Publications

@inproceedings{wangemnlp2025,
  title = {FakeSV-VLM: Taming VLM for Detecting Fake Short-Video News via Progressive Mixture-Of-Experts Adapter},
  author = {Wang, Junxi and Wang†, Yaxiong and Cheng, Lechao and Zhong†, Zhun},
  booktitle = {EMNLP Findings},
  year = {2025}
}

@inproceedings{shen2025mm,
  title = {Beyond Artificial Misalignment: Detecting and Grounding Semantic-Coordinated Multimodal Manipulations},
  author = {Shen, Jinjie and Wang†, Yaxiong and Pu, Nan and Cheng, Lechao and Zhong†, Zhun},
  booktitle = {ACM MM},
  year = {2025}
}

@article{zhao2025secov2,
  title = {SeCoV2: Semantic Connectivity-driven Pseudo-Labeling for Robust Cross-Domain Semantic Segmentation},
  author = {Zhao, Dong and Zang, Qi and Pu, Nan and Wang, Shuang and Sebe, Nicu and Zhong†, Zhun},
  journal = {TPAMI},
  year = {2025}
}

@inproceedings{liu2025generate,
  author = {Liu, Xiao and Pu, Nan and Zheng, Haiyang and Li, Wenjing and Sebe, Nicu and Zhong†, Zhun},
  booktitle = {ICCV},
  year = {2025}
}

@inproceedings{zhao2025iccv,
  title = {Pseudo-SD: Pseudo Controlled Stable Diffusion for Semi-Supervised and Cross-Domain Semantic Segmentation},
  author = {Zhao, Dong and Zang, Qi and Wang, Shuang and Sebe, Nicu and Zhong, Zhun},
  booktitle = {ICCV},
  year = {2025}
}

@inproceedings{xingicml2025,
  title = {Knowledge Swapping via Learning and Unlearning},
  author = {Xing, Mingyu and Cheng†, Lechao and Tang, Shenggeng and Wang, Yaxiong and Zhong†, Zhun and Wang, Meng},
  booktitle = {ICML},
  year = {2025}
}

@inproceedings{zhangijcai2025,
  title = {Towards Micro-Action Recognition with Limited Annotations: An Asynchronous Pseudo Labeling and Training Approach},
  author = {Zhang, Yan and Cheng†, Lechao and Wang, Yaxiong and Zhong†, Zhun and Wang, Meng},
  booktitle = {IJCAI},
  year = {2025}
}

@inproceedings{wang2025sigir,
  title = {Beyond General Alignment: Fine-Grained Entity-Centric Image-Text Matching with Multimodal Attentive Experts},
  author = {Wang, Yaxiong and Wu, Lianwei and Cheng, Lechao and Zhong, Zhun and Wu, Yujiao and Wang, Meng},
  booktitle = {SIGIR},
  year = {2025}
}

@inproceedings{zhang2025cvpr,
  title = {ASAP: Advancing Semantic Alignment Promotes Multi-Modal Manipulation Detecting and Grounding},
  author = {Zhang, Zhenxing and Wang†, Yaxiong and Cheng, Lechao and Zhong, Zhun and Guo, Dan and Wang, Meng},
  booktitle = {CVPR},
  year = {2025}
}

@inproceedings{zang2025cvpr,
  title = {Feature Spectrum Learning for Remote Sensing Change Detection},
  author = {Zang, Qi and Zhao, Dong and Wang, Shuang and Quan, Dou and Jiao, Licheng and Zhong, Zhun},
  booktitle = {CVPR},
  year = {2025}
}

@inproceedings{zhao2025cvpr,
  title = {FisherTune: Fisher-Guided Robust Tuning of Vision Foundation Models for Domain Generalized Segmentation},
  author = {Zhao, Dong and Li, Jinlong and Wang, Shuang and Wu, Mengyao and Zang, Qi and Sebe, Nicu and Zhong, Zhun},
  booktitle = {CVPR},
  year = {2025}
}

@inproceedings{WANG2025AAAI,
  title = {Prior-Constrained Association Learning for Fine-Grained Generalized Category Discovery},
  author = {Wang, Menglin and Zhong†, Zhun and Gong, Xiaojin},
  booktitle = {AAAI},
  year = {2025}
}

@inproceedings{zang2024changediff,
  title = {ChangeDiff: A Multi-Temporal Change Detection Data Generator with Flexible Text Prompts via Diffusion Model},
  author = {Zang, Qi and Yang, Jiayi and Wang, Shuang and Zhao, Dong and Yi, Wenjun and Zhong, Zhun},
  booktitle = {AAAI},
  year = {2025},
}

