Boqing Gong

is this you? claim profile

∙ 0 followers
Google ∙ University of Southern California ∙ Microsoft ∙ University of Central Florida

Principal Researcher in Tencent AI Lab at Seattle, Assistanf Professor at University of Florida from 2015 to 2017

Featured Co-authors

Jiebo Luo
140 publications
Li Zhang
131 publications
Alan Yuille
125 publications
Ming-Hsuan Yang
115 publications
Stefano Ermon
112 publications
Yang Zhang
110 publications
Cho-Jui Hsieh
99 publications
Tong Zhang
99 publications
Joshua B. Tenenbaum
98 publications
Dong Yu
94 publications
Cordelia Schmid
92 publications

VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text

We present a framework for learning multimodal representations from unla...
04/22/2021 ∙ by Hassan Akbari, et al. ∙ 21 ∙ share

read it
Class-Balanced Distillation for Long-Tailed Visual Recognition

Real-world imagery is often characterized by a significant imbalance of ...
04/12/2021 ∙ by Ahmet Iscen, et al. ∙ 20 ∙ share

read it
Robust and Accurate Object Detection via Adversarial Learning

Data augmentation has become a de facto component for training high-perf...
03/23/2021 ∙ by Xiangning Chen, et al. ∙ 10 ∙ share

read it
MoViNets: Mobile Video Networks for Efficient Video Recognition

We present Mobile Video Networks (MoViNets), a family of computation and...
03/21/2021 ∙ by Dan Kondratyuk, et al. ∙ 6 ∙ share

read it
A Simple and Effective Use of Object-Centric Images for Long-Tailed Object Detection

Object frequencies in daily scenes follow a long-tailed distribution. Ma...
02/17/2021 ∙ by Cheng Zhang, et al. ∙ 14 ∙ share

read it
Large-Scale Meta-Learning with Continual Trajectory Shifting

Meta-learning of shared initialization parameters has shown to be highly...
02/14/2021 ∙ by Jaewoong Shin, et al. ∙ 5 ∙ share

read it
Contrastive Learning for Label-Efficient Semantic Segmentation

Collecting labeled data for the task of semantic segmentation is expensi...
12/13/2020 ∙ by Xiangyun Zhao, et al. ∙ 13 ∙ share

read it
Ranking Neural Checkpoints

This paper is concerned with ranking many pre-trained deep neural networ...
11/23/2020 ∙ by Yandong Li, et al. ∙ 2 ∙ share

read it
Improving Object Detection with Selective Self-supervised Self-training

We study how to leverage Web images to augment human-curated object dete...
07/17/2020 ∙ by Yandong Li, et al. ∙ 32 ∙ share

read it
Complete Label: A Domain Adaptation Approach to Semantic Segmentation of LiDAR Point Clouds

We study an unsupervised domain adaptation problem for the semantic labe...
07/16/2020 ∙ by Li Yi, et al. ∙ 0 ∙ share

read it
Smooth Adversarial Training

It is commonly believed that networks cannot be both accurate and robust...
06/25/2020 ∙ by Cihang Xie, et al. ∙ 13 ∙ share

read it
When Ensembling Smaller Models is More Efficient than Single Large Models

Ensembling is a simple and popular technique for boosting evaluation per...
05/01/2020 ∙ by Dan Kondratyuk, et al. ∙ 22 ∙ share

read it
Neural Networks Are More Productive Teachers Than Human Raters: Active Mixup for Data-Efficient Knowledge Distillation from a Blackbox Model

We study how to train a student deep neural network for visual recogniti...
03/31/2020 ∙ by Dongdong Wang, et al. ∙ 2 ∙ share

read it
Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition from a Domain Adaptation Perspective

Object frequency in the real world often follows a power law, leading to...
03/24/2020 ∙ by Muhammad Abdullah Jamal, et al. ∙ 5 ∙ share

read it
MACER: Attack-free and Scalable Robust Training via Maximizing Certified Radius

