SVETLANA LAZEBNIK

PUBLICATIONS


2021

Bridging the Imitation Gap by Adaptive Insubordination.
L. Weihs*, U. Jain*, I.-J. Liu, J. Salvador, S. Lazebnik, A. Kembhavi, and A. Schwing.
Advances in Neural Information Processing Systems, 2021.
Project webpage
GridToPix: Training Embodied Agents with Minimal Supervision.
U. Jain, I.-J. Liu, S. Lazebnik, A. Kembhavi, L. Weihs*, and A. Schwing*.
International Conference on Computer Vision, 2021.
Project webpage
Interpretation of Emergent Communication in Heterogeneous Collaborative Embodied Agents.
S. Patel*, S. Wani*, U. Jain*, A. Schwing, S. Lazebnik, M. Savva, and A. X. Chang.
International Conference on Computer Vision, 2021.
Project webpage
Dressing in Order: Recurrent Person Image Generation for Pose Transfer, Virtual Try-on and Outfit Editing.
A. Cui, D. McKee, and S. Lazebnik.
International Conference on Computer Vision, 2021.
Project webpage

2020

Revisiting Image-Language Networks for Open-ended Phrase Detection.
B. Plummer, K. Shih, Y. Li, K. Xu, S. Lazebnik, S. Sclaroff, and K. Saenko.
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020.
A Cordial Sync: Going Beyond Marginal Policies for Multi-Agent Embodied Tasks.
U. Jain, L. Weihs, E. Kolve, A. Farhadi, S. Lazebnik, A. Kembhavi, and A. Schwing.
European Conference on Computer Vision, 2020.
Memory-Efficient Incremental Learning Through Feature Adaptation.
A. Iscen, J. Zhang, S. Lazebnik, and C. Schmid.
European Conference on Computer Vision, 2020.
Contextual Translation Embedding for Visual Relationship Detection and Scene Graph Generation.
Z.-S. Hung, A. Mallya, and S. Lazebnik.
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020.

2019

Two Body Problem: Collaborative Visual Task Completion.
U. Jain, L. Weihs, E. Kolve, M. Rastegari, S. Lazebnik, A. Farhadi, A. Schwing, and A. Kembhavi.
IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019.
Combining Multiple Cues for Visual Madlibs Question Answering.
T. Tommasi, A. Mallya, B. Plummer, S. Lazebnik, A. Berg, and T. Berg.
International Journal of Computer Vision, vol. 127, January 2019, pp. 38-60.
Learning Two-Branch Neural Networks for Image-Text Matching Tasks.
L. Wang, Y. Li, J. Huang, and S. Lazebnik.
IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 41, no. 2, February 2019, pp. 394-407.
  Proceedings of the International Conference on Computer Vision.
I. S. Kweon, S. Lazebnik, N. Paragios, and M.-H. Yang (editors).
IEEE/CVF, 2019.

2018

Out of the Box: Reasoning with Graph Convolution Nets for Factual Visual Question Answering.
M. Narasimhan, S. Lazebnik, and A. Schwing.
Advances in Neural Information Processing Systems, 2018.
Conditional Image-Text Embedding Networks.
B. Plummer, P. Kordas, H. Kiapour, S. Zheng, R. Piramuthu, and S. Lazebnik.
European Conference on Computer Vision, 2018.
Piggyback: Adapting a Single Network to Multiple Tasks by Learning to Mask Weights.
A. Mallya, D. Davis, and S. Lazebnik.
European Conference on Computer Vision, 2018.
PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning.
A. Mallya and S. Lazebnik.
IEEE Conference on Computer Vision and Pattern Recognition, 2018.
Two can Play this Game: Visual Dialog with Discriminative Question Generation and Answering.
U. Jain, S. Lazebnik, and A. Schwing.
IEEE Conference on Computer Vision and Pattern Recognition, 2018.

