Hongyang Li

Ph.D Student @ South China University of Technology
Research Intern @ International Digital Economy Academy (IDEA)
Guangdong-HongKong-Macau Greater Bay Area
Shenzhen, China

Email: ftwangyeunglei AT mail dot scut dot edu dot cn

Google Scholar | LinkedIn | Github

Hi! This is Hongyang Li, 李弘洋 in Chinese. I’m a second-year year Ph.D. student (2022-now) at the Department of Future Technology, South China University of Technology, supervised by Prof.Lei Zhang. I interned at International Digital Economy Academy. Previously, I obtained my bachelor’s degree from School of Electrical Engineering in South China University of Technology in 2021.

🔖 My research interests lie in Tracking Any Point, 3D Perception and Multi-modal Models.

💬 Feel free to contact me for any discussion and coorperation.

News

[2024/9] TAPTRv2 is accepted by NeurIPS2024.

[2024/7] TAPTRv2 is released! Check out our TAPTRv2 for more details.

[2024/7] Two papers are accepted by ECCV2024! Check out our TAPTR and LLaVA-Grounding for more details.

[2024/3] We release TAPTR. Check out project page for more details and online demos.

[2023/12] We release LLaVA-Grounding. Demo and inference code are available.

[2023/7] Two papers are accepted by ICCV2023. Check out our DFA3D and StableDINO.

[2023/2] We release DA-BEV that establishes a new SOTA performance on nuScenes 3D detection leaderboard–camera track. Check out our DA-BEV.

[2022/7] A paper is accepted by ECCV2022! Check out our DCL-Net.

[2021/9] A paper is accepted by NeurIPS2021! Check out our Sparse Steerable Convolution.

Selected Publications

TAPTRv2: Attention-based Position Update Improves Tracking Any Point

Hongyang Li, Hao Zhang, Shilong Liu, Zhaoyang Zeng, Feng Li, Tianhe Ren, Bohan Li, Lei Zhang

NeurIPS, 2024

BibTex

arXiv (pdf)

Project Page

Github (Comming Soon)

@article{li2024taptrv2,
          title={TAPTRv2: Attention-based Position Update Improves Tracking Any Point},
          author={Li, Hongyang and Zhang, Hao and Liu, Shilong and Zeng, Zhaoyang and Li, Feng and Ren, Tianhe and Bohan Li and Zhang, Lei},
          journal={arXiv preprint arXiv:2407.16291},
          year={2024}
        }

TAPTR: Tracking Any Point with Transformers as Detection

Hongyang Li, Hao Zhang, Shilong Liu, Zhaoyang Zeng, Tianhe Ren, Feng Li, Lei Zhang

ECCV, 2024

BibTex

arXiv (pdf)

Project Page

Github

@article{li2024taptr,
        title={TAPTR: Tracking Any Point with Transformers as Detection},
        author={Li, Hongyang and Zhang, Hao and Liu, Shilong and Zeng, Zhaoyang and Ren, Tianhe and Li, Feng and Zhang, Lei},
        journal={arXiv preprint arXiv:2403.13042},
        year={2024}
      }

LLaVA-Grounding: Grounded Visual Chat with Large Multimodal Models

Hao Zhang*, Hongyang Li*, Feng Li, Tianhe Ren, Xueyan Zou, Shilong Liu, Shijia Huang, Jianfeng Gao, Lei Zhang, Chunyuan Li, Jianwei Yang

ECCV, 2024

BibTex

arXiv (pdf)

Project Page

Github

@article{zhang2023llava,
      title={Llava-grounding: Grounded visual chat with large multimodal models},
      author={Zhang, Hao and Li, Hongyang and Li, Feng and Ren, Tianhe and Zou, Xueyan and Liu, Shilong and Huang, Shijia and Gao, Jianfeng and Zhang, Lei and Li, Chunyuan and others},
      journal={arXiv preprint arXiv:2312.02949},
      year={2023}
    }

DFA3D: 3D Deformable Attention For 2D-to-3D Feature Lifting

Hongyang Li*, Hao Zhang*, Zhaoyang Zeng, Shilong Liu, Feng Li, Tianhe Ren, Lei Zhang

ICCV, 2023

BibTex

arXiv (pdf)

Github

@inproceedings{li2023dfa3d,
      title={DFA3D: 3D Deformable Attention For 2D-to-3D Feature Lifting},
      author={Li, Hongyang and Zhang, Hao and Zeng, Zhaoyang and Liu, Shilong and Li, Feng and Ren, Tianhe and Zhang, Lei},
      booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
      pages={6684--6693},
      year={2023}
    }

DA-BEV: Depth Aware BEV Transformer for 3D Object Detection

Hao Zhang*, Hongyang Li*, Zhaoyang Zeng, Shilong Liu, Feng Li, Tianhe Ren, Lei Zhang

arxiv, 2023

BibTex

arXiv (pdf)

@article{zhang2023bev,
      title={Da-bev: Depth aware bev transformer for 3d object detection},
      author={Zhang, Hao and Li, Hongyang and Liao, Xingyu and Li, Feng and Liu, Shilong and Ni, Lionel M and Zhang, Lei},
      journal={arXiv e-prints},
      pages={arXiv--2302},
      year={2023}
    }

DCL-Net: Deep Correspondence Learning Network for 6D Pose Estimation

Hongyang Li*, Jiehong Lin*, Kui Jia

ECCV, 2022

BibTex

arXiv (pdf)

Github

@inproceedings{li2022dcl,
      title={DCL-Net: Deep Correspondence Learning Network for 6D Pose Estimation},
      author={Li, Hongyang and Lin, Jiehong and Jia, Kui},
      booktitle={European Conference on Computer Vision},
      pages={369--385},
      year={2022},
      organization={Springer}
    }

Sparse Steerable Convolutions: An Efficient Learning of SE(3)-Equivariant Features for Estimation and Tracking of Object Poses in 3D Space

Jiehong Lin*, Hongyang Li*, Kui Jia

NeurIPS, 2021

BibTex

arXiv (pdf)

Github

@article{lin2021sparse,
      title={Sparse steerable convolutions: An efficient learning of se (3)-equivariant features for estimation and tracking of object poses in 3d space},
      author={Lin, Jiehong and Li, Hongyang and Chen, Ke and Lu, Jiangbo and Jia, Kui},
      journal={Advances in Neural Information Processing Systems},
      volume={34},
      pages={16779--16790},
      year={2021}
    }

Awards

Principal's Scholarship & National Scholarships in 2023.
Principal's Scholarship & National Scholarships in 2022.
The First Prize Scholarship * 2 & The Second Prize Scholarship during 2018-2022.