Selected Publications

@inproceedings{shen2024mm,
  title={MM-WLAuslan: Multi-View Multi-Modal Word-Level Australian Sign Language Recognition Dataset},
  author={Shen, Xin and Du, Heming and Sheng, Hongwei and Wang, Shuyun and Chen, Hui and Chen, Huiqiang and Wu, Zhuojie and Du, Xiaobiao and Ying, Jiaying and Lu, Ruihan and others},
  booktitle={Advances in Neural Information Processing Systems},
  volume={37},
  pages={69700--69715},
  year={2024}
}
        

@inproceedings{ying2025ldpose,
  title={LDPose: Towards Inclusive Human Pose Estimation for Limb-Deficient Individuals in the Wild},
  author={Ying, Jiaying and Du, Heming and Zhang, Kaihao and Li, Lincheng and Yu, Xin},
  booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
  pages={9865--9875},
  year={2025}
}
        

@inproceedings{du20253drealcar,
  title={3drealcar: An in-the-wild rgb-d car dataset with 360-degree views},
  author={Du, Xiaobiao and Wang, Yida and Sun, Haiyang and Wu, Zhuojie and Sheng, Hongwei and Wang, Shuyun and Ying, Jiaying and Lu, Ming and Zhu, Tianqing and Zhan, Kun and Yu, Xin},
  booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
  pages={26488--26498},
  year={2025}
}
        

@article{wei2024plantseg,
  title={Plantseg: A large-scale in-the-wild dataset for plant disease segmentation},
  author={Wei, Tianqi and Chen, Zhi and Yu, Xin and Chapman, Scott and Melloy, Paul and Huang, Zi},
  journal={arXiv preprint arXiv:2409.04038},
  year={2024}
}
        

@inproceedings{wei2024benchmarking,
  title={Benchmarking in-the-wild multimodal disease recognition and a versatile baseline},
  author={Wei, Tianqi and Chen, Zhi and Huang, Zi and Yu, Xin},
  booktitle={Proceedings of the 32nd ACM International Conference on Multimedia},
  pages={1593--1601},
  year={2024}
}
        

@inproceedings{xu2025m3gym,
  title={M3GYM: A Large-Scale Multimodal Multi-view Multi-person Pose Dataset for Fitness Activity Understanding in Real-world Settings},
  author={Xu, Qingzheng and Cao, Ru and Shen, Xin and Du, Heming and Wang, Sen and Yu, Xin},
  booktitle={Proceedings of the Computer Vision and Pattern Recognition Conference},
  pages={12289--12300},
  year={2025}
}
        

@inproceedings{liu2024benchmarking,
  title={Benchmarking audio visual segmentation for long-untrimmed videos},
  author={Liu, Chen and Li, Peike Patrick and Yu, Qingtao and Sheng, Hongwei and Wang, Dadong and Li, Lincheng and Yu, Xin},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={22712--22722},
  year={2024}
}
        

@inproceedings{shen2023auslan,
  title={Auslan-daily: Australian sign language translation for daily communication and news},
  author={Shen, Xin and Yuan, Shaozu and Sheng, Hongwei and Du, Heming and Yu, Xin},
  booktitle={Advances in Neural Information Processing Systems},
  volume={36},
  pages={80455--80469},
  year={2023}
}
        

@article{khan2023rvd,
  title={RVD: a handheld device-based fundus video dataset for retinal vessel segmentation},
  author={Khan, MD Wahiduzzaman and Sheng, Hongwei and Zhang, Hu and Du, Heming and Wang, Sen and Coroneo, Minas and Hajati, Farshid and Shariflou, Sahar and Kalloniatis, Michael and Phu, Jack and Agar, Ashish and Huang, Zi and Golzan, Mojtaba and Yu, Xin},
  journal={Advances in Neural Information Processing Systems},
  volume={36},
  pages={18203--18224},
  year={2023}
}
        

@inproceedings{li2020word,
  title={Word-level deep sign language recognition from video: A new large-scale dataset and methods comparison},
  author={Li, Dongxu and Rodriguez, Cristian and Yu, Xin and Li, Hongdong},
  booktitle={Proceedings of the IEEE/CVF winter conference on applications of computer vision},
  pages={1459--1469},
  year={2020}
}
        

@inproceedings{shen2025cross,
  title={Cross-View Isolated Sign Language Recognition via View Synthesis and Feature Disentanglement},
  author={Xin Shen and Xinyu Wang and Lei Shen and Kaihao Zhang and Xin Yu},
  booktitle={ICCV},
  year={2025}
}
      