Adversarial training is one of the most popular ways to learn robust mod...
01/08/2020 ∙ by Runtian Zhai, et al. ∙ 4 ∙ share

read it
Look, Listen, and Act: Towards Audio-Visual Embodied Navigation

A crucial aspect of mobile intelligent agents is their ability to integr...
12/25/2019 ∙ by Chuang Gan, et al. ∙ 2 ∙ share

read it
Adversarial Examples Improve Image Recognition

Adversarial examples are commonly viewed as a threat to ConvNets. Here w...
11/21/2019 ∙ by Cihang Xie, et al. ∙ 24 ∙ share

read it
Compound Domain Adaptation in an Open World

Existing works on domain adaptation often assume clear boundaries betwee...
09/08/2019 ∙ by Ziwei Liu, et al. ∙ 5 ∙ share

read it
Domain Randomization and Pyramid Consistency: Simulation-to-Real Generalization without Accessing Target Domain Data

We propose to harness the potential of simulation for the semantic segme...
09/02/2019 ∙ by Xiangyu Yue, et al. ∙ 7 ∙ share

read it
Constructing Self-motivated Pyramid Curriculums for Cross-Domain Semantic Segmentation: A Non-Adversarial Approach

We propose a new approach, called self-motivated pyramid curriculum doma...
08/26/2019 ∙ by Qing Lian, et al. ∙ 13 ∙ share

read it
A Fast and Accurate One-Stage Approach to Visual Grounding

We propose a simple, fast, and accurate one-stage approach to visual gro...
08/18/2019 ∙ by Zhengyuan Yang, et al. ∙ 1 ∙ share

read it
Defending Against Adversarial Attacks Using Random Forests

As deep neural networks (DNNs) have become increasingly important and po...
06/16/2019 ∙ by Yifan Ding, et al. ∙ 1 ∙ share

read it
NATTACK: Learning the Distributions of Adversarial Examples for an Improved Black-Box Attack on Deep Neural Networks

Powerful adversarial attack methods are vital for understanding how to c...
05/01/2019 ∙ by Yandong Li, et al. ∙ 10 ∙ share

read it
Large-Scale Long-Tailed Recognition in an Open World

Real world data often have a long-tailed and open-ended distribution. A ...
04/10/2019 ∙ by Ziwei Liu, et al. ∙ 10 ∙ share

read it
Synthesized Policies for Transfer and Adaptation across Tasks and Environments

The ability to transfer in reinforcement learning is key towards buildin...
04/05/2019 ∙ by Hexiang Hu, et al. ∙ 6 ∙ share

read it
Joint Modeling of Dense and Incomplete Trajectories for Citywide Traffic Volume Inference

Real-time traffic volume inference is key to an intelligent city. It is ...
02/25/2019 ∙ by Xianfeng Tang, et al. ∙ 6 ∙ share

read it
A Curriculum Domain Adaptation Approach to the Semantic Segmentation of Urban Scenes

During the last half decade, convolutional neural networks (CNNs) have t...
12/24/2018 ∙ by Yang Zhang, et al. ∙ 0 ∙ share

read it
Classifier and Exemplar Synthesis for Zero-Shot Learning

Zero-shot learning (ZSL) enables solving a task without the need to see ...
12/16/2018 ∙ by Soravit Changpinyo, et al. ∙ 0 ∙ share

read it
Controllable Image-to-Video Translation: A Case Study on Facial Expression Generation

The recent advances in deep learning have made it possible to generate p...
08/09/2018 ∙ by Lijie Fan, et al. ∙ 6 ∙ share

read it
Improving Sequential Determinantal Point Processes for Supervised Video Summarization

It is now much easier than ever before to produce videos. While the ubiq...
07/28/2018 ∙ by Aidean Sharghi, et al. ∙ 4 ∙ share

read it
Optimize Deep Convolutional Neural Network with Ternarized Weights and High Accuracy