@inproceedings{zhao2024nips,
  title = {Connectivity-Driven Pseudo-Labeling Makes Stronger Cross-Domain Segmenters},
  author = {Zhao, Dong and Zang, Qi and Wang, Shuang and Sebe, Nicu and Zhong†, Zhun},
  booktitle = {NeurIPS},
  year = {2024}
}

@inproceedings{zheng2024nips,
  title = {Prototypical Hash Encoding for On-the-Fly Fine-Grained Category Discovery},
  author = {Zheng, Haiyang and Pu, Nan and Li†, Wenjing and Sebe, Nicu and Zhong†, Zhun},
  booktitle = {NeurIPS},
  year = {2024}
}

@inproceedings{ma2024nips,
  title = {Happy: A Debiased Learning Framework for Continual Generalized Category Discovery},
  author = {Ma, Shijie and Zhu, Fei and Zhong, Zhun and Liu, Wenzhuo and Zhang, Xu-Yao and Liu, Cheng-Lin},
  booktitle = {NeurIPS},
  year = {2024}
}

@inproceedings{yang2024graphgcd,
  title = {Learning to Distinguish Samples for Generalized Category Discovery},
  author = {Yang, Fengxiang and Pu, Nan and Li, Wenjing and Luo†, Zhiming and Li, Shaozi and Sebe, Nicu and Zhong†, Zhun},
  booktitle = {European Conference on Computer Vision},
  year = {2024}
}

@inproceedings{zheng2024textgcd,
  title = {Textual Knowledge Matters: Cross-Modality Co-Teaching for Generalized Visual Class Discovery},
  author = {Zheng, Haiyang and Pu, Nan and Li†, Wenjing and Sebe, Nicu and Zhong†, Zhun},
  booktitle = {European Conference on Computer Vision},
  year = {2024},
}

@inproceedings{yang2024mamber,
  title = {ReMamber: Referring Image Segmentation with Mamba Twister},
  author = {Yang, Yuhuan and Ma, Chaofan and Yao, Jiangchao and Zhong, Zhun and Zhang, Ya and Wang, Yanfeng},
  booktitle = {European Conference on Computer Vision},
  year = {2024}
}

@inproceedings{zang2024mm,
  title = {Generalized Source-free Domain-adaptive Segmentation via Reliable Knowledge Propagation},
  author = {Zang, Qi and Wang, Shuang and Zhao, Dong and Hu, Yang and Quan, Dou and Li, Jinlong and Sebe, Nicu and Zhong, Zhun},
  booktitle = {Proceedings of the 32st ACM International Conference on Multimedia},
  year = {2024}
}

@inproceedings{cao2024icml,
  title = {Envisioning Outlier Exposure for Out-of-distribution Detection},
  author = {Cao, Chentao and Zhong†, Zhun and Zhou, Zhanke and Liu, Yang and Liu, Tongliang and Han, Bo},
  booktitle = {ICML},
  year = {2024}
}

@inproceedings{wangfei2024frequency,
  title = {Frequency Decoupling for Motion Magnification via Multi-Level Isomorphic Architecture},
  author = {Wang, Fei and Guo, Dan and Li, Kun and Zhong, Zhun and Wang, Meng},
  booktitle = {CVPR},
  year = {2024}
}

@inproceedings{zhao2024stable,
  title = {Stable Neighbor Denoising for Source-free Domain Adaptive Segmentation},
  author = {Zhao, Dong and Wang†, Shuang and Zang, Qi and Jiao, Licheng and Sebe, Nicu and Zhong†, Zhun},
  booktitle = {CVPR},
  year = {2024}
}

@inproceedings{pu2024federated,
  title = {Federated generalized category discovery},
  author = {Pu, Nan and Li†, Wenjing and Ji, Xinyuan and Qin, Yalan and Sebe, Nicu and Zhong†, Zhun},
  booktitle = {CVPR},
  year = {2024}
}

@inproceedings{ma2024active,
  title = {Active Generalized Category Discovery},
  author = {Ma, Shijie and Zhu, Fei and Zhong, Zhun and Zhang, Xu-Yao and Liu, Cheng-Lin},
  booktitle = {CVPR},
  year = {2024}
}

