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

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for James M. Rehg

No RL, No Simulation: Learning to Navigate without Navigating


Oct 18, 2021
Meera Hahn, Devendra Chaplot, Shubham Tulsiani, Mustafa Mukadam, James M. Rehg, Abhinav Gupta


  Access Paper or Ask Questions

Ego4D: Around the World in 3,000 Hours of Egocentric Video


Oct 13, 2021
Kristen Grauman, Andrew Westbury, Eugene Byrne, Zachary Chavis, Antonino Furnari, Rohit Girdhar, Jackson Hamburger, Hao Jiang, Miao Liu, Xingyu Liu, Miguel Martin, Tushar Nagarajan, Ilija Radosavovic, Santhosh Kumar Ramakrishnan, Fiona Ryan, Jayant Sharma, Michael Wray, Mengmeng Xu, Eric Zhongcong Xu, Chen Zhao, Siddhant Bansal, Dhruv Batra, Vincent Cartillier, Sean Crane, Tien Do, Morrie Doulaty, Akshay Erapalli, Christoph Feichtenhofer, Adriano Fragomeni, Qichen Fu, Christian Fuegen, Abrham Gebreselasie, Cristina Gonzalez, James Hillis, Xuhua Huang, Yifei Huang, Wenqi Jia, Weslie Khoo, Jachym Kolar, Satwik Kottur, Anurag Kumar, Federico Landini, Chao Li, Yanghao Li, Zhenqiang Li, Karttikeya Mangalam, Raghava Modhugu, Jonathan Munro, Tullie Murrell, Takumi Nishiyasu, Will Price, Paola Ruiz Puentes, Merey Ramazanova, Leda Sari, Kiran Somasundaram, Audrey Southerland, Yusuke Sugano, Ruijie Tao, Minh Vo, Yuchen Wang, Xindi Wu, Takuma Yagi, Yunyi Zhu, Pablo Arbelaez, David Crandall, Dima Damen, Giovanni Maria Farinella, Bernard Ghanem, Vamsi Krishna Ithapu, C. V. Jawahar, Hanbyul Joo, Kris Kitani, Haizhou Li, Richard Newcombe, Aude Oliva, Hyun Soo Park, James M. Rehg, Yoichi Sato, Jianbo Shi, Mike Zheng Shou, Antonio Torralba, Lorenzo Torresani, Mingfei Yan, Jitendra Malik


  Access Paper or Ask Questions

Egocentric Activity Recognition and Localization on a 3D Map


May 27, 2021
Miao Liu, Lingni Ma, Kiran Somasundaram, Yin Li, Kristen Grauman, James M. Rehg, Chao Li


  Access Paper or Ask Questions

Discriminative Appearance Modeling with Multi-track Pooling for Real-time Multi-object Tracking


Jan 28, 2021
Chanho Kim, Li Fuxin, Mazen Alotaibi, James M. Rehg


  Access Paper or Ask Questions

Using Shape to Categorize: Low-Shot Learning with an Explicit Shape Bias


Jan 18, 2021
Stefan Stojanov, Anh Thai, James M. Rehg

* Project page, code and data available at https://rehg-lab.github.io/publication-pages/lowshot-shapebias/ 

  Access Paper or Ask Questions

Does Continual Learning = Catastrophic Forgetting?


Jan 18, 2021
Anh Thai, Stefan Stojanov, Isaac Rehg, James M. Rehg


  Access Paper or Ask Questions

4D Human Body Capture from Egocentric Video via 3D Scene Grounding


Nov 26, 2020
Miao Liu, Dexin Yang, Yan Zhang, Zhaopeng Cui, James M. Rehg, Siyu Tang


  Access Paper or Ask Questions

Where Are You? Localization from Embodied Dialog


Nov 16, 2020
Meera Hahn, Jacob Krantz, Dhruv Batra, Devi Parikh, James M. Rehg, Stefan Lee, Peter Anderson

* EMNLP 2020 

  Access Paper or Ask Questions

3D Reconstruction of Novel Object Shapes from Single Images


Jun 14, 2020
Anh Thai, Stefan Stojanov, Vijay Upadhya, James M. Rehg

* First two authors contributed equally 

  Access Paper or Ask Questions

In the Eye of the Beholder: Gaze and Actions in First Person Video


May 31, 2020
Yin Li, Miao Liu, James M. Rehg

* Submitted to TPAMI 

  Access Paper or Ask Questions

Approximate Inverse Reinforcement Learning from Vision-based Imitation Learning


Apr 17, 2020
Keuntaek Lee, Bogdan Vlahov, Jason Gibson, James M. Rehg, Evangelos A. Theodorou


