Amnon Shashua Last update: March 15, 2012

Curriculum Vitae—Amnon Shashua

Amnon Shashua

School of Computer Science and Engineering Tavor 26 Hebrew University of Mevasert Zion 90805, Jerusalem 91904, ISRAEL +972-2-5334525 (Home) email: [email protected] Born: May 26, 1960, Israel +972-2-658-5988 (Office) Citizenship: Israel +972-54-4533452 (Cell) +972-2-6585439 (Fax)

Contact Address

School of Computer Science and Engineering Hebrew University of Jerusalem Ross Bldg., Givat Ram Jerusalem 91904, ISRAEL [email protected]

Brief Biography

Amnon Shashua holds the Sachs chair in computer science at the Hebrew University. He received his Ph.D. degree in 1993 from the AI lab at MIT working on computational vision where he pioneered work on multiple view geometry and the recognition of objects under variable lighting. His work on multiple view geometry received best paper awards at the ECCV 2000, the Marr prize in ICCV 2001 and the Landau award in exact sciences in 2005. His work on Graphical Models received a best paper award at the UAI 2008. Prof. Shashua was the head of the School of Engineering and Computer Science at the Hebrew University of Jerusalem during the term 2003–2005. He is also well known on founding startup companies in computer vision and his latest brainchild Mobileye employs today 250 people developing systems-on-chip and computer vision algorithms for detecting pedestrians, vehicles, and traffic signs for driving assistance systems. For his industrial contributions prof. Shashua received the 2004 Kaye Innovation award from the Hebrew University.

Research Interests

My work spans the field of computational visual processing with specialization towards: • Multiple View Geometry: Visual Motion, Structure from Motion (SFM), “Dyanmic” (non-rigid) SFM, Indexing functions, Visual Recognition by Alignment, Indexing into Dy- namic Shapes.

1 • Photometric Issues in Visual Recognition: Relighting, Class-based Recognition under Lighting Variability. • Statistical Issues in Visual Recognition: Ordinal Regression (Ranking), Principal Com- ponent Analysis, issues of representation of collection of images, Learning over Sets, feature selection, graphical models. • Algebraic Systems for Image Coding and Statistical Inference: Non-negative tensor factorization (NTF), Probabilistic NTF, High-order affinity clustering and Symmetric NTF.

Education

Postdoc 1993 – 1994. Center for Biological and Computational Learning (CBCL), Massachusetts Institute of Technology. Host: Prof. Tomaso Poggio, department of Brain and Cognitive Sciences. Ph.D. 1989–1993. A.I. Laboratory, Department of Brain and Cognitive Sciences, Massachusetts Institute of Technology. M.Sc. 1986–1989. Math. & Computer Science, Weizmann Institute of Science. Advisor: Prof. Shimon Ullman. B.Sc. 1982–1985. Math. & Computer Science, Tel-Aviv University.

Awards

• Best Paper Award given at the European Conference on Computer Vision (ECCV), Dublin Ireland, June 2000, for the paper 30. • Honorable Mention for the 2001 Marr Prize given at the International Conference on Com- puter Vision (ICCV), Vancouver Canada, July 2001, for the paper [B36],[A15]. • First-prize winner of the 2004 Kaye Innovation Award at The Hebrew University. The award was presented in June during the 67th meeting of the university’s Board of Governors. • Recipient of the Israeli 2005 Landau award for Science and Research in the area of exact sciences — Robotics. • UAI Best Student Paper Runner Up Award given at the conference on Uncertainty in Artificial Intelligence (UAI), Helsinki, Finland July 2008, for the paper [B63].

Professional Affiliations

• 11/2003. Professor, School of Computer Science and Engineering, Hebrew University, Jerusalem. • 1999 – 2003. Associate Professor, School of Computer Science and Engineering, Hebrew University, Jerusalem. • 1996–1999. Senior Lecturer, School of Computer Science and Engineering, Hebrew Uni- versity, Jerusalem. • 1995–1996. Senior Lecturer, Computer Science department, the Technion, Haifa. • 2001–2002, Sabbatical. Visiting Professor, Computer Science department, Stanford Uni- versity. • Summer 1997. Visiting Professor, A.I. Laboratory, Massachusetts Institute of Technology. Host: Prof. Tomaso Poggio. • Summer 1996. Visiting Professor, David Sarnoff Research Center, Princeton NJ.

Academic Positions

• 10/2002 – 9/2005. Head of the School of Computer Science and Engineering, Hebrew Uni- versity of Jerusalem.

