2022

Data-efficient Vision Transformer

2021

Video-Audio-Text Transformer (VATT)

2020

Long-tailed visual recognition

2019

Normal adversarial attack

2018

Generative adversarial net

2017

Simulation → Real world

2016

Webly-supervised learning

2014

SeqDPP: sequential determinantal point process

2012

GFK: geodesic flow kernel

  Google Scholar     Semantic Scholar     DBLP


Preprints on ArXiv


* students I (co-)supervised.
= equal contribution among authors.

2022


    ICLR

When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations

International Conference on Learning Representations (ICLR), 2022 (Spotlight) X Chen, C-J Hsieh, and B Gong
⟼ [ PDF ]     [ ArXiv ]     [ Openreview ]     [ Model checkpoints ]


    ICLR

Surrogate Gap Minimization Improves Sharpness-Aware Training

International Conference on Learning Representations (ICLR), 2022 J Zhuang, B Gong, L Yuan, Y Cui, H Adam, N Dvornek, S Tatikonda, J Duncan, and T Liu
⟼ [ PDF ]     [ ArXiv ]     [ Openreview ]    [ Code ]


    ECCV

LESS: Label-Efficient Semantic Segmentation for LiDAR Point Clouds

European Conference on Computer Vision (ECCV), 2022 (Oral) M Liu, Y Zhou, CR Qin, B Gong, H Su, and D Anguelov
⟼ [ ArXiv ]


    ECCV

Anti-Neuron Watermarking: Protecting Personal Data Against Unauthorized Neural Networks

European Conference on Computer Vision (ECCV), 2022 Z Zou, B Gong, and L Wang
⟼ [ ArXiv ]


    CVPR

Contextualized Spatio-Temporal Contrastive Learning with Self-Supervision

IEEE/CVF Conference Computer Vision and Pattern Recognition (CVPR), 2022 L Yuan, R Qian, Y Cui, B Gong, B Gong, F Schroff, M-H Yang, H Adam, and T Liu
⟼ [ PDF ]     [ ArXiv ]     [ Code ]


    WACV

Federated Multi-Target Domain Adaptation

IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2022 C-H Yao, B Gong, Y Cui, H Qi, Y Zhu, and M-H Yang
⟼ [ PDF ]     [ ArXiv ]


    TPAMI

Open Long-Tailed Recognition In A Dynamic World

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2022 Z Liu=, Z Miao=, X Zhan, J Wang, B Gong, and S Yu
⟼ [ ArXiv ]


    CVIU

2.5 D visual relationship detection

Computer Vision and Image Understanding (CVIU), 2022 YC Su, S Changpinyo, X Chen, S Thoppay, CJ Hsieh, L Shapira, R Soricut, H Adam, M Brown, MH Yang, and B Gong
⟼ [ ArXiv ]     [ Data ]
2021


    CVPR

MoViNets: Mobile Video Networks for Efficient Video Recognition

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021D Kondratyuk, L Yuan, Y Li, L Zhang, M Tan, M Brown, and B Gong
⟼ [ PDF ]     [ ArXiv ]     [ Code coming soon ]


    CVPR

Ranking Neural Checkpoints

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021 Y Li*, X Jia, R Sang, Y Zhu, B Green, L Wang, and B Gong
⟼ [ PDF ]     [ ArXiv ]     [ Code coming soon ]


    CVPR

Robust and Accurate Object Detection via Adversarial Learning

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021 X Chen, C Xie, M Tan, L Zhang, C-J Hsieh, and B Gong
⟼ [ PDF ]     [ ArXiv ]     [ Detector checkpoints ]


    CVPR

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

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021 L Yi, B Gong, and T Funkhouser
⟼ [ PDF ]     [ ArXiv ]     


    CVPR

Adversarially Adaptive Normalization for Single Domain Generalization

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021 X Fan, Q Wang, J Ke, F Yang, B Gong, and M Zhou
⟼ [ PDF ]


    CVPR

Spatiotemporal Contrastive Video Representation Learning

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021 R Qian=, T Meng=, B Gong, M-H Yang, H Wang, S Belongie, and Y Cui
⟼ [ PDF ]     [ ArXiv ]     


    NeurIPS

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

Advances in Neural Information Processing Systems (NeurIPS), 2021 H Akbari, L Yuan, R Qian, W-H Chuang, S-F Chang, Y Cui, and B Gong
⟼ [ PDF ]     [ ArXiv ]      [ Openreview ]      [ Code ]


