Publications

@article{huang2026agenthoi,
  title     = {AgentHOI: Multi-Agent Reasoning for Human-Object-Interaction Video Generation via Implicit Representation Alignment},
  author    = {Huang, Ziyao and Li, Shunkai and Cao, Juan and Li, Chenyu and Zhang, Youliang and Zhou, Zixiang and Wang, Cong and Zhou, Yuan and Lu, Qinglin and Tang, Fan},
  journal   = {arXiv preprint arXiv:2607.22241},
  year      = {2026}
}

@article{rao2026streamhoi,
  title     = {StreamHOI: Interaction-aware Temporal Memory Adaptation for Streaming HOI Video Generation},
  author    = {Rao, Zejing and Zhang, Haoxian and Liu, Xiaoqiang and Meng, Yiping and Zhang, Guoxin and Wan, Pengfei and Tang, Fan and Lee, Tong-Yee},
  journal   = {arXiv preprint arXiv:2607.20174},
  year      = {2026}
}

@article{rao2026no,
  title     = {No Corners Cut: State-Grounded Transitions for Mid-Stream Prompt Switches in Video Generation},
  author    = {Rao, Zejing and Ren, Ketong and Liu, Xiaoqiang and Meng, Yiping and Zhang, Guoxin and Tang, Fan},
  journal   = {arXiv preprint arXiv:2609.38691},
  year      = {2026}
}

@article{deng2026sissi,
    author = "Deng, Yingying and He, Xiangyu and Tang, Fan and Dong, Weiming and Yin, Xucheng",
    title = "Sissi: Zero-shot Style-guided Image Synthesis via Semantic-style Integration",
    journal = "arXiv preprint arXiv:2601.06605",
    year = "2026"
}

@article{deng2025inversion,
    author = "Deng, Yingying and He, Xiangyu and Tang, Fan and Dong, Weiming and Yin, Xucheng",
    title = "Inversion-Free Style Transfer with Dual Rectified Flows",
    journal = "arXiv preprint arXiv:2511.20986",
    year = "2025"
}

@unpublished{li_music_multimodal_accepted,
  title = {A Survey on Cross-Modal Interaction Between Music and Multimodal Data},
  author = {Sifei Li and Mining Tan and Feier Shen and Minyan Luo and Zijiao Yin and Fan Tang and Weiming Dong and Changsheng Xu},
  journal = {Computational Visual Media},
  eprint = {2504.12796},
  archivePrefix = {arXiv},
  note = {Accepted for publication in Computational Visual Media; not yet published},
  url = {https://arxiv.org/abs/2504.12796}
}

@article{xu2026headrouter,
    author = {Xu, Yu and Tang, Fan and Cao, Juan and Kong, Xiaoyu and Zhang, Yuxin and Li, Jintao and Deussen, Oliver and Lee, Tong-Yee},
    title = {HeadRouter: A training-free image editing framework for MM-DiTs by adaptively routing attention heads},
    journal = {ACM Transactions on Graphics},
    year = {2026},
    doi = {10.1145/3797956},
    volume = {45},
    number = {3},
    pages = {27:1-27:14},
    articleno = {27}
}

@article{xu2026anchorcrafter,
    author = {Xu, Ziyi and Huang, Ziyao and Cao, Juan and Zhang, Yong and Cun, Xiaodong and Shuai, Qing and Wang, Yuchen and Bao, Linchao and Tang, Fan},
    title = {AnchorCrafter: Animate cyber-anchors selling your products via human-object interacting video generation},
    journal = {IEEE Transactions on Visualization and Computer Graphics},
    year = {2026},
    publisher = {IEEE},
    doi = {10.1109/TVCG.2026.3662720},
    volume = {32},
    number = {7},
    pages = {5098-5112}
}

@article{mi2026interactive,
    author = {Mi, Xiaoyue and Tang, Fan and Cao, Juan and Sheng, Qiang and Huang, Ziyao and Li, Peng and Liu, Yang and Lee, Tong-Yee},
    title = {Interactive Visual Assessment for Text-to-Image Generation Models},
    journal = {IEEE Transactions on Visualization and Computer Graphics},
    year = {2026},
    publisher = {IEEE},
    doi = {10.1109/TVCG.2026.3658714},
    volume = {32},
    number = {4},
    pages = {2944-2961}
}

@article{huang2026make,
    author = "Huang, Ziyao and Tang, Fan and Cao, Juan and Zhang, Yong and Cun, Xiaodong and Bo, Yihang and Li, Jintao and Lee, Tong-Yee",
    title = "Make-Your-Anchor+: Temporal Consistent 2D Avatar Generation via Video Diffusion Prior",
    journal = "IEEE Transactions on Visualization and Computer Graphics",
    year = "2026",
    publisher = "IEEE"
}