Editorial Positions

• Editorial Board: Journal of Vision, Communications and Image Representation (JVCIR) (1995 – 2000), IEEE. trans. on Pattern Analysis and Machine Intelligence (PAMI) (1999 – 2002). • Conference Program Chair: International Conference on Computer Vision (ICCV), Rio Brazil, 2007. • Conference Program Board: European Conference on Computer Vision (ECCV), 2002, 2004, 2006. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2003, 2004, 2005. • Conference Program Committee: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 1996, 1997, 1998, 2000, 2001. International Conference on Computer Vision (ICCV), 1998, 1999, 2001, 2003. European Conference on Computer Vision (ECCV), 2000, 2002, 2004. Neural Information Processing Systems (NIPS), 2004, 2005. • Organizing Committee: IEEE workshop on Representations of Visual Scenes, 1995. IEEE workshop on Multi-view Modeling and Analysis of Visual Scenes, 1999.

Teaching Experience

• Introduction to Machine Learning (Mandatory, Undergraduate), fall 2002–2008. • Primal/Dual Optimization in Machine Learning. Fall 2008. • Multilinear Systems and Invariant Theory, spring 2002 (at Stanford University). • Multiple View Geometry with Application in Computer Vision, fall 2001, 1997. • Intro to Computer Vision, spring 2001, 1997. • Data Structures (Mandatory 1st year undergraduate), spring 2000, 1999, 1998.

Students

• PhD Students: Stein, G.S. (co-advising with E. Grimson from MIT). Graduation, Feb. 1998. Publications [B16],[B21],[B22],[A9],[A10] Avidan, S. (1995 – 1999, Summa cumLaude). Publications [B13],[B15],[B17],[B18],[B20],[B27],[B24],[B28],[A12],[B33],[A11]. Kaminski, J. (1996 – 2000). Publications [B31],[B39],[A16]. Wexler, Y. (co-advising with R. Chellapa from UMD). Graduation, Jan. 2001. Publications [B34],[B26],[B35],[B14]. Wolf, L. (1999 — 2003). Publications [B30],[B32],[B35], [B36],[B38],[B43],[B42],[B41],[B48],[B49],[B50], [A15],[A17]. Hazan, T. (2004 – 2009). Publications [A20],[B51],[B52],[B54],[B55], [B60], [B61], [B63]. Polak, S. (2004 – 2010). Publications [B54], [B59],[B64]. Zass, R. (10/2005 – 2009). Publications [B55], [B57], [B58], [B62]. • MSc Students: Riklin Raviv, T. (1997 – 1999, Magna cumLaude). Publications [B25],[A13]. Segal, D. (1998 – 2000, Magna cumLaude). Publications [B29]. Levin, A. (1999 – 2001, Summa cumLaude). Publications [B37],[B42],[B40], [B44],[B45],[B46],[B47]. Alon, Y. (2005–2006). Publications [B56],[A19]. Zass, R. (2004 – 2005). Publications [B53]. Man, A. (2007–2008). Publications [B61].

Grants

• US-Israel Binational Science Foundation (BSF). “Multilinear Tensor”. Principle Investiga- tors: A. Shashua, M. Werman and C. Tomasi (Stanford U.). 1996 – 1999. $38,000 total. Resulting publications: [B9][B10][A7][B13]. • Commission of the European Communities, 4th Framework Program. “Visualization accross networks using graphics and uncalibrated acquisition of real data”. Principle Investigators: A. Shashua (Hebrew U.), A. Zisserman (Oxford U.), L. Van-Gool (Leuven U.), L. Shapiro (Sharp, UK), R. Whitaker (ECRC, Germany). 1996 – 1999, $330,000 total. Resulting publications: [A12][B20][B24]. • DARPA Image Understanding Program. Principle Investigators: S. Peleg, A. Shashua, M. Werman, D. Weinshall, M. Irani (Weizmann Institute). 1997 – 1999, $364,000 total. Resulting publications: [B14],[B15][B16][A10]. • Magnet program on Multi-media consortium. Principle Investigators from HU: S. Peleg, A. Shashua, M. Werman and D. Weinshall. 1997 – 2000, $279,000. Resulting publications: [A13],[B25]. • Israeli Ministry of Defense, “Automatic Target Recognition”. Principle Investigators: S. Peleg, A. Shashua, M. Werman. 1997–1999, $105,000. Resulting publications: [B22][B23]. • Commission of the European Communities, 5th Framework Program. “VIGOR”. Principle Investigators: A. Shashua, M. Werman (Hebrew U.), R. Horaud (Inria). 1998–2001, $197,000. Resulting publications: [B28]. • 3/1999 Ministry of Science. “Efficient Video Indexing and Browsing Based on Scene Rep- resentations”. Principle Investigators: A. Shashua (Hebrew U.), M. Irani (Weizmann), D. Keren (Haifa U.) and H. Hel-or (IDC). 1999 – 2002, $257,000 total. Resulting publications: [B34],[B35],[A11]. • Israel Academy of Sciences (ISF). “Trajectory Triangulation: On the Reconstruction of Dy- namic Scenes”. Principle Investigator: A. Shashua. 1999 – 2002, $92,000 total. Resulting publications: [B30],[B36],[A15],[B38]. • Israel Academy of Sciences (ISF). “Computational Learning from Instances Made from Im- age Sequences”. Principle Investigator: A. Shashua. 2003–2006, $122,000 total. Resulting publications: [B48],[A17]. • Israeli Ministry of Defense, “Learning Abnormal Trajectories”. Principle Investigators: A. Shashua, 2004 – 2005, $110,000. Resulting publications: [B51]. • German Israeli Foundation (GIF), “Kernel Based Representations using Unlabeled Data for Inference and Learning”. Principle Investigators: A. Shashua, Y. Singer (Hebrew U.), and B. Schoelkopf (Max Planck Inst.). 2005 — 2007, 168,000 Euro total. • Israel Academy of Sciences (ISF). ”Message Passing Algorithms for Inference and Learning”, 2010–2013.