    NeurIPS

On Model Calibration for Long-Tailed Object Detection and Instance Segmentation

Advances in Neural Information Processing Systems (NeurIPS), 2021 T-Y Pan=, C Zhang, Y Li, H Hu, D Xuan, S Changpinyo, B Gong, and W-L Chao
⟼ [ PDF ]      [ Openreview ]      [ Code ]


    ICML

Large-Scale Meta-Learning with Continual Trajectory Shifting

International Conference on Machine Learning (ICML), 2021 J Shin, HB Lee, B Gong, and SJ Hwang
⟼ [ PDF ]


    ICCV

A Lazy Approach to Long-Horizon Gradient-Based Meta-Learning

International Conference on Computer Vision (ICCV), 2021 M A Jamal*, L Wang, and B Gong
⟼ [ PDF ]


    ICCV

MosaicOS: A Simple and Effective Use of Object-Centric Images for Long-Tailed Object Detection

International Conference on Computer Vision (ICCV), 2021 C Zhang=, T-Y Pan=, Y Li, H Hu, D Xuan, S Changpinyo, B Gong, and W-L Chao
⟼ [ PDF ]     [ Model checkpoints ]


    ICCV

Contrastive Learning for Label Efficient Semantic Segmentation

International Conference on Computer Vision (ICCV), 2021 X Zhao, R Vemulapalli, PA Mansfield, B Gong, B Green, L Shapira, and Y Wu
⟼ [ PDF ]


    WACV

Analyzing Deep Neural Network’s Transferability via Fréchet Distance

IEEE Winter Conference on Applications of Computer Vision (WACV), 2021 Y Ding, L Wang, and B Gong
⟼ [ PDF ]


    BMVC

Class-Balanced Distillation for Long-Tailed Visual Recognition

Conference on Empirical Methods in Natural Language Processing (EMNLP), 2021 A Iscen, A Araujo, B Gong, C Schmid
⟼ [ PDF ]     [ Code ]


    EMNLP

CrossVQA: Scalably Generating Benchmarks For Systematically Testing VQA Generalization

Conference on Empirical Methods in Natural Language Processing (EMNLP), 2021 A Akula, S Changpinyo, B Gong, P Sharma, S-C Zhu, and R Soricut
⟼ [ PDF ]
2020


    CVPR

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

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020 (Oral) M Jamal*, M Brown, L Wang, M Yang, and B Gong
⟼ [ PDF ]     [ ArXiv ]     [ Slides ]    [ Code ]


    CVPR

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

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020 (Oral) D Wang, Y Li*, L Wang, and B Gong
⟼ [ PDF ]     [ ArXiv ]     [ Code ]


    CVPR

Open Compound Domain Adaptation

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020 (Oral) Z Liu=, Z Miao=, X Pan, X Zhan, D Lin, S Yu, and B Gong
⟼ [ PDF ]     [ ArXiv ]     [ Demo ]    [ Project page ]


    CVPR

Adversarial Examples Improve Image Recognition

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020 C Xie, M Tan, B Gong, J Wang, A Yuille, and Q Le
⟼ [ PDF ]     [ ArXiv ]


    CVPR

PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentation

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020 Y Zhang=*, Z Zhou=, P David, X Yue, Z Xi, B Gong, and H. Foroosh
⟼ [ PDF ]     [ Code ]


    ECCV

Improving Object Detection with Selective Self-Supervised Self-training

European Conference on Computer Vision (ECCV), 2020 Y Li*, D Huang, D Qin, and B Gong
⟼ [ ArXiv ]


    ICLR

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

International Conference on Learning Representations (ICLR), 2020 R Zhai, C Dan, D He, H Zhang, B Gong, P Ravikumar, C-J Hsieh, and L Wang
⟼ [ Openreview ]     [ PDF ]


    ICRA

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

International Conference on Learning Representations (ICLR), 2020 C Gan=, Y Zhang=, J Wu, B Gong, and J Tenenbaum
⟼ [ PDF ]     [ Demo ]     [ Project page ]
2019


    ICCV

A Fast and Accurate One-Stage Approach to Visual Grounding

International Conference on Computer Vision (ICCV), 2019 (Oral)Z Yang, B Gong, L Wang, W Huang, D Yu, and J Luo
⟼ [ ArXiv ]     [ Code ]     [ Slides ]     [ Poster ]