2017

Diverse and Accurate Image Description Using a Variational Auto-Encoder with an Additive Gaussian Encoding Space.
L. Wang, A. Schwing, and S. Lazebnik.
Advances in Neural Information Processing Systems, 2017.
Recurrent Models for Situation Recognition.
A. Mallya and S. Lazebnik.
International Conference on Computer Vision, 2017.
Phrase Localization and Visual Relationship Detection with Comprehensive Image-Language Cues.
B. Plummer, A. Mallya, C. Cervantes, J. Hockenmaier, and S. Lazebnik.
International Conference on Computer Vision, 2017.
Enhancing Video Summarization via Vision-Language Embedding.
B. Plummer, M. Brown, and S. Lazebnik.
IEEE Conference on Computer Vision and Pattern Recognition, 2017.
Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models.
B. Plummer, L. Wang, C. Cervantes, J. Caicedo, J. Hockenmaier, and S. Lazebnik.
International Journal of Computer Vision, vol. 123, no. 1, May 2017, pp. 74-93.
Project webpage with data.

2016

Solving Visual Madlibs with Multiple Cues.
T. Tommasi, A. Mallya, B. Plummer, S. Lazebnik, A. Berg, and T. Berg.
Proceedings of the British Machine Vision Conference, 2016.
Learning Models for Actions and Person-Object Interactions with Transfer to Question Answering.
A. Mallya and S. Lazebnik.
Proceedings of the European Conference on Computer Vision, 2016.
Learning Deep Structure-Preserving Image-Text Embeddings.
L. Wang, Y. Li, and S. Lazebnik.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016.
Adaptive Object Detection Using Adjacency and Zoom Prediction.
Y. Lu, T. Javidi, and S. Lazebnik.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016.
Code on GitHub.

2015

Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models.
B. Plummer, L. Wang, C. Cervantes, J. Caicedo, J. Hockenmaier, and S. Lazebnik.
International Conference on Computer Vision, 2015.
Project webpage with data.
Learning Informative Edge Maps for Indoor Scene Layout Prediction.
A. Mallya and S. Lazebnik.
International Conference on Computer Vision, 2015.
Active Object Localization with Deep Reinforcement Learning.
J. Caicedo and S. Lazebnik.
International Conference on Computer Vision, 2015.
Spotlight video with examples.
Where to Buy It: Matching Street Clothing Photos in Online Shops.
H. Kiapour, X. Han, S. Lazebnik, A. Berg, and T. Berg.
International Conference on Computer Vision, 2015.
Project webpage.
Scene Parsing with Object Instance Inference Using Regions and Per-exemplar Detectors.
J. Tighe, M. Niethammer, and S. Lazebnik.
International Journal of Computer Vision, vol. 112, no. 2, April 2015, pp. 150-171.

2014

Improving Image-Sentence Embeddings Using Large Weakly Annotated Photo Collections.
Y. Gong, L. Wang, M. Hodosh, J. Hockenmaier, and S. Lazebnik.
Proceedings of the European Conference on Computer Vision, 2014.
Multi-Scale Orderless Pooling of Deep Convolutional Activation Features.
Y. Gong, L. Wang, R. Guo, and S. Lazebnik.
Proceedings of the European Conference on Computer Vision, 2014.
Scene Parsing with Object Instances and Occlusion Ordering.
J. Tighe, M. Niethammer, and S. Lazebnik.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2014.
A Multi-View Embedding Space for Modeling Internet Images, Tags, and Their Semantics.
Y. Gong, Q. Ke, M. Isard, and S. Lazebnik.
International Journal of Computer Vision, vol. 106, no. 2, January 2014, pp. 210-233.
Asymmetric Distances for Binary Embeddings.
A. Gordo, F. Perronnin, Y. Gong, and S. Lazebnik.
IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 36, no. 1, January 2014, pp. 33-47.

