Gregory Shakhnarovich

82 papers A* 21A 3Journal 32Unranked 24

Year	Rank	Type	Title / Venue / Authors
2025	—	`conf`	EditDuet: A Multi-Agent System for Video Non-Linear Editing. SIGGRAPH (Conference Paper Track) Marcelo Sandoval-Castañeda, Bryan C. Russell, Josef Sivic, Gregory Shakhnarovich, Fabian Caba Heilbron
2025	J	`jnl`	EditDuet: A Multi-Agent System for Video Non-Linear Editing. CoRR Marcelo Sandoval-Castañeda, Bryan C. Russell, Josef Sivic, Gregory Shakhnarovich, Fabian Caba Heilbron
2024	A	`conf`	Transcrib3D: 3D Referring Expression Resolution through Large Language Models. IROS Jiading Fang, Xiangshan Tan, Shengjie Lin, Igor Vasiljevic, Vitor Guizilini, Hongyuan Mei, Rares Ambrus, Gregory Shakhnarovich, Matthew R. Walter
2024	J	`jnl`	Transcrib3D: 3D Referring Expression Resolution through Large Language Models. CoRR Jiading Fang, Xiangshan Tan, Shengjie Lin, Igor Vasiljevic, Vitor Guizilini, Hongyuan Mei, Rares Ambrus, Gregory Shakhnarovich, Matthew R. Walter
2023	J	`jnl`	6-DoF Stability Field via Diffusion Models. CoRR Takuma Yoneda, Tianchong Jiang, Gregory Shakhnarovich, Matthew R. Walter
2023	J	`jnl`	NeRFuser: Large-Scale Scene Representation by NeRF Fusion. CoRR Jiading Fang, Shengjie Lin, Igor Vasiljevic, Vitor Guizilini, Rares Ambrus, Adrien Gaidon, Gregory Shakhnarovich, Matthew R. Walter
2023	J	`jnl`	Self-Supervised Video Transformers for Isolated Sign Language Recognition. CoRR Marcelo Sandoval-Castañeda, Yanhong Li, Diane Brentari, Karen Livescu, Gregory Shakhnarovich
2023	—	`conf`	TTIC's Submission to WMT-SLT 23. WMT Marcelo Sandoval-Castañeda, Yanhong Li, Bowen Shi, Diane Brentari, Karen Livescu, Gregory Shakhnarovich
2022	A*	`conf`	Open-Domain Sign Language Translation Learned from Online Video. EMNLP Bowen Shi, Diane Brentari, Gregory Shakhnarovich, Karen Livescu
2022	—	`conf`	TTIC's WMT-SLT 22 Sign Language Translation System. WMT Bowen Shi, Diane Brentari, Gregory Shakhnarovich, Karen Livescu
2020	J	`jnl`	Analysis of diversity-accuracy tradeoff in image captioning. CoRR Ruotian Luo, Gregory Shakhnarovich
2020	J	`jnl`	Classification Confidence Estimation with Test-Time Data-Augmentation. CoRR Yuval Bahat, Gregory Shakhnarovich
2020	—	`conf`	Deformable Style Transfer. ECCV (26) Sunnie S. Y. Kim, Nicholas I. Kolkin, Jason Salavon, Gregory Shakhnarovich
2020	J	`jnl`	Deformable Style Transfer. CoRR Sunnie S. Y. Kim, Nicholas I. Kolkin, Jason Salavon, Gregory Shakhnarovich
2019	J	`jnl`	DIODE: A Dense Indoor and Outdoor DEpth Dataset. CoRR Igor Vasiljevic, Nicholas I. Kolkin, Shanyi Zhang, Ruotian Luo, Haochen Wang, Falcon Z. Dai, Andrea F. Daniele, Mohammadreza Mostajabi, Steven Basart, Matthew R. Walter, Gregory Shakhnarovich
2019	J	`jnl`	Natural and Adversarial Error Detection using Invariance to Image Transformations. CoRR Yuval Bahat, Michal Irani, Gregory Shakhnarovich
2019	A*	`conf`	Recurrent Back-Projection Network for Video Super-Resolution. CVPR Muhammad Haris, Gregory Shakhnarovich, Norimichi Ukita
2019	J	`jnl`	Semantic Speech Retrieval With a Visually Grounded Model of Untranscribed Speech. IEEE ACM Trans. Audio Speech Lang. Process. Herman Kamper, Gregory Shakhnarovich, Karen Livescu