    ICCV

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

International Conference on Computer Vision (ICCV), 2019 X Yue, Y Zhang, S Zhao, A Sangiovanni-Vincentelli, K Keutzer, and B Gong
⟼ [ ArXiv ]     [ Code ]


    ICCV

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

International Conference on Computer Vision (ICCV), 2019 Q Lian, F Lv, L Duan, and B Gong
⟼ [ ArXiv ]     [ Code ]


    ICML

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

International Conference on Machine Learning (ICML), 2019 (Spotlight)Y Li*=, L Li*=, L Wang, T Zhang, and B Gong
⟼ [ ArXiv ]     [ Code ]     [ Slides ]


    TPAMI

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

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2019 Y Zhang*, P David, H Foroosh, and B Gong
⟼ [ ArXiv ]     [ Conference version ]    [ Code ]


    ICLR

CAMOU: Learning Physical Vehicle Camouflages to Adversarially Attack Detectors in the Wild

International Conference on Learning Representations (ICLR), 2019 Y Zhang*, H Foroosh, P David, and B Gong
⟼ [ PDF ]     [ Openreview ]


    ICLR

DHER: Hindsight Experience Replay for Dynamic Goals

International Conference on Learning Representations (ICLR), 2019 M Fang, C Zhou, B Shi, B Gong, J Xu, and T Zhang
⟼ [ PDF ]      [ Openreview ]


    MM

Facial Image-to-Video Translation by a Hidden Affine Transformation

Proceedings of the 27th ACM International Conference on Multimedia (MM), 2019 G Shen, W Huang, C Gan, M Tan, J Huang, W Zhu, and B Gong
⟼ [ Paper ]     [ Code ]


    AAAI

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

The Thirty-Third AAAI Conference on Artificial Intelligence (AAAI), 2019 (Oral) L Fan, W Huang, C Gan, J Huang, and B Gong
⟼ [ PDF ]     [ Supplement ]


    CVPR

Large-Scale Long-Tailed Recognition in an Open World

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019 (Oral) Z Liu=, Z Miao=, X Zhan, J Wang, B Gong, and S Yu
⟼ [ ArXiv ]     [ Data and code ]


    CVPR

Not All Frames Are Equal: Weakly-Supervised Video Grounding with Contextual Similarity and Visual Clustering Losses

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019 J Shi, J Xu, B Gong, and X Xu
⟼ [ PDF ]


    WWW

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

The Web Conference (WWW), 2019 (Oral) X Tang, B Gong, Y Yu, H Yao, Y Li, H Xie, and X Wang
⟼ [ PDF ]


  AISTATS

A Robust Zero-Sum Game Framework for Pool-based Active Learning

International Conference on Artificial Intelligence and Statistics (AISTATS), 2019 D Zhu, Z Lin, X Wang, B Gong, and T Yang
⟼ [ PDF ]      [ Supplement ]


    WACV

End-to-End Video Captioning with Multitask Reinforcement Learning

IEEE Winter Conference on Applications of Computer Vision (WACV), 2019 L Li* and B Gong
⟼ [ PDF ]      [ Supplement ]


    WACV

Optimize Deep Convolutional Neural Network with Ternarized Weights and High Accuracy

IEEE Winter Conference on Applications of Computer Vision (WACV), 2019 Z He, B Gong, and D Fan
⟼ [ PDF ]      [ Supplement ]


    IJCV

Classifier and Exemplar Synthesis for Zero-Shot Learning

International Journal of Computer Vision (IJCV), 2019 S Changpinyo, WL Chao, B Gong, and F Sha
⟼ [ ArXiv ]     [ Code ]     [ Slides ]
2018


  NeurIPS

Synthesized Policies for Transfer and Adaptation across Environments and Tasks

Advances in Neural Information Processing Systems (NeurIPS), 2018 (Spotlight)H Hu=, L Chen=, B Gong, and F Sha
⟼ [ PDF ]      [ Supplement ]      [ Poster ]      [ Code ]


    ICLR

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

International Conference on Learning Representations (ICLR), 2018 X Wei*=, B Gong=, Z Liu, and L Wang
⟼ [ PDF ]      [ Reviews ]     [ Code ]