Deep convolution neural network has achieved great success in many artif...
07/20/2018 ∙ by Zhezhi He, et al. ∙ 2 ∙ share

read it
Defend Deep Neural Networks Against Adversarial Examples via Fixed andDynamic Quantized Activation Functions

Recent studies have shown that deep neural networks (DNNs) are vulnerabl...
07/18/2018 ∙ by Adnan Siraj Rakin, et al. ∙ 2 ∙ share

read it
How Local is the Local Diversity? Reinforcing Sequential Determinantal Point Processes with Dynamic Ground Sets for Supervised Video Summarization

The large volume of video content and high viewing frequency demand auto...
07/11/2018 ∙ by Yandong Li, et al. ∙ 8 ∙ share

read it
End-to-End Learning of Motion Representation for Video Understanding

Despite the recent success of end-to-end learned representations, hand-c...
04/02/2018 ∙ by Lijie Fan, et al. ∙ 0 ∙ share

read it
End-to-End Video Captioning with Multitask Reinforcement Learning

Although end-to-end (E2E) learning has led to promising performance on a...
03/21/2018 ∙ by Lijun Li, et al. ∙ 0 ∙ share

read it
Improving the Improved Training of Wasserstein GANs: A Consistency Term and Its Dual Effect

Despite being impactful on a variety of problems and applications, the g...
03/05/2018 ∙ by Xiang Wei, et al. ∙ 0 ∙ share

read it
A Semi-Supervised Two-Stage Approach to Learning from Noisy Labels

The recent success of deep neural networks is powered in part by large-s...
02/08/2018 ∙ by Yifan Ding, et al. ∙ 0 ∙ share

read it
Blind Pre-Processing: A Robust Defense Method Against Adversarial Examples

Deep learning algorithms and networks are vulnerable to perturbed inputs...
02/05/2018 ∙ by Adnan Siraj Rakin, et al. ∙ 0 ∙ share

read it
Robust Pre-Processing: A Robust Defense Method Against Adversary Attack

Deep learning algorithms and networks are vulnerable to perturbed inputs...
02/05/2018 ∙ by Adnan Siraj Rakin, et al. ∙ 0 ∙ share

read it
VQS: Linking Segmentations to Questions and Answers for Supervised Attention in VQA and Question-Focused Semantic Segmentation

Rich and dense human labeled datasets are among the main enabling factor...
08/15/2017 ∙ by Chuang Gan, et al. ∙ 0 ∙ share

read it
Curriculum Domain Adaptation for Semantic Segmentation of Urban Scenes

During the last half decade, convolutional neural networks (CNNs) have t...
07/29/2017 ∙ by Yang Zhang, et al. ∙ 0 ∙ share

read it
Query-Focused Video Summarization: Dataset, Evaluation, and A Memory Network Based Approach

Recent years have witnessed a resurgence of interest in video summarizat...
07/16/2017 ∙ by Aidean Sharghi, et al. ∙ 0 ∙ share

read it
Fast Zero-Shot Image Tagging

The well-known word analogy experiments show that the recent word vector...
05/31/2016 ∙ by Yang Zhang, et al. ∙ 0 ∙ share

read it
Synthesized Classifiers for Zero-Shot Learning

Given semantic descriptions of object classes, zero-shot learning aims t...
03/02/2016 ∙ by Soravit Changpinyo, et al. ∙ 0 ∙ share

read it
Improved Dropout for Shallow and Deep Learning

Dropout has been witnessed with great success in training deep neural ne...
02/06/2016 ∙ by Zhe Li, et al. ∙ 0 ∙ share

read it
Large-Margin Determinantal Point Processes

Determinantal point processes (DPPs) offer a powerful approach to modeli...
11/06/2014 ∙ by Boqing Gong, et al. ∙ 0 ∙ share

read it