Jinrong Yang

Hello! I am Jinrong Yang (杨金荣). I am currently a 4th year Ph.D student at the Huazhong University of Science and Technology (HUST), supervised by Xiaoping Li. I am also an intern at Megvii Technology, supervised by Xiangyu Zhang and Zheng Ge. Before that, I got my bachelor’s degree at China University of Mining and Technology (CUMT) in 2019 and was recommended to study for my doctor’s degree at HUST.

My research interest mainly focus on Multimodal learning (LLM, AIGC), 2/3D (Perception, Tracking, Prediction, and Planning).

News

Dec 12, 2023	Before the year was over, we had released four LLM-based multimodal models: (1) Referring Instruction Tuning Model ChatSpot; (2) Foresight Minds Model Merlin; (3) Synergistic Multimodal Comprehension and Creation Model DreamLLM; (4) Scaling up the Vision Vocabulary Model Vary.
Jan 25, 2023	My second paper of corresponding author (PCET) is accepted by IEEE Robotics and Automation Letters (RA-L). Congratulations to Pan Wang!
Jan 21, 2023	One paper (DBQ-SSD) is accepted by ICLR 2023
Nov 1, 2022	Three papers (BEVDepth, BEVStereo, LTrack) are accepted by AAAI 2023
Mar 2, 2022	One paper (StreamYOLO) is accepted by CVPR 2022, Oral Presentation
Sep 28, 2021	One paper (COSOC) is accepted by NeurIPS 2021

Selected publications

* indicates equal contribution, ** indicates corresponding author.

DreamLLM: Synergistic Multimodal Comprehension and Creation

Runpei Dong, Chunrui Han, Yuang Peng, Zekun Qi, Zheng Ge, Jinrong Yang, Liang Zhao, Jianjian Sun, Hongyu Zhou, Haoran Wei, and 1 more author

arXiv preprint arXiv:2309.11499, 2023

Bib HTML

@article{zhao2023dreamllm,
  title = {DreamLLM: Synergistic Multimodal Comprehension and Creation},
  author = {Dong, Runpei and Han, Chunrui and Peng, Yuang and Qi, Zekun and Ge, Zheng and Yang, Jinrong and Zhao, Liang and Sun, Jianjian and Zhou, Hongyu and Wei, Haoran and others},
  journal = {arXiv preprint arXiv:2309.11499},
  year = {2023},
}

ChatSpot: Bootstrapping Multimodal LLMs via Precise Referring Instruction Tuning

Liang Zhao, En Yu, Zheng Ge, Jinrong Yang, Haoran Wei, Hongyu Zhou, Jianjian Sun, Yuang Peng, Runpei Dong, Chunrui Han, and 1 more author

arXiv preprint arXiv:2307.09474, 2023

Bib HTML

@article{zhao2023chatspot,
  title = {ChatSpot: Bootstrapping Multimodal LLMs via Precise Referring Instruction Tuning},
  author = {Zhao, Liang and Yu, En and Ge, Zheng and Yang, Jinrong and Wei, Haoran and Zhou, Hongyu and Sun, Jianjian and Peng, Yuang and Dong, Runpei and Han, Chunrui and others},
  journal = {arXiv preprint arXiv:2307.09474},
  year = {2023},
}

GroupLane: End-to-End 3D Lane Detection with Channel-wise Grouping

Zhuoling Li, Chunrui Han, Zheng Ge, Jinrong Yang, En Yu, Haoqian Wang, Hengshuang Zhao, and Xiangyu Zhang

arXiv preprint arXiv:2307.09472, 2023

Bib HTML

@article{li2023grouplane,
  title = {GroupLane: End-to-End 3D Lane Detection with Channel-wise Grouping},
  author = {Li, Zhuoling and Han, Chunrui and Ge, Zheng and Yang, Jinrong and Yu, En and Wang, Haoqian and Zhao, Hengshuang and Zhang, Xiangyu},
  journal = {arXiv preprint arXiv:2307.09472},
  year = {2023},
}

GMM: Delving into Gradient Aware and Model Perceive Depth Mining for Monocular 3D Detection

