Xiaolong Wang

Assistant Professor, UC San Diego [GitHub] [Google Scholar] [CV]
Home Publication Group Contact

Ruihan Yang*, Minghao Zhang*, Nicklas Hansen, Huazhe Xu, Xiaolong Wang.
Learning Vision-Guided Quadrupedal Locomotion End-to-End with Cross-Modal Transformers.
arXiv, 2021.

[arXiv] [project page]

Miao Hao*, Yizhuo Li*, Zonglin Di*, Nitesh B. Gundavarapu, Xiaolong Wang.
Test-Time Personalization with a Transformer for Human Pose Estimation.
arXiv, 2021.

[arXiv] [project page]

Nicklas Hansen, Hao Su, Xiaolong Wang.
Stabilizing Deep Q-Learning with ConvNets and Vision Transformers under Data Augmentation.
arXiv, 2021.

[arXiv] [project page] [code]

Minghao Zhang*, Pingcheng Jian*, Yi Wu, Huazhe Xu, Xiaolong Wang.
Disentangled Attention as Intrinsic Regularization for Bimanual Multi-Object Manipulation.
arXiv, 2021.

[arXiv] [project page]

Zihang Lai, Sifei Liu, Alexei A. Efros, Xiaolong Wang.
Video Autoencoder: Self-supervised Disentanglement of 3D Structure and Motion.
International Conference on Computer Vision (ICCV), 2021 (Oral Presentation).

Jiarui Xu, Xiaolong Wang.
Rethinking Self-supervised Correspondence Learning: A Video Frame-level Similarity Perspective.
International Conference on Computer Vision (ICCV), 2021 (Oral Presentation).

[arXiv] [project page]

Hanwen Jiang*, Shaowei Liu*, Jiashun Wang, Xiaolong Wang.
Hand-Object Contact Consistency Reasoning for Human Grasps Generation.
International Conference on Computer Vision (ICCV), 2021 (Oral Presentation).

[arXiv] [project page]

Jiteng Mu, Weichao Qiu, Adam Kortylewski, Alan Yuille, Nuno Vasconcelos, Xiaolong Wang.
A-SDF: Learning Disentangled Signed Distance Functions for Articulated Shape Representation.
International Conference on Computer Vision (ICCV), 2021.

[arXiv] [project page]

Haiping Wu, Xiaolong Wang.
Contrastive Learning of Image Representations with Cross-Video Cycle-Consistency.
International Conference on Computer Vision (ICCV), 2021.

[arXiv] [project page]

Yinbo Chen, Zhuang Liu, Huijuan Xu, Trevor Darrell, Xiaolong Wang.
Meta-Baseline: Rethinking the Effectiveness of Simple Meta-Learning for Few-Shot Learning.
International Conference on Computer Vision (ICCV), 2021.

[arXiv] [code]

Xin Wang, Thomas E. Huang, Benlin Liu, Fisher Yu, Xiaolong Wang, Joseph E. Gonzalez, Trevor Darrell.
Robust Object Detection via Instance-Level Temporal Cycle Confusion.
International Conference on Computer Vision (ICCV), 2021.

[arXiv] [project page]

Tete Xiao, Colorado J Reed, Xiaolong Wang, Kurt Keutzer, Trevor Darrell.
Region Similarity Representation Learning.
International Conference on Computer Vision (ICCV), 2021.

[arXiv] [code]

Elad Levi, Tete Xiao, Xiaolong Wang, Trevor Darrell.
Rethinking preventing class-collapsing in metric learning with margin-based losses.
International Conference on Computer Vision (ICCV), 2021.

[arXiv]

Ilija Radosavovic, Xiaolong Wang, Lerrel Pinto, Jitendra Malik.
State-Only Imitation Learning for Dexterous Manipulation.
International Conference on Intelligent Robots and Systems (IROS), 2021.

[arXiv] [project page] [Talk]

Amir Bar, Roei Herzig, Xiaolong Wang, Anna Rohrbach, Gal Chechik, Trevor Darrell, Amir Globerson.
Compositional Video Synthesis with Action Graphs.
International Conference on Machine Learning (ICML), 2021.

