About AIMIA

Artificial Intelligence & Medical Image Analysis Lab

The Group Artificial Intelligence and Medical Image Analysis (AIMIA) belongs to the Digital Media Research Center of Peking University, guided by Dr. Chen Jie, the associate professor of the School of Electronic and Computer Engineering of Peking University.

AIMIA has established cooperative relationships with other research groups, including international research groups, in the Digital Media Research Center of Peking University, as well as in Pengcheng Laboratory and Shenzhen Bay Laboratory.

Our research focuses on Multimodal Large Language Model (MLLM), Artificial Intelligence-Generated Content (AIGC), Embodied AI and AI for science.

Multimodal Large Language Model (MLLM)

Multimodal Large Language Models (MLLM) are advanced artificial intelligence models designed to understand and process multiple modalities, including text, images, audio, etc. By applying deep learning techniques and large sets of data for training, these models are able to figure out patterns and relationships between models.

Application Area 1: Natural Language Processing
- NLP model structure innovation
- Learning Feedback Enhancement
- Distributed Training
- Model Optimization
- Other related technologies.

Application Area 2: Computer Vision and Pattern Recognition
- Image Segmentation and Classification
- Image Semantic Understanding
- Semi-supervised Learning
- Weakly Supervised Learning, etc.

Application Area 3: Multimodal and Multi-perspective Learning
Explore how to combine multiple sources of information and learn information in datasets from multiple perspectives. These applications include graphic retrieval, 3D object detection, machine translation, etc.

Application Area 4: Medical Image Analysis
The purpose of Medical Image Analysis is to detect the interest areas and targets in medical images qualitatively or quantitatively, and to explore the connotation of images, so as to provide information reference for clinicians or researchers. The main research fields include image classification and segmentation, disease diagnosis, image registration, medical report generation, etc. 

AIGC:AI Generated Content

AIGC aims at using artificial intelligence algorithms to generate content with certain creativity and quality. It applies model training and data learning to generate content based on input criteria and guidance. For instance, if we input keywords, descriptions or samples, AIGC will generate articles, images, audio, etc. accordingly.

Embodied Intelligence: Embodied AI

Embodied intelligence is a subfield of AI research. It focuses on enabling intelligent systems to perceive, understand, and engage with their environment through actual interaction. Embodied intelligence aims to integrate sensors, action mechanisms, and decision-making capabilities to enable intelligent systems to act and interact with the physical world as humans do.

By blending perception, cognition, and behavior, embodied intelligence models are able to learn the structure and rules of the environment and take appropriate actions. This comprehensive approach allows embodied intelligence to be applied to robotics, autonomous vehicles, augmented reality and more, facilitating closer interaction and cooperation between intelligent systems and the human environment.

AI for Science

AI for Science means pre-training models with strong generalization capabilities, thus enabling them to tackle multiple downstream tasks related to major bottlenecks in science, which include controllable targeted peptide design, virus mutation prediction, antibody generation and key property prediction, protein structure prediction, RNA structure and function prediction, etc.

Recent News

  • New Accepted Papers:
    Jul.2024 1 paper accepted to IJCV. Con![Pengchong Qiao]
    Jul.2024 4 papers accepted to ECCV. Con![Peng Jin, Mengjun Cheng, Qiran Zou, Kehan Li]
    Jun.2024 1 paper accepted to IEEE TMI. Con![Shiyu Li].
    Mar.2024 1 paper selected as CVPR Highlight paper. Con![Yian Zhao].
    Feb.2024 3 papers accepted to CVPR. Con![Pengchong Qiao, Yian Zhao].
    Jan.2024  1 paper accepted to ICLR. Con![Zhilin Huang].
    Dec.2023  1 paper accepted to AAAI. Con![Zesen Cheng].
    Oct.2023 1 paper accepted to Nucleic Acids Research. Con![Yikun Zhang].
    Sep.2023 1 paper accepted to NeurIPS. Con![Yu Wang].
    Sep.2023 1 paper accepted to IEEE TMM. Con![Yiming Liu].
    Jul.2023 5 papers accepted to ICCV. Con![Pengxu Wei, Yujing Sun, Peng Jin, Kehan Li, Hongliang He, Jun Wang, Runyi Yu].
    Jun.2023 1 paper recognized as ICASSP top 3% paper. Con![Bin Fu].
    Apr.2023 1 paper accepted to IEEE TIP. Con![Hao Li].
    Apr.2023 3 papers accepted to IJCAI. Con![Peng Jin, Hao Li, Zesen Cheng].
    Mar.2023  3 papers selected as CVPR Highlight paper. Con![Peng Jin, Kehan Li, Haoliang Zhao].
    Feb.2023  6 papers accepted to CVPR. Con![Pengchong Qiao, Zesen Cheng, Peng Jin, Kehan Li, Yu Wang, Haoliang Zhao].
    Feb.2023  2 papers accepted to ICASSP. Con![Jifan Zhang, Bin Fu].
  • Pengcheng Shennong shortlisted for the ACM Gordon Bell Special Prize for HPC-Based COVID-19 Research (the only project from the Chinese team shortlisted this time) !!
    About Pengcheng Shennong:https://aigene.cloudbrain2.pcl.ac.cn
    About ACM Gordon Bell Prize: See Pubulications.

