I am a software engineer at Google DeepMind where I work on research projects in computer vision and machine learning. My work has been productized into Google Photos and Waymo. Before joining Google Research, I worked as an applied scientist in AWS Rekognition.

I obtained my PhD at Department of Computer Science, University of Maryland, College Park supervied by Prof. David W. Jacobs in 2019. Before that, I received an M.Phil. from the University of Hong Kong under supervision of Dr. Kenneth K.Y. Wong in 2012, and a B.Eng in the University of Science and Technology of China in 2010.

During my PhD studies, I was lucky to join Adobe Research, NEC Labs America and National ICT (NICTA) Australia as a research intern.

Selected Publications

full list

Videoprism: A Foundational Visual Encoder for Video Understanding.
Long Zhao, Nitesh B. Gundavarapu, Liangzhe Yuan, Hao Zhou, Luke Friedman, Rui Qian, Tobias Weyand, Yue Zhao, Rachel Hornung, David A. Ross, Huisheng Wang, Hartwig Adam, Mikhail Sirotenko, Shen Yan, Jennifer J. Sun, Florian Schroff, Ming-Hsuan Yang, Ting Liu and Boqing Gong.
ICML, 2024.

VideoGLUE: Video General Understanding Evaluation of Foundation Models.
Liangzhe Yuan, Nitesh Bharadwaj Gundavarapu, Long Zhao, Hao Zhou, Yin Cui, Lu Jiang, Xuan Yang, Menglin Jia, Tobias Weyand, Luke Friedman, Mikhail Sirotenko, Huisheng Wang, Florian Schroff, Hartwig Adam, Ming-Hsuan Yang, Ting Liu and Boqing Gong.
Arxiv, 2023.

Towards Regression-Free Neural Networks for Diverse Compute Platforms.
Rahul Duggal, Hao Zhou, Shuo Yang, Jun Fang, Yuanjun Xiong and Wei Xia.
ECCV, 2022.

Compatibility-aware Heterogeneous Visual Search.
Rahul Duggal, Hao Zhou, Shuo Yang, Yuanjun Xiong, Wei Xia, Zhuowen Tu, Stefano Soatto.
CVPR, 2021. Coverd by Graceful AI

Deep Single-Image Portrait Relighting.
Hao Zhou, Sunil Hadap, Kalyan Sunkavalli and David W. Jacobs
ICCV, 2019. Porject Coverd by Two Minutes Paper

GLoSH: Global-Local Spherical Harmonics for Intrinsic Image Decomposition.
Hao Zhou, Xiang Yu and David W. Jacobs
ICCV, 2019. (Oral)

Label Denoising Adversarial Network (LDAN) for Inverse Lighting of Faces.
Hao Zhou, Jin Sun, Yaser Yacoob and David W. Jacobs
CVPR, 2018. (Spotlight)

Less is More: Towards Compact CNNs.
Hao Zhou, Jose M. Alvarez and Fatih Porikli.
ECCV, 2016. (Spotlight)

Markov Weight Fields for Face Sketch Synthesis.
Hao Zhou, Zhanghui Kuang and Kwan-Yee K. Wong.
CVPR, 2012.

Dissertation

Using CNNs to Understand Lighting Without Real Labeled Training Data.
Hao Zhou
University of Maryland, College Park, Aug 2019.