@inproceedings{fang2026resca,
    author = "Fang, Haipeng and Li, Yu and Tang, Fan and Lu, Yixing and Cao, Juan and Tang, Sheng",
    title = "ResCa: Residual Caching for Diffusion Transformers Acceleration",
    booktitle = "Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Conference",
    year = "2026"
}

@inproceedings{xu2026tag,
    author = "Xu, Yu and Yan, Hongbin and Cao, Juan and Cheng, Yiji and Hang, Tiankai and He, Runze and Yin, Zijin and Zhang, Shiyi and Zhang, Yuxin and Li, Jintao and Wang, Chunyu and Lu, Qinglin and Lee, Tong-Yee and Tang, Fan",
    title = "TAG-MoE: Task-Aware Gating for Unified Generative Mixture-of-Experts",
    booktitle = "Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Conference",
    year = "2026"
}

@inproceedings{zhong2026graspall,
  title     = {GraspALL: Adaptive Structural Compensation from Illumination Variation for Robotic Garment Grasping in Any Low-Light Conditions},
  author    = {Zhong, Haifeng and Han, Wenshuo and Wang, Zhouyu and Feng, Runyang and Tang, Fan and Lee, Tong-Yee and Fan, Zipei and Wu, Ruihai and Wang, Yuran and Dong, Hao and Chen, Hechang and Chang, Hyung Jin and Gao, Yixing},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2026}
}

@inproceedings{xu2026beyond,
    author = "Xu, Yu and Zhang, Yuxin and Cao, Juan and Gao, Lin and Wang, Chunyu and Deussen, Oliver and Lee, Tong-Yee and Tang, Fan",
    title = "Beyond Pixels: Visual Metaphor Transfer via Schema-Driven Agentic Reasoning",
    booktitle = "SIGGRAPH Asia 2026 Conference Papers",
    year = "2026"
}

@inproceedings{xu2026breaking,
  title     = {Breaking the Uniformity Trap: Scaling Video Diffusion Model via SplitMoE},
  author    = {Xu, Yu and Zhang, Yuxin and Yang, Xiao and Yang, Haotian and Wang, Yizhi and Huang, Xinwei and Lin, Minxuan and Wang, Angtian and Ma, Chongyang and Tang, Fan},
  booktitle = {Advances in Neural Information Processing Systems},
  year      = {2026}
}

@inproceedings{pmlr-v306-zhu26q,
  title = {FlatLab: A Unified Methodology Framework and Simulation-Based Benchmark for Robotic Manipulation of Flat Objects},
  author = {Xingyu Zhu and Wenshuo Han and Zhouyu Wang and Yuran Wang and Ruihai Wu and Hao Dong and Fan Tang and Hechang Chen and Hyung Jin Chang and Yixing Gao},
  year = {2026},
  booktitle = {Proceedings of the 43rd International Conference on Machine Learning},
  volume = {306},
  pages = {167064--167086}
}

@inproceedings{ren2026imitating,
  title     = {Imitating the Truth: Attention-aware Truth-Guided Enhancement for Hallucination Mitigation in Large Vision-Language Models},
  author    = {Ren, Hairui and Wang, Zixuan and Yang, Yibo and Zhao, He and Tang, Fan and Guo, Dandan and Chang, Yi},
  booktitle = {International Conference on Learning Representations},
  year      = {2026}
}

@inproceedings{mi2026video,
    author = {Mi, Xiaoyue and Yu, Wenqing and Lian, Jiesong and Jie, Shibo and Zhong, Ruizhe and Liu, Zijun and Zhang, Guozhen and Zhou, Zixiang and Xu, Zhiyong and Zhou, Yuan and Lu, Qinglin and Tang, Fan},
    title = {Video Generation Models Are Good Latent Reward Models},
    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Conference（Findings Track）},
    year = {2026},
    doi = {10.1109/CVPRF71909.2026.00454},
    pages = {4719-4728}
}

@inproceedings{xu2026geohoi,
  title     = {GeoHOI: Geometry-Enhanced Human-Object Interaction Video Generation via Hierarchical Multi-Modal Injection},
  author    = {Xu, Ziyi and Rao, Zejing and Cao, Juan and Liu, Xiaoqiang and Fang, Zhixue and Zhang, Haoxian and Tang, Songlin and Tang, Fan},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (Findings Track)},
  year      = {2026}
}

@article{jiang2026parameter,
  title     = {Parameter Efficient Emotional Transfer for Fine-Grained Emotional Audio-Driven Talking Portrait Generation},
  author    = {Jiang, Yiguo and Cun, Xiaodong and Zhang, Yong and He, Tao and Tang, Fan and Pun, Chi-Man},
  journal   = {IEEE Transactions on Multimedia},
  year      = {2026}
}