[arXiv] [project page]

Yinbo Chen, Sifei Liu, Xiaolong Wang.
Learning Continuous Image Representation with Local Implicit Image Function.
Conference on Computer Vision and Pattern Recognition (CVPR), 2021 (Oral Presentation).

[arXiv] [code] [project page]

Jiashun Wang, Huazhe Xu, Jingwei Xu, Sifei Liu, Xiaolong Wang.
Synthesizing Long-Term 3D Human Motion and Interaction in 3D Scenes.
Conference on Computer Vision and Pattern Recognition (CVPR), 2021.

[arXiv] [code] [project page]

Shaowei Liu*, Hanwen Jiang*, Jiarui Xu, Sifei Liu, Xiaolong Wang.
Semi-Supervised 3D Hand-Object Poses Estimation with Interactions in Time.
Conference on Computer Vision and Pattern Recognition (CVPR), 2021.

[arXiv] [code] [project page]

Nicklas Hansen, Xiaolong Wang.
Generalization in Reinforcement Learning by Soft Data Augmentation.
International Conference on Robotics and Automation (ICRA), 2021.

[arXiv] [code] [project page]

Qiang Zhang, Tete Xiao, Alexei A. Efros, Lerrel Pinto, Xiaolong Wang.
Learning Cross-domain Correspondence for Control with Dynamics Cycle-consistency.
International Conference on Learning Representations (ICLR), 2021 (Oral Presentation).

[arXiv] [code] [project page]

Nicklas Hansen, Rishabh Jangir, Yu Sun, Guillem Alenyà, Pieter Abbeel, Alexei A. Efros, Lerrel Pinto, Xiaolong Wang.
Self-Supervised Policy Adaptation during Deployment.
International Conference on Learning Representations (ICLR), 2021 (Spotlight Presentation).

[arXiv] [code] [project page] [bair blog post]

Tete Xiao, Xiaolong Wang, Alexei A. Efros, Trevor Darrell.
What Should Not Be Contrastive in Contrastive Learning.
International Conference on Learning Representations (ICLR), 2021.

[arXiv]

Haozhi Qi, Xiaolong Wang, Deepak Pathak, Yi Ma, Jitendra Malik.
Learning Long-term Visual Dynamics with Region Proposal Interaction Networks.
International Conference on Learning Representations (ICLR), 2021.

[arXiv] [code] [project page] [Talk]

Yunfei Li, Huazhe Xu, Yilin Wu, Xiaolong Wang, Yi Wu.
Solving Compositional Reinforcement Learning Problems via Task Reduction.
International Conference on Learning Representations (ICLR), 2021.

[arXiv] [code] [project page]

Zhenggang Tang, Chao Yu, Boyuan Chen, Huazhe Xu, Xiaolong Wang, Fei Fang, Simon Shaolei Du, Yu Wang, Yi Wu.
Discovering Diverse Multi-Agent Strategic Behavior via Reward Randomization.
International Conference on Learning Representations (ICLR), 2021.

[arXiv] [code] [project page]

Ruihan Yang, Huazhe Xu, Yi Wu, Xiaolong Wang.
Multi-Task Reinforcement Learning with Soft Modularization.
Conference on Neural Information Processing Systems (NeurIPS), 2020.

[pdf] [code] [project page] [Talk]

Xueting Li, Sifei Liu, Shalini De Mello, Kihwan Kim, Xiaolong Wang, Ming-Hsuan Yang, Jan Kautz.
Online Adaptation for Consistent Mesh Reconstruction in the Wild.
Conference on Neural Information Processing Systems (NeurIPS), 2020.

[pdf] [project page]

Jingwei Xu, Huazhe Xu, Bingbing Ni, Xiaokang Yang, Xiaolong Wang, Trevor Darrell.
Hierarchical Style-based Networks for Motion Synthesis.
European Conference on Computer Vision (ECCV), 2020.

[arXiv] [project page] [BibTeX]

Yu Sun, Xiaolong Wang, Zhuang Liu, John Miller, Alexei A. Efros, Moritz Hardt.
Test-Time Training with Self-Supervision for Generalization under Distribution Shifts.
International Conference on Machine Learning (ICML), 2020.

