeurIPS Workshop on Foundation Models for Decision Making},
 year      = {2023},
}

@article{li23dualrc,
 author  = {Xinghui Li and Kai Han and Shuda Li and Victor Prisacariu},
 title   = {DualRC: A Dual-Resolution Learning Framework with Neighbourhood Consensus for Visual Correspondences},
 journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)},
 year    = {2023},
}

@inproceedings{zhao23learning,
 author    = {Bingchen Zhao and Xin Wen and Kai Han},
 title     = {Learning Semi-supervised Gaussian Mixture Models for Generalized Category Discovery},
 booktitle = {International Conference on Computer Vision (ICCV)},
 year      = {2023},
}

@inproceedings{han23open,
 author    = {Cong Han and Yujie Zhong and Dengjie Li and Kai Han and Lin Ma},
 title     = {Open-Vocabulary Semantic Segmentation with Decoupled One-Pass Network},
 booktitle = {International Conference on Computer Vision (ICCV)},
 year      = {2023},
}

@inproceedings{roberts2023satin,
  title    = {SATIN: A Multi-Task Metadataset for Classifying Satellite Imagery using Vision-Language Models},
  author   = {Jonathan Roberts and Kai Han and Samuel Albanie},
  booktitle  = {ICCV TNGCV Workshop},
  year     = {2023},
}

@inproceedings{hao2023ade,
 author    = {Shaozhe Hao and Kai Han and Kwan-Yee K. Wong},
 title     = {Learning Attention as Disentangler for Compositional Zero-shot Learning},
 booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
 year      = {2023},
}

@inproceedings{cao2023sesdf,
author    = {Yukang Cao and Kai Han and Kwan-Yee K. Wong},
title     = {SeSDF: Self-evolved Signed Distance Field for Implicit 3D Clothed Human Reconstruction},
booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
year      = {2023},
}

@inproceedings{joseph22ncdwf,
 author    = {K J Joseph and Sujoy Paul and Gaurav Aggarwal and Soma Biswas and Piyush Rai and Kai Han and Vineeth N Balasubramanian},
 title     = {Novel Class Discovery without Forgetting},
 booktitle = {European Conference on Computer Vision (ECCV)},
 year      = {2022},
}

@inproceedings{vaze22generalized,
 author    = {Sagar Vaze and Kai Han and Andrea Vedaldi and Andrew Zisserman},
 title     = {Generalized Category Discovery},
 booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
 year      = {2022},
}

@inproceedings{cao22jiff,
 author    = {Yukang Cao and Guanying Chen and Kai Han and Wenqi Yang and Kwan-Yee K. Wong},
 title     = {JIFF: Jointly-aligned Implicit Face Function for High Quality Single View Clothed Human Reconstruction},
 booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
 year      = {2022},
}

@inproceedings{zhu22sharpcontour,
 author    = {Chenming Zhu and Xuanye Zhang and Yanran Li and Liangdong Qiu and Kai Han and Xiaoguang Han},
 title     = {SharpContour: A Contour-based Boundary Refinement Approach for Efficient and Accurate Instance Segmentation},
 booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
 year      = {2022},
}

@inproceedings{joseph22spacing,
 author    = {K J Joseph and Sujoy Paul and Gaurav Aggarwal and Soma Biswas and Piyush Rai and Kai Han and Vineeth N Balasubramanian},
 title     = {Spacing Loss for Discovering Novel Categories},
 booktitle = {CVPR Workshop on Continual Learning in Computer Vision},
 year      = {2022},
}

@inproceedings{vaze22openset,
 author    = {Sagar Vaze and Kai Han and Andrea Vedaldi and Andrew Zisserman},
 title     = {Open-Set Recognition: A Good Closed-Set Classifier is All You Need?},
 booktitle = {International Conference on Learning Representations (ICLR)},
 year      = {2022},
}

@inproceedings{zhao21novel,
 author     = {Bingchen Zhao and Kai Han},
 title      = {Novel Visual Category Discovery with Dual Ranking Statistics and Mutual Knowledge Distillation},
 booktitle  = {Conference on Neural Information Processing Systems (NeurIPS)},
 year       = {2021}
}

@inproceedings{jia21joint,
 author    = {Xuhui Jia and Kai Han and Yukun Zhu and Bradley Green},
 title     = {Joint Representation Learning and Novel Category Discovery on Single- and Multi-modal Data},
 booktitle = {International Conference on Computer Vision (ICCV)},
 year      = {2021}
}