@inproceedings{mi2026visual,
    author = "Mi, Xiaoyue and Tang, Fan and Wu, You and Cao, Juan and Li, Peng and Liu, Yang",
    title = "Visual-friendly concept protection via selective adversarial perturbations",
    booktitle = "Proceedings of the AAAI Conference on Artificial Intelligence",
    year = "2026"
}

@article{deng2026z,
  title     = {Z-STAR+: A Zero-shot Style Transfer Method via Adjusting Style Distribution},
  author    = {Deng, Yingying and He, Xiangyu and Tang, Fan and Dong, Weiming},
  journal   = {Computational Visual Media},
  year      = {2026}
}

@article{xu2025b4m,
    author = "Xu, Yu and Tang, Fan and Cao, Juan and Zhang, Yuxin and Deussen, Oliver and Dong, Weiming and Li, Jintao and Lee, Tong-Yee",
    title = "B4M: Breaking Low-Rank Adapter for Making Content-Style Customization",
    journal = "ACM Transactions on Graphics",
    volume = "44",
    number = "2",
    pages = "1--17",
    year = "2025",
    publisher = "ACM New York, NY"
}

@article{huang2025creativesynth,
    author = "Huang, Nisha and Dong, Weiming and Zhang, Yuxin and Tang, Fan and Li, Ronghui and Ma, Chongyang and Li, Xiu and Lee, Tong-Yee and Xu, Changsheng",
    title = "CreativeSynth: Cross-art-attention for artistic image synthesis with multimodal diffusion",
    journal = "IEEE Transactions on Visualization and Computer Graphics",
    year = "2025",
    publisher = "IEEE"
}

@article{zhang2025motioncrafter,
    author = "Zhang, Yuxin and Dong, Weiming and Tang, Fan and Huang, Nisha and Huang, Haibin and Ma, Chongyang and Wan, Pengfei and Lee, Tong-Yee and Xu, Changsheng",
    title = "MotionCrafter: Plug-and-Play Motion Guidance for Diffusion Models",
    journal = "IEEE Transactions on Visualization and Computer Graphics",
    year = "2025",
    publisher = "IEEE"
}

@inproceedings{fang2025attend,
    author = "Fang, Haipeng and Tang, Sheng and Cao, Juan and Zhang, Enshuo and Tang, Fan and Lee, Tong-Yee",
    title = "Attend to Not Attended: Structure-then-Detail Token Merging for Post-training DiT Acceleration",
    booktitle = "Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Conference",
    pages = "18083--18092",
    year = "2025"
}

@inproceedings{ren2025beyond,
    author = "Ren, Hairui and Tang, Fan and Zhao, He and Wang, Zixuan and Guo, Dandan and Chang, Yi",
    title = "Beyond Words: Augmenting Discriminative Richness via Diffusions in Unsupervised Prompt Learning",
    booktitle = "Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Conference",
    pages = "25135--25144",
    year = "2025"
}

@inproceedings{deng2025z,
    author = "Deng, Yingying and He, Xiangyu and Tang, Fan and Dong, Weiming",
    title = "Z-Magic: Zero-shot Multiple Attributes Guided Image Creator",
    booktitle = "Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Conference",
    pages = "18390--18400",
    year = "2025"
}

@inproceedings{mi2025adversarial,
    author = "Mi, Xiaoyue and Tang, Fan and Yang, Zonghan and Wang, Danding and Cao, Juan and Li, Peng and Liu, Yang",
    title = "Adversarial robust memory-based continual learner",
    booktitle = "Proceedings of the IEEE/CVF International Conference on Computer Vision",
    pages = "562--572",
    year = "2025"
}

@inproceedings{zhong2025amdanet,
    author = "Zhong, Haifeng and Tang, Fan and Chen, Zhuo and Chang, Hyung Jin and Gao, Yixing",
    title = "AMDANet: Attention-Driven Multi-Perspective Discrepancy Alignment for RGB-Infrared Image Fusion and Segmentation",
    booktitle = "Proceedings of the IEEE/CVF International Conference on Computer Vision",
    pages = "10645--10655",
    year = "2025"
}

@inproceedings{zhou2025multi,
    author = "Zhou, Zijun and Deng, Yingying and He, Xiangyu and Dong, Weiming and Tang, Fan",
    title = "Multi-turn Consistent Image Editing",
    booktitle = "Proceedings of the IEEE/CVF International Conference on Computer Vision",
    pages = "15792--15801",
    year = "2025"
}

@inproceedings{huang2025homa,
    author = "Huang, Ziyao and Zhou, Zixiang and Cao, Juan and Ma, Yifeng and Chen, Yi and Rao, Zejing and Xu, Zhiyong and Wang, Hongmei and Lin, Qin and Zhou, Yuan and Lu, Qinglin and Tang, Fan",
    title = "HOMA: Towards Generic Human-Object Interaction in Multimodal Driven Human Animation with Weak Conditions",
    booktitle = "Proceedings of the SIGGRAPH Asia 2025 Conference Papers",
    pages = "1--12",
    year = "2025"
}