[arXiv] [code and project page] [BibTeX]

Haozhi Qi, Chong You, Xiaolong Wang, Yi Ma, Jitendra Malik.
Deep Isometric Learning for Visual Recognition.
International Conference on Machine Learning (ICML), 2020.

[arXiv] [code] [project page] [BibTeX]

Qian Long*, Zihan Zhou*, Abhinav Gupta, Fei Fang, Yi Wu†, Xiaolong Wang†.
Evolutionary Population Curriculum for Scaling Multi-Agent Reinforcement Learning.
International Conference on Learning Representations (ICLR), 2020.

[arXiv] [project page] [BibTeX] [code]

Joanna Materzynska, Tete Xiao, Roei Herzig, Huijuan Xu†, Xiaolong Wang†, Trevor Darrell†.
Something-Else: Compositional Action Recognition with Spatial-Temporal Interaction Networks.
Conference on Computer Vision and Pattern Recognition (CVPR), 2020.

[arXiv] [project page] [BibTeX] [dataset annotation]

Xueting Li*, Sifei Liu*, Shalini De Mello, Xiaolong Wang, Jan Kautz, and Ming-Hsuan Yang.
Joint-task Self-supervised Learning for Temporal Correspondence.
Conference on Neural Information Processing Systems (NeurIPS), 2019.

[arXiv] [project page] [BibTeX] [code]

Xiaolong Wang*, Allan Jabri* and Alexei A. Efros.
Learning Correspondence from the Cycle-consistency of Time.
Conference on Computer Vision and Pattern Recognition (CVPR), 2019 (Oral Presentation).
(*indicates equal contributions.)

[project page] [slides] [result video] [oral talk]
[arXiv] [BibTeX] [code]

Xueting Li, Sifei Liu, Kihwan Kim, Xiaolong Wang, Ming-Hsuan Yang, and Jan Kautz.
Putting Humans in a Scene: Learning Affordance in 3D Indoor Environments.
Conference on Computer Vision and Pattern Recognition (CVPR), 2019.

[arXiv] [BibTeX]

Wei Yang, Xiaolong Wang, Ali Farhadi, Abhinav Gupta and Roozbeh Mottaghi.
Visual Semantic Navigation using Scene Priors.
International Conference on Learning Representations (ICLR), 2019.

[arXiv] [video] [BibTeX]

Xiaolong Wang and Abhinav Gupta.
Videos as Space-Time Region Graphs.
European Conference on Computer Vision (ECCV), 2018.

[arXiv] [BibTeX]

Tian Ye, Xiaolong Wang, James Davidson, and Abhinav Gupta.
Interpretable Intuitive Physics Model.
European Conference on Computer Vision (ECCV), 2018.

[pdf] [BibTeX] [code] [techxplore]

Xiaolong Wang, Ross Girshick, Abhinav Gupta, and Kaiming He.
Non-local Neural Networks.
Conference on Computer Vision and Pattern Recognition (CVPR), 2018.

[arXiv] [BibTeX] [code]

Xiaolong Wang*, Yufei Ye*, and Abhinav Gupta.
Zero-shot Recognition via Semantic Embeddings and Knowledge Graphs.
Conference on Computer Vision and Pattern Recognition (CVPR), 2018. (*indicates equal contributions.)

[arXiv] [BibTeX] [code]

Wei Yang , Wanli Ouyang, Xiaolong Wang, Jimmy Ren, Hongsheng Li and Xiaogang Wang.
3D Human Pose Estimation in the Wild by Adversarial Learning.
Conference on Computer Vision and Pattern Recognition (CVPR), 2018.

