Our paper “CADQ: Attribute-Consistent Face Cartoonization with Cross-modal Aligned and Deformable Quantization” has been accepted to ACM Multimedia 2025! 🎉
Apr 2025
Our paper “Q-Norm: Robust Representation Learning via Quality-Adaptive Normalization” has been accepted to ICCV 2025! 🎉
@inproceedings{hu2026lotbonc,title={LotBoNC: Novel Botnet Traffic Classification under Long-tailed Distributions},author={Hu, Huancheng and Li, Ziyun and Doerr, Christian},booktitle={ACM Asia Conference on Computer and Communications Security (AsiaCCS)},year={2026},}
2025
EurIPS
EnfoPath: Energy-Informed Analysis of Generative Trajectories in Flow Matching
Ziyun Li, Ben Dai, Huancheng Hu, and 2 more authors
@inproceedings{li2025enfopath,title={EnfoPath: Energy-Informed Analysis of Generative Trajectories in Flow Matching},author={Li, Ziyun and Dai, Ben and Hu, Huancheng and Boström, Henrik and Lim, Soon Hoe},booktitle={EurIPS Workshop},year={2025},}
COPA
FlowGuard: Guarding Flow Matching via Conformal Sampling
Ziyun Li, and Henrik Boström
In Conformal and Probabilistic Prediction With Applications (COPA), 2025
@inproceedings{li2025flowguard,title={FlowGuard: Guarding Flow Matching via Conformal Sampling},author={Li, Ziyun and Boström, Henrik},booktitle={Conformal and Probabilistic Prediction With Applications (COPA)},year={2025},}
OJCOMS
BoNC: Discovering and Classifying Novel Encrypted Botnet Traffic
Huancheng Hu, Ziyun Li, and Christian Doerr
Open Journal of Communication Societies (OJCOMS), 2025
@article{hu2025bonc,title={BoNC: Discovering and Classifying Novel Encrypted Botnet Traffic},author={Hu, Huancheng and Li, Ziyun and Doerr, Christian},journal={Open Journal of Communication Societies (OJCOMS)},year={2025},}
ICCV
Q-Norm: Robust Representation Learning via Quality-Adaptive Normalization
Ying Zhou, Lanning Zhang, Fei Gao, Ziyun Li, Maoying Qiao, Jinlan Xu, and Nannan Wang
In International Conference on Computer Vision (ICCV), 2025
@inproceedings{zhou2025qnorm,title={Q-Norm: Robust Representation Learning via Quality-Adaptive Normalization},author={Zhou, Ying and Zhang, Lanning and Gao, Fei and Li, Ziyun and Qiao, Maoying and Xu, Jinlan and Wang, Nannan},booktitle={International Conference on Computer Vision (ICCV)},year={2025},url={https://openreview.net/pdf?id=n9hVZyT2po}}
ACMM
CADQ: Attribute-Consistent Face Cartoonization with Cross-modal Aligned and Deformable Quantization
Yongjie Hu, Yifan Jiang, Ziyun Li, and 3 more authors
In ACM International Conference on Multimedia, 2025
@inproceedings{hu2025adq,title={CADQ: Attribute-Consistent Face Cartoonization with Cross-modal Aligned and Deformable Quantization},author={Hu, Yongjie and Jiang, Yifan and Li, Ziyun and Gao, Fei and Boström, Henrik and Wang, Nannan},booktitle={ACM International Conference on Multimedia},year={2025},url={https://openreview.net/forum?id=ugVxtxXM9A}}
AAAI
QuARF: Quality-Adaptive Receptive Fields for Degraded Image Perception
@article{gao2025quarf,title={QuARF: Quality-Adaptive Receptive Fields for Degraded Image Perception},author={Gao, Fei and Zhou, Ying and Li, Ziyun and Han, Wenwang and Shi, Jiaqi and Qiao, Maoying and Xu, Jinlan and Wang, Nannan},journal={AAAI Conference on Artificial Intelligence},year={2025},}
TIP
S^3OIL: Semi-Supervised SAR-to-Optical Image Translation via Multi-Scale and Cross-Set Matching
Xi Yang, Haoyuan Shi, Ziyun Li, and 3 more authors
@article{yang2025s3oil,title={S$^3$OIL: Semi-Supervised SAR-to-Optical Image Translation via Multi-Scale and Cross-Set Matching},author={Yang, Xi and Shi, Haoyuan and Li, Ziyun and Qiao, Maoying and Gao, Fei and Wang, Nannan},journal={IEEE Transactions on Image Processing},year={2025},}
ICME
BI-RADS Boosted Breast Cancer Diagnosis With Masked Pretraining On Imbalanced Ultrasound Data
Xueqian Pang, Ziyun Li, Junhui Lv, and 3 more authors
In IEEE International Conference on Multimedia and Expo (ICME), 2025
@inproceedings{pang2025birads,title={BI-RADS Boosted Breast Cancer Diagnosis With Masked Pretraining On Imbalanced Ultrasound Data},author={Pang, Xueqian and Li, Ziyun and Lv, Junhui and Ge, Ruiquan and Wu, Zhuoxuan and Gao, Fei},booktitle={IEEE International Conference on Multimedia and Expo (ICME)},year={2025},}
arXiv
FlowTS: Time Series Generation via Rectified Flow