2019	A*	`conf`	Style Transfer by Relaxed Optimal Transport and Self-Similarity. CVPR Nicholas I. Kolkin, Jason Salavon, Gregory Shakhnarovich
2018	J	`jnl`	Confidence from Invariance to Image Transformations. CoRR Yuval Bahat, Gregory Shakhnarovich
2018	A*	`conf`	Deep Back-Projection Networks for Super-Resolution. CVPR Muhammad Haris, Gregory Shakhnarovich, Norimichi Ukita
2018	A*	`conf`	Discriminability Objective for Training Descriptive Captions. CVPR Ruotian Luo, Brian L. Price, Scott Cohen, Gregory Shakhnarovich
2018	J	`jnl`	Discriminability objective for training descriptive captions. CoRR Ruotian Luo, Brian L. Price, Scott Cohen, Gregory Shakhnarovich
2018	A*	`conf`	Regularizing Deep Networks by Modeling and Predicting Label Structure. CVPR Mohammadreza Mostajabi, Michael Maire, Gregory Shakhnarovich
2018	J	`jnl`	Regularizing Deep Networks by Modeling and Predicting Label Structure. CoRR Mohammadreza Mostajabi, Michael Maire, Gregory Shakhnarovich
2018	—	`conf`	Semantic Speech Retrieval With a Visually Grounded Model of Untranscribed Speech. CVPR Workshops Herman Kamper, Gregory Shakhnarovich, Karen Livescu
2017	A*	`conf`	Colorization as a Proxy Task for Visual Understanding. CVPR Gustav Larsson, Michael Maire, Gregory Shakhnarovich
2017	J	`jnl`	Colorization as a Proxy Task for Visual Understanding. CoRR Gustav Larsson, Michael Maire, Gregory Shakhnarovich
2017	A*	`conf`	Comprehension-Guided Referring Expressions. CVPR Ruotian Luo, Gregory Shakhnarovich
2017	J	`jnl`	Comprehension-guided referring expressions. CoRR Ruotian Luo, Gregory Shakhnarovich
2017	—	`conf`	FractalNet: Ultra-Deep Neural Networks without Residuals. ICLR (Poster) Gustav Larsson, Michael Maire, Gregory Shakhnarovich
2017	J	`jnl`	Lexicon-free fingerspelling recognition from video: Data, models, and signer adaptation. Comput. Speech Lang. Taehwan Kim, Jonathan Keane, Weiran Wang, Hao Tang, Jason Riggle, Gregory Shakhnarovich, Diane Brentari, Karen Livescu
2017	J	`jnl`	Semantic keyword spotting by learning from images and speech. CoRR Herman Kamper, Gregory Shakhnarovich, Karen Livescu
2017	A*	`conf`	Training Deep Networks to be Spatially Sensitive. ICCV Nicholas I. Kolkin, Gregory Shakhnarovich, Eli Shechtman
2017	J	`jnl`	Training Deep Networks to be Spatially Sensitive. CoRR Nicholas I. Kolkin, Gregory Shakhnarovich, Eli Shechtman
2017	A	`conf`	Visually Grounded Learning of Keyword Prediction from Untranscribed Speech. INTERSPEECH Herman Kamper, Shane Settle, Gregory Shakhnarovich, Karen Livescu
2017	J	`jnl`	Visually grounded learning of keyword prediction from untranscribed speech. CoRR Herman Kamper, Shane Settle, Gregory Shakhnarovich, Karen Livescu
2016	J	`jnl`	Depth from a Single Image by Harmonizing Overcomplete Local Network Predictions. CoRR Ayan Chakrabarti, Jingyu Shao, Gregory Shakhnarovich
2016	J	`jnl`	Diverse Sampling for Self-Supervised Learning of Semantic Segmentation. CoRR Mohammadreza Mostajabi, Nicholas I. Kolkin, Gregory Shakhnarovich
