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 Gregory Shakhnarovich

Classification Confidence Estimation with Test-Time Data-Augmentation


Jun 30, 2020
Yuval Bahat, Gregory Shakhnarovich


  Access Paper or Ask Questions

Deformable Style Transfer


Mar 24, 2020
Sunnie S. Y. Kim, Nicholas Kolkin, Jason Salavon, Gregory Shakhnarovich


  Access Paper or Ask Questions

Analysis of diversity-accuracy tradeoff in image captioning


Feb 27, 2020
Ruotian Luo, Gregory Shakhnarovich


  Access Paper or Ask Questions

DIODE: A Dense Indoor and Outdoor DEpth Dataset


Aug 29, 2019
Igor Vasiljevic, Nick Kolkin, Shanyi Zhang, Ruotian Luo, Haochen Wang, Falcon Z. Dai, Andrea F. Daniele, Mohammadreza Mostajabi, Steven Basart, Matthew R. Walter, Gregory Shakhnarovich


  Access Paper or Ask Questions

Natural and Adversarial Error Detection using Invariance to Image Transformations


Feb 01, 2019
Yuval Bahat, Michal Irani, Gregory Shakhnarovich


  Access Paper or Ask Questions

Semantic speech retrieval with a visually grounded model of untranscribed speech


Oct 31, 2018
Herman Kamper, Gregory Shakhnarovich, Karen Livescu

* IEEE/ACM Transactions on Audio, Speech and Language Processing 27 (2019) 89-98 
* 10 pages, 3 figures, 5 tables; accepted to the IEEE/ACM Transactions on Audio, Speech and Language Processing 

  Access Paper or Ask Questions

Discriminability objective for training descriptive captions


Jun 08, 2018
Ruotian Luo, Brian Price, Scott Cohen, Gregory Shakhnarovich

* CVPR2018 

  Access Paper or Ask Questions

Regularizing Deep Networks by Modeling and Predicting Label Structure


Apr 05, 2018
Mohammadreza Mostajabi, Michael Maire, Gregory Shakhnarovich

* to appear at CVPR 2018 

  Access Paper or Ask Questions

Confidence from Invariance to Image Transformations


Apr 02, 2018
Yuval Bahat, Gregory Shakhnarovich


  Access Paper or Ask Questions

Learning Representations for Automatic Colorization


Aug 13, 2017
Gustav Larsson, Michael Maire, Gregory Shakhnarovich

* ECCV 2016 (Project page: http://people.cs.uchicago.edu/~larsson/colorization/

  Access Paper or Ask Questions

Colorization as a Proxy Task for Visual Understanding


Aug 13, 2017
Gustav Larsson, Michael Maire, Gregory Shakhnarovich

* CVPR 2017 (Project page: http://people.cs.uchicago.edu/~larsson/color-proxy/

  Access Paper or Ask Questions

Training Deep Networks to be Spatially Sensitive


Aug 07, 2017
Nicholas Kolkin, Gregory Shakhnarovich, Eli Shechtman

* ICCV 2017 

  Access Paper or Ask Questions

Examining the Impact of Blur on Recognition by Convolutional Networks


May 30, 2017
Igor Vasiljevic, Ayan Chakrabarti, Gregory Shakhnarovich


  Access Paper or Ask Questions

FractalNet: Ultra-Deep Neural Networks without Residuals


May 26, 2017
Gustav Larsson, Michael Maire, Gregory Shakhnarovich

* updated with ImageNet results; published as a conference paper at ICLR 2017; project page at http://people.cs.uchicago.edu/~larsson/fractalnet/ 

  Access Paper or Ask Questions

Visually grounded learning of keyword prediction from untranscribed speech


May 25, 2017
Herman Kamper, Shane Settle, Gregory Shakhnarovich, Karen Livescu

* 5 pages, 3 figures, 5 tables; small updates, added link to code; accepted to Interspeech 2017 

  Access Paper or Ask Questions

Comprehension-guided referring expressions


Jan 12, 2017
Ruotian Luo, Gregory Shakhnarovich


  Access Paper or Ask Questions

Diverse Sampling for Self-Supervised Learning of Semantic Segmentation


Dec 06, 2016
Mohammadreza Mostajabi, Nicholas Kolkin, Gregory Shakhnarovich


  Access Paper or Ask Questions

Lexicon-Free Fingerspelling Recognition from Video: Data, Models, and Signer Adaptation


Sep 26, 2016
Taehwan Kim, Jonathan Keane, Weiran Wang, Hao Tang, Jason Riggle, Gregory Shakhnarovich, Diane Brentari, Karen Livescu

* arXiv admin note: substantial text overlap with arXiv:1608.08339 

  Access Paper or Ask Questions

Depth from a Single Image by Harmonizing Overcomplete Local Network Predictions


Sep 07, 2016
Ayan Chakrabarti, Jingyu Shao, Gregory Shakhnarovich

* NIPS 2016. Project page at http://www.ttic.edu/chakrabarti/mdepth/ 

  Access Paper or Ask Questions

Feedforward semantic segmentation with zoom-out features


Dec 02, 2014
Mohammadreza Mostajabi, Payman Yadollahpour, Gregory Shakhnarovich


  Access Paper or Ask Questions