@article{wang2024styletalk++,
  title={Styletalk++: A unified framework for controlling the speaking styles of talking heads},
  author={Wang, Suzhen and Ma, Yifeng and Ding, Yu and Hu, Zhipeng and Fan, Changjie and Lv, Tangjie and Deng, Zhidong and Yu, Xin},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  volume={46},
  number={6},
  pages={4331--4347},
  year={2024}
}
@inproceedings{ma2023styletalk,
  title={Styletalk: One-shot talking head generation with controllable speaking styles},
  author={Ma, Yifeng and Wang, Suzhen and Hu, Zhipeng and Fan, Changjie and Lv, Tangjie and Ding, Yu and Deng, Zhidong and Yu, Xin},
  booktitle={Proceedings of the AAAI conference on artificial intelligence},
  volume={37},
  number={2},
  pages={1896--1904},
  year={2023}
}
@inproceedings{wang2021audio2head,
  title={Audio2Head: Audio-driven One-shot Talking-head Generation with Natural Head Motion},
  author={Wang, Suzhen and Li, Lincheng and Ding, Yu and Fan, Changjie and Yu, Xin},
  booktitle={Proceedings of the Thirtieth International Joint Conference On Artificial Intelligence, Ijcai 2021},
  pages={1098--1105},
  year={2021},
  organization={International Joint Conferences on Artificial Intelligence Organization}
}
      

@inproceedings{qi2023diverse,
  title={Diverse 3D hand gesture prediction from body dynamics by bilateral hand disentanglement},
  author={Qi, Xingqun and Liu, Chen and Sun, Muyi and Li, Lincheng and Fan, Changjie and Yu, Xin},
  booktitle={Proceedings of the IEEE/CVF conference on computer vision and pattern recognition},
  pages={4616--4626},
  year={2023}
}
      

@inproceedings{li2020transferring,
  title={Transferring cross-domain knowledge for video sign language recognition},
  author={Li, Dongxu and Yu, Xin and Xu, Chenchen and Petersson, Lars and Li, Hongdong},
  booktitle={Proceedings of the IEEE/CVF conference on computer vision and pattern recognition},
  pages={6205--6214},
  year={2020}
}
      

@inproceedings{zhang2020copy,
  title={Copy and paste GAN: Face hallucination from shaded thumbnails},
  author={Zhang, Yang and Tsang, Ivor W and Luo, Yawei and Hu, Chang-Hui and Lu, Xiaobo and Yu, Xin},
  booktitle={Proceedings of the IEEE/CVF conference on computer vision and pattern recognition},
  pages={7355--7364},
  year={2020}
}
@article{zhang2021recursive,
  title={Recursive copy and paste GAN: Face hallucination from shaded thumbnails},
  author={Zhang, Yang and Tsang, Ivor W and Luo, Yawei and Hu, Changhui and Lu, Xiaobo and Yu, Xin},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  volume={44},
  number={8},
  pages={4321--4338},
  year={2021}
}
      

@inproceedings{lin2021gait,
  title={Gait recognition via effective global-local feature representation and local temporal aggregation},
  author={Lin, Beibei and Zhang, Shunli and Yu, Xin},
  booktitle={Proceedings of the IEEE/CVF international conference on computer vision},
  pages={14648--14656},
  year={2021}
}
      

@inproceedings{chen2024tpr,
  title={TPR: Topology-preserving reservoirs for generalized zero-shot learning},
  author={Chen, Hui and Liu, Yanbin and Ma, Yongqiang and Zheng, Nanning and Yu, Xin},
  booktitle={Advances in Neural Information Processing Systems},
  volume={37},
  pages={102229--102254},
  year={2024}
}
        

@inproceedings{xu2025mdam3,
    title={MDAM3: A Misinformation Detection and Analysis Framework for Multitype Multimodal Media},
    author={Xu, Qingzheng and Du, Heming and {\L}ukasik, Szymon and Zhu, Tianqing and Wang, Sen and Yu, Xin},
    booktitle={Proceedings of the ACM on Web Conference 2025},
    pages={5285--5296},
    year={2025}
}
        

@inproceedings{wang2025blind,
  title={Blind Bitstream-corrupted Video Recovery via Metadata-guided Diffusion Model},
  author={Wang, Shuyun and Zhang, Hu and Shen, Xin and Wang, Dadong and Yu, Xin},
  booktitle={Proceedings of the Computer Vision and Pattern Recognition Conference},
  pages={22975--22984},
  year={2025}
}
        