@inproceedings{yang2024diversity,
  title = {Diversity-Authenticity Co-constrained Stylization for Federated Domain Generalization in Person Re-identification},
  author = {Yang, Fengxiang and Zhong, Zhun and Luo, Zhiming and He, Yifan and Li, Shaozi and Sebe, Nicu},
  booktitle = {AAAI},
  volume = {38},
  number = {6},
  pages = {6477--6485},
  year = {2024}
}

@inproceedings{liu2024iclr,
  title = {Democratizing Fine-grained Visual Recognition with Large Language Models},
  author = {Liu, Mingxuan and Roy, Subhankar and Li, Wenjing and Zhong†, Zhun and Sebe, Nicu and Ricci, Elisa},
  booktitle = {ICLR},
  year = {2024}
}

@inproceedings{wang2023nips,
  title = {Discover and Align Taxonomic Context Priors for Open-world Semi-Supervised Learning},
  author = {Wang, Yu and Zhong, Zhun and Qiao, Pengchong and Cheng, Xuxin and Zheng, Xiawu and Liu, Chang and Sebe, Nicu and Ji, Rongrong and Chen, Jie},
  booktitle = {NeurIPS},
  year = {2023}
}

@article{zhao2024ijcv,
  title = {Style-Hallucinated Dual Consistency Learning: A Unified Framework for Visual Domain Generalization},
  author = {Zhao, Yuyang and Zhong, Zhun and Zhao, Na and Sebe, Nicu and Lee, Gim Hee},
  journal = {International Journal of Computer Vision},
  year = {2023},
}

@article{nan2023lifelongreid,
  title = {A Memorizing and Generalizing Framework for Lifelong Person Re-Identification},
  author = {Pu, Nan and Zhong†, Zhun and Sebe, Nicu and Lew, Michael},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2023},
  publisher = {IEEE}
}

@inproceedings{lu2023multi,
  title = {Multi-View Domain Adaptive Object Detection on Camera Networks},
  author = {Lu, Yan and Zhong, Zhun and Shu, Yuanchao},
  booktitle = {AAAI},
  year = {2023}
}

@inproceedings{ling2022cross,
  title = {Cross-Modality Earth Mover's Distance for Visible Thermal Person Re-Identification},
  author = {Ling, Yongguo and Zhong, Zhun and Cao, Donglin and Luo, Zhiming and Lin, Yaojin and Li, Shaozi and Sebe, Nicu},
  booktitle = {AAAI},
  year = {2023}
}

@inproceedings{weng2023,
  title = {Exploring Non-Target Knowledge for Improving Ensemble Universal Adversarial Attacks},
  author = {Weng, Juanjuan and Luo, Zhiming and Zhong, Zhun and Lin, Dazhen and Li, Shaozi},
  booktitle = {AAAI},
  year = {2023}
}

@inproceedings{wu2023sparsely,
  title = {Sparsely Annotated Semantic Segmentation With Adaptive Gaussian Mixtures},
  author = {Wu, Linshan and Zhong, Zhun and Fang, Leyuan and He, Xingxin and Liu, Qiang and Ma, Jiayi and Chen, Hao},
  booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023}
}

@inproceedings{wang2023dynamically,
  title = {Dynamically Instance-Guided Adaptation: A Backward-Free Approach for Test-Time Domain Adaptive Semantic Segmentation},
  author = {Wang, Wei and Zhong, Zhun and Wang, Weijie and Chen, Xi and Ling, Charles and Wang, Boyu and Sebe, Nicu},
  booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023}
}

@inproceedings{pu2023dynamic,
  title = {Dynamic Conceptional Contrastive Learning for Generalized Category Discovery},
  author = {Pu, Nan and Zhong†, Zhun and Sebe, Nicu},
  booktitle = {Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2023}
}

@article{wang2023100,
  title = {100-Driver: A Large-Scale, Diverse Dataset for Distracted Driver Classification},
  author = {Wang, Jing and Li, Wenjing and Li, Fang and Zhang, Jun and Wu, Zhongcheng and Zhong, Zhun and Sebe, Nicu},
  journal = {IEEE Transactions on Intelligent Transportation Systems},
  year = {2023},
  publisher = {IEEE}
}

@article{liu2023mitigating,
  title = {Mitigating robust overfitting via self-residual-calibration regularization},
  author = {Liu, Hong and Zhong†, Zhun and Sebe, Nicu and Satoh, Shin'ichi},
  journal = {Artificial Intelligence},
  pages = {103877},
  year = {2023},
  publisher = {Elsevier}
}

