Boqing Gong

Research Scientist


Boqing Gong is a research scientist at Google, Seattle. His research in machine learning and computer vision focuses on efficiency, generalization, and the visual analytics of objects, scenes, human activities, and their attributes. Before joining Google in 2019, he worked in Tencent and was a tenure-track Assistant Professor at the University of Central Florida (UCF). He received an NSF CRII award in 2016 and an NSF BIGDATA award in 2017, both of which were the first of their kinds ever granted to UCF. He received his Ph.D. in 2015 at the University of Southern California, where the Viterbi Fellowship partially supported his work.


Program co-chair for WACV'23. Tutorial co-chair for CVPR'22, Area chair for CVPR'20, '22, ECCV'20, ICML'19-22, NeurIPS'19-22, ICLR'21-22, ICCV'19-21, AISTATS'19, and WACV'18-20, Senior area chair (meta-reviewer) for AAAI'20-21. NSF Panelist. Reviewer for NeurIPS, ICML, CVPR, ICCV, ECCV, ICLR, AISTATS, T-PAMI, IJCV, JMLR, etc.

CVPR'17, '21 Outstanding Reviewer


Download CV

Recent talks

Read Slides

What's New

  • 2022
  • 2021
  • 2020
  • 2019
  • 2018
  • 2017
  • 2016
  • 2015
Check out our 2022 papers!
A short course on Transformer at ICASSP 2022

Check out our course webpage

Program co-chair for WACV 2023
Tutorial co-chair for CVPR 2022

Check out our blog post about the tutorial selection process

Area chair for NeurIPS 2022, ICML 2022, ICLR 2022, and CVPR 2022
Papers on mobile video networks, adversarial deep learning, and domain adaptation/generalization (2021)
IEEE CVPR 2021 Tutorial on "Long-Tailed Visual Recognition"
Invited speaker at the IEEE CVPR 2021 Workshop on Learning from Limited and Imperfect Data
Serving as an area chair for NeurIPS 2021, ICCV 2021, ICML 2021, and ICLR 2021
Serving on three NSF panels (2021)
Papers on adversarial deep learning, long-tailed classification, and domain adaptation (2020)
Invited Talks on "Towards Visual Recognition in the Wild: Long-Tailed Sources and Open Compound Targets" (06/2020)

Presented at CVPR 2020 Workshops on Learning from Imperfect Data and Adversarial Machine Learning in Computer Vision, respectively

read more
Invited Talks on "Long-Tailed Visual Recognition" (2020)

Presented at CVPR 2020 Area Chair Workshop and WACV 2020 Workshop on Vision Applications and Solutions to Biased or Scarce Data

read more
Serving as an area chair of NeurIPS 2020, CVPR 2020, ECCV 2020, ICML 2020, and WACV 2020 (02/2019)
Serving on two NSF panels (2020)
Papers published on adversarial attack, vision+language, domain adaptation, and reinforcement learning (2019)
Code released for our ICCV'19 paper on domain generalization (08/2019).
Code released for our ICCV'19 paper on domain adaptation (08/2019).
Code released for our ICML'19 paper on black-box adversarial attacks (05/2019). Congrats, Yandong and Lijun!
Data and code released for our CVPR'19 paper on open and long-tailed recognition (04/2019)
Code released for our NeurIPS'18 paper on policy transfer and adaptation (04/2019)
Area chair of NeurIPS'19, ICML'19, ICCV'19, and AISTATS'19 (02/2019)
NSF panelist (2019)
Nine Papers Published in 2018
12/2018: Talk at IEEE BIGDATA Workshop on Big Data Transfer Learning

"Curriculum Domain Adaptation: Using Simulation for Real".

read more: Slides
11/2018: Talk at INFORMS Special Session on Stochastic Optimization Methods and Approximation Theory in Machine Learning

"The Multiple Shades of Dropout for Discriminative and Generative Deep Neural Networks". Dropout, which independently zeros out the outputs of neurons at random, has become one of the most popular techniques in training deep neural networks due to its simplicity and remarkable effectiveness. This talk reveals multiple shades of dropout for both discriminative and generative deep neural networks, mainly covering our following works: [Li et al., NIPS'16] and [Wei, Gong, et al., ICLR'18].