@inproceedings{xu2025context,
    author = "Xu, Yu and Tang, Fan and Wu, You and Gao, Lin and Deussen, Oliver and Yan, Hongbin and Li, Jintao and Cao, Juan and Lee, Tong-Yee",
    title = "In-Context Brush: Zero-shot Customized Subject Insertion with Context-Aware Latent Space Manipulation",
    booktitle = "Proceedings of the SIGGRAPH Asia 2025 Conference Papers",
    pages = "1--12",
    year = "2025"
}

@inproceedings{deng2025fireflow,
    author = "Deng, Yingying and He, Xiangyu and Mei, Changwang and Wang, Peisong Wang and Tang, Fan",
    title = "FireFlow: Fast Inversion of Rectified Flow for Image Semantic Editing",
    booktitle = "Forty-second International Conference on Machine Learning",
    year = "2025"
}

@article{fang2025moanimate,
  title     = {MoAnimate: Bridging the Motion-Oriented Latent Representation Gaps in Human Video Animation},
  author    = {Fang, Haipeng and Tang, Sheng and Sun, Zhihao and Huang, Ziyao and Cao, Juan and Tang, Fan and Zhang, Yongdong},
  journal   = {IEEE Transactions on Circuits and Systems for Video Technology},
  year      = {2025}
}

@article{huang2024identity,
    author = "Huang, Ziyao and Tang, Fan and Zhang, Yong and Cao, Juan and Li, Chengyu and Tang, Sheng and Li, Jintao and Lee, Tong-Yee",
    title = "Identity-preserving face swapping via dual surrogate generative models",
    journal = "ACM Transactions on Graphics",
    volume = "43",
    number = "5",
    pages = "1--19",
    year = "2024",
    publisher = "ACM New York, NY, USA"
}

@article{zhou2024comprehensive,
    author = "Zhou, Zijun and Tang, Fan and Zhang, Yuxin and Deussen, Oliver and Cao, Juan and Dong, Weiming and Li, Xiangtao and Lee, Tong-Yee",
    title = "A comprehensive evaluation of arbitrary image style transfer methods",
    journal = "IEEE Transactions on Visualization and Computer Graphics",
    volume = "31",
    number = "9",
    pages = "5668--5686",
    year = "2024",
    publisher = "IEEE"
}

@inproceedings{wu2024u,
    author = "Wu, You and Liu, Kean and Mi, Xiaoyue and Tang, Fan and Cao, Juan and Li, Jintao",
    title = "U-VAP: User-specified visual appearance personalization via decoupled self augmentation",
    booktitle = "Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Conference",
    pages = "9482--9491",
    year = "2024"
}

@inproceedings{deng2024z,
    author = "Deng, Yingying and He, Xiangyu and Tang, Fan and Dong, Weiming",
    title = "Z*: Zero-shot style transfer via attention reweighting",
    booktitle = "Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Conference",
    pages = "6934--6944",
    year = "2024"
}

@inproceedings{huang2024make,
    author = "Huang, Ziyao and Tang, Fan and Zhang, Yong and Cun, Xiaodong and Cao, Juan and Li, Jintao and Lee, Tong-Yee",
    title = "Make-Your-Anchor: A diffusion-based 2D avatar generation framework",
    booktitle = "Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Conference",
    pages = "6997--7006",
    year = "2024"
}

@inproceedings{li2024dance,
    author = "Li, Sifei and Dong, Weiming and Zhang, Yuxin and Tang, Fan and Ma, Chongyang and Deussen, Oliver and Lee, Tong-Yee and Xu, Changsheng",
    title = "Dance-to-music generation with encoder-based textual inversion",
    booktitle = "SIGGRAPH Asia 2024 Conference Papers",
    pages = "1--11",
    year = "2024"
}

@inproceedings{jia2024revealing,
    author = "Jia, Yunbing and Kong, Xiaoyu and Tang, Fan and Gao, Yixing and Dong, Weiming and Yang, Yi",
    title = "Revealing the Two Sides of Data Augmentation: An Asymmetric Distillation-based Win-Win Solution for Open-Set Recognition",
    booktitle = "Thirty-Third International Joint Conference on Artificial Intelligence",
    year = "2024"
}

@article{ren2024modality,
    author = "Ren, Hairui and Tang, Fan and Zheng, Huangjie and Zhao, He and Guo, Dandan and Chang, Yi",
    title = "Modality-consistent prompt tuning with optimal transport",
    journal = "IEEE Transactions on Circuits and Systems for Video Technology",
    year = "2024",
    publisher = "IEEE"
}