* Reported amounts represent my part of the funding for the whole duration.

Invited and Keynote Talks

• International Workshop on Computer Vision And Applied Geometry, August 1995, Nord- fjordeid, Norway. Invited Speaker: “Multiple-View Geometry and Photometry and the Tri- linear Tensor”. • The 1998 Stockholm Workshop on Computational Vision, Rosenon Island, Sweden, August 1998. Invited Speaker: “On non-rigid space and motion considerations”. • Indian Converence on Vision and Graphics (ICVGIP), Bangalore, India Dec. 2000. Keynote Speaker: “On Recent Advances in Selected Topics in Theoretical and Applied Areas in Computer Vision”. • Borad Area Colloquium, Computer Science Department Stanford University, Oct. 2001. “3D Interpretation of Dynamic and Non-Rigid Scenes”. • Workshop on Theoretical Research on Computer Vision held in Okayama University, Japan in Sep. 2002. Keynote Speaker: “3D intrepretation of dynamic and non-rigid scenes”. • Lectures Series on ”Multilinear Systems in Perception”, University of Milano, Mathematics Department, July 5–8, 2004. • Center for Vision Research (CVR) 2005 conference, York University, June 2005. • ”Madua” popular science lecture program, the Authority of the Community and Youth, the Hebrew University. Feb. 19, 2006. • Computer Vision Distinguished Speaker Series, University of Central Florida, Sep. 14, 2006. • Keynote speaker at the ”workshop on Component Analysis Methods for Classification, Clus- tering, Modeling and Estimation Problems in Computer Vision”, June 22, 2007. • Invited speaker to the workshop ”Multi-Manifold Data Modeling and Applications”, hosted by University of Minnesota, Oct. 27-30, 2008 • Keynote speaker at the 7th IAPR Workshop on Graph-based Representations in Pattern Recognition (GBR 2009), May 2628, 2009, Venice, Italy. • Keynote speaker at the SIAM conference on Imaging Science, Chicago, IL, Aug. 12–14, 2010. • Keynote speaker at the Israeli IMCV conference, Jan. 19, 2011. • Keynote speaker at the ”MIT150 Symposia: Brains, Minds and Machines Symposium”, May 3–5, 2011.

Publications

Note: The superscript (S)denotes a student co-author and (C)denotes a colleague. Peer-Reviewed Journal Papers [A1] Shashua, A. Projective Structure from Uncalibrated Images: Structure from Motion and Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI) Vol. 16(8), pp. 778–790, 1994. Preliminary Version in Conference paper [4]

[A2] Shashua, A. and Navab, N.(C)On The Concept of Relative Affine Structure. Zeitschrift f¨ur Photogrammetrie und Fernerkundung, 5/94 Wichmann Verlag, Karlsruhe, pp. 181–189, October 1994.