[arXiv] [BibTeX]

Xiaolong Wang, Kaiming He, and Abhinav Gupta.
Transitive Invariance for Self-supervised Visual Representation Learning.
International Conference on Computer Vision (ICCV), 2017

[pdf] [BibTeX] [caffe_model(RGB order input)] [caffe_prototxt]

Yuan Yuan, Xiaodan Liang, Xiaolong Wang, Dit-Yan Yeung, and Abhinav Gupta.
Temporal Dynamic Graph LSTM for Action-driven Video Object Detection.
International Conference on Computer Vision (ICCV), 2017

[pdf] [BibTeX] [dataset]

Xiaolong Wang*, Rohit Girdhar*, and Abhinav Gupta.
Binge Watching: Scaling Affordance Learning from Sitcoms.
Conference on Computer Vision and Pattern Recognition (CVPR), 2017 (spotlight presentation) (*indicates equal contributions.)

[pdf] [BibTeX] [dataset] [project page] [spotlight video]

Xiaolong Wang, Abhinav Shrivastava, and Abhinav Gupta.
A-Fast-RCNN: Hard Positive Generation via Adversary for Object Detection.
Conference on Computer Vision and Pattern Recognition (CVPR), 2017

[pdf] [BibTeX] [code]

Xiaolong Wang and Abhinav Gupta.
Generative Image Modeling using Style and Structure Adversarial Networks.
European Conference on Computer Vision (ECCV), 2016

[pdf] [BibTeX] [code] [models and dataset]

Gunnar A. Sigurdsson, Gül Varol, Xiaolong Wang, Ivan Laptev, Ali Farhadi, Abhinav Gupta.
Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding.
European Conference on Computer Vision (ECCV), 2016

[pdf] [BibTeX] [dataset]

Xiaolong Wang, Ali Farhadi, and Abhinav Gupta.
Actions ~ Transformations.
Conference on Computer Vision and Pattern Recognition (CVPR), 2016

[pdf] [BibTeX] [dataset]

Xiaolong Wang and Abhinav Gupta.
Unsupervised Learning of Visual Representations using Videos.
International Conference on Computer Vision (ICCV), 2015

[pdf] [BibTeX] [code] [model] [mined_patches] [project page] [spotlight video]

Xiaolong Wang, David F. Fouhey, and Abhinav Gupta.
Designing Deep Networks for Surface Normal Estimation.
Conference on Computer Vision and Pattern Recognition (CVPR), 2015.

[pdf] [BibTeX] [results for NYU Depth V2] [code and models] [project page]

David F. Fouhey, Xiaolong Wang, and Abhinav Gupta.
In Defense of the Direct Perception of Affordances.
arXiv, 2015.

[pdf]

Xiaolong Wang, Liliang Zhang, Liang Lin, Zhujin Liang, and Wangmeng Zuo.
Deep Joint Task Learning for Generic Object Extraction.
Advances in Neural Information Processing Systems (NIPS), 2014.

[pdf] [dataset] [test code] [results]

Keze Wang, Xiaolong Wang, and Liang Lin.
Deep Structured Models for 3D Human Activity Recognition.
ACM International Conference on Multimedia (MM), 2014. (full paper, oral presentation)

[pdf]

Zhujin Liang, Xiaolong Wang, Rui Huang, and Liang Lin.
An Expressive Deep Model for Parsing Human Action from a Single Image.
International Conference on Multimedia and Expo (ICME), 2014. (oral presentation, Best Student Paper Award)

[pdf]

Xiaolong Wang, Liang Lin, and Lichao Huang, Shuicheng Yan.
Incorporating Structural Alternatives and Sharing into Hierarchy for Multiclass Object Recognition and Detection.
Conference on Computer Vision and Pattern Recognition (CVPR), 2013.

[pdf]

Xiaolong Wang and Liang Lin.
Dynamical And-Or Graph Learning for Object Shape Modeling and Detection.
Advances in Neural Information Processing Systems (NIPS), 2012.

[pdf]

Liang Lin, Xiaolong Wang, Wei Yang, and Jian-Huang Lai.
Learning Contour-Fragment-based Shape Model with And-Or Tree Representation.
Conference on Computer Vision and Pattern Recognition (CVPR), 2012.

[pdf]

Wei Yang, Xiaolong Wang, Liang Lin, Chengying Gao.
Interactive CT image segmentation with online discriminative learning.
International Conference on Image Processing (ICIP), 2011.

[pdf]