Junfeng He

Short bio

Junfeng He is a research scientist in Google Research. He got his bachelor and master degree from Tsinghua University, and PhD from Columbia University.
His full publication list can be found in google scholar page

Research areas

His major research areas include computer vision, machine learning, search/retrieval/ranking, HCI, and health. He has >15 years research experience on image retrieval&classification, image editing and its detection, ranking, large scale (approximate) machine learning, etc.
His current research interest is the intersection of computer vision and human vision/perception, for instance

using computer vision techniques to model and understand human gaze/attention/perception

applications of human perception/attention modeling especially related to health/education/social-good/improving-user-experience

leveraging human vision/perception to inspire and improve computer vision models/systems

related trustworthy ML problems such as privacy/fairness/interpretation, etc.

Recent research papers

Modeling of gaze tracking and its applications

Accelerating eye movement research via accurate and affordable smartphone eye tracking, N Valliappan, N Dai, E Steinberg, J He, K Rogers…, Nature Communications, 2020

On-Device Few-Shot Personalization for Real-Time Gaze Estimation, Junfeng He, Khoi Pham, Nachiappan Valliappan, Pingmei Xu, Chase Roberts, Dmitry Lagun, Vidhya Navalpakkam, ICCV 2019 GAZE workshop , Best paper

Gazegan-unpaired adversarial image generation for gaze estimation, M Sela, P Xu, J He, V Navalpakkam, D Lagun, arXiv preprint arXiv:1711.09767, 2017

Modeling of human attention/perception/vision and its applications

, Learning from Unique Perspectives: User-aware Saliency Modeling, Shi Chen, Nachiappan Valliappan, Shaolei Shen, Xinyu Ye, Kai J Kohlhoff, Junfeng He⁺, CVPR 2023

Deep Saliency Prior for Reducing Visual Distraction, Kfir Aberman*, Junfeng He*, Yossi Gandelsman, Inbar Mosseri, David E Jacobs, Kai Kohlhoff, Yael Pritch, Michael Rubinstein, CVPR 2022

Leverage human vision/perception to improve computer vision

, Teacher-generated spatial-attention labels boost robustness and accuracy ofcontrastive models, Yushi Yao*, Chang Ye*, Junfeng He⁺, Gamaleldin Fathy Elsayed⁺, CVPR 2023

Teacher-generated pseudo human spatial-attention labels boost contrastive learning models>, Yushi Yao, CHANG YE, Junfeng He, Gamaleldin Fathy Elsayed, SVRHM Workshop@ NeurIPS 2022

Related trustworthy ML problems

Differentially Private Heatmaps, Badih Ghazi, Junfeng He, Kai Kohlhoff, Ravi Kumar, Pasin Manurangsi, Vidhya Navalpakkam, Nachiappan Valliappan, AAAI 2023

Media coverage

Leverage human attention/saliency models to improve JPEG XL compression

Google Opensource Blogpost for using saliency in JPEG XL

Google Opensource Blogpost for oepn sourcing attention center model (and its application in JPEG XL)

Awards

Publication&OpenSourcing Excellence Award , Perira org, Google Research, 2021

Best Paper Award , ICCV GAZE workshop, 2019