Get our free extension to see links to code for papers anywhere online!

Add to Chrome

Add to Firefox

Picture for Yuandong Tian

Yuandong Tian

Building Generalizable Agents with a Realistic and Rich 3D Environment

Apr 08, 2018
Yi Wu, Yuxin Wu, Georgia Gkioxari, Yuandong Tian

Figure 1 for Building Generalizable Agents with a Realistic and Rich 3D Environment

Figure 2 for Building Generalizable Agents with a Realistic and Rich 3D Environment

Figure 3 for Building Generalizable Agents with a Realistic and Rich 3D Environment

Figure 4 for Building Generalizable Agents with a Realistic and Rich 3D Environment

* updated with improved content and more experinemnts

Access Paper or Ask Questions

3D Interpreter Networks for Viewer-Centered Wireframe Modeling

Apr 03, 2018
Jiajun Wu, Tianfan Xue, Joseph J. Lim, Yuandong Tian, Joshua B. Tenenbaum, Antonio Torralba, William T. Freeman

Figure 1 for 3D Interpreter Networks for Viewer-Centered Wireframe Modeling

Figure 2 for 3D Interpreter Networks for Viewer-Centered Wireframe Modeling

Figure 3 for 3D Interpreter Networks for Viewer-Centered Wireframe Modeling

Figure 4 for 3D Interpreter Networks for Viewer-Centered Wireframe Modeling

* International Journal of Computer Vision, 2018
* Journal preprint of arXiv:1604.08685 (IJCV, in press). The first two authors contributed equally to this work

Access Paper or Ask Questions

Channel-Recurrent Autoencoding for Image Modeling

Mar 11, 2018
Wenling Shang, Kihyuk Sohn, Yuandong Tian

Figure 1 for Channel-Recurrent Autoencoding for Image Modeling

Figure 2 for Channel-Recurrent Autoencoding for Image Modeling

Figure 3 for Channel-Recurrent Autoencoding for Image Modeling

Figure 4 for Channel-Recurrent Autoencoding for Image Modeling

* Code: https://github.com/WendyShang/crVAE. Supplementary Materials: http://www-personal.umich.edu/~shangw/wacv18_supplementary_material.pdf

Access Paper or Ask Questions

When is a Convolutional Filter Easy To Learn?

Feb 28, 2018
Simon S. Du, Jason D. Lee, Yuandong Tian

Figure 1 for When is a Convolutional Filter Easy To Learn?

Figure 2 for When is a Convolutional Filter Easy To Learn?

Figure 3 for When is a Convolutional Filter Easy To Learn?

* Published as a conference paper at ICLR 2018

Access Paper or Ask Questions

CoDraw: Visual Dialog for Collaborative Drawing

Dec 15, 2017
Jin-Hwa Kim, Devi Parikh, Dhruv Batra, Byoung-Tak Zhang, Yuandong Tian

Figure 1 for CoDraw: Visual Dialog for Collaborative Drawing

Figure 2 for CoDraw: Visual Dialog for Collaborative Drawing

Figure 3 for CoDraw: Visual Dialog for Collaborative Drawing

Figure 4 for CoDraw: Visual Dialog for Collaborative Drawing

* 22 pages, 19 figures, including appendix

Access Paper or Ask Questions

An Analytical Formula of Population Gradient for two-layered ReLU network and its Applications in Convergence and Critical Point Analysis

May 24, 2017
Yuandong Tian

Figure 1 for An Analytical Formula of Population Gradient for two-layered ReLU network and its Applications in Convergence and Critical Point Analysis

Figure 2 for An Analytical Formula of Population Gradient for two-layered ReLU network and its Applications in Convergence and Critical Point Analysis

Figure 3 for An Analytical Formula of Population Gradient for two-layered ReLU network and its Applications in Convergence and Critical Point Analysis

Figure 4 for An Analytical Formula of Population Gradient for two-layered ReLU network and its Applications in Convergence and Critical Point Analysis

* International Conference on Machine Learning (ICML) 2017

Access Paper or Ask Questions

Semantic Amodal Segmentation

Dec 14, 2016
Yan Zhu, Yuandong Tian, Dimitris Mexatas, Piotr Dollár

Figure 1 for Semantic Amodal Segmentation

Figure 2 for Semantic Amodal Segmentation

Figure 3 for Semantic Amodal Segmentation

Figure 4 for Semantic Amodal Segmentation

* major update including new COCO data, metrics, and baselines

Access Paper or Ask Questions

Single Image 3D Interpreter Network

Oct 04, 2016
Jiajun Wu, Tianfan Xue, Joseph J. Lim, Yuandong Tian, Joshua B. Tenenbaum, Antonio Torralba, William T. Freeman

Figure 1 for Single Image 3D Interpreter Network

Figure 2 for Single Image 3D Interpreter Network

Figure 3 for Single Image 3D Interpreter Network

Figure 4 for Single Image 3D Interpreter Network

* ECCV 2016 (oral). The first two authors contributed equally to this work

Access Paper or Ask Questions

Better Computer Go Player with Neural Network and Long-term Prediction

Feb 29, 2016
Yuandong Tian, Yan Zhu

* 10 pages, 9 without references. Submission for ICLR 2016

Access Paper or Ask Questions