[A3] Shashua, A. Algebraic Functions For Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI) Vol. 17(8), pp. 779–789, 1995. Preliminary Version in Conference paper [6]

[A4] Shashua, A. and Navab, N.(C)Relative Affine Structure: Canonical Model for 3D from 2D Geometry and Applications. IEEE Transactions on Pattern Analysis and Machine Intelli- gence (PAMI) Vol. 18(9), pp. 873–883, 1996. Preliminary Version in Conference paper [8]

[A5] Shashua, A. On Photometric Issues in 3D Visual Recognition from a Single 2D Image. International Journal of Computer Vision (IJCV), 21(1/2), pp. 99–122, 1997. Preliminary Version in Conference paper [3]

[A6] Shashua, A. and Toelg, S.(C)The Quadric Reference Surface: Theory and Applications. International Journal of Computer Vision (IJCV), 23(2), pp. 185-198, 1997. Preliminary Version in Conference paper [7]

[A7] Avidan, S.(S)and Shashua,A. Novel View Synthesis by Cascading Trilinear Tensors. IEEE Transactions on Visualization and Computer Graphics (TVCG), 4(4), 1998. Preliminary Version in Conference paper [17]

[A8] A. Shashua. On the Relationship Between the Support Vector Machine for Classification and Sparsified Fisher’s Linear Discriminant. Neural Processing Letters, 9(2): 129–139, 1999.

[A9] Stein, G.(S)and Shashua, A. On Degeneracy of Linear Reconstruction from Three Views: Linear Line Complex and Applications. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), Vol. 21(3), pp. 244–251, 1999. Preliminary Version in Conference paper [21]

[A10] Stein, G.S.(S)and Shashua, A. Model-based Brightness Constraints: on Direct Estimation of Structure and Motion and Applications. . IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), Vol. 22(9), pp. 992–1015, 2000. Preliminary Version in Conference paper [16]

[A11] Avidan, S.(S)and Shashua, A. Trajectory Triangulation: 3D Reconstruction of Moving Points from a Monocular Image Sequence. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), Vol. 22(4), pp. 348–357, 2000. Preliminary Version in Conference paper [27],[28] [A12] Avidan, S.(S)and Shashua, A. Threading Fundamental Matrices. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), Vol. 23(1), pp. 73–77, 2001. Preliminary Version in Conference paper [20] [A13] Shashua, A. and Riklin Raviv, T.(S)The Quotient Image: Class Based Re-rendering and Recognition With Varying Illuminations. IEEE Transactions on Pattern Analysis and Ma- chine Intelligence (PAMI), Vol. 23(2), pp. 129–139, 2001. Preliminary Version in Conference paper [25] [A14] Shashua, A. and Wexler, Y.(S)Q-warping: Direct Computation of Quadratic Reference Surfaces. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), Vol. 23(8), pp. 920–925, 2001. Preliminary Version in Conference paper [26] [A15] Wolf, L.(S)and Shashua, A. On Projection Matrices Pk −→ P2, k = 3, ··· , 6, and their Applications in Computer Vision. International Journal of Computer Vision (IJCV), 48(1), pp. 53–67, 2002. Preliminary Version in Conference paper [36] [A16] Kaminski, J.Y.(S)and Shashua, A. Multiple-view geometry of general algebraic curves. International Journal of Computer Vision (IJCV), To Appear. Preliminary Version in Conference paper [31][39] [A17] Wolf, L.(S)and Shashua, A. Learning over Sets using Kernel Principal Angles. Journal of Machine Learning Research, 4(10):913–931, 2003. Preliminary Version in Conference paper [48] [A18] Wolf, L.(S)and Shashua, A. Feature Selection for Unsupervised and Supervised Inference: the Emergence of Sparsity in a Weight-based Approach. Journal of Machine Learning Re- search (JMLR), 6(11):1885-1887, 2005. Preliminary Version in Conference paper [??] [A19] R. Mason(C), J. Radford(C), D. Kumar(C), R. Walters(C), B. Fulkerson(C), E. Jones(C), D. Caldwell(C), J. Meltzer(C), Y. Alon(S), A. Shashua, H. Hattori(C), N. Takeda(C), E. Frazzoli(C), and S. Soatto(C). The Golem Group / UCLA Autonomous Ground Vehicle in the DARPA Grand Challenge. Journal of Field Robotics 23(8), 527-553, 2006. [A20] Hazan, T.(S)and Shashua, A. Norm-Product Belief Propagation: Primal-Dual Message- Passing for Approximate Inference. IEEE Trans. on Information Theory, 56(12):6294–6316, 2010.

