Epipolar Transformers

May 10, 2020
Yihui He, Rui Yan, Katerina Fragkiadaki, Shoou-I Yu

* CVPR 2020 

  Access Model/Code and Paper
Embodied Language Grounding with Implicit 3D Visual Feature Representations

Oct 02, 2019
Mihir Prabhudesai, Hsiao-Yu Fish Tung, Syed Ashar Javed, Maximilian Sieb, Adam W. Harley, Katerina Fragkiadaki


  Access Model/Code and Paper
Graph-Structured Visual Imitation

Jul 11, 2019
Maximilian Sieb, Zhou Xian, Audrey Huang, Oliver Kroemer, Katerina Fragkiadaki

* 8 pages, 3 figures, 1 table 

  Access Model/Code and Paper
Embodied View-Contrastive 3D Feature Learning

Jul 10, 2019
Adam W. Harley, Fangyu Li, Shrinidhi K. Lakshmikanth, Xian Zhou, Hsiao-Yu Fish Tung, Katerina Fragkiadaki


  Access Model/Code and Paper
Reinforcement Learning of Active Vision for Manipulating Objects under Occlusions

Feb 16, 2019
Ricson Cheng, Arpit Agarwal, Katerina Fragkiadaki

* Proceedings of Machine Learning Research 87 (2018) 422--431 
* The paper was present in Conference of Robot Learning 2018 

  Access Model/Code and Paper
Image Disentanglement and Uncooperative Re-Entanglement for High-Fidelity Image-to-Image Translation

Jan 11, 2019
Adam W. Harley, Shih-En Wei, Jason Saragih, Katerina Fragkiadaki


  Access Model/Code and Paper
Learning Spatial Common Sense with Geometry-Aware Recurrent Networks

Dec 31, 2018
Hsiao-Yu Fish Tung, Ricson Cheng, Katerina Fragkiadaki


  Access Model/Code and Paper
Model Learning for Look-ahead Exploration in Continuous Control

Nov 20, 2018
Arpit Agarwal, Katharina Muelling, Katerina Fragkiadaki

* This is a pre-print of our paper which is accepted in AAAI 2018 

  Access Model/Code and Paper
Reinforcement Learning of Active Vision forManipulating Objects under Occlusions

Nov 20, 2018
Ricson Cheng, Arpit Agarwal, Katerina Fragkiadaki

* Proceedings of Machine Learning Research 87 (2018) 422--431 
* The paper was present in Conference of Robot Learning 2018 

  Access Model/Code and Paper
Geometry-Aware Recurrent Neural Networks for Active Visual Recognition

Nov 03, 2018
Ricson Cheng, Ziyan Wang, Katerina Fragkiadaki

* To appear in NIPS2018 

  Access Model/Code and Paper
Reward Learning from Narrated Demonstrations

Apr 27, 2018
Hsiao-Yu Fish Tung, Adam W. Harley, Liang-Kang Huang, Katerina Fragkiadaki

* The work has been accepted to Conference on Computer Vision and Pattern Recognition (CVPR) 2018 

  Access Model/Code and Paper
Depth-Adaptive Computational Policies for Efficient Visual Tracking

Jan 01, 2018
Chris Ying, Katerina Fragkiadaki

* presented at EMMCVPR 2017 in Venice, Italy 

  Access Model/Code and Paper
Self-supervised Learning of Motion Capture

Dec 04, 2017
Hsiao-Yu Fish Tung, Hsiao-Wei Tung, Ersin Yumer, Katerina Fragkiadaki

* Neural Information Processing Systems (NIPS) 2017 

  Access Model/Code and Paper
Adversarial Inverse Graphics Networks: Learning 2D-to-3D Lifting and Image-to-Image Translation from Unpaired Supervision

Sep 02, 2017
Hsiao-Yu Fish Tung, Adam W. Harley, William Seto, Katerina Fragkiadaki

* The IEEE International Conference on Computer Vision (ICCV), 2017, pp. 4354-4362 

  Access Model/Code and Paper
Motion Prediction Under Multimodality with Conditional Stochastic Networks

May 05, 2017
Katerina Fragkiadaki, Jonathan Huang, Alex Alemi, Sudheendra Vijayanarasimhan, Susanna Ricco, Rahul Sukthankar


  Access Model/Code and Paper
SfM-Net: Learning of Structure and Motion from Video

Apr 25, 2017
Sudheendra Vijayanarasimhan, Susanna Ricco, Cordelia Schmid, Rahul Sukthankar, Katerina Fragkiadaki


  Access Model/Code and Paper
Human Pose Estimation with Iterative Error Feedback

Jun 12, 2016
Joao Carreira, Pulkit Agrawal, Katerina Fragkiadaki, Jitendra Malik


  Access Model/Code and Paper
Learning Visual Predictive Models of Physics for Playing Billiards

Jan 19, 2016
Katerina Fragkiadaki, Pulkit Agrawal, Sergey Levine, Jitendra Malik


  Access Model/Code and Paper
Recurrent Network Models for Human Dynamics

Sep 29, 2015
Katerina Fragkiadaki, Sergey Levine, Panna Felsen, Jitendra Malik

* International Conference on Computer Vision 2015 

  Access Model/Code and Paper
Learning to Segment Moving Objects in Videos

May 08, 2015
Katerina Fragkiadaki, Pablo Arbelaez, Panna Felsen, Jitendra Malik


  Access Model/Code and Paper