Publications

2026

1. ICML

   Position: Human-Centric Vision Requires Topological Generalization Beyond Fixed Skeletal Topologies

   Heming Du, Jiaying Ying, Kaihao Zhang, and 2 more authors

   In International Conference on Machine Learning (ICML), 2026

   Joint first author with Jiaying Ying

   Bib

   @inproceedings{du2026position,
     title = {Position: Human-Centric Vision Requires Topological Generalization Beyond Fixed Skeletal Topologies},
     author = {Du, Heming and Ying, Jiaying and Zhang, Kaihao and Zhu, Tianqing and Yu, Xin},
     booktitle = {International Conference on Machine Learning (ICML)},
     year = {2026},
     note = {Joint first author with Jiaying Ying}
   }

2. CVPR

   ResiHMR: Residual-Limb Aware Single-Image 3D Human Mesh Recovery for Individuals with Limb Loss

   Jiaying Ying, Heming Du, Kaihao Zhang, and 2 more authors

   In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026

   Joint first author with Jiaying Ying

   arXiv Bib HTML PDF

   @inproceedings{du2026resihmr,
     title = {ResiHMR: Residual-Limb Aware Single-Image 3D Human Mesh Recovery for Individuals with Limb Loss},
     author = {Ying, Jiaying and Du, Heming and Zhang, Kaihao and Tweedy, Sean M. and Yu, Xin},
     booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
     year = {2026},
     note = {Joint first author with Jiaying Ying}
   }

3. ICLR

   InclusiveVidPose: Bridging the Pose Estimation Gap for Individuals with Limb Deficiencies in Video-Based Motion

   Heming Du, Jiaying Ying, Sen Wang, and 3 more authors

   In International Conference on Learning Representations (ICLR), 2026

   Joint first author with Jiaying Ying

   Bib HTML Website

   @inproceedings{du2026inclusivevidpose,
     title = {InclusiveVidPose: Bridging the Pose Estimation Gap for Individuals with Limb Deficiencies in Video-Based Motion},
     author = {Du, Heming and Ying, Jiaying and Wang, Sen and Li, Xue and Zhang, Kaihao and Yu, Xin},
     booktitle = {International Conference on Learning Representations (ICLR)},
     year = {2026},
     note = {Joint first author with Jiaying Ying}
   }

4. ICRA

   Déjà Vu: Unlocking Transparent Action Reasoning for Object-Goal Navigation via Large Language Models

   Heming Du, Sen Wang, Xue Li, and 1 more author

   In IEEE International Conference on Robotics and Automation (ICRA), 2026

   Bib

   @inproceedings{du2026dejavu,
     title = {Déjà Vu: Unlocking Transparent Action Reasoning for Object-Goal Navigation via Large Language Models},
     author = {Du, Heming and Wang, Sen and Li, Xue and Yu, Xin},
     booktitle = {IEEE International Conference on Robotics and Automation (ICRA)},
     year = {2026},
   }

5. AAAI

   FreDN: Spectral Disentanglement for Time Series Forecasting via Learnable Frequency Decomposition

   Zhongde An, Jinhong You, Jiyanglin Li, and 4 more authors

   In AAAI Conference on Artificial Intelligence (AAAI), 2026

   Joint corresponding author

   Bib

   @inproceedings{an2026fredn,
     title = {FreDN: Spectral Disentanglement for Time Series Forecasting via Learnable Frequency Decomposition},
     author = {An, Zhongde and You, Jinhong and Li, Jiyanglin and Tang, Yiming and Li, Wen and Du, Heming and Du, Shouguo},
     booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
     year = {2026},
     note = {Joint corresponding author}
   }

2025

1. ICCV

   LDPose: Towards Inclusive Human Pose Estimation for Limb-Deficient Individuals in the Wild

   Jiaying Ying, Heming Du, Kaihao Zhang, and 2 more authors

   In IEEE/CVF International Conference on Computer Vision (ICCV), 2025

   Joint first author with Jiaying Ying

   DOI Bib HTML PDF

   @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 = {IEEE/CVF International Conference on Computer Vision (ICCV)},
     year = {2025},
     doi = {10.1109/ICCV51701.2025.00920},
     note = {Joint first author with Jiaying Ying}
   }

2. NeurIPS

   When One Moment Isn’t Enough: Multi-Moment Retrieval with Cross-Moment Interactions

