Haoqi Fan

Researcher in Computer Vision
Facebook AI Research
E-mail: haoqifan [at] gmail [dot] com


About Me

Haoqi Fan is an AI Researcher who works on multimodal foundational models. He spent 7 years at Facebook AI Research (FAIR). He graduated from the Robotics Institute of Carnegie Mellon University. His research interests lie in computer vision and deep learning.

Recent News

  • May 2025: Released BAGEL for unified multimodal research and application, it quickly soared to the #1 trending model on Hugging Face. GitHub stars

    		•
  • Apr 2021: Released PyTorchVideo - a deep learning library for video understanding research.  GitHub stars

  • Jun 2020: Co-organized tutorials on Visual Recognition for Images, Video, and 3D at CVPR 2020 and ECCV 2020.

    		•
  • Nov 2019: Released PySlowFast codebase for video understanding research. GitHub stars

    		•
  • Nov 2019: Co-organized a tutorial on Images, Video, and 3D research and code at ICCV 2019.

    		•
  • June 2019: Won the 1st place of AVA video activity detection challenge at the International Challenge on Activity Recognition (ActvityNet) ICCV 2019.

    		•

    Selected Publications

    Emerging Properties in Unified Multimodal Pretraining
    Chaorui Deng∗, Deyao Zhu∗, Kunchang Li∗, Chenhui Gou∗, Feng Li∗, Zeyu Wang, Shu Zhong, Weihao Yu, Xiaonan Nie, Ziang Song, Guang Shi§, Haoqi Fan∗† Paper website code huggingface
    Scaling Language-Image Pre-training via Masking
    Yanghao Li*, Haoqi Fan*, Ronghang Hu*, Christoph Feichtenhofer†, Kaiming He†
    Arxiv, 2022
    Paper
    Masked Autoencoders As Spatiotemporal Learners
    Christoph Feichtenhofer*, Haoqi Fan*, Yanghao Li, Kaiming He
    NeurIPS, 2022
    Paper code
    Multiscale Vision Transformers
    Haoqi Fan*, Bo Xiong*, Karttikeya Mangalam*, Yanghao Li*, Zhicheng Yan, Jitendra Malik, Christoph Feichtenhofer
    ICCV, 2021
    Paper code
    Improved Multiscale Vision Transformers for Classification and Detection
    Yanghao Li, Chao-Yuan Wu, Haoqi Fan, Karttikeya Mangalam, Bo Xiong, Jitendra Malik, Christoph Feichtenhofer
    Tech Report, 2021
    Paper code
    Momentum contrast for unsupervised visual representation learning
    Kaiming He, Haoqi Fan, Yuxin Wu, Saining Xie, Ross Girshick
    Conference on Computer Vision and Pattern Recognition (CVPR), 2020 (Oral)
    Best Paper Nomination
    Paper code
    Improved Baselines with Momentum Contrastive Learning
    Xinlei Chen, Haoqi Fan, Ross Girshick, Kaiming He
    2-Page Tech Report, 2020
    Paper code
    On the Importance of Asymmetry for Siamese Representation Learning
    Xiao Wang*, Haoqi Fan*, Yuandong Tian, Daisuke Kihara, Xinlei Chen
    CVPR, 2022
    Paper code
    Slowfast networks for video recognition
    Christoph Feichtenhofer, Haoqi Fan, Jitendra Malik, Kaiming He
    International Conference on Computer Vision (ICCV), 2019 (Oral)
    Paper code
    Stacked Latent Attention for Multimodal Reasoning
    Haoqi Fan, Jiatong Zhou
    Conference on Computer Vision and Pattern Recognition (CVPR), 2018
    Paper
    Going deeper into first-person activity recognition
    Minghuang Ma, Haoqi Fan, Kris M. Kitani
    Conference on Computer Vision and Pattern Recognition (CVPR), 2016
    Paper

    Open Source Projects

    BAGEL: The Open-Source Unified Multimodal Model
    Chaorui Deng∗, Deyao Zhu∗, Kunchang Li∗, Chenhui Gou∗, Feng Li∗, Zeyu Wang, Shu Zhong, Weihao Yu, Xiaonan Nie, Ziang Song, Guang Shi§, Haoqi Fan∗† GitHub stars
    PySlowFast: video understanding codebase for state-of-the-art research
    Haoqi Fan, Yanghao Li, Wan-Yen Lo, Christoph Feichtenhofer
    GitHub stars
    PyTorchVideo: A Deep Learning Library for Video Understanding
    Haoqi Fan *, Tullie Murrell *,
    Heng Wang ‡, Kalyan Vasudev Alwala‡, Yanghao Li‡, Yilei Li‡, Bo Xiong ‡,
    Nikhila Ravi, Meng Li, Haichuan Yang, Jitendra Malik, Ross Girshick, Matt Feiszli,
    Aaron Adcock†, Wan-Yen Lo†, Christoph Feichtenhofer †
    GitHub stars Paper Post