Team

Mobirise Website Builder
Jie Chen (陈杰)
Associate professor

Research interest: Computer vision and pattern recognition; AI4Science; Natural language processing; Medical image analysis.

Email:jiechen2019 at pku dot edu dot cn

Full-Width Gallery

Ph.D Students
Mobirise Website Builder
Zhiwei Nie

Deep Learning, AI for Science, Bioinformatics

Mobirise Website Builder
Pengchong Qiao

Semi-supervised Learning,
Computer Vision

Mobirise Website Builder
Mengjun Cheng

Segmentation, Cross-modal, Deep Learning

Mobirise Website Builder
Zesen Cheng

Computer Vision,
Image Segmentation

Full-Width Gallery

Master's Students
Mobirise Website Builder
Hao Li
Master (2021)

Visual Question Answering,
Scene-Text based VQA

Mobirise Website Builder
Peng Jin
Master (2021)

Text-Video Retrieval

Mobirise Website Builder
Runyi Yu
Master (2021)

Computer Vision

Mobirise Website Builder
Yujing Sun
Master (2021)

Image Restoration,
Super-resolution

Mobirise Website Builder
Kehan Li
Master (2021)

Computer Vision,
Image Segmentation

Mobirise Website Builder
Zhuo Leng
Master (2021)

Detection and Segmentation

Mobirise Website Builder
Qiankun Ma
Master (2022)

Deep Learning,
Semi-supervised Learning

Mobirise Website Builder
Yu Wang
Master (2022)

Computer Vision,
Semi-supervised Learning

Mobirise Website Builder
Jun Wang 
Master (2022)

Computer Vision,
Medical Image Analysis

Mobirise Website Builder
Yikun Zhang
Master (2022)

Bioinformatics,
AI for Science

Mobirise Website Builder
Yihan Zhang
Master (2022)

Bioinformatics,
AI for Science

Mobirise Website Builder
Shiyu Li
Master (2022)

Medical Report Generation

Mobirise Website Builder
Luna Wang
Master (2023)

Computer Vision,
Image Segmentation

Mobirise Website Builder
Yuke Li
Master (2023)

Multi-modal,
Deep Learning

Mobirise Website Builder
Rushi Ye
Master (2023)

 Computer Vision,
 AIGC

Mobirise Website Builder
Yian Zhao
Master (2023)

Object Detection,
Image Segmentation

Mobirise Website Builder
Yiming Ma
Master (2023)

Deep learning

Mobirise Website Builder
Xudong Liu
Master (2023)

Deep learning,
NLP

Alumni

  • PostDoc:
    Zhiqiang Gao (SenseTime Shanghai), Zhennan Wang (Haomo)
  • Ph.D:
    Yimo Guo (Siemens USA), Xiaobai Li(Finland), Wei Ke (Xi'an Jiaotong University), Qing Liu (Central South University), Na Liu (Tianjin University of Technology), Boyu Yang (Huawei), Ruiping Wang(Institute of Computing Technology, Chinese Academy of Sciences), Hongliang He (Suzhou University)
  • Master:
    2017 fall:Lun Huang (Duke University, outstanding graduate of Peking University, outstanding graduate of Beijing), Yaxian Xia (Alibaba), Qian Wu (NetEASE)
    2018 fall:Ruizhe Geng (Bilibili), Zhongyi Huang(Tencent)
    2019 fall:Chi Zhang (Tencent), ShuboWang (Alibaba), Zishang Kong,Lin Wang (Microsoft), Qian Ren,Weifeng Zhang (Tencent), Chong Zhang (Jingdong), Liwen Zhu (Tencent), Zhaodong Kang (Baidu)
    2020 fall: Yan Ren (Public Institution), Bin Fu (Huawei), Zhidan Wei (Local Government), Jinhua Huang (University of Rochester), Yalu Cheng (Local Government), Jifan Zhang

Honors & Distinctions

> Finalist for the 2022 "Gordon Bell New Crown Special Award" (The finalist only contains three teams in the world. AIMIA is the only Chinese team in the finalist.)
> First place in CAMEO 2022, an internationally renowned protein structure prediction competition
> The second Prize of National Science and Technology Progress Award in 2015: Local Modeling of Visual Patterns and Nonlinear Feature Acquisition Theory and Method 
> The second prize of National Science and Technology Progress Award in 2005: Face Recognition Theory, Technology, System and Application
> The first prize of the Face verification competition of the First China Biometrics Competition (BVC2004)
> First place in the IAPR ICB 2006 Face Verification Competition, organized by Josef Kittler of the University of Surrey, UK

Openings

We welcome undergraduates and graduate students who are interested in scientific research and have strong ability to withstand pressure to apply for master’s degree and doctor’s degree in the School of Electronic and Computer Engineering of Peking University to engage in Computer Vision /AI for Science/ AIGC related research. (Click here for admission information)

Contacts

jiechen2019 at pku dot edu dot cn
lijx at pkusz dot edu dot cn

Peking University Shenzhen Graduate School
No. 2199 Lishui Road, Nanshan District, Shenzhen

AI Website Software