   Zhuo Cao, Heming Du, Bingqing Zhang, and 3 more authors

   In Conference on Neural Information Processing Systems (NeurIPS), 2025

   Joint first author with Zhuo Cao

   DOI Bib

   @inproceedings{cao2025multimoment,
     title = {When One Moment Isn't Enough: Multi-Moment Retrieval with Cross-Moment Interactions},
     author = {Cao, Zhuo and Du, Heming and Zhang, Bingqing and Yu, Xin and Li, Xue and Wang, Sen},
     booktitle = {Conference on Neural Information Processing Systems (NeurIPS)},
     year = {2025},
     note = {Joint first author with Zhuo Cao},
     doi = {10.52202/085713-5715}
   }

3. ICCV

   Quantifying and Narrowing the Unknown: Interactive Text-to-Video Retrieval via Uncertainty Minimization

   Bingqing Zhang, Zhuo Cao, Heming Du, and 3 more authors

   In IEEE/CVF International Conference on Computer Vision (ICCV), 2025

   DOI Bib HTML PDF

   @inproceedings{zhang2025interactive,
     title = {Quantifying and Narrowing the Unknown: Interactive Text-to-Video Retrieval via Uncertainty Minimization},
     author = {Zhang, Bingqing and Cao, Zhuo and Du, Heming and Yu, Xin and Li, Xue and Wang, Sen},
     booktitle = {IEEE/CVF International Conference on Computer Vision (ICCV)},
     year = {2025},
     doi = {10.1109/ICCV51701.2025.02054}
   }

4. WWW

   AuslanWeb: A Scalable Web-Based Australian Sign Language Communication System for Deaf and Hearing Individuals

   Xin Shen, Heming Du, Hongwei Sheng, and 2 more authors

   In The Web Conference (WWW), 2025

   DOI Bib

   @inproceedings{shen2025auslanweb,
     title = {AuslanWeb: A Scalable Web-Based Australian Sign Language Communication System for Deaf and Hearing Individuals},
     author = {Shen, Xin and Du, Heming and Sheng, Hongwei and Li, Lincheng and Zhang, Kaihao},
     booktitle = {The Web Conference (WWW)},
     year = {2025},
     doi = {10.1145/3696410.3714525}
   }

5. IJCAI

   Multimodal Retina Image Analysis Survey: Datasets, Tasks and Methods

   Hongwei Sheng, Heming Du, Xin Shen, and 2 more authors

   In International Joint Conference on Artificial Intelligence (IJCAI), 2025

   DOI Bib HTML PDF

   @inproceedings{sheng2025retina,
     title = {Multimodal Retina Image Analysis Survey: Datasets, Tasks and Methods},
     author = {Sheng, Hongwei and Du, Heming and Shen, Xin and Wang, Sen and Yu, Xin},
     booktitle = {International Joint Conference on Artificial Intelligence (IJCAI)},
     year = {2025},
     doi = {10.24963/ijcai.2025/1182}
   }

2024

1. NeurIPS

   MM-WLAuslan: Multi-View Multi-Modal Word-Level Australian Sign Language Recognition Dataset

   Xin Shen, Heming Du, Hongwei Sheng, and 9 more authors

   In Conference on Neural Information Processing Systems (NeurIPS), Datasets and Benchmarks Track, 2024

   DOI Bib

   @inproceedings{shen2024mmwlauslan,
     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 Xu, Qingzheng and Yu, Xin},
     booktitle = {Conference on Neural Information Processing Systems (NeurIPS), Datasets and Benchmarks Track},
     year = {2024},
     doi = {10.52202/079017-2227}
   }

2023

1. CVPR

   Object-Goal Visual Navigation via Effective Exploration of Relations Among Historical Navigation States

   Heming Du, Lincheng Li, Zi Huang, and 1 more author

   In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023

   DOI Bib HTML PDF

   @inproceedings{du2023hinl,
     title = {Object-Goal Visual Navigation via Effective Exploration of Relations Among Historical Navigation States},
     author = {Du, Heming and Li, Lincheng and Huang, Zi and Yu, Xin},
     booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
     year = {2023},
     doi = {10.1109/CVPR52729.2023.00252}
   }

