AboutPublicationsTutorialsPressVideo TalksStudents
Amnon Shashua
Sachs Professor of Computer Science

Publications

2008-2014 2003-2007 1999-2002 1994-1998 1988-1993

2008 - 2017

Y. Levine, O. Sharir, N. Cohen and A. Shashua. Bridging Many-Body Quantum Physics and Deep Learning via Tensor Networks. ArXiv:1803.09780 April, 2018

O. Sharir and A. Shashua. Sum-Product-Quotient Networks. International Conference on Artificial Intelligence and Statistics (AISTATS). April, 2018

N. Cohen, R. Tamari and A. Shashua. Boosting Dilated Convolutional Networks with Mixed Tensor Decompositions. Oral track, International Conference on Learning Representations (ICLR) April, 2018

Y. Levine, D. Yakira, N. Cohen and A. Shashua. Deep Learning and Quantum Entanglement: Fundamental Connections with Implications to Network Design. International Conference on Learning Representations (ICLR) April, 2018

O. Sharir and A. Shashua. On the Expressive Power of Overlapping Operations of Deep Networks. International Conference on Learning Representations (ICLR) April, 2018

Y. Levine, O. Sharir and A. Shashua. Benefits of Depth for Long-Term Memory of Recurrent Networks. Workshop track, International Conference on Learning Representations (ICLR) April, 2018

S. Shalev-Shwartz, S. Shammah and A. Shashua. On a Formal Model of Safe and Scalable Self-driving Cars. ArXiv:1708.06374 Aug., 2017

N. Cohen and A. Shashua. Inductive Bias of Deep Convolutional Networks through Pooling Geometry. International Conference on Learning Representations (ICLR). April, 2017

O. Tadmor, Y. Wexler, T. Rosenwein, S. Shalev-Shwartz and A. Shashua. Learning a Metric Embedding for Face Recognition using the Multibatch Method. Neural Information and Processing Systems (NIPS). Dec. 2016

S. Shalev-Shwartz, S. Shammah and A. Shashua. Safe, Multi-Agent, Reinforcement Learning for Autonomous Driving. NIPS Workshop on ŇLearning, Inference and Control of Multi-Agent SystemsÓ Dec., 2016

O. Sharir, R. Tamari, N. Cohen and A. Shashua. Tensorial Mixture Models. ArXiv:1610.04167. Oct., 2016

N. Cohen and A. Shashua. Convolutional Rectifier Networks as Generalized Tensor Decompositions. International Conference on Machine Learning (ICML), June 2016. Extended manuscript in ArXiv:1603.00162.

N. Cohen, O. Sharir and A. Shashua. On the Expressive Power of Deep Learning: A Tensor Analysis. Conference on Learning Theory (COLT), June 2016

N. Cohen, O. Sharir and A. Shashua. Deep SimNets. Conference on Computer Vision and Pattern Recognition (CVPR). June, 2016

S. Shalev-Shwartz and A. Shashua. On the Sample Complexity of End-to-end Training vs. Semantic Abstraction Training. ArXiv:1604.06915. April, 2016

S. Shalev-Shwartz, N. Ben-Zrihem, A. Cohen and A. Shashua. Long-term Planning by Short-term Prediction. ArXiv:1602.01580. Feb., 2016

N. Cohen and A. Shashua. SimNets: A Generalization of Convolutional Networks. NIPS workshop on Deep Learning. Dec. 2014. Arxiv:1410.0781. Nov., 2014

T. Hazan, J. Peng and A. Shashua. Tightening Fractional Covering Upper Bounds on the Partition Function for High-Order Region Graphs. Uncertainty in Artificial Intelligence (UAI). August 2012.

A. Shashua. Is the brain a good model for machine intelligence? Nature, V.482, pp. 462-463, 23/2/2012.

S. Shalev-Schwartz, Y. Wexler and A. Shashua. ShareBoost: Efficient Multiclass Learning with Feature Sharing Neural Information and Processing Systems (NIPS), Dec., 2011. A more detailed version in Arxiv:1109.0820.

T. Hazan and A. Shashua. Norm-Product Belief Propagation: Primal-Dual Message-Passing for Approximate Inference IEEE Trans. on Information Theory, 56(12):6294–6316, 2010.

