Inclusive GAN: Improving Data and Minority Coverage in Generative Models

Apr 12, 2020
Ning Yu, Ke Li, Peng Zhou, Jitendra Malik, Larry Davis, Mario Fritz

  Access Model/Code and Paper

State-Only Imitation Learning for Dexterous Manipulation

Apr 07, 2020
Ilija Radosavovic, Xiaolong Wang, Lerrel Pinto, Jitendra Malik

* Videos available at https://people.eecs.berkeley.edu/~ilija/soil 

  Access Model/Code and Paper

Multimodal Image Synthesis with Conditional Implicit Maximum Likelihood Estimation

Apr 07, 2020
Ke Li, Shichong Peng, Tianhao Zhang, Jitendra Malik

* To appear in International Journal of Computer Vision (IJCV). arXiv admin note: text overlap with arXiv:1811.12373 

  Access Model/Code and Paper

It Is Not the Journey but the Destination: Endpoint Conditioned Trajectory Prediction

Apr 04, 2020
Karttikeya Mangalam, Harshayu Girase, Shreyas Agarwal, Kuan-Hui Lee, Ehsan Adeli, Jitendra Malik, Adrien Gaidon

* 14 pages, 6 figures, 3 tables 

  Access Model/Code and Paper

Audiovisual SlowFast Networks for Video Recognition

Jan 23, 2020
Fanyi Xiao, Yong Jae Lee, Kristen Grauman, Jitendra Malik, Christoph Feichtenhofer

* Technical report 

  Access Model/Code and Paper

Side-Tuning: Network Adaptation via Additive Side Networks

Dec 31, 2019
Jeffrey O Zhang, Alexander Sax, Amir Zamir, Leonidas Guibas, Jitendra Malik

* See project website at http://sidetuning.berkeley.edu 

  Access Model/Code and Paper

Learning to Navigate Using Mid-Level Visual Priors

Dec 23, 2019
Alexander Sax, Jeffrey O. Zhang, Bradley Emi, Amir Zamir, Silvio Savarese, Leonidas Guibas, Jitendra Malik

* In Conference on Robot Learning, 2019. See project website and demos at http://perceptual.actor/ 

  Access Model/Code and Paper

3D Scene Graph: A Structure for Unified Semantics, 3D Space, and Camera

Oct 06, 2019
Iro Armeni, Zhi-Yang He, JunYoung Gwak, Amir R. Zamir, Martin Fischer, Jitendra Malik, Silvio Savarese

* ICCV 2019 

  Access Model/Code and Paper

Predicting 3D Human Dynamics from Video

Aug 20, 2019
Jason Y. Zhang, Panna Felsen, Angjoo Kanazawa, Jitendra Malik

* To Appear in ICCV 2019. (v2: Updated "3D Pose from Video" in Related Work.) 

  Access Model/Code and Paper

Learning Individual Styles of Conversational Gesture

Jun 10, 2019
Shiry Ginosar, Amir Bar, Gefen Kohavi, Caroline Chan, Andrew Owens, Jitendra Malik

* CVPR 2019 

  Access Model/Code and Paper

Mesh R-CNN

Jun 06, 2019
Georgia Gkioxari, Jitendra Malik, Justin Johnson

  Access Model/Code and Paper

Learning Navigation Subroutines by Watching Videos

May 29, 2019
Ashish Kumar, Saurabh Gupta, Jitendra Malik

  Access Model/Code and Paper

Which Tasks Should Be Learned Together in Multi-task Learning?