@article{wu2023querying,
  title = {Querying Labeled for Unlabeled: Cross-Image Semantic Consistency Guided Semi-Supervised Semantic Segmentation},
  author = {Wu, Linshan and Fang, Leyuan and He, Xingxin and He, Min and Ma, Jiayi and Zhong, Zhun},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2023},
  publisher = {IEEE}
}

@inproceedings{zhong2022advstyle,
  title = {Adversarial Style Augmentation for Domain Generalized Urban-Scene Segmentation},
  author = {Zhong*†, Zhun and Zhao*, Yuyang and Lee, Gim Hee and Sebe, Nicu},
  booktitle = {NeurIPS},
  year = {2022}
}

@inproceedings{zhao2022shdc,
  title = {Style-Hallucinated Dual Consistency Learning for Domain Generalized Semantic Segmentation},
  author = {Zhao, Yuyang and Zhong, Zhun and Zhao, Na and Sebe, Nicu and Lee, Gim Hee},
  booktitle = {ECCV},
  year = {2022}
}

@inproceedings{zhang20213d,
  title = {3D-Aware Semantic-Guided Generative Model for Human Synthesis},
  author = {Zhang, Jichao and Sangineto, Enver and Tang, Hao and Siarohin, Aliaksandr and Zhong, Zhun and Sebe, Nicu and Wang, Wei},
  booktitle = {ECCV},
  year = {2022}
}

@article{zhao2021source,
  title = {Source-Free Open Compound Domain Adaptation in Semantic Segmentation},
  author = {Zhao*, Yuyang and Zhong*†, Zhun and Luo, Zhiming and Lee, Gim Hee and Sebe, Nicu},
  journal = {IEEE Transactions on Circuits and Systems for Video Technology},
  year = {2022}
}

@article{lin2022,
  title = {Joint Representation Learning and Keypoint Detection for Cross-view Geo-localization},
  author = {Lin, Jinliang and Zheng, Zhedong and Zhong, Zhun and Luo, Zhiming and Li, Shaozi and Yang, Yi and Sebe, Nicu},
  journal = {IEEE Transactions on Image Processing (TIP)},
  year = {2022}
}

@inproceedings{zhao2022ncdss,
  title = {Novel Class Discovery in Semantic Segmentation},
  author = {Zhao, Yuyang and Zhong, Zhun and Sebe, Nicu and Lee, Gim Hee},
  booktitle = {Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022}
}

@inproceedings{incd2022,
  title = {Class-incremental Novel Class Discovery},
  author = {Roy, Subhankar and Liu, Mingxuan and Zhong, Zhun and Sebe, Nicu and Ricci, Elisa},
  booktitle = {ECCV},
  year = {2022}
}

@article{metaAD,
  author = {Yang, Fengxiang and Weng, Juanjuan and Zhong, Zhun and Liu, Hong and Wang, Zheng and Luo, Zhiming and Cao, Donglin and Li, Shaozi and Satoh, Shin'ichi and Sebe, Nicu},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  title = {Towards Robust Person Re-Identification by Defending Against Universal Attackers},
  year = {2022},
  pages = {1-17},
  doi = {10.1109/TPAMI.2022.3199013}
}

@inproceedings{Fini_2021_ICCV,
  author = {Fini, Enrico and Sangineto, Enver and Lathuilière, Stéphane and Zhong†, Zhun and Nabi, Moin and Ricci, Elisa},
  title = {A Unified Objective for Novel Class Discovery},
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), Oral},
  year = {2021}
}

@inproceedings{Zhong_2021_CVPR,
  author = {Zhong*, Zhun and Fini*, Enrico and Roy, Subhankar and Luo, Zhiming and Ricci, Elisa and Sebe, Nicu},
  title = {Neighborhood Contrastive Learning for Novel Class Discovery},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021},
  pages = {10867-10875}
}

@inproceedings{zhong2021openmix,
  title = {OpenMix: Reviving Known Knowledge for Discovering Novel Visual Categories in An Open World},
  author = {Zhong, Zhun and Zhu, Linchao and Luo, Zhiming and Li, Shaozi and Yang, Yi and Sebe, Nicu},
  booktitle = {Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021}
}

@inproceedings{Yang2021MetaCam,
  title = {Joint Noise-Tolerant Learning and Meta Camera Shift Adaptation for Unsupervised Person Re-Identification},
  author = {Yang*, Fengxiang and Zhong*, Zhun and Luo, Zhiming and Yuanzheng, Cai and Li, Shaozi and Sebe, Nicu},
  booktitle = {Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021}
}