2013

Iterative Quantization: A Procrustean Approach to Learning Binary Codes for Large-Scale Image Retrieval.
Y. Gong, S. Lazebnik, A. Gordo, and F. Perronnin.
IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 35, no. 12, December 2013, pp. 2916-2929.
ITQ code.
Finding Things: Image Parsing with Regions and Per-Exemplar Detectors.
J. Tighe and S. Lazebnik.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2013.
Learning Binary Codes for High-dimensional Data Using Bilinear Projections.
Y. Gong, S. Kumar, H. Rowley, and S. Lazebnik.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2013.
Towards Open-Universe Image Parsing with Broad Coverage.
J. Tighe and S. Lazebnik.
Proceedings of IAPR International Conference on Machine Vision Applications, 2013, invited paper.
A Recursive Procedure for Density Estimation on the Binary Hypercube.
M. Raginsky, J. Silva, S. Lazebnik, and R. Willett.
Electronic Journal of Statistics, vol. 7, 2013, pp. 820-858.
Open-access paper.
SuperParsing: Scalable Nonparametric Image Parsing with Superpixels.
J. Tighe and S. Lazebnik.
International Journal of Computer Vision, vol. 101, no. 2, January 2013, pp. 329-349.

2012

Angular Quantization-Based Binary Codes for Fast Similarity Search.
Y. Gong, S. Kumar, V. Verma and S. Lazebnik.
Advances in Neural Information Processing Systems, 2012.
Proceedings of the 12th European Conference on Computer Vision.
A. Fitzgibbon, S. Lazebnik, P. Perona, Y. Sato, and C. Schmid (editors).
Lecture Notes in Computer Science, volumes 7572-7578, Springer-Verlag, 2012.

2011

Understanding Scenes on Many Levels.
J. Tighe and S. Lazebnik.
Proceedings of the IEEE International Conference on Computer Vision, 2011.
Scene Recognition and Weakly Supervised Object Localization with Deformable Part-Based Models.
M. Pandey and S. Lazebnik.
Proceedings of the IEEE International Conference on Computer Vision, 2011.
Iterative Quantization: A Procrustean Approach to Learning Binary Codes.
Y. Gong and S. Lazebnik.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2011.
ITQ code.
Comparing Data-Dependent and Data-Independent Embeddings for Classification and Ranking of Internet Images.
Y. Gong and S. Lazebnik.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2011.
Modeling and Recognition of Landmark Image Collections Using Iconic Scene Graphs.
R. Raguram, C. Wu, J.-M. Frahm, and S. Lazebnik.
International Journal of Computer Vision, vol. 95, no. 3, December 2011, pp. 213-239.

2010

SuperParsing: Scalable Nonparametric Image Parsing with Superpixels.
J. Tighe and S. Lazebnik.
Proceedings of the European Conference on Computer Vision, 2010.
Building Rome on a Cloudless Day.
J.-M. Frahm, P. Georgel, D. Gallup, T. Johnson, R. Raguram, C. Wu, Y.-H. Jen, E. Dunn, B. Clipp, S. Lazebnik, and M. Pollefeys.
Proceedings of the European Conference on Computer Vision, 2010.
Video.
Fast Robust Large-scale Mapping from Video and Internet Photo Collections.
J.-M. Frahm, M. Pollefeys, S. Lazebnik, C. Zach, D. Gallup, B. Clipp, R. Raguram, C. Wu, and T. Johnson.
ISPRS Journal of Photogrammetry and Remote Sensing, vol. 65, no. 6 (special issue on 100 years of ISPRS), 2010, pp. 538-549.
Fast Robust Reconstruction of Large Scale Environments.
J.-M. Frahm, M. Pollefeys, S. Lazebnik, B. Clipp, D. Gallup, R. Raguram, and C. Wu.
Conference on Information Sciences and Systems (CISS), 2010.

2009

Locality Sensitive Binary Codes from Shift-Invariant Kernels.
M. Raginsky and S. Lazebnik.
Advances in Neural Information Processing Systems, 2009.
Supervised Learning of Quantizer Codebooks by Information Loss Minimization.
S. Lazebnik and M. Raginsky.
IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 31, no. 7, July 2009, pp. 1294-1309.
An Empirical Bayes Approach to Contextual Region Classification.
S. Lazebnik and M. Raginsky.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2009.
Spatial Pyramid Matching.
S. Lazebnik, C. Schmid, and J. Ponce.
Object Categorization: Computer and Human Vision Perspectives.
S. Dickinson, A. Leonardis, B. Schiele, and M. Tarr (eds.), Cambridge University Press, 2009.