    ECCV

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

European Conference on Computer Vision (ECCV), 2018 Y Li*, L Wang, T Yang, and B Gong
⟼ [ PDF ]


    ECCV

Improving Sequential Determinantal Point Processes for Supervised Video Summarization

European Conference on Computer Vision (ECCV), 2018 A Sharghi*, A Borji, C Li, T Yang, and B Gong
⟼ [ PDF ]      [ Supplement ]


    CVPR

Face Detector Adaptation without Negative Transfer or Catastrophic Forgetting

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018 M A Jamal*, H Li, and B Gong
⟼ [ PDF ]      [ Supplement ]


    CVPR

Geometry-Guided CNN for Self-Supervised Video Representation Learning

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018 C Gan*, B Gong, K Liu, H Su, and L Guibas
⟼ [ PDF ]


    CVPR

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

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018 (Spotlight)L Fan, W Huang, C Gan, S Ermon, B Gong, and J Huang
⟼ [ PDF ]      [ Supplement ]      [ Code ]


    WACV

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

IEEE Winter Conference on Applications of Computer Vision (WACV), 2018 Y Ding*, L Wang, D Fan, and B Gong
⟼ [ PDF ]


    TOMM

Learning a Multi-Concept Video Retrieval Model with Multiple Latent Variables

ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), 2018 A Mazaheri*, B Gong, and M Shah
⟼ [ PDF ]


    TMSCS

Exploring A SOT-MRAM based In-Memory Computing for Data Processing

IEEE Transactions on Multi-Scale Computing Systems (TMSCS), 2018 Z He, Z Yang*, S Angizi, B Gong, and D Fan
⟼ [ PDF ]
2017


    ICCV

Curriculum Domain Adaptation for Semantic Segmentation of Urban Scenes

IEEE International Conference on Computer Vision (ICCV), 2017 Y Zhang*, P David, and B Gong
⟼ [ PDF ]      [ Extended version ]      [ Code ]


    ICCV

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

IEEE International Conference on Computer Vision (ICCV), 2017 C Gan*, Y Li, H Li, C Sun, and B Gong
⟼ [ PDF ]      [ Extended version ]      [ Code and data ]


    CVPR

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

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017 A Sharghi*, J Laurel*, and B Gong
⟼ [ PDF ]      [ Supplement ]      [ Summary 1 (drink+food) ]      [ Summary 2 (street+chocolate) ]


    CVPR

Improving Facial Attribute Prediction using Semantic Segmentation

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017 M Kalayeh, B Gong, and M Shah
⟼ [ PDF ]


    Book
  Chapter

Geodesic Flow Kernel and Landmarks: Kernel Methods for Unsupervised Domain Adaptation

Domain Adaptation in Computer Vision Applications, Springer (Book Chapter), 2017 B Gong, K Grauman, and F Sha
⟼ [ Link ]      [ Paper (GFK) ]      [ Paper (Landmarks) ]      [ Code (GFK) ]


    Book
  Chapter

A Multisource Domain Generalization Approach to Visual Attribute Detection

Domain Adaptation in Computer Vision Applications, Springer (Book Chapter), 2017 C Gan*, T Yang, and B Gong
⟼ [ Link ]      [ Paper ]


    ACII

Weighted Geodesic Flow Kernel for Interpersonal Mutual Inuence Modeling and Emotion Recognition in Dyadic Interactions

Affective Computing and Intelligence Interaction (ACII), 2017 (Oral)Z Yang, B Gong, and S Narayanan
⟼ [ PDF ]
2016


    NIPS

Improved Dropout for Shallow and Deep Learning

Advances in Neural Information Processing Systems (NIPS), 2016 Z Li, B Gong, T Yang
⟼ [ PDF ]      [ Supplement ]      [ Reviews ]


    ECCV

Query-Focused Extractive Video Summarization

European Conference on Computer Vision (ECCV), 2016 A Sharghi*, B Gong, M Shah
⟼ [ ArXiv ]


    ECCV

Webly-supervised Video Recognition by Mutually Voting for Relevant Web Images and Web Video Frames

European Conference on Computer Vision (ECCV), 2016 C Gan*, C Sun, L Duan, and B Gong
⟼ [ PDF ]


    ECCV

An Empirical Study and Analysis of Generalized Zero-Shot Learning for Object Recognition in the Wild

