Mingfei Chen

I am a first-year Ph.D. student in the Electrical and Computer Engineering department at University of Washington, Seattle. Currently, I am a member of NeuroAI Lab advised by Prof. Eli Shlizerman, focusing on the audio-visual learning, as well as the related applications.

Before that, I recieved my B.S. degree from the Computer Science and Technology department of Huazhong University of Science and Technology of China in 2020. I am also lucky to work on language-guided video retrieval with Prof. Chang Wen Chen and Prof. Junsong Yuan, human detection and segmentation in Bytedance AI Lab, human-object interaction (HOI) with Prof. Si Liu, multiple-object tracking (MOT) with Prof. Jenq-Neng Hwang in IPL lab, and 3D photo-realistic digital human rendering with Prof. Shuicheng Yan and Prof. Jiashi Feng in Sea AI Lab.

I'm currently looking for research intern roles for Summer 2024!

Email  /  CV  /  Google Scholar  /  Github  /  LinkedIn  /  Twitter

profile photo
News

  • [Sep. 2023] Present at ICCV2023 AV4D workshop!
  • [Sep. 2023] Start my Ph.D journey at UW ECE department, NeuroAI Lab!
  • [Jul. 2023] One first-author paper on audio-visual learning got accepted by ICCV2023!
  • [Sep. 2022] One co-first author paper on implicit neural acoustic fields got accepted by NeurIPS2022!
  • [Jul. 2022] One first-author paper on 3D photo-realistic digital human rendering got accepted by ECCV2022!
  • [Jan. 2022] Join NeuroAI Lab, work with Prof. Eli Shlizerman on audio-visual related research.
  • [Sep. 2021] Join ECE department at University of Washington, Seattle, as a master student.
  • [Jun. 2021] Join Sea AI Lab and NUS Learning and Vision Lab as research intern, work with Prof. Shuicheng Yan and Prof. Jiashi Feng on 3D photo-realistic digital human rendering.
  • [Mar. 2021] One first-author paper on human-object interaction got accepted by CVPR2021!
  • [Jul. 2020] Join Sensetime Research as research intern, work on human-object interaction.
  • [Jun. 2020] My thesis on Language-guided Video Retrieval was awarded with Outstanding undergraduate graduation thesis of Huazhong University of Science and Technology!
  • [Sep. 2019] Join Bytedance AI Lab as Computer Vision Algorithm Intern.
  • [Jul. 2019] Join CUHK (Shenzhen) as research assistant, work with Prof. Chang Wen Chen and Prof. Junsong Yuan on Language-guided Video Retrieval.
  • Research
    Be Everywhere - Hear Everything (BEE): Audio Scene Reconstruction by Sparse Audio-Visual Samples
    Mingfei Chen, Kun Su, Eli Shlizerman
    International Conference on Computer Vision (ICCV), 2023
    paper / bibtex / poster / video / [Code Coming Soon]

    We introduce a novel method and end-to-end integrated rendering pipeline which allows the listener to be everywhere and hear everything (BEE) in a dynamic scene in real time, based on sparse audio-visual samples.

    INRAS: Implicit Neural Representation for Audio Scenes
    Kun Su*, Mingfei Chen*, Eli Shlizerman
    Neural Information Processing Systems (NeurIPS), 2022
    paper / bibtex / poster / video / supplementary with code

    We propose an Implicit Neural Representation for Audio Scenes, INRAS, for efficient representation of spatial audio fields with high fidelity.

    Geometry-Guided Progressive NeRF for Generalizable and Efficient Neural Human Rendering
    Mingfei Chen, Jianfeng Zhang, Xiangyu Xu, Lijuan Liu, Yujun Cai, Jiashi Feng, Shuicheng Yan
    European Conference on Computer Vision (ECCV), 2022
    paper / bibtex / poster / video / code

    We develop a geometry-guided generalizable and efficient Neural Radiance Field (NeRF) pipeline for high-fidelity free-viewpoint human body synthesis under settings with sparse camera views.

    TR-MOT: Multi-Object Tracking by Reference
    Mingfei Chen, Yue Liao, Si Liu, Fei Wang, Jenq-Neng Hwang
    arxiv preprint, 2022
    arXiv / bibtex

    We propose a novel Reference Search (RS) module to provide a more reliable association based on the deformable transformer structure, which is natural to learn the feature alignment for each object among frames.

    Reformulating HOI Detection As Adaptive Set Prediction
    Mingfei Chen*, Yue Liao*, Si Liu, Zhiyuan Chen, Fei Wang, Chen Qian
    Computer Vision and Pattern Recognition (CVPR), 2021
    paper / bibtex / poster / code

    We reformulate HOI detection as an adaptive set prediction problem, with this novel formulation, we propose an Adaptive Set-based one-stage framework (AS-Net) with parallel instances and interaction branches.

    Graduate Teaching

  • [Spring 2022 TA] UW EE 596: Introduction to Deep Learning Applications and Theory (website).
  • [Winter & Spring 2023 TA] UW EE 497/498/598: Engineering Entrepreneurial Capstone (website).
  • Services

  • Reviewer for: AAAI-23, AAAI-24.
  • Student organizer for: University of Washington NeuroAI Seminar.
  • Session chair for: ICCV2023 AV4D workshop.
  • Awards & Honors

  • [2020] Huazhong University of Science and Technology Outstanding undergraduate graduation thesis.
  • [2018, 2019] Huazhong University of Science and Technology Merit Student Scholarship.
  • [2018] Meritorious Winner of Mathematical Contest In Modeling (MCM/ICM).
  • [2018] Excellent Team Prize of Central & Southern China District of Future Lab Image Recognition Algorithm Competition.
  • [2017] Huazhong University of Science and Technology Undergraduate Excellent Student (Top 1% in 35000).