  Access Paper or Ask Questions

Orthogonal Over-Parameterized Training


Apr 09, 2020
Weiyang Liu, Rongmei Lin, Zhen Liu, James M. Rehg, Li Xiong, Le Song

* Technical Report 

  Access Paper or Ask Questions

Detecting Attended Visual Targets in Video


Mar 30, 2020
Eunji Chong, Yongxin Wang, Nataniel Ruiz, James M. Rehg

* Accepted to CVPR 2020 

  Access Paper or Ask Questions

A Functional EM Algorithm for Panel Count Data with Missing Counts


Mar 28, 2020
Alexander Moreno, Zhenke Wu, Jamie Yap, David Wetter, Cho Lam, Inbal Nahum-Shani, Walter Dempsey, James M. Rehg

* 18 pages 

  Access Paper or Ask Questions

Neural Similarity Learning


Dec 06, 2019
Weiyang Liu, Zhen Liu, James M. Rehg, Le Song

* NeurIPS 2019 (v3) 

  Access Paper or Ask Questions

Compressive Hyperspherical Energy Minimization


Jun 12, 2019
Rongmei Lin, Weiyang Liu, Zhen Liu, Chen Feng, Zhiding Yu, James M. Rehg, Li Xiong, Le Song


  Access Paper or Ask Questions

Locally Weighted Regression Pseudo-Rehearsal for Online Learning of Vehicle Dynamics


May 13, 2019
Grady Williams, Brian Goldfain, James M. Rehg, Evangelos A. Theodorou

* 10 pages, 4 figures 

  Access Paper or Ask Questions

Tripping through time: Efficient Localization of Activities in Videos


Apr 25, 2019
Meera Hahn, Asim Kadav, James M. Rehg, Hans Peter Graf


  Access Paper or Ask Questions

Learning to Generate Synthetic Data via Compositing


Apr 10, 2019
Shashank Tripathi, Siddhartha Chandra, Amit Agrawal, Ambrish Tyagi, James M. Rehg, Visesh Chari

* Accepted to CVPR 2019, supplementary material included 

  Access Paper or Ask Questions

Unsupervised 3D Pose Estimation with Geometric Self-Supervision


Apr 09, 2019
Ching-Hang Chen, Ambrish Tyagi, Amit Agrawal, Dylan Drover, Rohith MV, Stefan Stojanov, James M. Rehg


  Access Paper or Ask Questions

Paying More Attention to Motion: Attention Distillation for Learning Video Representations


Apr 05, 2019
Miao Liu, Xin Chen, Yun Zhang, Yin Li, James M. Rehg


  Access Paper or Ask Questions

Action2Vec: A Crossmodal Embedding Approach to Action Learning


Jan 02, 2019
Meera Hahn, Andrew Silva, James M. Rehg


  Access Paper or Ask Questions

Taking a Deeper Look at the Inverse Compositional Algorithm


Dec 17, 2018
Zhaoyang Lv, Frank Dellaert, James M. Rehg, Andreas Geiger


  Access Paper or Ask Questions

Vision-Based High Speed Driving with a Deep Dynamic Observer


Dec 10, 2018
Paul Drews, Grady Williams, Brian Goldfain, Evangelos A. Theodorou, James M. Rehg


  Access Paper or Ask Questions

Learning to Localize and Align Fine-Grained Actions to Sparse Instructions


Sep 22, 2018
Meera Hahn, Nataniel Ruiz, Jean-Baptiste Alayrac, Ivan Laptev, James M. Rehg


  Access Paper or Ask Questions

Learning Rigidity in Dynamic Scenes with a Moving Camera for 3D Motion Field Estimation


Jul 30, 2018
Zhaoyang Lv, Kihwan Kim, Alejandro Troccoli, Deqing Sun, James M. Rehg, Jan Kautz

* This work is accepted at European Conference on Computer Vision 2018. Project page (with the video): http://research.nvidia.com/publication/2018-09_Learning-Rigidity-in The codes will be released at https://github.com/NVlabs/learningrigidity 

  Access Paper or Ask Questions