European Conference on Computer Vision (ECCV), 2016 (Spotlight)WL Chao=, S Changpinyo=, B Gong, and F Sha
⟼ [ ArXiv ]      [ Spotlight slides ]      [ Poster ]


    CVPR

Fast Zero-Shot Image Tagging *

IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2016 Y Zhang*, B Gong, and M Shah
⟼ [ Open access ]      [ Extended version ]      [ Related work ]


    CVPR

Learning Attributes Equals Multi-Source Domain Generalization *

IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2016 (Spotlight)C Gan, T Yang, and B Gong
⟼ [ Open access ]      [ Spotlight ]      [ Book chapter ]


    CVPR

Synthesized Classifiers for Zero-Shot Learning

IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2016 (Oral)=S Changpinyo, =WL Chao, B Gong, and F Sha
⟼ [ Open access ]      [ Supplement ]      [ Code ]      [ Oral slides ]      [ Poster ]


    

Learning a Multi-concept Video Retrieval Model with Multiple Latent Variables

IEEE International Symposium on Multimedia, 2016 A Mazaheri*, B Gong, and M Shah
⟼ [ PDF ]      [ Extended version ]
2015 and before


    PhD
   Thesis

Kernel Methods for Unsupervised Domain Adaptation

Ph.D. Dissertation, University of Southern California, 2015 B Gong
⟼ [ PDF ]


    UAI

Large-Margin Determinantal Point Processes

Conference on Uncertainty in Artificial Intelligence (UAI), 2015 WL Chao=, B Gong=, K Grauman, F Sha
⟼ [ PDF ]      [ Supplement ]      [ Code ]      [ Poster ]


    IJCV

Learning Kernels for Unsupervised Domain Adaptation with Applications to Visual Object Recognition

International Journal of Computer Vision (IJCV), Springer, 2014 B Gong, K Grauman, and F Sha
⟼ [ Link ]


    NIPS

Diverse Sequential Subset Selection for Supervised Video Summarization

Advances in Neural Information Processing Systems (NIPS), 2014 =B Gong, =WL Chao, K Grauman, and F Sha
⟼ [ PDF ]      [ Supplement ]      [ Reviews ]      [ Code ]      [ Poster ]


    ICML

Connecting the Dots with Landmarks: Discriminatively Learning Domain-Invariant Features for Unsupervised Domain Adaptation

International Conference on Machine Learning (ICML), 2013 (Oral)B Gong, K Grauman, and F Sha
⟼ [ PDF ]      [ Supplement ]      [ Oral slides ]


    NIPS

Reshaping Visual Datasets for Domain Adaptation

Advances in Neural Information Processing Systems (NIPS), 2013 B Gong, K Grauman, and F Sha
⟼ [ PDF ]      [ Supplement ]      [ Reviews ]


    TMM

Learning Semantic Signatures for 3D Object Retrieval

IEEE Transactions on Multimedia (T-MM), 2013 B Gong, J Liu, X Wang, and X Tang
⟼ [ PDF ]


    CVPR

Geodesic Flow Kernel for Unsupervised Domain Adaptation

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2012 (Oral)B Gong, Y Shi, F Sha, and K Grauman
⟼ [ PDF ]      [ Supplement ]      [ Code ]      [ Oral slides ]


Workshop

Overcoming Dataset Bias: An Unsupervised Domain Adaptation Approach

NIPS Workshop on Large Scale Visual Recognition and Retrieval (BigVision), 2012 (Oral)B Gong, F Sha, and K Grauman
⟼ [ PDF ]


    MM

3D Object Retrieval with Semantic Attributes

ACM International Conference on Multimedia (MM), 2011 B Gong, J Liu, X Wang, and X Tang
⟼ [ PDF ]


   Master
   Thesis

3D Object Retrieval and Recognition

Master of Philosophy Dissertation, The Chinese University of Hong Kong, 2010 B Gong
⟼ [ PDF ]


    MM

Boosting 3D Object Retrieval by Object Flexibility

ACM International Conference on Multimedia (MM), 2009 B Gong, C Xu, J Liu, and X Wang
⟼ [ PDF ]


    MM

Automatic Facial Expression Recognition on A Single 3D Face by Exploring Shape Deformation

ACM International Conference on Multimedia (MM), 2009 B Gong, Y Wang, J Liu, and X Wang
⟼ [ PDF ]