@inproceedings{tinchev20xresolution,
 author    = {Georgi Tinchev and Shuda Li and Kai Han and David Mitchell and Rigas Kouskouridas},
 title     = {{$\mathbb{X}$}Resolution Correspondence Networks},
 booktitle = {British Machine Vision Conference (BMVC)},
 year      = {2021}
}

@inproceedings{rebuffi21lsdc,
 author    = {Sylvestre-Alvise Rebuffi and Sebastien Ehrhardt and Kai Han and Andrea Vedaldi and Andrew Zisserman},
 title     = {LSD-C: Linearly Separable Deep Clusters},
 booktitle = {ICCV Workshop on Visual Inductive Priors for Data-Efficient Deep Learning},
 year      = {2021}
}

@inproceedings{wang21contrastive,
 author     = {Peng Wang and Kai Han and Xiu-Shen Wei and Lei Zhang and Lei Wang},
 title      = {Contrastive Learning based Hybrid Networks for Long-Tailed Image Classification},
 booktitle  = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
 year       = {2021},
}

@article{han21autonovel,
 author  = {Kai Han and Sylvestre-Alvise Rebuffi and Sebastien Ehrhardt and Andrea Vedaldi and Andrew Zisserman},
 title   = {AutoNovel: Automatically Discovering and Learning Novel Visual Categories},
 journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)},
 year    = {2021},
}

@article{li21anisotropic,
 author  = {Jie Li and Peng Wang and Kai Han and Yu Liu},
 title   = {Anisotropic Convolutional Neural Networks for RGB-D based Semantic Scene Completion},
 journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)},
 year    = {2021},
}

@article{han21fixed,
 title   = {Fixed Viewpoint Mirror Surface Reconstruction under an Uncalibrated Camera},
 author  = {Kai Han and Miaomiao Liu and Dirk Schnieders and Kwan-Yee K. Wong},
 journal = {IEEE Transactions on Image Processing (TIP)},
 year    = {2021}
}

@inproceedings{li20dualrc,
 author     = {Xinghui Li and Kai Han and Shuda Li and Victor Prisacariu},
 title      = {Dual-Resolution Correspondence Networks},
 booktitle  = {Conference on Neural Information Processing Systems (NeurIPS)},
 year       = {2020},
}

@inproceedings{han20automatically,
 author    = {Kai Han and Sylvestre-Alvise Rebuffi and Sebastien Ehrhardt and Andrea Vedaldi and Andrew Zisserman},
 title     = {Automatically Discovering and Learning New Visual Categories with Ranking Statistics},
 booktitle = {International Conference on Learning Representations (ICLR)},
 year      = {2020},
}

@inproceedings{li20correspondence,
 author    = {Shuda Li and Kai Han and Theo W. Costain and Henry Howard-Jenkins and Victor Prisacariu},
 title     = {Correspondence Networks with Adaptive Neighbourhood Consensus},
 booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
 year      = {2020},
}

@inproceedings{li20anisotropic,
 author    = {Jie Li and Kai Han and Peng Wang and Yu Liu and Xia Yuan},
 title     = {Anisotropic Convolutional Networks for 3D Semantic Scene Completion},
 booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
 year      = {2020},
}

@inproceedings{rebuffi20SSL,
 title={Semi-Supervised Learning with Scarce Annotations},
 author={Sylvestre-Alvise Rebuffi and Sebastien Ehrhardt and Kai Han and  Andrea Vedaldi and Andrew Zisserman},
 booktitle={CVPR Deep Vision Workshop},
 year={2020}
}

@article{chen20deepps,
 title   = {Deep Photometric Stereo for Non-Lambertian Surfaces},
 author  = {Guanying Chen and Kai Han and Boxin Shi and Yasuyuki Matsushita and Kwan-Yee K. Wong},
 journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)},
 year    = {2020}
}

@inproceedings{han19DTC,
 author    = {Kai Han and Andrea Vedaldi and Andrew Zisserman},
 title     = {Learning to Discover Novel Visual Categories via Deep Transfer Clustering},
 booktitle = {International Conference on Computer Vision (ICCV)},
 year      = {2019}
}