Peer-Reviewed Conference Proceedings [B1] Shashua, A. and Ullman, S. Structural Saliency: the Detection of Globally Salient Structures Using a Locally Connected Network. International Conference on Computer Vision (ICCV), pp. 321–327, Dec. 1988, Tarpon Springs, Florida. [B2] Shashua, A. and Ullman, S. Grouping Contours by Iterated Pairing Network. In Lipp- mann,R.P., Moody,J.E. and Touretzky,D.S. (eds.) Advances in Neural Information Process- ing Systems 3, pp. 335–341, Morgan Kaufmann Publishers, CA, 1991 (Proc. of NIPS’90). [B3] Shashua, A. Illumination and View Position in 3D Visual Recognition. In J.E. Moody, S.J. Hanson and R.P. Lippmann (eds.) Advances in Neural Information Processing Systems 4, pp. 404–411, Morgan Kaufmann Publishers, CA 1992 (Proc. of NIPS’91).

[B4] Shashua, A. Projective Depth: A Geometric Invariant For 3D Reconstruction From Two Perspective/Orthographic Views and For Visual Recognition. International Conference on Computer Vision (ICCV), pp. 583–590, May 1993, Berlin, Germany.

[B5] Shashua, A. A Geometric Invariant For Visual Recognition and 3D Reconstruction From Two Perspective/Orthographic Views. Proceedings of the IEEE 2nd Qualitative Vision Work- shop, pp. 107–117, June 1993, New York, NY.

[B6] Shashua, A. Trilinearity in Visual Recognition by Alignment. European Conference on Computer Vision (ECCV), pp. 479–484, May 1994, Stockholm, Sweden.

[B7] Shashua, A. and Toelg, S.(C)The Quadric Reference Surface: Applications in Registering Views of Complex 3D Objects. European Conference on Computer Vision (ECCV), pp. 407– 416, May 1994, Stockholm, Sweden.

[B8] Shashua, A. and Navab, N.(C)Relative Affine Structure: Theory and Application for 3D Reconstruction From Perspective Views. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 483–489, June 1994, Seattle, Washington.

[B9] Shashua, A. and Werman, M.(C)On the Trilinear Tensor of Three Perspective Views and its Underlying Geometry. International Conference on Computer Vision (ICCV), pp. 920–925, June 1995, Boston MA.

[B10] Werman, M.(C)and Shashua, A. Elimination: An Approach to the Study of 3D-from-2D. International Conference on Computer Vision (ICCV), pp. 473–479, June 1995, Boston MA.

[B11] Shashua, A. and Werman, M.(C)On the Trilinear Tensor of Three Perspective Views and its Underlying Geometry. Proceedings of the Europe-China workshop on Geometrical Modelling and Invariants for Computer Vision, pp. 110–117, April 1995, Xi’an, China.

[B12] Weinshall,D.(C)and Werman, M.(C)and Shashua, A. Shape Tensors for Efficient and Learn- able Indexing. Proceedings of the workshop on Scene Representations, pp. 58–65, June 1995, Cambridge, MA.

[B13] Shashua, A. and Avidan, S.(S)The Rank 4 Constraint in Multiple (≥ 3) View Geometry. European Conference on Computer Vision (ECCV), pp. 196–206, April 1996, Cambridge United-Kingdom.

[B14] Weinshall,D.(C)and Werman, M.(C)and Shashua, A. Duality of multi-point and multi-frame geometry: Fundamental shape matrices and tensors. European Conference on Computer Vision (ECCV), pp. 217–227, April 1996, Cambridge United-Kingdom.

[B15] Rousso, B.(S)and Avidan, S.(S)and Shashua, A. and Peleg, S.(C)Robust Recovery of Camera Rotation from Three Frames. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 796–802, June 1996, San-Francisco, CA. [B16] Stein, G.(S)and Shashua, A.. Model-based Brightness Constraints: on Direct Estimation of Structure and Motion. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 400–406, June 1997.

[B17] Avidan, S.(S)and Shashua, A. Novel View Synthesis in Tensor Space. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1034–1040, June 1997.

[B18] Avidan, S.(S)Evgeniou, T.(S)Shashua, A. and Poggio, T.(C)Image-Based View Synthesis by Combining Trilinear Tensors and Learning Techniques. ACM Conference on Virtual Reality and Systems (VRST), pp. 140–145, Sep. 1997.

[B19] Maybank, S.(C)and Shashua, A. Ambiguity from Reconstruction From Images of Six Points. International Conference on Computer Vision (ICCV), pp. 703–708, Jan 1998, Bombay India.

[B20] Avidan, S.(S)and Shashua, A. Threading Fundamental Matrices. European Conference on Computer Vision (ECCV), pp. 124–140, June 1998, Germany.