May 21, 2019
Trevor Standley, Amir R. Zamir, Dawn Chen, Leonidas Guibas, Jitendra Malik, Silvio Savarese

* See project website at http://taskgrouping.stanford.edu/ 

  Access Model/Code and Paper

ShapeMask: Learning to Segment Novel Objects by Refining Shape Priors

Apr 05, 2019
Weicheng Kuo, Anelia Angelova, Jitendra Malik, Tsung-Yi Lin

  Access Model/Code and Paper

Habitat: A Platform for Embodied AI Research

Apr 02, 2019
Manolis Savva, Abhishek Kadian, Oleksandr Maksymets, Yili Zhao, Erik Wijmans, Bhavana Jain, Julian Straub, Jia Liu, Vladlen Koltun, Jitendra Malik, Devi Parikh, Dhruv Batra

  Access Model/Code and Paper

Combining Optimal Control and Learning for Visual Navigation in Novel Environments

Mar 06, 2019
Somil Bansal, Varun Tolani, Saurabh Gupta, Jitendra Malik, Claire Tomlin

* Project website: https://vtolani95.github.io/WayPtNav/ 

  Access Model/Code and Paper

Cognitive Mapping and Planning for Visual Navigation

Feb 07, 2019
Saurabh Gupta, Varun Tolani, James Davidson, Sergey Levine, Rahul Sukthankar, Jitendra Malik

* Extended IJCV Version of the original paper at CVPR17. Project website with code, models, simulation environment and videos: https://sites.google.com/view/cognitive-mapping-and-planning/ 

  Access Model/Code and Paper

Trajectory Normalized Gradients for Distributed Optimization

Jan 24, 2019
Jianqiao Wangni, Ke Li, Jianbo Shi, Jitendra Malik

  Access Model/Code and Paper

Learning Independent Object Motion from Unlabelled Stereoscopic Videos

Jan 08, 2019
Zhe Cao, Abhishek Kar, Christian Haene, Jitendra Malik

  Access Model/Code and Paper

Mid-Level Visual Representations Improve Generalization and Sample Efficiency for Learning Active Tasks

Dec 31, 2018
Alexander Sax, Bradley Emi, Amir R. Zamir, Leonidas Guibas, Silvio Savarese, Jitendra Malik

* See project website and demos at http://perceptual.actor 

  Access Model/Code and Paper

Non-Adversarial Image Synthesis with Generative Latent Nearest Neighbors

Dec 21, 2018
Yedid Hoshen, Jitendra Malik

  Access Model/Code and Paper

SlowFast Networks for Video Recognition

Dec 10, 2018
Christoph Feichtenhofer, Haoqi Fan, Jitendra Malik, Kaiming He

* Technical report 

  Access Model/Code and Paper

Learning 3D Human Dynamics from Video

Dec 04, 2018
Angjoo Kanazawa, Jason Zhang, Panna Felsen, Jitendra Malik

  Access Model/Code and Paper

Visual Memory for Robust Path Following

Dec 03, 2018
Ashish Kumar, Saurabh Gupta, David Fouhey, Sergey Levine, Jitendra Malik

* Neural Information Processing Systems (NeurIPS) 2018. Oral Presentation 

  Access Model/Code and Paper

Are All Training Examples Created Equal? An Empirical Study

Nov 30, 2018
Kailas Vodrahalli, Ke Li, Jitendra Malik

* 12 pages, 12 figures 

  Access Model/Code and Paper

On the Implicit Assumptions of GANs

Nov 29, 2018
Ke Li, Jitendra Malik

* 8 pages 

  Access Model/Code and Paper

Diverse Image Synthesis from Semantic Layouts via Conditional IMLE

Nov 29, 2018
Ke Li, Tianhao Zhang, Jitendra Malik

* 15 pages, 14 figures 

  Access Model/Code and Paper

Implicit Maximum Likelihood Estimation

Oct 22, 2018
Ke Li, Jitendra Malik

* 21 pages, 4 figures. In the interest of promoting discussion, we make the reviews available at https://people.eecs.berkeley.edu/~ke.li/papers/imle_reviews.pdf 

  Access Model/Code and Paper

SFV: Reinforcement Learning of Physical Skills from Videos

Oct 15, 2018
Xue Bin Peng, Angjoo Kanazawa, Jitendra Malik, Pieter Abbeel, Sergey Levine

  Access Model/Code and Paper

Super-Resolution via Conditional Implicit Maximum Likelihood Estimation

Oct 02, 2018
Ke Li, Shichong Peng, Jitendra Malik

* 12 pages, 7 figures 

  Access Model/Code and Paper