About

I am a PhD student in the Stanford Vision Lab, advised by Professor Fei-Fei Li .
I'm mainly interested in deep learning, especially applied to computer vision.

Publications

A Hierarchical Approach for Generating Descriptive Image Paragraphs
Jonathan Krause, Justin Johnson, Ranjay Krishna, Li Fei-Fei
arXiv 2016
Perceptual Losses for Real-Time Style Transfer and Super-Resolution
Justin Johnson, Alexandre Alahi, Li Fei-Fei
ECCV 2016
Visual Genome: Connecting Language and Vision
using Crowdsourced Dense Image Annotations
Ranjay Krishna, Yuke Zhu, Oliver Groth, Justin Johnson,
Kenji Hata, Joshua Kravitz, Stephanie Chen, Yannis Kalantidis,
Li-Jia Li, David A. Shamma, Michael S. Bernstein, Li Fei-Fei
IJCV 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
Image Retrieval using Scene Graphs
Justin Johnson, Ranjay Krishna, Michael Stark, Li-Jia Li, David Ayman Shamma, Michael Bernstein, Li Fei-Fei
CVPR 2015

Projects

neural-style

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.

cnn-vis

A tool to use convolutional neural networks to generate images, inspired by Google's Inceptionism.

torch-rnn

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.

simple-amt

A micro-framework I built to make it easier to create and launch tasks on Amazon's Mechanical Turk.

cnn-benchmarks

Benchmarks for popular convolutional neural network models on different GPUs.

Teaching

Winter 2015-2016:

I am co-teaching CS 231n: Convolutional Neural Networks for Visual Recognition.

Winter 2014-2015:

I was a teaching assistant for CS 231n: Convolutional Neural Networks for Visual Recognition.

Fall 2013-2014:

I was a teaching assistant for CS 131: Computer Vision: Foundations and Applications.
This was an undergrad-level course intended to introduce the basics of computer vision.