[B21] Stein, G.(S)and Shashua, A. On Degeneracy of Linear Reconstruction from Three Views: Linear Line Complex and Applications. European Conference on Computer Vision (ECCV), pp. 862–878, June 1998, Germany.

[B22] Stein, G.(S)and Shashua, A. Direct Estimatation of Motion and Extended Scene Structure from a Moving Stereo Rig. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 211–218, June 1998.

[B23] Shashua, A. Omni-Rig Sensors: What Can be Done With a Non-Rigid Vision Platform? Workshop on Applications of Computer Vision (WACV), pp. 174–179, Princeton, Oct. 1998.

[B24] Avidan, S.(S)and Shashua, A. Tensor Embedding of the Fundamental Matrix. Post-ECCV SMILE Workshop, June 1998, Frieburg, Germany. Springer LNCS series, Vol. 1506, pp. 133–148, 1998.

[B25] Riklin Raviv, T.(S)and Shashua, A. The Quotient Image: Class Based Recognition and Synthesis Under Varying Illumination Conditions. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 566 – 573, June 1999.

[B26] Wexler, Y.(S)and Shashua, A. Q-warping: Direct Computation of Quadratic Reference Surfaces. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 333 – 340, June 1999.

[B27] Avidan, S.(S)and Shashua, A. Trajectory Triangulation: On Dynamic Scenes Viewed from a Moving Camera. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 62 – 67, June 1999.

[B28] Shashua, A., Avidan, S.(S)and Werman, M.(C)Trajectory Triangulation over Conic Sections. International Conference on Computer Vision (ICCV), pp. 330 – 337, Greece, 1999.

[B29] Segal, D.(S)and Shashua, A. 3D Reconstruction from Tangent-of-Sight Measurements of a Moving Object Seen from a Moving Camera. European Conference on Computer Vision (ECCV), pp. 220–234, June 2000, Dublin, Ireland. [B30] Shashua, A. and Wolf, L.(S)Homography Tensors: On Algebraic Entities That Represent Three Views of Static or Moving Planar Points. European Conference on Computer Vision (ECCV), pp. 163–177, June 2000, Dublin, Ireland. Won the “best paper” award.

[B31] Kaminsky, J.Y.(S)and Shashua, A. On calibration and reconstruction from planar curves. European Conference on Computer Vision (ECCV), pp. 256–270, June 2000, Dublin, Ireland.

[B32] Shashua, A. and Wolf, L.(S)On the Structure and Properties of the Quadrifocal Tensor. European Conference on Computer Vision (ECCV), pp. 354–368, June 2000, Dublin, Ireland.

[B33] Shashua, A. and Avidan, S.(S)On the Reprojection of 3D and 2D Scenes Without Explicit Model Selection. European Conference on Computer Vision (ECCV), pp. 468–482, June 2000, Dublin, Ireland.

[B34] Wexler, Y.(S)and Shashua, A. On the Synthesis of Dynamic Scenes from Reference Views. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 133–139, June 2000.

[B35] Wolf, L.(S), Shashua, A. and Wexler, Y.(S)Join Tensors: on 3D-to-3D Alignment of Dy- namic Sets. International Conference on Pattern Recognition (ICPR), pp. 99–102, Sep. 2000, Barcelona, Spain.

[B36] Wolf, L.(S)and Shashua, A. On Projection Matrices Pk −→ P2, k = 3, ··· , 6, and their Applications in Computer Vision. International Conference on Computer Vision (ICCV), pp. 412–419, July 2001, Vancouver Canada. Won the “MARR Prize” award.

[B37] Shashua, A. and Levin, A.(S)Multi-frame Infinitesimal Motion Model for the Reconstruction of (Dynamic) Scenes with Multiple Linearly Moving Objects. International Conference on Computer Vision (ICCV), pp. 592–599, July 2001, Vancouver Canada.

[B38] Wolf, L.(S)and Shashua, A. Affine 3-D Reconstruction from Two Projective Images of Independently Translating Planes. International Conference on Computer Vision (ICCV), pp. 238–244, July 2001, Vancouver Canada.

[B39] Kaminski, J.Y.(S)and Fryers, M.(C)and Shashua, A. and Teicher, M.(C)Multiple View Geometry of Non-planar Algebraic Curves. International Conference on Computer Vision (ICCV), pp. 181–186, July 2001, Vancouver Canada.

[B40] Shashua, A. and Levin, A.(S)Linear Image Coding for Regression and Classification using the Tensor-rank Principle. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 42–49, Dec. 2001, Hawaii.