2016	J	`jnl`	Examining the Impact of Blur on Recognition by Convolutional Networks. CoRR Igor Vasiljevic, Ayan Chakrabarti, Gregory Shakhnarovich
2016	J	`jnl`	FractalNet: Ultra-Deep Neural Networks without Residuals. CoRR Gustav Larsson, Michael Maire, Gregory Shakhnarovich
2016	—	`conf`	Learning Representations for Automatic Colorization. ECCV (4) Gustav Larsson, Michael Maire, Gregory Shakhnarovich
2016	J	`jnl`	Learning Representations for Automatic Colorization. CoRR Gustav Larsson, Michael Maire, Gregory Shakhnarovich
2016	J	`jnl`	Lexicon-Free Fingerspelling Recognition from Video: Data, Models, and Signer Adaptation. CoRR Taehwan Kim, Jonathan Keane, Weiran Wang, Hao Tang, Jason Riggle, Gregory Shakhnarovich, Diane Brentari, Karen Livescu
2015	A*	`conf`	Feedforward semantic segmentation with zoom-out features. CVPR Mohammadreza Mostajabi, Payman Yadollahpour, Gregory Shakhnarovich
2014	A	`conf`	A Consistent Estimator of the Expected Gradient Outerproduct. UAI Shubhendu Trivedi, Jialei Wang, Samory Kpotufe, Gregory Shakhnarovich
2014	J	`jnl`	Feedforward semantic segmentation with zoom-out features. CoRR Mohammadreza Mostajabi, Payman Yadollahpour, Gregory Shakhnarovich
2014	—	`conf`	Knowing a Good HOG Filter When You See It: Efficient Selection of Filters for Detection. ECCV (1) Ejaz Ahmed, Gregory Shakhnarovich, Subhransu Maji
2014	J	`jnl`	Part and Attribute Discovery from Relative Annotations. Int. J. Comput. Vis. Subhransu Maji, Gregory Shakhnarovich
2013	A*	`conf`	A Systematic Exploration of Diversity in Machine Translation. EMNLP Kevin Gimpel, Dhruv Batra, Chris Dyer, Gregory Shakhnarovich
2013	A*	`conf`	Discriminative Re-ranking of Diverse Segmentations. CVPR Payman Yadollahpour, Dhruv Batra, Gregory Shakhnarovich
2013	A*	`conf`	Fingerspelling Recognition with Semi-Markov Conditional Random Fields. ICCV Taehwan Kim, Gregory Shakhnarovich, Karen Livescu
2013	A*	`conf`	Image Segmentation by Cascaded Region Agglomeration. CVPR Zhile Ren, Gregory Shakhnarovich
2013	A*	`conf`	Part Discovery from Partial Correspondence. CVPR Subhransu Maji, Gregory Shakhnarovich
2012	—	`conf`	American sign language fingerspelling recognition with phonological feature-based tandem models. SLT Taehwan Kim, Karen Livescu, Gregory Shakhnarovich
2012	—	`conf`	Diverse M-Best Solutions in Markov Random Fields. ECCV (5) Dhruv Batra, Payman Yadollahpour, Abner Guzmán-Rivera, Gregory Shakhnarovich
2012	—	`conf`	Part Annotations via Pairwise Correspondence. HCOMP@AAAI Subhransu Maji, Gregory Shakhnarovich
2012	J	`jnl`	Viewpoint-aware object detection and continuous pose estimation. Image Vis. Comput. Daniel Glasner, Meirav Galun, Sharon Alpert, Ronen Basri, Gregory Shakhnarovich
2011	—	`ch.`	Face Recognition in Subspaces. Handbook of Face Recognition Gregory Shakhnarovich, Baback Moghaddam
2011	A*	`conf`	Viewpoint-aware object detection and pose estimation. ICCV Daniel Glasner, Meirav Galun, Sharon Alpert, Ronen Basri, Gregory Shakhnarovich
2010	—	`conf`	Sparse Coding for Learning Interpretable Spatio-Temporal Primitives. NIPS Taehwan Kim, Gregory Shakhnarovich, Raquel Urtasun