Weixin Mao*, Jinrong Yang*, Zheng Ge, Lin Song, Hongyu Zhou, Tiezheng Mao, Zeming Li, and Osamu Yoshie

arXiv preprint arXiv:2306.17450, 2023

Bib HTML

@article{mao2023gmm,
  title = {GMM: Delving into Gradient Aware and Model Perceive Depth Mining for Monocular 3D Detection},
  author = {Mao*, Weixin and Yang*, Jinrong and Ge, Zheng and Song, Lin and Zhou, Hongyu and Mao, Tiezheng and Li, Zeming and Yoshie, Osamu},
  journal = {arXiv preprint arXiv:2306.17450},
  year = {2023},
}

Exploring Recurrent Long-term Temporal Fusion for Multi-view 3D Perception

Chunrui Han, Jianjian Sun, Zheng Ge, Jinrong Yang, Runpei Dong, Hongyu Zhou, Weixin Mao, Yuang Peng, and Xiangyu Zhang

arXiv preprint arXiv:2303.05970, 2023

Bib HTML

@article{han2023exploring,
  title = {Exploring Recurrent Long-term Temporal Fusion for Multi-view 3D Perception},
  author = {Han, Chunrui and Sun, Jianjian and Ge, Zheng and Yang, Jinrong and Dong, Runpei and Zhou, Hongyu and Mao, Weixin and Peng, Yuang and Zhang, Xiangyu},
  journal = {arXiv preprint arXiv:2303.05970},
  year = {2023},
}

DBQ-SSD: Dynamic Ball Query for Efficient 3D Object Detection

Jinrong Yang*, Lin Song*, Songtao Liu, Weixin Mao, Zeming Li, Xiaoping Li, Hongbin Sun, Jian Sun, and Nanning Zheng

In International Conference on Learning Representations (ICLR), 2023

Bib HTML

@inproceedings{yang2022dbq,
  title = {DBQ-SSD: Dynamic Ball Query for Efficient 3D Object Detection},
  author = {Yang*, Jinrong and Song*, Lin and Liu, Songtao and Mao, Weixin and Li, Zeming and Li, Xiaoping and Sun, Hongbin and Sun, Jian and Zheng, Nanning},
  year = {2023},
  booktitle = {International Conference on Learning Representations (ICLR)},
}

Implicit and Efficient Point Cloud Completion for 3D Single Object Tracking

Pan Wang, Liangliang Ren, Shengkai Wu, Jinrong Yang**, En Yu, Hangcheng Yu, and Xiaoping Li

IEEE Robotics and Automation Letters, 2023

Bib HTML

@article{wang2022implicit,
  title = {Implicit and Efficient Point Cloud Completion for 3D Single Object Tracking},
  author = {Wang, Pan and Ren, Liangliang and Wu, Shengkai and Yang**, Jinrong and Yu, En and Yu, Hangcheng and Li, Xiaoping},
  year = {2023},
  journal = {IEEE Robotics and Automation Letters},
}

BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detection

Yinhao Li, Zheng Ge, Guanyi Yu, Jinrong Yang, Zengran Wang, Yukang Shi, Jianjian Sun, and Zeming Li

In Proceeding of Association for the Advancement of Artificial Intelligence (AAAI), 2023

Bib HTML Code

@inproceedings{li2022bevdepth,
  title = {BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detection},
  author = {Li, Yinhao and Ge, Zheng and Yu, Guanyi and Yang, Jinrong and Wang, Zengran and Shi, Yukang and Sun, Jianjian and Li, Zeming},
  booktitle = {Proceeding of Association for the Advancement of Artificial Intelligence (AAAI)},
  year = {2023},
}

BEVStereo: Enhancing Depth Estimation in Multi-view 3D Object Detection with Dynamic Temporal Stereo

Yinhao Li, Han Bao, Zheng Ge, Jinrong Yang, Jianjian Sun, and Zeming Li

In Proceeding of Association for the Advancement of Artificial Intelligence (AAAI), 2023

Bib HTML Code

@inproceedings{li2022bevstereo,
  title = {BEVStereo: Enhancing Depth Estimation in Multi-view 3D Object Detection with Dynamic Temporal Stereo},
  author = {Li, Yinhao and Bao, Han and Ge, Zheng and Yang, Jinrong and Sun, Jianjian and Li, Zeming},
  booktitle = {Proceeding of Association for the Advancement of Artificial Intelligence (AAAI)},
  year = {2023},
}

