I am an Assistant Professor at the University of Michigan and a Research Scientist at Facebook AI Research (FAIR).
I'm broadly interested in computer vision and machine learning. My research involves visual reasoning, vision and language, image generation, and 3D reasoning using deep neural networks.
I received my PhD from Stanford University, advised by Fei-Fei Li.


PhD Students


University of Michigan

EECS 498/598: Deep Learning for Computer Vision [Fall 2019] [Fall 2020] [Winter 2022]
EECS 442: Computer Vision [Winter 2020] [Winter 2021]

Stanford University

CS 231N: Convolutional Neural Networks for Visual Recognition (2017 Lecture Videos)


Bootstrap Your Own Correspondences
Mohamed El Banani, Justin Johnson
ICCV 2021 (Oral)
PixelSynth: Generating a 3D-Consistent Experience from a Single Image
Chris Rockwell, David Fouhey, Justin Johnson
ICCV 2021
Rethinking "Batch" in BatchNorm
Yuxin Wu, Justin Johnson
arXiv 2021
UnsupervisedR&R: Unsupervised Point Cloud Registration via Differentiable Rendering
Mohamed El Banani, Luya Gao, Justin Johnson
CVPR 2021 (Oral)
CASTing Your Model: Learning to Localize Improves Self-Supervised Representations
CVPR 2021
VirTex: Learning Visual Representations from Textual Annotations
Karan Desai, Justin Johnson
CVPR 2021
Accelerating 3D Deep Learning with PyTorch3D
Nikhila Ravi, Jeremy Reizenstein, David Novotny, Taylor Gordon,
Wan-Yen Lo, Justin Johnson, Georgia Gkioxari
arXiv 2020
Temporal Reasoning via Audio Question Answering
Haytham Fayek, Justin Johnson
IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2020
SynSin: End-to-end View Synthesis from a Single Image
CVPR 2020 (Oral)
PHYRE: A New Benchmark for Physical Reasoning
NeurIPS 2019
Mesh R-CNN
Georgia Gkioxari, Jitendra Malik, Justin Johnson
ICCV 2019
On Network Design Spaces for Visual Recognition
ICCV 2019
HiDDeN: Hiding Data With Deep Networks
Jiren Zhu*, Russell Kaplan*, Justin Johnson, Li Fei-Fei
[* indicates equal contribution]
ECCV 2018
Image Generation from Scene Graphs
Justin Johnson, Agrim Gupta, Li Fei-Fei
CVPR 2018
Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks
CVPR 2018
Inferring and Executing Programs for Visual Reasoning
ICCV 2017 (Oral)
Characterizing and Improving Stability in Neural Style Transfer
ICCV 2017
CLEVR: A Diagnostic Dataset for
Compositional Language and Elementary Visual Reasoning
CVPR 2017
A Hierarchical Approach for Generating Descriptive Image Paragraphs
CVPR 2017 (Spotlight)
Visual Genome: Connecting Language and Vision
using Crowdsourced Dense Image Annotations
IJCV 2017
Perceptual Losses for Real-Time Style Transfer and Super-Resolution
Justin Johnson, Alexandre Alahi, Li Fei-Fei
ECCV 2016
DenseCap: Fully Convolutional Localization Networks for Dense Captioning
Justin Johnson*, Andrej Karpathy*, Li Fei-Fei
[* indicates equal contribution]
CVPR 2016 (Oral)
Visualizing and Understanding Recurrent Networks
Andrej Karpathy*, Justin Johnson*, Li Fei-Fei
[* indicates equal contribution]
ICLR Workshop 2016
Love Thy Neighbors: Image Annotation by Exploiting Image Metadata
Justin Johnson*, Lamberto Ballan*, Li Fei-Fei
[* indicates equal contribution]
ICCV 2015

Side Projects


A Torch implementation of the neural style transfer algorithm from the paper "A Neural Algorithm of Artistic Style" by Leon A. Gatys, Alexander S. Ecker, and Matthias Bethge.


Train character-level language models in torch, and sample from them to generate text. The language model is implemented with efficient, reusable RNN and LSTM modules.


A micro-framework that makes it easy to create and launch tasks on Amazon's Mechanical Turk.


Benchmarks for popular convolutional neural network models on different GPUs.