@article{huang2024diffstyler,
    author = {Huang, Nisha and Zhang, Yuxin and Tang, Fan and Ma, Chongyang and Huang, Haibin and Dong, Weiming and Xu, Changsheng},
    title = {DiffStyler: Controllable dual diffusion for text-driven image stylization},
    journal = {IEEE Transactions on Neural Networks and Learning Systems},
    year = {2025},
    publisher = {IEEE},
    doi = {10.1109/TNNLS.2023.3342645},
    volume = {36},
    number = {2},
    pages = {3370-3383}
}

@inproceedings{li2024music,
    author = "Li, Sifei and Zhang, Yuxin and Tang, Fan and Ma, Chongyang and Dong, Weiming and Xu, Changsheng",
    title = "Music style transfer with time-varying inversion of diffusion models",
    booktitle = "Proceedings of the AAAI Conference on Artificial Intelligence",
    volume = "38",
    number = "1",
    pages = "547--555",
    year = "2024"
}

@inproceedings{wu2024lighting,
    author = "Wu, Kexin and Tang, Fan and Liu, Ning and Deussen, Oliver and Dong, Weiming and Lee, Tong-Yee",
    title = "Lighting Image/Video Style Transfer Methods by Iterative Channel Pruning",
    booktitle = "IEEE International Conference on Acoustics, Speech and Signal Processing",
    pages = "3800--3804",
    year = "2024",
    organization = "IEEE"
}

@article{dong2024rowcolumn,
  title = {Row-Column Separated Attention Based Low-Light Image/Video Enhancement},
  author = {Chengqi Dong and Zhiyuan Cao and Tuoshi Qi and Kexin Wu and Yixing Gao and Fan Tang},
  year = {2024},
  journal = {Computer Graphics Forum},
  volume = {43},
  number = {6},
  pages = {e15192},
  doi = {10.1111/cgf.15192}
}

@inproceedings{Mi_2024_BMVC,
  title = {Topology-preserving Adversarial Training for Alleviating Natural Accuracy Degradation},
  author = {Xiaoyue Mi and Fan Tang and Yepeng Weng and Danding Wang and Juan Cao and Sheng Tang and Peng Li and Yang Liu},
  year = {2024},
  booktitle = {35th British Machine Vision Conference 2024}
}

@article{zhang2023unified,
    author = "Zhang, Yuxin and Tang, Fan and Dong, Weiming and Huang, Haibin and Ma, Chongyang and Lee, Tong-Yee and Xu, Changsheng",
    title = "A unified arbitrary style transfer framework via adaptive contrastive learning",
    journal = "ACM Transactions on Graphics",
    volume = "42",
    number = "5",
    pages = "1--16",
    year = "2023",
    publisher = "ACM New York, NY"
}

@article{zhang2023prospect,
    author = "Zhang, Yuxin and Dong, Weiming and Tang, Fan and Huang, Nisha and Huang, Haibin and Ma, Chongyang and Lee, Tong-Yee and Deussen, Oliver and Xu, Changsheng",
    title = "ProSpect: Prompt spectrum for attribute-aware personalization of diffusion models",
    journal = "ACM Transactions on Graphics",
    volume = "42",
    number = "6",
    pages = "1--14",
    year = "2023",
    publisher = "ACM New York, NY, USA"
}

@article{chen2023spa,
    author = "Chen, Dong and Pan, Xingjia and Tang, Fan and Dong, Weiming and Xu, Changsheng",
    title = "SPA2Net: Structure-preserved attention activated network for weakly supervised object localization",
    journal = "IEEE Transactions on Image Processing",
    volume = "32",
    pages = "5779--5793",
    year = "2023",
    publisher = "IEEE"
}

@inproceedings{huang2023adaptive,
    author = "Huang, Dihe and Chen, Ying and Liu, Yong and Liu, Jianlin and Xu, Shang and Wu, Wenlong and Ding, Yikang and Tang, Fan and Wang, Chengjie",
    title = "Adaptive assignment for geometry aware local feature matching",
    booktitle = "Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Conference",
    pages = "5425--5434",
    year = "2023"
}

@inproceedings{zhang2023inversion,
    author = "Zhang, Yuxin and Huang, Nisha and Tang, Fan and Huang, Haibin and Ma, Chongyang and Dong, Weiming and Xu, Changsheng",
    title = "Inversion-based style transfer with diffusion models",
    booktitle = "Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Conference",
    pages = "10146--10156",
    year = "2023"
}

@inproceedings{yang2023progressive,
    author = "Yang, Tianyun and Wang, Danding and Tang, Fan and Zhao, Xinying and Cao, Juan and Tang, Sheng",
    title = "Progressive open space expansion for open-set model attribution",
    booktitle = "Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Conference",
    pages = "15856--15865",
    year = "2023"
}