2. WACV

   Weakly-Supervised Point Cloud Instance Segmentation with Geometric Priors

   Heming Du, Xin Yu, Farookh Hussain, and 3 more authors

   In IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2023

   DOI Bib HTML PDF

   @inproceedings{du2023weakly,
     title = {Weakly-Supervised Point Cloud Instance Segmentation with Geometric Priors},
     author = {Du, Heming and Yu, Xin and Hussain, Farookh and Armin, Mohammad Ali and Petersson, Lars and Li, Weihao},
     booktitle = {IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)},
     year = {2023},
     doi = {10.1109/WACV56688.2023.00425}
   }

3. NeurIPS

   Auslan-Daily: Australian Sign Language Translation for Daily Communication and News

   Xin Shen, Shaozu Yuan, Hongwei Sheng, and 2 more authors

   In Conference on Neural Information Processing Systems (NeurIPS), Datasets and Benchmarks Track, 2023

   DOI Bib

   @inproceedings{shen2023auslandaily,
     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 = {Conference on Neural Information Processing Systems (NeurIPS), Datasets and Benchmarks Track},
     year = {2023},
     doi = {10.52202/075280-3527}
   }

4. NeurIPS

   RVD: A Handheld Device-Based Fundus Video Dataset for Retinal Vessel Segmentation

   Md Wahiduzzaman Khan, Hongwei Sheng, Hu Zhang, and 11 more authors

   In Conference on Neural Information Processing Systems (NeurIPS), 2023

   DOI Bib

   @inproceedings{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 Theodore and Hajati, Farshid and Shariflou, Sahar and Kalloniatis, Michael and Phu, Jack and Agar, Ashish and Huang, Zi and Golzan, Mojtaba and Yu, Xin},
     booktitle = {Conference on Neural Information Processing Systems (NeurIPS)},
     year = {2023},
     doi = {10.52202/075280-0801}
   }

2022

1. AAAI

   Monocular Camera-Based Point-Goal Navigation by Learning Depth Channel and Cross-Modality Pyramid Fusion

   Tianqi Tang, Heming Du, Xin Yu, and 1 more author

   In AAAI Conference on Artificial Intelligence (AAAI), 2022

   Joint first author with Tianqi Tang

   DOI Bib

   @inproceedings{tang2022monocular,
     title = {Monocular Camera-Based Point-Goal Navigation by Learning Depth Channel and Cross-Modality Pyramid Fusion},
     author = {Tang, Tianqi and Du, Heming and Yu, Xin and Yang, Yi},
     booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
     year = {2022},
     note = {Joint first author with Tianqi Tang},
     doi = {10.1609/aaai.v36i5.20480}
   }

2. CAAI Trans.

   Probabilistic Time Series Forecasting with Deep Non-Linear State Space Models

   Heming Du, Shouguo Du, and Wen Li

   CAAI Transactions on Intelligence Technology, 2022

   DOI Bib

   @article{du2022probabilistic,
     title = {Probabilistic Time Series Forecasting with Deep Non-Linear State Space Models},
     author = {Du, Heming and Du, Shouguo and Li, Wen},
     journal = {CAAI Transactions on Intelligence Technology},
     year = {2022},
     doi = {10.1049/cit2.12085}
   }

2021

1. ICLR

   VTNet: Visual Transformer Network for Object Goal Navigation

   Heming Du, Xin Yu, and Liang Zheng

   In International Conference on Learning Representations (ICLR), 2021

   Bib HTML PDF Code

   @inproceedings{du2021vtnet,
     title = {VTNet: Visual Transformer Network for Object Goal Navigation},
     author = {Du, Heming and Yu, Xin and Zheng, Liang},
     booktitle = {International Conference on Learning Representations (ICLR)},
     year = {2021},
   }

2020

1. ECCV

   Learning Object Relation Graph and Tentative Policy for Visual Navigation

   Heming Du, Xin Yu, and Liang Zheng

   In European Conference on Computer Vision (ECCV), 2020

   DOI Bib HTML PDF Code

   @inproceedings{du2020learning,
     title = {Learning Object Relation Graph and Tentative Policy for Visual Navigation},
     author = {Du, Heming and Yu, Xin and Zheng, Liang},
     booktitle = {European Conference on Computer Vision (ECCV)},
     year = {2020},
     doi = {10.1007/978-3-030-58571-6_2}
   }