[B41] Wolf, L.(S)and Shashua, A. Two-body Segmentation from Two Perspective Views. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 263–270, Dec. 2001, Hawaii. [B42] Levin, A.(S), Wolf, L.(S)and Shashua, A. Time-varying Shape Tensors for Scenes with Multiply Moving Points. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 623–630, Dec. 2001, Hawaii.

[B43] Zomet, A.(S)and Wolf, L.(S)and Shashua, A. Omni-rig: Linear Self-recalibration of a Rig with Varying Internal and External Parameters. International Conference on Computer Vi- sion (ICCV), pp. 135–141, July 2001, Vancouver Canada.

[B44] Levin, A.(S)and Shashua, A. Principal Component Analysis Over Continuous Subspaces and Intersection of Half-spaces. European Conference on Computer Vision (ECCV), pp. 133–147, May 2002, Copenhagen, Denmark.

[B45] Levin, A.(S)and Shashua,A. Revisiting Single-view Shape Tensors: Theory and Applications. European Conference on Computer Vision (ECCV), pp. 256–270, May 2002, Copenhagen, Denmark.

[B46] Shashua, A., Levin, A.(S)and Avidan, S.(C)Manifold Pursuit: A New Approach to Appear- ance Based Recognition. International Conference on Pattern Recognition (ICPR), August 2002, Quebec, Canada.

[B47] Shashua, A. and Levin, A.(S)Taxonomy of Large Margin Principle Algorithms for Ordinal Regression Problems. Advances in Neural Information Processing Systems (NIPS), Vancouver Canada, Dec. 2002.

[B48] Wolf, L.(S)and Shashua, A. Kernel Principal Angles for Classification Machines with Appli- cations to Image Sequence Interpretation. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2003, Madison.

[B49] Wolf, L.(S)and Shashua, A. Feature Selection for Unsupervised and Supervised Inference: the Emergence of Sparsity in a Weighted-based Approach. International Conference on Com- puter Vision (ICCV), Oct. 2003, Nice France.

[B50] Shashua, A. and Wolf, L.(S)Kernel Feature Selection with Side Data using a Spectral Ap- proach. Proc. of the European Conference on Computer Vision (ECCV), May 2004, Prague, Czech Republic.

[B51] Shashua, A. and Hazan, T.(S)Threading Kernel functions: on Bridging the Gap between Representations and Algorithms. Advances in Neural Information Processing Systems (NIPS), Vancouver Canada, Dec. 2004.

[B52] Shashua, A. and Hazan, T.(S)Non-Negative Tensor Factorization with Applications to Statistics and Computer Vision. International Conference on Machine Learning (ICML) Bonn, Germany, Aug., 2005.

[B53] Zass, R.(S)and Shashua, A. A Unifying Approach to Hard and Probabilistic Clustering. International Conference on Computer Vision (ICCV) Beijing, China, Oct., 2005.

[B54] Hazan, T.(S), Polak, S.(S)and Shashua, A. Sparse Image Coding using a 3D Non-negative Tensor Factorization. International Conference on Computer Vision (ICCV) Beijing, China, Oct., 2005. [B55] Shashua, A., Zass, R.(S)and Hazan, T.(S)Multi-way Clustering Using Super-symmetric Non-negative Tensor Factorization. Proc. of the European Conference on Computer Vision (ECCV), Graz, Austria, May 2006.

[B56] Alon, Y.(S), Ferencz, A.(C)and Shashua, A. Off-road Path Following using Region Classi- fication and Geometric Projection Constraints. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2006, NY.

[B57] Zass, R.(S)and Shashua, A. Doubly Stochastic Normalization for Spectral Clustering. Ad- vances in Neural Information Processing Systems (NIPS), Vancouver Canada, Dec. 2006.

[B58] Zass, R.(S)and Shashua, A. Nonnegative Sparse PCA. Advances in Neural Information Processing Systems (NIPS), Vancouver Canada, Dec. 2006.

[B59] Polak, S.(S)and Shashua, A. Latent Model Clustering and Applications to Visual Recogni- tion. International Conference on Computer Vision (ICCV) Rio, Brazil, Oct., 2007.

[B60] Hazan. T.(S), Hardoon, R.(S)and Shashua, A. pLSA for Sparse Arrays With Tsallis Pseudo- Additive Divergence: Noise Robustness and Algorithm. International Conference on Com- puter Vision (ICCV) Rio, Brazil, Oct., 2007.