Generalizing Multiple Object Tracking to Unseen Domains by Introducing Natural Language Representation

En Yu, Songtao Liu, Zhuoling Li, Jinrong Yang, Shoudong Han, Wenbing Tao, and others

In Proceeding of Association for the Advancement of Artificial Intelligence (AAAI), 2023

Bib HTML

@inproceedings{yu2022generalizing,
  title = {Generalizing Multiple Object Tracking to Unseen Domains by Introducing Natural Language Representation},
  author = {Yu, En and Liu, Songtao and Li, Zhuoling and Yang, Jinrong and Han, Shoudong and Tao, Wenbing and others},
  booktitle = {Proceeding of Association for the Advancement of Artificial Intelligence (AAAI)},
  year = {2023},
}

Real-time Object Detection for Streaming Perception

Jinrong Yang, Songtao Liu, Zeming Li, Xiaoping Li, and Jian Sun

In Proceeding of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022

Bib HTML Code

@inproceedings{yang2022real,
  title = {Real-time Object Detection for Streaming Perception},
  author = {Yang, Jinrong and Liu, Songtao and Li, Zeming and Li, Xiaoping and Sun, Jian},
  booktitle = {Proceeding of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2022},
}

Towards 3D Object Detection with 2D Supervision

Jinrong Yang, Tiancai Wang, Zheng Ge, Weixin Mao, Xiaoping Li, and Xiangyu Zhang

arXiv preprint arXiv:2211.08287, 2022

Bib HTML

@article{yang2022towards,
  title = {Towards 3D Object Detection with 2D Supervision},
  author = {Yang, Jinrong and Wang, Tiancai and Ge, Zheng and Mao, Weixin and Li, Xiaoping and Zhang, Xiangyu},
  year = {2022},
  journal = {arXiv preprint arXiv:2211.08287},
}

Quality Matters: Embracing Quality Clues for Robust 3D Multi-Object Tracking

Jinrong Yang*, En Yu*, Zeming Li, Xiaoping Li, and Wenbing Tao

arXiv preprint arXiv:2208.10976, 2022

Bib HTML

@article{yang2022quality,
  title = {Quality Matters: Embracing Quality Clues for Robust 3D Multi-Object Tracking},
  author = {Yang*, Jinrong and Yu*, En and Li, Zeming and Li, Xiaoping and Tao, Wenbing},
  year = {2022},
  journal = {arXiv preprint arXiv:2208.10976},
}

Iou-balanced Loss Functions for Single-stage Object Detection

Shengkai Wu*, Jinrong Yang*, Xinggang Wang, and Xiaoping Li

Pattern Recognition Letters (PRL), 2022

Bib HTML

@article{wu2022iou,
  title = {Iou-balanced Loss Functions for Single-stage Object Detection},
  author = {Wu*, Shengkai and Yang*, Jinrong and Wang, Xinggang and Li, Xiaoping},
  year = {2022},
  journal = {Pattern Recognition Letters (PRL)},
}

Rectifying the Shortcut Learning of Background for Few-shot Learning

Xu Luo, Longhui Wei, Liangjian Wen, Jinrong Yang, Lingxi Xie, Zenglin Xu, and Qi Tian

In Proceeding of Advances in Neural Information Processing Systems (NeurIPS), 2021

Bib HTML Code

@inproceedings{luo2021rectifying,
  title = {Rectifying the Shortcut Learning of Background for Few-shot Learning},
  author = {Luo, Xu and Wei, Longhui and Wen, Liangjian and Yang, Jinrong and Xie, Lingxi and Xu, Zenglin and Tian, Qi},
  booktitle = {Proceeding of Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
}

Collaborators

张祥雨(Xiangyu Zhang), 黎泽明(Zeming Li), 葛政(Zheng Ge), 刘松涛(Songtao Liu)

Reviewer

Computer Vision Conference: CVPR, ICCV, ECCV
Machine Learning Conference: NeurIPS, ICLR, AAAI
Robotics Conference: ICRA, IROS
Journal: TPAMI, TCSVT, TMM, PRL, IET CV