Yang Hu, Xiao Wang, Zezhen Ding, Lirong Wu, Huatian Zhang, Stan Z. Li, Sheng Wang, Jiheng Zhang, Ziyun Li, and Tianlong Chen
@article{hu2025flowts,title={FlowTS: Time Series Generation via Rectified Flow},author={Hu, Yang and Wang, Xiao and Ding, Zezhen and Wu, Lirong and Zhang, Huatian and Li, Stan Z. and Wang, Sheng and Zhang, Jiheng and Li, Ziyun and Chen, Tianlong},journal={arXiv preprint},year={2025},note={Co-corresponding author}}
2024
IJCNN
Otem-IGCD: An Optimal Transport-based EM Framework for Imbalanced Generalized Category Discovery
Ziyun Li, Ben Dai, Christoph Meinel, and 1 more author
In International Joint Conference on Neural Networks (IJCNN), 2024
@inproceedings{li2024otem,title={Otem-IGCD: An Optimal Transport-based EM Framework for Imbalanced Generalized Category Discovery},author={Li, Ziyun and Dai, Ben and Meinel, Christoph and Yang, Haojin},booktitle={International Joint Conference on Neural Networks (IJCNN)},year={2024},note={Oral}}
2023
TMLR
Supervised Knowledge May Hurt Novel Class Discovery Performance
Ziyun Li, Jona Otholt, Ben Dai, and 3 more authors
@article{li2023supervised,title={Supervised Knowledge May Hurt Novel Class Discovery Performance},author={Li, Ziyun and Otholt, Jona and Dai, Ben and Hu, Di and Meinel, Christoph and Yang, Haojin},journal={Transactions on Machine Learning Research},year={2023},note={CoLLAs Reward}}
ICCV
Generalized Categories Discovery for Long-tailed Recognition
Ziyun Li, Christoph Meinel, and Haojin Yang
In Workshop on Out-of-distribution Generalization in Computer Vision, ICCV, 2023
@inproceedings{li2023generalized,title={Generalized Categories Discovery for Long-tailed Recognition},author={Li, Ziyun and Meinel, Christoph and Yang, Haojin},booktitle={Workshop on Out-of-distribution Generalization in Computer Vision, ICCV},year={2023},}
IJCNN
SMKD: Selective Mutual Knowledge Distillation
Ziyun Li, Christoph Meinel, Haojin Yang, and 4 more authors
In International Joint Conference on Neural Networks (IJCNN), 2023
@inproceedings{li2023smkd,title={SMKD: Selective Mutual Knowledge Distillation},author={Li, Ziyun and Meinel, Christoph and Yang, Haojin and Wang, Xinshao and Robertson, Neil M. and Clifton, David A. and Hu, Di},booktitle={International Joint Conference on Neural Networks (IJCNN)},year={2023},note={Oral}}
@inproceedings{li2023imbagcd,title={ImbaGCD: Imbalanced Generalized Category Discovery},author={Li, Ziyun and Dai, Ben and Meinel, Christoph and Yang, Haojin},booktitle={CVPR Workshop},year={2023},note={Spotlight}}
2022
NeurIPS
A Closer Look at Novel Class Discovery from the Labeled Set
Ziyun Li, Jona Otholt, Ben Dai, and 3 more authors
@inproceedings{li2022closer,title={A Closer Look at Novel Class Discovery from the Labeled Set},author={Li, Ziyun and Otholt, Jona and Dai, Ben and Hu, Di and Meinel, Christoph and Yang, Haojin},booktitle={Workshop on Distribution Shifts, NeurIPS},year={2022},}
NeurIPS
Not All Knowledge Is Created Equal: Mutual Distillation of Confident Knowledge
Ziyun Li, Christoph Meinel, Haojin Yang, and 4 more authors
In Workshop on Trustworthy and Socially Responsible Machine Learning, NeurIPS, 2022
@inproceedings{li2022not,title={Not All Knowledge Is Created Equal: Mutual Distillation of Confident Knowledge},author={Li, Ziyun and Meinel, Christoph and Yang, Haojin and Wang, Xinshao and Robertson, Neil M. and Clifton, David A. and Hu, Di},booktitle={Workshop on Trustworthy and Socially Responsible Machine Learning, NeurIPS},year={2022},}
2019
Neurocomputing
Style-adaptive Photo Aesthetic Rating via Multi-task Learning
@article{gao2019style,title={Style-adaptive Photo Aesthetic Rating via Multi-task Learning},author={Gao, Fei and Li, Ziyun and Yu, Jun and Huang, Qingming and Tian, Qi},journal={Neurocomputing},year={2019},}
2017
ICME
Convolutional neural networks for intestinal hemorrhage detection in wireless capsule endoscopy images
Panpeng Li, Ziyun Li, Fei Gao, and 2 more authors
In IEEE International Conference on Multimedia and Expo (ICME), 2017
@inproceedings{li2017convolutional,title={Convolutional neural networks for intestinal hemorrhage detection in wireless capsule endoscopy images},author={Li, Panpeng and Li, Ziyun and Gao, Fei and Wan, Li and Yu, Jun},booktitle={IEEE International Conference on Multimedia and Expo (ICME)},year={2017},}