2008

Near-Minimax Recursive Density Estimation on the Binary Hypercube.
M. Raginsky, S. Lazebnik, R. Willett, and J. Silva.
Advances in Neural Information Processing Systems, 2008.
Analysis of Human Attractiveness Using Manifold Kernel Regression.
B. Davis and S. Lazebnik.
Proceedings of the IEEE International Conference on Image Processing (Special Session on Aesthetics, Mood, and Emotion), 2008.
Modeling and Recognition of Landmark Image Collections Using Iconic Scene Graphs.
X. Li, C. Wu, C. Zach, S. Lazebnik and J.-M. Frahm.
Proceedings of the European Conference on Computer Vision, 2008.
Computing Iconic Summaries for General Visual Concepts.
R. Raguram and S. Lazebnik.
First IEEE Workshop on Internet Vision (held in conjunction with CVPR), 2008.

2007

Learning Nearest-Neighbor Quantizers from Labeled Data by Information Loss Minimization.
S. Lazebnik and M. Raginsky.
International Conference on Artificial Intelligence and Statistics, 2007.
Projective Visual Hulls.
S. Lazebnik, Y. Furukawa, and J. Ponce.
International Journal of Computer Vision, vol. 74, no. 2, August 2007, pp. 137-165.
Segmenting, Modeling, and Matching Video Clips Containing Multiple Moving Objects.
F. Rothganger, S. Lazebnik, C. Schmid, and J. Ponce.
IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 29, no. 3, March 2007, pp. 477-491.
Local Features and Kernels for Classification of Texture and Object Categories: A Comprehensive Study.
J. Zhang, M. Marszalek, S. Lazebnik, and C. Schmid.
International Journal of Computer Vision, vol. 73, no. 2, June 2007, pp. 213-238.

2006

Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories.
S. Lazebnik, C. Schmid, and J. Ponce.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, New York, June 2006, vol. II, pp. 2169-2178.
MATLAB code, 15 scene category dataset.
Local, Semi-Local and Global Models for Texture, Object and Scene Recognition.
S. Lazebnik.
Ph.D. Dissertation, May 2006 (also Beckman CVR Technical Report 2006-01).
Defense slides.
3D Object Modeling and Recognition Using Local Affine-Invariant Image Descriptors and Multi-View Spatial Constraints.
F. Rothganger, S. Lazebnik, C. Schmid, and J. Ponce.
International Journal of Computer Vision, vol. 66, no. 3, March 2006, pp. 231-259.
Dataset Issues in Object Recognition.
J. Ponce, T. L. Berg, M. Everingham, D. A. Forsyth, M. Hebert, S. Lazebnik, M. Marszalek, C. Schmid, B. C. Russell, A. Torralba, C. K. I. Williams, J. Zhang, and A. Zisserman.
Toward Category-Level Object Recognition, Springer-Verlag Lecture Notes in Computer Science vol. 4170.
J. Ponce, M. Hebert, C. Schmid, and A. Zisserman (eds.), 2006, pp. 29-48.
A Discriminative Framework for Texture and Object Recognition Using Local Image Features.
S. Lazebnik, C. Schmid, and J. Ponce.
Toward Category-Level Object Recognition, Springer-Verlag Lecture Notes in Computer Science vol. 4170.
J. Ponce, M. Hebert, C. Schmid, and A. Zisserman (eds.), 2006, pp. 423-442.
3D Object Modeling and Recognition from Photographs and Image Sequences.
F. Rothganger, S. Lazebnik, C. Schmid, and J. Ponce.
Toward Category-Level Object Recognition, Springer-Verlag Lecture Notes in Computer Science vol. 4170.
J. Ponce, M. Hebert, C. Schmid, and A. Zisserman (eds.), 2006, pp. 105-126.