@inproceedings{Zhao2021M3L,
  title = {Learning to Generalize Unseen Domains via Memory-based Multi-Source Meta-Learning for Person Re-Identification},
  author = {Zhao*, Yuyang and Zhong*, Zhun and Yang, Fengxiang and Luo, Zhiming and Li, Shaozi and Sebe, Nicu},
  booktitle = {Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021}
}

@inproceedings{Roy2021CGCT,
  title = {Curriculum Graph Co-Teaching for Multi-Target Domain Adaptation},
  author = {Roy, Subhankar and Krivosheev, Evgeny and Zhong†, Zhun and Ricci, Elisa and Sebe, Nicu},
  booktitle = {Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2021}
}

@inproceedings{Yang2021MetaAttack,
  title = {Learning to Attack Real-World Models for Person Re-identification via Virtual-Guided MetaLearning},
  author = {Yang, Fengxiang and Zhong, Zhun and Liu, Hong and Wang, Zheng and Luo, Zhiming and Li, Shaozi and Sebe, Nicu and Satoh, Shin’ichi},
  booktitle = {AAAI},
  year = {2021}
}

@article{zhong2020memory,
  title = {Learning to Adapt Invariance in Memory for Person Re-identification},
  author = {Zhong, Zhun and Zheng, Liang and Luo, Zhiming and Li, Shaozi and Yang, Yi},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)},
  year = {2021},
  volume = {43},
  number = {8},
  pages = {2723-2738},
  doi = {10.1109/TPAMI.2020.2976933},
  issn = {1939-3539}
}

@inproceedings{zhong2020erasing,
  title = {Random Erasing Data Augmentation},
  author = {Zhong, Zhun and Zheng, Liang and Kang, Guoliang and Li, Shaozi and Yang, Yi},
  booktitle = {AAAI},
  year = {2020},
}

@inproceedings{zhong2019invariance,
  title = {Invariance Matters: Exemplar Memory for Domain Adaptive Person Re-identification},
  author = {Zhong, Zhun and Zheng, Liang and Luo, Zhiming and Li, Shaozi and Yang, Yi},
  booktitle = {Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019}
}

@article{zhong2019camstyle,
  title = {CamStyle: A Novel Data Augmentation Method for Person Re-identification},
  author = {Zhong, Zhun and Zheng, Liang and Zheng, Zhedong and Li, Shaozi and Yang, Yi},
  journal = {IEEE Transactions on Image Processing},
  volume = {28},
  number = {3},
  pages = {1176--1190},
  publisher = {IEEE},
  year = {2019}
}

@inproceedings{zhong2018generalizing,
  title = {Generalizing A Person Retrieval Model Hetero-and Homogeneously},
  author = {Zhong, Zhun and Zheng, Liang and Li, Shaozi and Yang, Yi},
  booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
  pages = {172--188},
  year = {2018}
}

@inproceedings{zhong2018camera,
  title = {Camera style adaptation for person re-identification},
  author = {Zhong, Zhun and Zheng, Liang and Zheng, Zhedong and Li, Shaozi and Yang, Yi},
  booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  pages = {5157--5166},
  year = {2018}
}

@inproceedings{zhong2017re,
  title = {Re-ranking person re-identification with k-reciprocal encoding},
  author = {Zhong, Zhun and Zheng, Liang and Cao, Donglin and Li, Shaozi},
  booktitle = {Computer Vision and Pattern Recognition (CVPR), 2017 IEEE Conference on},
  pages = {3652--3661},
  year = {2017},
  organization = {IEEE}
}

@article{zhong2017class,
  title = {Class-specific object proposals re-ranking for object detection in automatic driving},
  author = {Zhong, Zhun and Lei, Mingyi and Cao, Donglin and Fan, Jianping and Li, Shaozi},
  journal = {Neurocomputing},
  volume = {242},
  pages = {187--194},
  year = {2017},
  publisher = {Elsevier}
}

@article{zhong2017detecting,
  title = {Detecting ground control points via convolutional neural network for stereo matching},
  author = {Zhong, Zhun and Su, Songzhi and Cao, Donglin and Li, Shaozi and Lv, Zhihan},
  journal = {Multimedia Tools and Applications},
  volume = {76},
  number = {18},
  pages = {18473--18488},
  year = {2017},
  publisher = {Springer}
}

@article{zhong2015unsupervised,
  title = {Unsupervised domain adaption dictionary learning for visual recognition},
  author = {Zhong, Zhun and Li, Zongmin and Li, Runlin and Sun, Xiaoxia},
  journal = {ICIP-NoShow-PAKDD},
  year = {2015}
}