@article{ren20232,
    author = "Ren, Hairui and Tang, Fan and Pan, Xingjia and Cao, Juan and Dong, Weiming and Lin, Zhiwen and Yan, Ke and Xu, Changsheng",
    title = "A2Pt: Anti-Associative Prompt Tuning for Open Set Visual Recognition",
    journal = "IEEE Transactions on Multimedia",
    volume = "26",
    pages = "8419--8431",
    year = "2023",
    publisher = "IEEE"
}

@article{lin2023smnet,
    author = "Lin, Shideng and Tang, Fan and Dong, Weiming and Pan, Xingjia and Xu, Changsheng",
    title = "SMNet: Synchronous multi-scale low light enhancement network with local and global concern",
    journal = "IEEE Transactions on Multimedia",
    volume = "25",
    pages = "9506--9517",
    year = "2023",
    publisher = "IEEE"
}

@article{dong2023semantic,
    author = "Dong, Shuwei and Kong, Xiaoyu and Pan, Xingjia and Tang, Fan and Li, Wei and Chang, Yi and Dong, Weiming",
    title = "Semantic-context graph network for point-based 3D object detection",
    journal = "IEEE Transactions on Circuits and Systems for Video Technology",
    volume = "33",
    number = "11",
    pages = "6474--6486",
    year = "2023",
    publisher = "IEEE"
}

@article{kong2023exploring,
    author = "Kong, Xiaoyu and Deng, Yingying and Tang, Fan and Dong, Weiming and Ma, Chongyang and Chen, Yongyong and He, Zhenyu and Xu, Changsheng",
    title = "Exploring the temporal consistency of arbitrary style transfer: A channelwise perspective",
    journal = "IEEE Transactions on Neural Networks and Learning Systems",
    volume = "35",
    number = "6",
    pages = "8482--8496",
    year = "2023",
    publisher = "IEEE"
}

@article{wang2023towards,
    author = "Wang, Cong and Tang, Fan and Zhang, Yong and Wu, Tieru and Dong, Weiming",
    title = "Towards harmonized regional style transfer and manipulation for facial images",
    journal = "Computational Visual Media",
    volume = "9",
    number = "2",
    pages = "351--366",
    year = "2023",
    publisher = "TUP"
}

@inproceedings{huang2023region,
    author = "Huang, Nisha and Tang, Fan and Dong, Weiming and Lee, Tong-Yee and Xu, Changsheng",
    title = "Region-aware diffusion for zero-shot text-driven image editing",
    booktitle = "Computational Visual Media Conference",
    pages = "1--13",
    year = "2023"
}

@article{ma2023crossrectify,
    author = {Ma, Chengcheng and Pan, Xingjia and Ye, Qixiang and Tang, Fan and Dong, Weiming and Xu, Changsheng},
    title = {CrossRectify: Leveraging disagreement for semi-supervised object detection},
    journal = {Pattern Recognition},
    volume = {137},
    pages = {109280},
    year = {2023},
    publisher = {Pergamon},
    doi = {10.1016/j.patcog.2022.109280},
    articleno = {109280}
}

@inproceedings{zhang2022domain,
    author = "Zhang, Yuxin and Tang, Fan and Dong, Weiming and Huang, Haibin and Ma, Chongyang and Lee, Tong-Yee and Xu, Changsheng",
    title = "Domain enhanced arbitrary image style transfer via contrastive learning",
    booktitle = "ACM SIGGRAPH 2022 conference proceedings",
    pages = "1--8",
    year = "2022"
}

@inproceedings{deng2022stytr2,
    author = "Deng, Yingying and Tang, Fan and Dong, Weiming and Ma, Chongyang and Pan, Xingjia and Wang, Lei and Xu, Changsheng",
    title = "StyTr2: Image style transfer with transformers",
    booktitle = "Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Conference",
    pages = "11326--11336",
    year = "2022"
}

@inproceedings{li2022siod,
    author = "Li, Hanjun and Pan, Xingjia and Yan, Ke and Tang, Fan and Zheng, Wei-Shi",
    title = "SIOD: Single instance annotated per category per image for object detection",
    booktitle = "Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Conference",
    pages = "14197--14206",
    year = "2022"
}

@inproceedings{huang2022draw,
    author = {Huang, Nisha and Tang, Fan and Dong, Weiming and Xu, Changsheng},
    title = {Draw your art dream: Diverse digital art synthesis with multimodal guided diffusion},
    booktitle = {Proceedings of the 30th ACM International Conference on Multimedia},
    pages = {1085-1094},
    year = {2022},
    doi = {10.1145/3503161.3548282}
}