read more: Slides
09/2018: Talk at ECCV Workshop on Visual Learning and Embodied Agents in Simulation Environments

"Domain Adaptation and Transfer: All You Need to Use Simulation 'for Real'". Domain adaptation from simulation to the real world, and vice versa, for semantic segmentation and learning policies.

read more: Slides
09/2018: Talk at ECCV Workshop on Compact and Efficient Feature Representation and Learning in Computer Vision

"Learning and Adapting from the Web for Visual Recognition".

read more: Slides
06/2018: Talk at CVPR The 2nd Workshop on Visual Understanding by Learning from Web Data

"Learning from Web Data and Adapting Beyond It", which inlcudes the Web data of 1) noisy labels, 2) accurate labels, and 3) multi-modalities by semi-supervised learning, curriculum learning, and kernel mean matching, respectively. It mainly covers our following works: [Ding et al., WACV'18], [Wei, Gong, et al., ICLR'18], [Gan et al., CVPR'18], [Zhang et al., ICCV'17], [Gan et al., ECCV'16], and [Sharghi et al., ECCV'16].

read more: Slides
05/2018: Be serving as an Area Chair for IEEE WACV 2019
01/2018: Joined Tencent AI Lab (Seattle)
Seven Papers Published in 2017

Two at CVPR, two at ICCV, two book chapters, and one at ACII.

read more
10/2017: Talk at Department of Computer Engineering, University of California at Santa Cruz

"Domain Adaptation for Robust Visual Recognition". It is about our following works: [Gong, et al., ICML'13], [Gan et al., ECCV'16], [Gan et al., CVPR'16], and [Zhang et al., ICCV'17].

read more: slides
08/2017: Received the Third NSF Award as a PI

"BIGDATA: IA: Distributed Semi-Supervised Training of Deep Models and Its Applications in Video Understanding" (transferred to Mubarak Shah and Liqiang Wang). This project investigates semi-supervised training of deep neural network models using large-scale labeled and unlabeled data in a distributed fashion.

read more
07/2017: Selected as One of the Outstanding Reviewers by the IEEE CVPR 2017 Organization Committee
05/2017: Received the Second Gift Grant from Adobe Research

for our researcho on "Face Detector Adaptation without Forgetting".

Served as a panelist for two NSF panels in 2016
Eight Papers Published in 2016

Three at IEEE CVPR, three at ECCV, one at NIPS, and one at Symposium Multemedia.

read more
10/2016: Received the Second NSF Award as a Co-PI

Project: "Collaborative Research: Florida-IT-Pathways to Success (Flit-Path)".

10/2016: Received a Gift Grant from Adobe Research

for our researcho on "User-Guided Visual Analytics".

09/2016: Talk at the Army Research Office / Information Science Institute Workshop on Multi-Modal Data Analysis for Human Activity Detection

"Domain Adaptation Approaches to Human Activity Detection, Recognition, and Summarization".

03/2016: Received My First NSF Award as a So-PI

"CRII: RI: Multi-Source Domain Generalization Approaches to Visual Attribute Detection". This project investigates how to accurately and robustly detect attributes from images (videos, and 3D data), with the goal of developing and publicly providing effective attribute detection tools.

read more
12/2015: Talk at the AI Seminar of Information Science Institute, University of Southern California
11/2015: Talk at the ICDM Workshop on Practical Transfer Learning

"Reshaping Datasets for Unsupervised Domain Adaptation", which is about our following works: [Gong et al., CVPR'12], [Gong, et al., ICML'13], and [Gong et al., NIPS'13].

read more: Slides
08/2015: Joined University of Central Florida as an Assistant Professor (tenure-track)
06/2015: Defended Ph.D. thesis


Ph.D. in Computer Science

University of Southern California

Visiting graduate student in Computer Science

University of Texas at Austin
Summer, 2012

Master of Philosophy in Information Engineering

The Chinese University of Hong Kong

Bachelor in Eletronic Information Engineering

University of Science and Technology of China


I am interested in developing novel algorithms to understand objects, human activities, scenes, and their attributes. I strive to understand the mathematical structures of research questions in order to develop effective and efficient algorithmic solutions, with strong analytical properties and compelling practical performance.

read more