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

G.P. Stein, Y. Gdalyahu and A. Shashua. Stereo-Assist: Top-down Stereo for Driver Assistance Systems. Proc. of the IEEE Intelligent Vehicles Symposium (IV2010), San Diego, CA, June 2010.

G. Pragier and A. Shashua The Latent Bernoulli-Gauss Model for Data Analysis ICML 2010 Workshop on Topic Models: Structure, Applications, Evaluation, and Extensions.

T. Hazan and A. Shashua. Convergent Message-Passing Algorithms for Inference over General Graphs with Convex Free Energies. The 24th Conference on Uncertainty in Artificial Intelligence (UAI) Helsinki, July 2008.

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

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

2003 - 2007

S. Polak and A. Shashua Latent Model Clustering and Applications to Visual Recognition. International Conference on Computer Vision (ICCV) Rio, Brazil, Oct 2007.

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

T. Hazan and A. Shashua An Efficient Algorithm for Maximum Tsallis Entropy using Fenchel-duality. Technical Report 2007-110, Leibniz Center for Research, School of Computer Science and Eng The Hebrew University of Jerusalem, June 2007.

T. Hazan and A. Shashua Analysis of L2-loss for Probabilistically valid Factorizations under General Additive Noise. Technical Report 2007-13, Leibniz Center for Research, School of Computer Science and Eng The Hebrew University of Jerusalem, April, 2007.

R. Zass and A. Shashua Doubly Stochastic Normalization for Spectral Clustering. Neural Information and Processing Systems (NIPS), Dec 2006.

R. Mason, J. Radford, D. Kumar, R. Walters, B. Fulkerson, E. Jones, D. Caldwell, J. Meltzer, Y. Alon, A. Shashua, H. Hattori, N. Takeda, E. Frazzoli, and S. Soatto. The Golem Group / UCLA Autonomous Ground Vehicle in the DARPA Grand Challenge. Journal of Field Robotics 23(8), 527-553, 2006.

Y. Alon, A. Ferencz and A. Shashua Off-road Path Following using Region Classification and Geometric Projection Constraints. Conf. on Computer Vision and Pattern Recognition (CVPR),NY June 2006, NY.

A. Shashua, R. Zass and T. Hazan Multi-way Clustering Using Super-symmetric Non-negative Tensor Factorization. Proc. of the European Conference on Computer Vision (ECCV) May 2006, Graz, Austria.

L. Wolf and A. Shashua Feature Selection for Unsupervised and Supervised Inference: the Emergence of Sparsity in a Weight-based Approach.A> Journal of Machine Learning Research (JMLR), 6(11):1885-1887, 2005

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

T. Hazan, S. Polak and A. Shashua Sparse Image Coding using a 3D Non-negative Tensor Factorization. International Conference on Computer Vision (ICCV) Beijing, China, Oct 2005

A. Shashua and T. Hazan Non-Negative Tensor Factorization with Applications to Statistics and Computer Vision. International Conference on Machine Learning (ICML) Aug. 2005.

A. Shashua and T. Hazan. Algebraic Set Kernels with Application to Inference Over Local Image Representations. Neural Information and Processing Systems (NIPS) Dec 2004

A. Shashua and L. Wolf Dynamic P^n to P^n Alignment. To appear in Handbook of Computational Geometry for Pattern Recognition, Computer Vision, Neurocomputing and Robotics. Eduardo Bayro-Corrochano (eds.). Springer-Verlag, 2004

E. Dagan, O. Mano, G. Stein and A. Shashua Forward Collision Warning with a Single Camera. Proc. of the IEEE Intelligent Vehicles Symposium (IV2004), June 2004, Parma, Italy.

A. Shashua, Y. Gdalyahu and G. Hayon. Pedestrian Detection for Driving Assistance Systems: Single-frame Classification and System Level Performance. Proc. of the IEEE Intelligent Vehicles Symposium (IV2004), June 2004, Parma, Italy.

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

J. Kaminski and A. Shashua. Multiple View Geometry of General Algebraic Curves. International Journal on Computer Vision (IJCV), 56(3), pp. 195-219, 2004

Lior Wolf and A. Shashua. Learning over Sets using Kernel Principal Angles Journal of Machine Learning Research (JMLR), 4(10):913-931, 2003.