@article{song2022non,
    author = "Song, Yu and Tang, Fan and Dong, Weiming and Xu, Changsheng",
    title = "Non-dominated sorting based multi-page photo collage",
    journal = "Computational Visual Media",
    volume = "8",
    number = "2",
    pages = "199--212",
    year = "2022",
    publisher = "Tsinghua University Press Beijing"
}

@article{xu2022transformers,
    author = "Xu, Yifan and Wei, Huapeng and Lin, Minxuan and Deng, Yingying and Sheng, Kekai and Zhang, Mengdan and Tang, Fan and Dong, Weiming and Huang, Feiyue and Xu, Changsheng",
    title = "Transformers in computational visual media: A survey",
    journal = "Computational Visual Media",
    volume = "8",
    number = "1",
    pages = "33--62",
    year = "2022",
    publisher = "TUP"
}

@article{wei2022comparative,
    author = "Wei, Hua-Peng and Deng, Ying-Ying and Tang, Fan and Pan, Xing-Jia and Dong, Wei-Ming",
    title = "A comparative study of CNN-and transformer-based visual style transfer",
    journal = "Journal of Computer Science and Technology",
    volume = "37",
    number = "3",
    pages = "601--614",
    year = "2022",
    publisher = "Springer Nature Singapore Singapore"
}

@article{zhang2022portrait,
    author = "Zhang, Yuxin and Tang, Fan and Dong, Weiming and Le, Thi-Ngoc-Hanh and Xu, Changsheng and Lee, Tong-Yee",
    title = "Portrait Map Art Generation by Asymmetric Image-to-Image Translation",
    journal = "Leonardo",
    pages = "28--36",
    year = "2022"
}

@article{song2021balance,
    author = "Song, Yu and Tang, Fan and Dong, Weiming and Huang, Feiyue and Lee, Tong-Yee and Xu, Changsheng",
    title = "Balance-aware grid collage for small image collections",
    journal = "IEEE Transactions on Visualization and Computer Graphics",
    volume = "29",
    number = "2",
    pages = "1330--1344",
    year = "2021",
    publisher = "IEEE"
}

@inproceedings{pan2021unveiling,
    author = "Pan, Xingjia and Gao, Yingguo and Lin, Zhiwen and Tang, Fan and Dong, Weiming and Yuan, Haolei and Huang, Feiyue and Xu, Changsheng",
    title = "Unveiling the potential of structure preserving for weakly supervised object localization",
    booktitle = "Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Conference",
    pages = "11642--11651",
    year = "2021"
}

@inproceedings{ruan2021dae,
    author = "Ruan, Shulan and Zhang, Yong and Zhang, Kun and Fan, Yanbo and Tang, Fan and Liu, Qi and Chen, Enhong",
    title = "DAE-GAN: Dynamic aspect-aware GAN for text-to-image synthesis",
    booktitle = "Proceedings of the IEEE/CVF International Conference on Computer Vision",
    pages = "13960--13969",
    year = "2021"
}

@inproceedings{deng2021arbitrary,
    author = "Deng, Yingying and Tang, Fan and Dong, Weiming and Huang, Haibin and Ma, Chongyang and Xu, Changsheng",
    title = "Arbitrary Video Style Transfer via Multi-Channel Correlation",
    booktitle = "Proceedings of the AAAI Conference on Artificial Intelligence",
    pages = "1210--1217",
    year = "2021"
}

@article{lin2021distribution,
    author = {Lin, Minxuan and Tang, Fan and Dong, Weiming and Li, Xiao and Xu, Changsheng and Ma, Chongyang},
    title = {Distribution aligned multimodal and multi-domain image stylization},
    journal = {ACM Transactions on Multimedia Computing, Communications, and Applications},
    volume = {17},
    number = {3},
    pages = {96:1-96:17},
    year = {2021},
    publisher = {ACM New York, NY},
    doi = {10.1145/3450525},
    articleno = {96}
}

@article{chen2021siamcpn,
    author = "Chen, Dong and Tang, Fan and Dong, Weiming and Yao, Hanxing and Xu, Changsheng",
    title = "SiamCPN: Visual tracking with the Siamese center-prediction network",
    journal = "Computational Visual Media",
    volume = "7",
    number = "2",
    pages = "253--265",
    year = "2021",
    publisher = "Tsinghua University Press Beijing"
}

@article{pan2020self,
    author = "Pan, Xingjia and Tang, Fan and Dong, Weiming and Gu, Yang and Song, Zhichao and Meng, Yiping and Xu, Pengfei and Deussen, Oliver and Xu, Changsheng",
    title = "Self-supervised feature augmentation for large image object detection",
    journal = "IEEE Transactions on Image Processing",
    volume = "29",
    pages = "6745--6758",
    year = "2020",
    publisher = "IEEE"
}

