Jiangpeng He

jhe2[at]iu[dot]edu
he416[at]purdue[dot]edu

Hi, I am currently a tenure-track Assistant Professor in the Department of Computer Science at Indiana University Bloomington. Previously, I was a Postdoctoral Associate at MIT, working with Dr. Hermano Igo Krebs on Smart Rehabilitation Robotics. I also served as an Adjunct Professor in the Department of Electrical and Computer Engineering at Purdue University.

I earned my Ph.D. in Electrical and Computer Engineering from Purdue University, in the Video and Image Processing Lab (VIPER), where I had the privilege of being advised by Prof. Fengqing Maggie Zhu and Prof. Edward Delp.

Prior to my doctoral studies, I obtained my bachelor’s degree from the University of Electronic Science and Technology of China, Chengdu.

I warmly welcome anyone interested in collaborating or discussing research with me, whether remotely or in person. Potential topics related to continual learning, long-tail learning, and AI for health care.

I am seeking highly motivated Ph.D students. Please email me your CV if you are interested. Make sure to indicate whether you are applying for PhD or the Research Intern in your email title.

news

Feb 27, 2026	Our paper Physically Informed 3D Food Reconstruction: Methods and Results is accepted to IEEE Journal of Biomedical and Health Informatics (JBHI)
Feb 26, 2026	Our paper Continual Distillation of Teacher from Different Domains is accepted to CVPR 2026
Feb 12, 2026	I am honored to co-chair the MetaFood Workshop at CVPR 2026. Call for papers open now, find more information Here
Nov 09, 2025	Our paper Food Image Generation on Multi-Noun Categories is accepted to WACV 2026
Nov 07, 2025	Our paper PANDA - Patch And Distribution-Aware Augmentation for Long-Tailed Exemplar-Free Continual Learning is accepted to AAAI 2026 (23,680 submission, 4,167 accepted, 17.6% overall acceptance rate). Paper and source code can be found Here.
Jul 23, 2025	I gave the talk AI-Powered Image-Based Dietary Assessment in the NIH-funded course The Mathematical Sciences in Obesity Research at Chicago.
Apr 24, 2025	Our paper Long-Tailed Continual Learning For Visual Food Recognition is accepted to IEEE Transactions on Multimedia. We introduced new food image benchmark datasets VFN186 that simulates the real-world food consumption patterns for healthy people, type-1 and type-2 diabetes to perfrom continual learning. The paper and dataset can be accessed Here.
Feb 26, 2025	Can we use LoRA to continusouly learn new tasks? Our paper CL-LoRA: Continual Low-Rank Adaptation for Rehearsal-Free Class-Incremental Learning is accepted to CVPR 2025. Paper and source code can be found Here.
Feb 21, 2025	I am honored to co-chair the 2nd MetaFood Workshop Workshop at CVPR 2025. Call for paper is now open!
Sep 17, 2024	Our MetaFood3D dataset is now available — the first comprehensive 3D food dataset with nutrition values

selected publications

TMM

Long-Tailed Continual Learning For Visual Food Recognition

Jiangpeng He, Xiaoyan Zhang, Luotao Lin, Jack Ma, Heather A. Eicher-Miller, and Fengqing Zhu

IEEE Transactions on Multimedia, 2025

Bib PDF Code

@article{he_2025_tmm,
  title = {Long-Tailed Continual Learning For Visual Food Recognition},
  author = {He, Jiangpeng and Zhang, Xiaoyan and Lin, Luotao and Ma, Jack and Eicher-Miller, Heather A. and Zhu, Fengqing},
  journal = {IEEE Transactions on Multimedia},
  year = {2025}
}

CVPR

CL-LoRA: Continual Low-Rank Adaptation for Rehearsal-Free Class-Incremental Learning

Jiangpeng He, Zhihao Duan, and Fengqing Zhu

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025

Bib PDF Code

@article{he_2025_cllora,
  title = {CL-LoRA: Continual Low-Rank Adaptation for Rehearsal-Free Class-Incremental Learning},
  author = {He, Jiangpeng and Duan, Zhihao and Zhu, Fengqing},
  journal = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  pages = {30534-30544},
  year = {2025}
}

CVPR

Gradient reweighting: Towards imbalanced class-incremental learning

Jiangpeng He

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024

Bib PDF Code

@article{he2024gradient,
  title = {Gradient reweighting: Towards imbalanced class-incremental learning},
  author = {He, Jiangpeng},
  journal = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  pages = {16668--16677},
  year = {2024}
}

CVPR

Towards Backward-Compatible Continual Learning of Image Compression

Zhihao Duan, Ming Lu, Justin Yang, Jiangpeng He^†, Zhan Ma, and Fengqing Zhu

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024

Bib PDF Code

@article{duan2024continual_compression,
  title = {Towards Backward-Compatible Continual Learning of Image Compression},
  author = {Duan, Zhihao and Lu, Ming and Yang, Justin and He, Jiangpeng and Ma, Zhan and Zhu, Fengqing},
  journal = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  pages = {25564--25573},
}

WACV

Online Class-Incremental Learning For Real-World Food Image Classification

Siddeshwar Raghavan, Jiangpeng He^†, and Fengqing Zhu

Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2024

Bib PDF

@article{raghavan2024online,
  title = {Online Class-Incremental Learning For Real-World Food Image Classification},
  author = {Raghavan, Siddeshwar and He, Jiangpeng and Zhu, Fengqing},
  journal = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)},
  pages = {8195--8204},
  year = {2024},
}

WACV

Online Continual Learning via Candidates Voting

Jiangpeng He, and Fengqing Zhu

Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2022

Bib PDF

@article{He_2022_WACV,
  author = {He, Jiangpeng and Zhu, Fengqing},
  title = {Online Continual Learning via Candidates Voting},
  journal = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)},
  year = {2022},
  pages = {3154-3163}
}

CVPR

Incremental learning in online scenario

Jiangpeng He, Runyu Mao, Zeman Shao, and Fengqing Zhu

Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (CVPR), 2020

Bib PDF

@article{he2020incremental,
  title = {Incremental learning in online scenario},
  author = {He, Jiangpeng and Mao, Runyu and Shao, Zeman and Zhu, Fengqing},
  journal = {Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (CVPR)},
  pages = {13926--13935},
  year = {2020}
}

Nutrients

Long-Tailed Food Classification

Jiangpeng He, Luotao Lin, Heather A. Eicher-Miller, and Fengqing Zhu

Nutrients, 2023

Bib PDF

@article{he2022long,
  author = {He, Jiangpeng and Lin, Luotao and Eicher-Miller, Heather A. and Zhu, Fengqing},
  title = {Long-Tailed Food Classification},
  journal = {Nutrients},
  volume = {15},
  year = {2023}
}

ICIP

Single-stage heavy-tailed food classification

Jiangpeng He, and Fengqing Zhu

2023

Oral

Bib PDF

@article{he2023single,
  highlight = {Oral},
  title = {Single-stage heavy-tailed food classification},
  author = {He, Jiangpeng and Zhu, Fengqing},
  booktitle = {2023 IEEE International Conference on Image Processing (ICIP)},
  pages = {1115--1119},
  year = {2023},
  organization = {IEEE}
}