L. Wolf, A. Shashua and S. Mukherjee. Selecting relevant genes with a spectral approach. Submitted, Sep 2004.

Lior Wolf and A. Shashua. Feature Selection for Unsupervised and Supervised Inference: the Emergence of Sparsity in a Weighted-based Approach. International Conference on Computer Vision (ICCV) 2003. (An extended version in JMLR)

Lior Wolf and A. Shashua. Kernel Principal Angles for Classification Machines with Applications to Image Sequence Interpretation. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), June 2003, Madison, Wisconsin.

G.P. Stein, O. Mano and A. Shashua Vision-based ACC with a Single Camera: Bounds on Range and Range Rate Accuracy. IEEE Intelligent Vehicles Symposium (IV2003) June 2003, Columbus, OH

1999-2002

A. Shashua, R. Meshulam, L. Wolf, A. Levin and G. Kalai. On Representation Theory in Computer Vision Problems. Technical Report 2002-44, Leibniz Center for Research, School of Computer Science and Eng., The Hebrew University of Jerusalem, July, 2002.

A. Shashua and A. Levin. Ranking with Large Margin Principle: Two Approaches. Neural Information and Processing Systems Dec. 2002

Lior Wolf and A. Shashua. On Projection Matrices P^k -> P^2, k=3,...,6, and their Applications in Computer Vision. International Journal on Computer Vision (IJCV) 48(1), Honorable Mention for the 2001 Marr Prize

A. Levin and A. Shashua. Principal Component Analysis Over Continuous Subspaces and Intersection of Half-spaces. Proc. of the European Conference on Computer Vision (ECCV) May 2002, Copenhagen, Denmark.

A. Levin and A. Shashua. Revisiting Single-view Shape Tensors: Theory and Applications. Proc. of the European Conference on Computer Vision (ECCV), May 2002, Copenhagen, Denmark.

A. Shashua, A. Levin and S. Avidan. Manifold Pursuit: A New Approach to Appearance Based Recognition. International Conference on Pattern Recognition (ICPR), August 2002, Quebec, Canada.

A. Shashua and A. Levin. Linear Image Coding for Regression and Classification using the Tensor-rank Principle. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Dec. 2001, Hawaii.

Lior Wolf and A. Shashua. Two-body Segmentation from Two Perspective Views. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Dec. 2001, Hawaii.

A. Levin, Lior Wolf and A. Shashua. Time-varying Shape Tensors for Scenes with Multiply Moving Points. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Dec. 2001, Hawaii.

Lior Wolf and A. Shashua. On Projection Matrices P^k -> P^2, k=3,...,6, and their Applications in Computer Vision. International Conference on Computer Vision (ICCV) ancouver, Canada, July, 2001 .

Lior Wolf and A. Shashua Affine 3-D Reconstruction from Two Projective Images of Independently Translating Planes International Conference on Computer Vision (ICCV) Vancouver, Canada, July, 2001

A. Zomet, Lior Wolf and A. Shashua. Multi-frame Infinitesimal Motion Model for the Reconstruction of (Dynamic) Scenes with Multiple Linearly Moving Objects International Conference on Computer Vision (ICCV) Vancouver, Canada July, 2001

A. Zomet, Lior Wolf and A. Shashua Omni-rig: Linear Self-recalibration of a Rig with Varying Internal and External Parameters International Conference on Computer Vision (ICCV) Vancouver, Canada July, 2001

J. Y. Kaminski, M. Fryers, A. Shashua and M. Teicher Multiple View Geometry of Non-planar Algebraic Curves International Conference on Computer Vision (ICCV) Vancouver, Canada July, 2001

S. Avidan and A. Shashua Threading Fundamental Matrices IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI) 2001

A. Shashua and T. Riklin Raviv The Quotient Image: Class Based Re-rendering and Recognition With Varying Illuminations IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), Vol. 23(2), pp. 129--139 2001

S. Avidan and A. Shashua 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, June 2000, Dublin, Ireland. best paper award winner

A. Shashua and Lior Wolf Homography Tensors: On Algebraic Entities That Represent Three Views of Static or Moving Planar Points. Proc. of the European Conference on Computer Vision (ECCV) Dublin, Ireland. Best paper award winner. June 2000