@article{deng2020exploring,
    author = "Deng, Yingying and Tang, Fan and Dong, Weiming and Ma, Chongyang and Huang, Feiyue and Deussen, Oliver and Xu, Changsheng",
    title = "Exploring the representativity of art paintings",
    journal = "IEEE Transactions on Multimedia",
    volume = "23",
    pages = "2794--2805",
    year = "2020",
    publisher = "IEEE"
}

@inproceedings{deng2020arbitrary,
    author = {Deng, Yingying and Tang, Fan and Dong, Weiming and Sun, Wen and Huang, Feiyue and Xu, Changsheng},
    title = {Arbitrary style transfer via multi-adaptation network},
    booktitle = {Proceedings of the 28th ACM international conference on Multimedia},
    pages = {2719-2727},
    year = {2020},
    doi = {10.1145/3394171.3414015}
}

@article{pan2019content,
    author = "Pan, Xingjia and Tang, Fan and Dong, Weiming and Ma, Chongyang and Meng, Yiping and Huang, Feiyue and Lee, Tong-Yee and Xu, Changsheng",
    title = "Content-based visual summarization for image collections",
    journal = "IEEE Transactions on Visualization and Computer Graphics",
    volume = "27",
    number = "4",
    pages = "2298--2312",
    year = "2019",
    publisher = "IEEE"
}

@article{tang2019image,
    author = "Tang, Fan and Dong, Weiming and Meng, Yiping and Ma, Chongyang and Wu, Fuzhang and Li, Xinrui and Lee, Tong-Yee",
    title = "Image retargetability",
    journal = "IEEE Transactions on Multimedia",
    volume = "22",
    number = "3",
    pages = "641--654",
    year = "2019",
    publisher = "IEEE"
}

@article{zhao2019joint,
    author = "Zhao, Yucheng and Tang, Fan and Dong, Weiming and Huang, Feiyue and Zhang, Xiaopeng",
    title = "Joint face alignment and segmentation via deep multi-task learning",
    journal = "Multimedia Tools and Applications",
    volume = "78",
    number = "10",
    pages = "13131--13148",
    year = "2019",
    publisher = "Springer US New York"
}

@article{deng2019selective,
    author = "Deng, Yingying and Tang, Fan and Dong, Weiming and Wu, Fuzhang and Deussen, Oliver and Xu, Changsheng",
    title = "Selective clustering for representative paintings selection",
    journal = "Multimedia Tools and Applications",
    volume = "78",
    number = "14",
    pages = "19305--19323",
    year = "2019",
    publisher = "Springer US New York"
}

@inproceedings{song2018photo,
    author = "Song, Yu and Tang, Fan and Dong, Weiming and Zhang, Xiaopeng and Deussen, Oliver and Lee, Tong-Yee",
    title = "Photo squarization by deep multi-operator retargeting",
    booktitle = "Proceedings of the 26th ACM international Conference on Multimedia",
    pages = "1047--1055",
    year = "2018"
}

@article{tang2017animated,
    author = "Tang, Fan and Dong, Weiming and Meng, Yiping and Mei, Xing and Huang, Feiyue and Zhang, Xiaopeng and Deussen, Oliver",
    title = "Animated construction of Chinese brush paintings",
    journal = "IEEE Transactions on Visualization and Computer Graphics",
    volume = "24",
    number = "12",
    pages = "3019--3031",
    year = "2017",
    publisher = "IEEE"
}

@incollection{deng2017style,
    author = "Deng, Yingying and Tang, Fan and Dong, Weiming and Yao, Hanxing and Hu, Bao-Gang",
    title = "Style-oriented representative paintings selection",
    booktitle = "SIGGRAPH Asia 2017 Posters",
    pages = "1--2",
    year = "2017"
}

@inproceedings{liu2016flower,
    author = "Liu, Yuanyuan and Tang, Fan and Zhou, Dengwen and Meng, Yiping and Dong, Weiming",
    title = "Flower classification via convolutional neural network",
    booktitle = "2016 IEEE International Conference on Functional-Structural Plant Growth Modeling, Simulation, Visualization and Applications (FSPMA)",
    pages = "110--116",
    year = "2016",
    organization = "IEEE"
}

@incollection{meng2016optimal,
    author = "Meng, Yiping and Tang, Fan and Dong, Weiming and Zhang, Xiaopeng",
    title = "Optimal character composing for Chinese calligraphic artwork",
    booktitle = "SIGGRAPH ASIA 2016 Posters",
    pages = "1--2",
    year = "2016"
}

@incollection{tang2014animated,
    author = "Tang, Fan and Meng, Yiping and Dong, Weiming and Mei, Xing and Huang, Feiyue and Zhang, Xiaopeng",
    title = "Animated construction of ink-wash paintings",
    booktitle = "SIGGRAPH Asia 2014 Posters",
    pages = "1--1",
    year = "2014"
}