Publications (by date)

• Interpreting the Ratio Criterion for Matching SIFT Descriptors. Avi Kaplan, Tamar Avraham, Michael Lindenbaum. ECCV 2016

• Depth Perception in Autostereograms: 1/f-Noise is Best‏. Yael Yankelevsky, Ishai Shvartz, Tamar Avraham, Alfred M. Bruckstein. JOSA 2016

• Temporal Face Embedding and Propagation in Photo Collections. Markus Brenner, Tamar Avraham, Michael Lindenbaum, and Ebroul Izquierdo. In proceeding of the IEEE ICIP (International Conference on Image Processing), 2014

• Learning Appearance Transfer for Person Re-Identification. Tamar Avraham and Michael Lindenbaum, invited book chapter in S. Gong, M. Cristani, S. Yan, C.C. Loy (Eds.).Person Re-Identification, Springer, January 2014 (book preface & intro: The Re-Identification Challenge), See more  details and code

• Transitive Re-identification. Yulia Brand, Tamar Avraham, and Michael Lindenbaum, BMVC (British Machine Vision Conference) 2013, extended abstract, presentation, See more details and code

• Learning Implicit Transfer for Person Re-identification. Tamar Avraham, Ilya Gurvich, Michael Lindenbaum, and Shaul Markovitch, 1st International Workshop on Re-Identification (Re-Id 2012) In conjunction with ECCV 2012, LNCS 7583, pp. 381–390, See more details and code

• Multiple Region Categorization for Scenery Images. Tamar Avraham, Ilya Gurvich, and Michael Lindenbaum, 16^th International Conference on Image Analysis and Processing, 2011, LNCS 6978, pp. 38-47. Presentation

• Modeling Combined Proximity-Similarity Effects in Visual Search. Tamar Avraham, Yaffa Yeshurun and Michael Lindenbaum, Vision Science Society Annual Meeting (VSS), 2011. Presentation

• Multi-Scale Ultrawide Foveated Video Extrapolation. Amit Adies, Tamar Avraham and Yoav Schechner, IEEE-ICCP (International Conference on Computer Photography), 2011.

• Ultrawide Foveated Video Extrapolation. Tamar Avraham and Yoav Schechner, IEEE Journal of Selected Topics in Signal Processing 5(2), 2011. Special Issue on Recent Advances in Processing for Consumer Displays. See movie. See more details and examples.

• Non-Local Characteristics of Scenery Images: Statistics, 3D Reasoning, and a Generative Model. Tamar Avraham and Michael Lindenbaum, ECCV10 – The 11th European Conference on Computer Vision,.Volume V, LNCS6315, pages 99-112, 2010Supplementary document. Poster. Presentation.
• Esaliency (Extended Saliency): Meaningful Attention Using Stochastic Image Modeling Tamar Avraham and Michael Lindenbaum, IEEE-Transactions on Pattern Analysis and Machine Learning (T-PAMI), 32(4):693-708, 2010.
• Predicting Visual Search Performance by Quantifying Stimuli Similarities. Tamar Avraham, Yaffa Yeshurun and Michael Lindenbaum,  Journal of Vision, 8(4):9, 1-22, 2008.

• Evaluating the ability of computer-vision visual search models to predict human performance. Tamar Avraham, Yaffa Yeshurun and Michael Lindenbaum, Vision Science Society Annual Meeting (VSS07), 2007.
• Esaliency – A Stochastic Attention Model Incorporating Similarity Information and Knowledge-Based Preferences. Tamar Avraham and Michael Lindenbaum, International Workshop on the Representation and Use of Prior Knowledge in Vision, in conjunction with ECCV06, 2006.
• Dynamic Visual Search Using Inner Scene Similarity – Algorithms and Bounds. Tamar Avraham and Michael Lindenbaum, IEEE-Transactions on Pattern Analysis and Machine Learning (T-PAMI), 28(2):151-264, 2006.
• Inherent Limitations of Visual Search and the Role of Inner-Scene Similarity. Tamar Avraham and Michael Lindenbaum WAPCV04 – 2nd International Workshop on Attention and Performance in Computational Vision. Lecture Notes in Computer Science, vol. 3368, pp. 16-28, Springer-Verlag, 2005.
• Dynamic Visual Search Using Inner Scene Similarity – Algorithms and Inherent Limitations. Tamar Avraham and Michael Lindenbaum, ECCV04 – The 8th European Conference on Computer Vision.. Volume II, pages 58-70, 2004.
• A Probabilistic Estimation Approach for Dynamic Visual Search. Tamar Avraham and Michael Lindenbaum, WAPCV03 – First International Workshop on Attention and Performance in Computer Vision. 2003.