2005

Estimation of Intrinsic Dimensionality Using High-Rate Vector Quantization.
M. Raginsky and S. Lazebnik.
Advances in Neural Information Processing Systems 18, MIT Press, 2005, pp. 1105-1112.
A Maximum Entropy Framework for Part-Based Texture and Object Recognition.
S. Lazebnik, C. Schmid, and J. Ponce.
Proceedings of the IEEE International Conference on Computer Vision, Beijing, China, October 2005, vol. 1, pp. 832-838.
A Sparse Texture Representation Using Local Affine Regions.
S. Lazebnik, C. Schmid, and J. Ponce.
IEEE Transactions on Pattern Analysis and Machine Intelligence, August 2005, vol. 27, no. 8, pp. 1265-1278.
UIUC texture dataset.
The Local Projective Shape of Smooth Surfaces and Their Outlines.
S. Lazebnik and J. Ponce.
International Journal of Computer Vision, June 2005, vol. 63, no. 1, pp. 65-83.
Pattern Recognition with Local Invariant Features.
C. Schmid, G. Dorko, S. Lazebnik, K. Mikolajczyk, and J. Ponce.
Handbook of Pattern Recognition and Computer Vision, 3rd edition.
C.H. Chen and P.S.P Wang editors, World Scientific Publishing Co., 2005, pp. 71-92.

2004

Semi-Local Affine Parts for Object Recognition.
S. Lazebnik, C. Schmid, and J. Ponce.
Proceedings of the British Machine Vision Conference, Kingston, UK, September 2004, vol. 2, pp. 959-968.
Segmenting, Modeling, and Matching Video Clips Containing Multiple Moving Objects.
F. Rothganger, S. Lazebnik, C. Schmid, and J. Ponce.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Washington, DC, June 2004, vol. 2, pp. 914-921.
Toward True 3D Object Recognition.
J. Ponce, S. Lazebnik, F. Rothganger, and C. Schmid.
Congrès de Reconnaissance des Formes et Intelligence Artificielle, Toulouse, France, January 2004.

2003

Affine-Invariant Local Descriptors and Neighborhood Statistics for Texture Recognition.
S. Lazebnik, C. Schmid, and J. Ponce.
Proceedings of the IEEE International Conference on Computer Vision, Nice, France, October 2003, pp. 649-655.
The Local Projective Shape of Smooth Surfaces and Their Outlines.
S. Lazebnik and J. Ponce.
Proceedings of the IEEE International Conference on Computer Vision, Nice, France, October 2003, pp. 83-89.
A Sparse Texture Representation Using Affine-Invariant Regions.
S. Lazebnik, C. Schmid, and J. Ponce.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Madison, WI, June 2003, Vol. II, pp. 319-324.
3D Object Modeling and Recognition Using Affine-Invariant Patches and Multi-View Spatial Constraints.
F. Rothganger, S. Lazebnik, C. Schmid, and J. Ponce.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Madison, WI, June 2003, Vol. II, pp. 272-277.
3D Photography from Photographs and Video Clips.
J. Ponce, F. Rothganger, S. Lazebnik, K. McHenry, C. Schmid, S. Mahamud, and M. Hebert.
Proceedings of the International Symposium on Core Research for Evolutional Science, Technology (CREST) --- Ikeuchi Project, Tokyo, Japan, 2003, pp. 153-182.

2002

Projective Visual Hulls.
S. Lazebnik.
M.S. Thesis, December 2002 (also Beckman CVR Technical Report 2002-01).
Winner of the David J. Kuck Best Master's Thesis Award.
On Pencils of Tangent Planes and the Recognition of Smooth 3D Shapes from Silhouettes.
S. Lazebnik, A. Sethi, C. Schmid, D. Kriegman, J. Ponce and M. Hebert.
Proceedings of the European Conference on Computer Vision, Copenhagen, Denmark, May 2002.
Springer-Verlag Lecture Notes in Computer Science 2352, pp. 651-665.

2001

Visibility-Based Pursuit Evasion in Three-Dimensional Environments.
S. Lazebnik.
Beckman CVR Technical Report 2001-01.
On Computing Exact Visual Hulls of Solids Bounded by Smooth Surfaces.
S. Lazebnik, E. Boyer, and J. Ponce.
Proceedings of the 2001 IEEE Conference on Computer Vision and Pattern Recognition, Kauai, Hawaii, December 2001, Vol. 1, pp. 156-161.