A. Shashua and Lior Wolf On the Structure and Properties of the Quadrifocal Tensor. Proc. of the European Conference on Computer Vision (ECCV). Dublin, Ireland. June 2000

A. Shashua and S. Avidan . On the Reprojection of 3D and 2D Scenes Without Explicit Model Selection Proc. of the European Conference on Computer Vision (ECCV), Dublin, Ireland. June 2000

A. Shashua and S. Avidan On the Reprojection of 3D and 2D Scenes Without Explicit Model Selection. Proc. of the European Conference on Computer Vision (ECCV), Dublin, Ireland. June 2000

D. Segal and A. Shashua 3D Reconstruction from Tangent-of-Sight Measurements of a Moving Object Seen from a Moving Camera. Proc. of the European Conference on Computer Vision (ECCV), Ireland. June, 2000

J. Kaminski and A. Shashua. On the Calibration and Reconstruction from Planar Curves Proc. of the European Conference on Computer Vision (ECCV), June, 2000

Y. Wexler and A. Shashua. On the Synthesis of Dynamic Scenes from Reference Views. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), South Carolina. June, 2000

Lior Wolf, A. Shashua and Y. Wexler. Join Tensors: on 3D-to-3D alignment of Dynamic Sets. Proc. of the Int. Conf. on Pattern Recog. (ICPR), Barcelona Sep, 2000

G.P. Stein, O. Mano and A. Shashua. A Robust Method for Computing Vehicle Ego-motion. IEEE Intelligent Vehicles Symposium (IV2000),Dearborn, MI Oct, 2000

G.P. Stein and A. Shashua. Model-based Brightness Constraints: on Direct Estimation of Structure and Motion. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI) Vol. 22(9), pp. 992--1015. 2000

A. Shashua, S. Avidan and M. Werman Trajectory Triangulation over Conic Sections. International Conference on Computer Vision (ICCV) Sep, 1999

S. Avidan and A. Shashua Trajectory Triangulation of Lines: Reconstruction of a 3D point Moving along a Line from a Monocular Image Sequence. IEEE Conf, on Computer Vision and Pattern Recognition (CVPR). June, 1999

T. Riklin Raviv and A. Shashua The Quotient Image: Class Based Re-rendering and Recognition With Varying Illuminations. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR). June, 1999

Y. Wexler and A. Shashua. Q-warping: Direct Computation of Quadratic Reference Surfaces. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR). June, 1999 (An extended version)

A. Shashua. On the Equivalence Between the Support Vector Machine for Classification and Sparsified Fisher's Linear Discriminant. Neural Processing Letters, 9(2): 129--139, 1999

G. P. Stein and A. Shashua 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

1994-1998

S. Avidan and A. Shashua Tensor Embedding of the Fundamental Matrix. Post-ECCV SMILE Workshop, Frieburg, Germany. Springer LNCS series, Vol. 1506 June 1998 (Journal Version (submitted)

A. Shashua. Omni-Rig Sensors: What Can be Done With a Non-Rigid Vision Platform?. Proc. of the Workshop on Applications of Computer Vision (WACV), Princeton. Oct, 1998.

S. Avidan and A. Shashua Threading Fundamental Matrices. ECCV'98, Frieburg, Germany. June, 1998 (Journal version to appear)

G. P. Stein and A. Shashua. On Degeneracy of Linear Reconstruction from Three Views: Linear Line Complex and Applications. ECCV'98, Frieburg, Germany. June, 1998

G. P. Stein and A. Shashua. Direct Estimation of Motion and Extended Scene Structure from a Moving Stereo Rig CVPR'98, Santa Barbara. June, 1998

S.J. Maybank and A. Shashua. Ambiguity in Reconstruction from Images of Six Points . In Proc. of the International Conference on Computer Vision (ICCV). Bombay, India. January, 1998

A. Shashua. 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

G.P. Stein and A. Shashua. Model-based Brightness Constraints: on Direct Estimation of Structure and Motion. CVPR June, 1997 (For demo click here )

