Ju He

I am a second-year Computer Science Ph.D. student at Johns Hopkins University, where I am fortunate to be advised by Bloomberg Distinguished Professor Alan L. Yuille.

Before that, I received the B.S. in Computer Science from Peking University. I have also spent great time at ByteDance, SenseTime, and Momenta. I will spend my next summer at Meta as a Research Scientist Intern.

I'm exploring various learning-based computer vision problems. Currently, I am interested in image segmentation and egocentric vision.

Feel free to contact me through: jhe47@jh.edu.

Google Scholar  /  LinkedIn  /  GitHub

profile photo
Publications
PartImageNet: A Large, High-Quality Dataset of Parts
Ju He, Shuo Yang, Shaokang Yang, Adam Kortylewski, Xiaoding Yuan, Jie-Neng Chen, Shuai Liu, Cheng Yang, Qihang Yu, Alan Yuille
arXiv preprint, 2021
PDF / Code

TransMix: Attend to Mix for Vision Transformers
Jie-Neng Chen, Shuyang Sun, Ju He, Philip Torr, Alan Yuille, Song Bai
CVPR, 2022
PDF / Code

Learning from Temporal Gradient for Semi-supervised Action Recognition
Junfei Xiao, Longlong Jing, Lin Zhang, Ju He, Qi She, Zongwei Zhou, Alan Yuille, Yingwei Li
CVPR, 2022
PDF

ROBIN: A Benchmark for Robustness to Individual Nuisances in Real-World Out-of-Distribution Shifts
Bingchen Zhao, Shaozuo Yu, Wufei Ma, Mingxin Yu, Shenxiao Mei, Angtian Wang, Ju He, Alan Yuille, Adam Kortylewski
arXiv preprint, 2021
PDF / Project Page

Rethinking Re-Sampling in Imbalanced Semi-Supervised Learning
Ju He, Adam Kortylewski, Shaokang Yang, Shuai Liu, Cheng Yang, Changhu Wang, Alan Yuille
arXiv preprint, 2021
PDF / Code

TransFG: A Transformer Architecture for Fine-grained Recognition
Ju He, Jie-Neng Chen, Shuai Liu, Adam Kortylewski, Cheng Yang, Yutong Bai, Changhu Wang, Alan Yuille
AAAI, 2022
PDF / Code

Compositional Generative Networks and Robustness to Perceptible Image Changes
Adam Kortylewski, Ju He, Qing Liu, Christian Cosgrove, Chenglin Yang, Alan Yuille
CISS, 2021
PDF

COMPAS: Representation Learning with Compositional Part Sharing for Few-Shot Classification
Ju He, Adam Kortylewski, Alan Yuille
arXiv preprint, 2021
PDF

Semi-synthesis: A fast way to produce effective datasets for stereo matching
Ju He*, Enyu Zhou*, Liusheng Sun, Fei Lei, Chenyang Liu, Wenxiu Sun
CVPRW on Autonomous Driving, 2021
PDF

Compositional Convolutional Neural Networks: A Deep Architecture with Innate Robustness to Partial Occlusion
Adam Kortylewski, Ju He, Qing Liu, Alan Yuille
CVPR, 2020
PDF / Code / Supplementary / Video

POINT CLOUD ATTRIBUTE INPAINTING IN GRAPH SPECTRAL DOMAIN
Ju He, Zeqing Fu, Wei Hu, Zongming Guo
ICIP, 2019   Oral
PDF

Experience
  • Research Intern, ByteDance, Jan. 2021 - Present
  • Research Assistant, Johns Hopkins University, Sep. 2020 - Present
  • Research Intern, SenseTime Research, Jul. 2020 - Dec. 2020
  • Research Intern, Johns Hopkins University, Summer 2019
  • Research Assistant, Peking University, Sep. 2018 - Jun. 2020
  • Research Intern, Momenta, Jun. 2018 - Oct. 2018

Last update: Mar. 2022      Template