2009	J	`jnl`	Discovery of phosphorylation motif mixtures in phosphoproteomics data. Bioinform. Anna M. Ritz, Gregory Shakhnarovich, Arthur R. Salomon, Benjamin J. Raphael
2008	—	`conf`	A Slicing-Based Coherence Measure for Clusters of DTI Integral Curves. MICCAI (1) Çagatay Demiralp, Gregory Shakhnarovich, Song Zhang, David H. Laidlaw
2008	J	`jnl`	Nearest-Neighbor Methods in Learning and Vision. IEEE Trans. Neural Networks Gregory Shakhnarovich, Trevor Darrell, Piotr Indyk
2006	A*	`conf`	An investigation of computational and informational limits in Gaussian mixture clustering. ICML Nathan Srebro, Gregory Shakhnarovich, Sam T. Roweis
2006	—	`conf`	Conditional Random People: Tracking Humans with CRFs and Grid Filters. CVPR (1) Leonid Taycher, David Demirdjian, Trevor Darrell, Gregory Shakhnarovich
2006	—	`conf`	Nonlinear physically-based models for decoding motor-cortical population activity. NIPS Gregory Shakhnarovich, Sung-Phil Kim, Michael J. Black
2005	A*	`conf`	Avoiding the "Streetlight Effect": Tracking by Exploring Likelihood Modes. ICCV David Demirdjian, Leonid Taycher, Gregory Shakhnarovich, Kristen Grauman, Trevor Darrell
2005	—	`conf`	Face Recognition with Image Sets Using Manifold Density Divergence. CVPR (1) Ognjen Arandjelovic, Gregory Shakhnarovich, John Fisher, Roberto Cipolla, Trevor Darrell
2005	J	`jnl`	Learning silhouette features for control of human motion. ACM Trans. Graph. Liu Ren, Gregory Shakhnarovich, Jessica K. Hodgins, Hanspeter Pfister, Paul A. Viola
2005	—	`—`	Learning task-specific similarity. Gregory Shakhnarovich
2004	—	`conf`	Learning silhouette features for control of human motion. SIGGRAPH Sketches Liu Ren, Gregory Shakhnarovich, Jessica K. Hodgins, Hanspeter Pfister, Paul A. Viola
2004	—	`conf`	Virtual Visual Hulls: Example-Based 3D Shape Inference from Silhouettes. ECCV Workshop SMVP Kristen Grauman, Gregory Shakhnarovich, Trevor Darrell
2003	—	`conf`	A Bayesian Approach to Image-Based Visual Hull Reconstruction. CVPR (1) Kristen Grauman, Gregory Shakhnarovich, Trevor Darrell
2003	A*	`conf`	Fast Pose Estimation with Parameter-Sensitive Hashing. ICCV Gregory Shakhnarovich, Paul A. Viola, Trevor Darrell
2003	A*	`conf`	Inferring 3D Structure with a Statistical Image-Based Shape Model. ICCV Kristen Grauman, Gregory Shakhnarovich, Trevor Darrell
2002	—	`conf`	A Unified Learning Framework for Real Time Face Detection and Classification. FGR Gregory Shakhnarovich, Paul A. Viola, Baback Moghaddam
2002	—	`conf`	Boosted Dyadic Kernel Discriminants. NIPS Baback Moghaddam, Gregory Shakhnarovich
2002	—	`conf`	Face Recognition from Long-Term Observations. ECCV (3) Gregory Shakhnarovich, John W. Fisher III, Trevor Darrell
2002	—	`conf`	On Probabilistic Combination of Face and Gait Cues for Identification. FGR Gregory Shakhnarovich, Trevor Darrell
2001	—	`conf`	Integrated Face and Gait Recognition From Multiple Views. CVPR (1) Gregory Shakhnarovich, Lily Lee, Trevor Darrell
2001	A*	`conf`	Smoothed Bootstrap and Statistical Data Cloning for Classifier Evaluation. ICML Gregory Shakhnarovich, Ran El-Yaniv, Yoram Baram