@inproceedings{vo19unsup,
 title     = {Unsupervised Image Matching and Object Discovery as Optimization},
 author    = {Huy V. Vo and Francis Bach and Minsu Cho and Kai Han and Yann LeCun and Patrick P\'{e}rez and Jean Ponce},
 booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
 year      = {2019}
}

@inproceedings{chen19SDPS_Net,
 title     = {Self-calibrating Deep Photometric Stereo Networks},
 author    = {Guanying Chen and Kai Han and Boxin Shi and Yasuyuki Matsushita and Kwan-Yee K. Wong},
 booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
 year      = {2019}
}

@article{chen19LTOM,
 title   = {Learning Transparent Object Matting},
 author  = {Guanying Chen and Kai Han and Kwan-Yee K. Wong},
 journal = {International Journal of Computer Vision (IJCV)},
 year    = {2019}
}

@inproceedings{chen18ps_fcn,
 title     = {PS-FCN: A Flexible Learning Framework for Photometric Stereo},
 author    = {Guanying Chen and Kai Han and Kwan-Yee K. Wong},
 booktitle = {European Conference on Computer Vision (ECCV)},
 year      = {2018}
}

@inproceedings{chen18tom_net,
 title     = {TOM-Net: Learning Transparent Object Matting from a Single Image},
 author    = {Guanying Chen and Kai Han and Kwan-Yee K. Wong},
 booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
 year      = {2018}
}

@article{han18dense,
 title   = {Dense Reconstruction of Transparent Objects by Altering Incident Light Paths through Refraction},
 author  = {Kai Han and Kwan-Yee K. Wong and Miaomiao Liu},
 journal = {International Journal of Computer Vision (IJCV)},
 year    = {2018}
}

@inproceedings{han17scnet,
 title     = {SCNet: Learning Semantic Correspondence},
 author    = {Kai Han and Rafael S. Rezende and Bumsub Ham and Kwan-Yee K. Wong and Minsu Cho and Cordelia Schmid and Jean Ponce},
 booktitle = {International Conference on Computer Vision (ICCV)},
 year      = {2017}
}

@inproceedings{han16single,
 author    = {Kai Han and Kwan-Yee K. Wong and Xiao Tan},
 title     = {Single View 3D Reconstruction under an Uncalibrated Camera and an Unknown Mirror Sphere},
 booktitle = {International Conference on 3D Vision (3DV)},
 year      = {2016}
}

@inproceedings{han16mirror,
 author    = {Kai Han and Kwan-Yee K. Wong and Dirk Schnieders and Miaomiao Liu},
 title     = {Mirror Surface Reconstruction under an Uncalibrated Camera},
 booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
 year      = {2016}
}

@inproceedings{han15afixed,
 author    = {Kai Han and Kwan-Yee K. Wong and Miaomiao Liu},
 title     = {A Fixed Viewpoint Approach for Dense Reconstruction of Transparent Objects},
 booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
 year      = {2015}
}

@inproceedings{wang2024hilo,
 author    = {Hongjun Wang and Sagar Vaze and Kai Han},
 title     = {HiLo: A Learning Framework for Generalized Category Discovery Robust to Domain Shifts},
 journal   = {arXiv preprint arXiv:2408.04591},
 year      = {2024},
}

@article{Roberts2024GRAB,
 author    = {Jonathan Roberts and Kai Han and Samuel Albanie},
 title     = {GRAB: A Challenging GRaph Analysis Benchmark for Large Multimodal Models},
 journal   = {arXiv preprint arXiv:2408.11817},
 year      = {2024},
}

@article{hao2023ViCo,
 author    = {Shaozhe Hao and Kai Han and Shihao Zhao and Kwan-Yee K. Wong},
 title     = {ViCo: Detail-Preserving Visual Condition for Personalized Text-to-Image Generation},
 journal   = {arXiv preprint arXiv:2306.00971},
 year      = {2023},
}

@article{li23SimSC,
  title    = {SimSC: A Simple Framework for Semantic Correspondence with Temperature Learning},
  author   = {Xinghui Li and Kai Han and Xingchen Wan and Victor Adrian Prisacariu},
  journal  = {arXiv preprint arXiv:2305.02385},
  year     = {2023},
}

@phdthesis{han18phd,
 author = {Kai Han},
 title  = {Single view reconstruction of transparent, mirror and diffuse surfaces},
 school = {Department of Computer Science, The University of Hong Kong},
 year   = {2018}
}