S. Avidan and A. Shashua. Novel View Synthesis in Tensor Space. CVPR .June, 1997 (For demo click here )

S. Avidan, T. Evgeniou, A. Shashua and T. Poggio Image-Based View Synthesis by Combining Trilinear Tensors and Learning Techniques. ACM VRST'97 Conference. 1997

A. Shashua On Photometric Issues in 3D Visual Recognition from a Single 2D Image. International Journal of Computer Vision (IJCV), 21(1/2), 99-122. 1997 (For demo click here )

A. Shashua and S. Toelg. The Quadric Reference Surface: Theory and Applications. International Journal of Computer Vision (IJCV), 23(2), 185-198. 1997

A. Shashua and S.J. Maybank. Degenerate $N$ point Configurations of Three Views: Do Critical Surfaces Exist? Hebrew University, Computer Science TR 96-19, Nov. 1996.

S. Avidan and A. Shashua. Unifying Two-View and Three-View Geometry. Hebrew University, Computer Science TR 96-21 Nov, 1996

A. Shashua and N. Navab Relative Affine Structure: Canonical Model for 3D from 2D Geometry and Applications. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI) Vol. 18(9), pp. 873--883. 1996

A. Shashua and S. Avidan. The Rank4 Constraint In Multiple View Geometry ECCV 1996

D. Weinshall, M. Werman and A. Shashua. Duality Of Multi-Point And Multi-Frame Geometry: Fundamental Shape Matrices And Tensors. ECCV 1996

B. Rousso, S. Avidan, A. Shashua and S. Peleg. Robust Recovery of Camera Rotation from Three Frames. CVPR. June, 1996 (For demo click here )

A. Shashua Multiple-view Geometry and Photometry. "Recent Progress in Computer Vision", Springer-Verlag, LNCS series - Invited papers of ACCV'95, Singapore Dec, 1995.

A.Shashua and P. Anandan. Trilinear Constraints Revisited: Generalized Trilinear Constraints And The Tensor Brightness Constraint. In Proc. of the ARPA Image Understanding Workshop, Palm Springs. Feb, 1996.

S. Avidan and A. Shashua. Tensorial Transfer: On the Representation of $N>3$ Views of a 3D Scene. In Proc. of the ARPA Image Understanding Workshop, Palm Springs. Feb, 1996.

S. Avidan and A. Shashua. Novel View Synthesis in Tensor Space. Technion, CIS Report 9602, January, 1996

A. Shashua. Algebraic Functions For Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI) Vol. 17(8), pp. 779--789. 1995

A. Shashua and M. Werman. On the Trilinear Tensor of Three Perspective Views and its Underlying Geometry In Proc. of the International Conference on Computer Vision (ICCV).Boston, MA. June, 1995

M. Werman and A. Shashua. Elimination: An Approach to the Study of 3D-from-2D "Recent Progress in Computer Vision", Springer-Verlag, LNCS series - Invited papers of ACCV'95, Singapore. June, 1995

A. Shashua. Multiple-view Geometry and Photometry. /b> Springer-Verlag, LNCS series - Invited papers of ACCV'95, Singapore Dec, 1995.

A. Shashua. Trilinear Functions For Visual Recognition Trilinear Functions For Visual Recognition Proc. of the European Conference on Computer Vision (ECCV), pp. 479-484.Stockholm, Sweden. May, 1994

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

A. Shashua 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

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

1988-1993

A. Shashua 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.Berlin, Germany. May, 1993

D. Beymer, A. Shashua and T. Poggio Example Based Image Analysis and Synthesis. MIT, AI Memo 1431. October, 1993.

A. Shashua Geometry and Photometry in 3D Visual Recognition. Ph.D. Thesis, MIT, AITR-1401. Nov, 1992.

A. Shashua and S. Ullman. Grouping Contours by Iterated Pairing Network In Lippmann,R.P., Moody,J.E. and Touretzky,D.S. (eds.) Advances in Neural Information Processing Systems 3, pp. 335--341, Morgan Kaufmann Publishers, CA, 1991

A. Shashua 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.(Proc. of NIPS'91). 1992

A. Shashua and S. Ullman. Structural Saliency: the Detection of Globally Salient Structures Using a Locally Connected Network In Proc. of the International Conference on Computer Vision (ICCV),Tarpon Springs, Florida. Dec, 1988


Designed by Tali Gutman ©