@inproceedings{hu2024efficientdreamer,
  title={Efficientdreamer: High-fidelity and robust 3d creation via orthogonal-view diffusion priors},
  author={Hu, Zhipeng and Zhao, Minda and Zhao, Chaoyi and Liang, Xinyue and Li, Lincheng and Zhao, Zeng and Fan, Changjie and Zhou, Xiaowei and Yu, Xin},
  booktitle={Proceedings of the IEEE/CVF conference on computer vision and pattern recognition},
  pages={4949--4958},
  year={2024}
}
      

@inproceedings{hu2024cpt,
  title={CPT-VR: Improving Surface Rendering via Closest Point Transform with View-Reflection Appearance},
  author={Hu, Zhipeng and Zhang, Yongqiang and Liu, Chen and Li, Lincheng and Peng, Sida and Zhou, Xiaowei and Fan, Changjie and Yu, Xin},
  booktitle={European Conference on Computer Vision},
  pages={223--239},
  year={2024}
}
      

@inproceedings{qiu2024freeavatar,
  title={FreeAvatar: Robust 3D Facial Animation Transfer by Learning an Expression Foundation Model},
  author={Qiu, Feng and Zhang, Wei and Liu, Chen and An, Rudong and Li, Lincheng and Ding, Yu and Fan, Changjie and Hu, Zhipeng and Yu, Xin},
  booktitle={SIGGRAPH Asia 2024 Conference Papers},
  pages={1--11},
  year={2024}
}
      

@inproceedings{wu2023nefii,
  title={Nefii: Inverse rendering for reflectance decomposition with near-field indirect illumination},
  author={Wu, Haoqian and Hu, Zhipeng and Li, Lincheng and Zhang, Yongqiang and Fan, Changjie and Yu, Xin},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={4295--4304},
  year={2023}
}
      

@article{shi2022accurate,
  title={Accurate 3-DoF camera geo-localization via ground-to-satellite image matching},
  author={Shi, Yujiao and Yu, Xin and Liu, Liu and Campbell, Dylan and Koniusz, Piotr and Li, Hongdong},
  journal={IEEE transactions on pattern analysis and machine intelligence},
  volume={45},
  number={3},
  pages={2682--2697},
  year={2022}
}
@inproceedings{shi2020looking,
  title={Where am i looking at? joint location and orientation estimation by cross-view matching},
  author={Shi, Yujiao and Yu, Xin and Campbell, Dylan and Li, Hongdong},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={4064--4072},
  year={2020}
}
@inproceedings{shi2020optimal,
  title={Optimal feature transport for cross-view image geo-localization},
  author={Shi, Yujiao and Yu, Xin and Liu, Liu and Zhang, Tong and Li, Hongdong},
  booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
  volume={34},
  number={07},
  pages={11990--11997},
  year={2020}
}
@article{shi2019spatial,
  title={Spatial-aware feature aggregation for image based cross-view geo-localization},
  author={Shi, Yujiao and Liu, Liu and Yu, Xin and Li, Hongdong},
  journal={Advances in Neural Information Processing Systems},
  volume={32},
  year={2019}
}
      

@article{fan2021deep,
  title={Deep hierarchical representation of point cloud videos via spatio-temporal decomposition},
  author={Fan, Hehe and Yu, Xin and Yang, Yi and Kankanhalli, Mohan},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  volume={44},
  number={12},
  pages={9918--9930},
  year={2021},
  publisher={IEEE}
}
@article{fan2022pstnet,
  title={Pstnet: Point spatio-temporal convolution on point cloud sequences},
  author={Fan, Hehe and Yu, Xin and Ding, Yuhang and Yang, Yi and Kankanhalli, Mohan},
  journal={arXiv preprint arXiv:2205.13713},
  year={2022}
}
      

@inproceedings{yu20206dof,
  title={6DoF Object Pose Estimation via Differentiable Proxy Voting Regularizer.},
  author={Yu, Xin and Zhuang, Zheyu and Koniusz, Piotr and Li, Hongdong},
  booktitle={BMVC},
  pages={1--13},
  year={2020}
}
      

@inproceedings{Tian_2019_CVPR,
  author = {Tian, Yurun and Yu, Xin and Fan, Bin and Wu, Fuchao and Heijnen, Huub and Balntas, Vassileios},
  title = {SOSNet: Second Order Similarity Regularization for Local Descriptor Learning},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  month = {June},
  year = {2019}
}