[B61] Hazan. T.(S), Man, A.(S)and Shashua, A. A Parallel Decomposition Solver for SVM: Distributed Dual Ascend using Fenchel Duality. Conf. on Computer Vision and Pattern Recognition (CVPR), June 2008, Anchorage, Alaska.

[B62] Zass, R.(S)and Shashua, A. Probabilistic Graph and Hypergraph Matching. Conf. on Computer Vision and Pattern Recognition (CVPR), June 2008, Anchorage, Alaska.

[B63] Hazan, T.(S)and Shashua, A. Convergent Message-Passing Algorithms for Inference over General Graphs with Convex Free Energies. Conf. on Uncertainty in AI (UAI), Helsinki, July 2008. Won the “best student paper runner up” award.

[B64] Polak, S.(S)and Shashua, A. The Semi-Explicit Shape Model for Multi-object Detection and Classification. Proc. of the European Conference on Computer Vision (ECCV) Crete, Greece, Sep., 2010.

[B65] Stein, G.P.(C), Gdalyahu, Y.(C)and Shashua, A. Stereo-Assist: Top-down Stereo for Driver Assistance Systems. Proc. of the IEEE Intelligent Vehicles Symposium (IV2010), San Diego, CA, June 2010. Won the “best paper” award.

[B66] Shalev-Schwartz, S.(C), Wexler, Y.(C)and Shashua, A. ShareBoost: Efficient Multiclass Learning with Feature Sharing, Neural Information and Processing Systems (NIPS), Dec., 2011.

Book Chapters [C1] Shashua,A. On Geometric and Algebraic Aspects of 3D Affine and Projective Structures from Perspective 2D Views. In Applications of Invariance in Computer Vision, J. Mundy, A. Zisserman & D. Forsyth (eds.), pp. 127–143, Springer-Verlag LNCS No. 825, 1994. [C2] Shashua,A. Multiple-view Geometry and Photometry. In Recent Progress in Computer Vi- sion, Springer-Verlag, LNCS series, pp. 225–240, — Invited papers of ACCV’95, Singapore Dec. 1995.

[C3] Shashua, A. Trilinear Tensor: The Fundamental Construct of Multiple-view Geometry and its Applications. International Workshop on Algebraic Frames For The Perception Action Cycle (AFPAC97), Kiel Germany Sep. 8–9, 1997. Proceedings appeared in Springer-Verlag, LNCS series, pp. 190–206, 1997.

[C4] Shashua, A. Dynamic P n to P n Alignment. In Handbook of Computational Geometry for Pattern Recognition, Computer Vision, Neurocomputing and Robotics. Eduardo Bayro- Corrochano (eds.), Springer-Verlag, 2004.

Dissertations [D1] Shashua, A. Structural Saliency: the Detection of Globally Salient Structures Using a Lo- cally Connected Network. Master thesis, Department of Mathematics and Computer Science, Weizmann Institute. Resulting Publications: [B1].

[D2] Shashua, A. Geometry and Photometry in 3D Visual Recognition. Doctoral thesis, De- partment of Brain and Cognitive Sciences, Massachusetts Institute of Technology. Resulting Publications: [A1],[A5].

Patents [E1] 7,786,898, US Patent: ”Fusion of far infrared and visible images in enhanced obstacle de- tection in automotive applications”.

[E2] 1,236,126, EU Patent, ”System for Detecting Obstacles to Vehicle Motion”.

[E3] 1,741,079, EU Patent, ”Collision Warning System”.

[E4] 6,438,263, US Patent, ”Apparatus and method for 3-dimensional surface geometry recon- struction”.

[E5] 6,219,444, US Patent, ”Synthesizing virtual two dimensional images of three dimensional space from a collection of real two dimensional images”.

[E6] 6,167,151, US Patent, ”Apparatus and method for 3-dimensional surface geometry recon- struction”.

[E7] 6,094,198, US Patent, ”System and method for reconstructing surface elements of solid objects in a three-dimensional scene from a plurality of two dimensional images of the scene”.

[E8] 6,052,124, US Patent, ”System and method for directly estimating three-dimensional struc- ture of objects in a scene and camera motion from three two-dimensional views of the scene”.

[E9] 5,821,943, US Patent, ”Apparatus and method for recreating and manipulating a 3D object based on a 2D projection thereof”.

[E10] 5,745,668, US Patent, ”Example-based image analysis and synthesis using pixelwise corre- spondence”. [E11] 5,745,636, US Patent, ”System and method for rendering images

[E12] 5,598,515, US Patent, ”System and method for reconstructing surface elements of solid objects in a three-dimensional scene from a plurality of two dimensional images of the scene”.