Ph.D. Thesis

I received my Ph.D. degree from the computer science department, Technion, Israel, in 2008. My
supervisor was Prof. Michael Lindenbaum.

My Thesis mainly deals with different aspects of visual attention for
computer vision systems, but also includes a psychophysical study performed
in cooperation with Dr.
Yaffa Yeshurun, the psychology department, the Haifa University.
Click
here to download my thesis.

To visit our visual attention page, that includes a
downloadable application implementing the Esaliency and VSLE algorithm click here. For saliency maps obtained
from applying the Esaliency algorithm on different datasets, download: Esaliency maps for Bruce
& Tsotsos’s dataset, Esaliency maps for Judd
& Torallba’s dataset, Esaliency maps for Koostra’s
dataset .

Teaching

·    2000-2003: Introduction To Computability Theory (236343)

·    2002-2004: Signal and Image Processing by Computer (236327)

2004: Project in Advanced Programming B – Attention in Computer Vision (236512)

          List of Projects: Migrating ezvision (enabling the usage of Itti’s saliency detection implementation in Windows) – Alexander Kanevsky and Lila Astrachen, 2004Similarity Measures for Attention Order Control – Ishay Goldin and Andrei Sherban, 2004Bottom-up Saliency (Itti based) – Nimrod Bar and Shahar Roth, 2004Learning based Segmentation – Zach Bar, Lior Talker, Moshe Perez, 2004Similarity Measures – Victoria Tchoudakov and Yefim Grossman, 2004Object Recognition using Attention – Muhammad Zidan and Alla Ganaim, 2004Integrating Modules for Visual Attention – Einav Namer and Danny Swartz, 2004

· 2008-2009: Projects advisor, the VISL (the Vision and
Image Sciences lab), electrical engineering dept.

List of Projects:

Image extrapolation based on Drori, Cohen-Or, and Yeshurun’s Image Completion method – Amnon Drory, 2008

Image extrapolation based on Efros and Freeman’s image quilting and on Criminisi et al’s image completion – Noa Fish and Ido Grinblat, 2008

Seam carving for image resizing and extrapolation, based on the paper of Avidan et al – Yosi Chen and Ariel Saba, 2008

· 2005-2007, Since 2009: Advisor for projects in
Intelligent Systems (236754), the ISL lab, the computer science dept.

List of Projects:

Saliency and segmentation for multi-objects – Nancy Sarhan and Samer Abu Samra, 2013

Boundary ownership and depth estimation – Alexandra Levinsky, 2013

Attribute Detection for Face Recognition and Verification – Oded Messer, Alexander Leibenzon, Nave Zeltzer, 2013

Pattern Detection in Dental Images – Yair Atzmon 2013

Improving an affine tracker using pedestrian detection – Diana Soldeo, 2013

Transfer learning using methods designed for re-identification – Efrat Leker, Hilla Goldsher, 2012

Pedestrian re-identification across non-overlapping cameras – Ilya Gurvich, 2012

Context-based object detection – Nitsan Chrizman and Michael Cherkassy, 2011

segmenting scenery images – Inbal Livni and Dolev Raviv, 2011

Background objects recognition – Ilya Gurvich, 2010

A visual attention application – Shai Kadmi and Irena Byzalov, 2010

Face recognition over time – Yonit Nataf and Noa Zifin, 2010

Stochastic attention models for multiple target scenes – Asaf Arnon, 2006

Object Recognition with SIFT (based on David Lowe 2004) – Danny Alboher, 2006

Finding the most promising segments – Tomer Rotstein and Yaarit Hosravi, 2005

Segmentation using the ‘blobworld’ approach – Joseph Vainshtein and Yuval Oren, 2005

Image Quilting and Coloring – Anna Kloper, 2004