default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDAmnon Shashua
Person information
- affiliation: Hebrew University of Jerusalem, Israel
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
showing all ?? records
2020 – today
- 2024
[c89]Dor Muhlgay, Ori Ram, Inbal Magar, Yoav Levine, Nir Ratner, Yonatan Belinkov, Omri Abend, Kevin Leyton-Brown, Amnon Shashua, Yoav Shoham:
Generating Benchmarks for Factuality Evaluation of Language Models. EACL (1) 2024: 49-66- [c88]Eliya Segev, Maya Alroy, Ronen Katsir, Noam Wies, Ayana Shenhav, Yael Ben-Oren, David Zar, Oren Tadmor, Jacob Bitterman, Amnon Shashua, Tal Rosenwein:
Align With Purpose: Optimize Desired Properties in CTC Models with a General Plug-and-Play Framework. ICLR 2024 - [c87]Yotam Wolf, Noam Wies, Oshri Avnery, Yoav Levine, Amnon Shashua:
Fundamental Limitations of Alignment in Large Language Models. ICML 2024 - [i42]Yotam Wolf, Noam Wies, Dorin Shteyman, Binyamin Rothberg, Yoav Levine, Amnon Shashua:
Tradeoffs Between Alignment and Helpfulness in Language Models. CoRR abs/2401.16332 (2024) - 2023
- [j21]Ori Ram, Yoav Levine, Itay Dalmedigos, Dor Muhlgay, Amnon Shashua, Kevin Leyton-Brown, Yoav Shoham:
In-Context Retrieval-Augmented Language Models. Trans. Assoc. Comput. Linguistics 11: 1316-1331 (2023) - [c86]Nir Ratner, Yoav Levine, Yonatan Belinkov, Ori Ram, Inbal Magar, Omri Abend, Ehud Karpas, Amnon Shashua, Kevin Leyton-Brown, Yoav Shoham:
Parallel Context Windows for Large Language Models. ACL (1) 2023: 6383-6402 - [c85]Noam Wies
, Yoav Levine, Amnon Shashua:
Sub-Task Decomposition Enables Learning in Sequence to Sequence Tasks. ICLR 2023 - [c84]Noam Wies, Yoav Levine, Amnon Shashua:
The Learnability of In-Context Learning. NeurIPS 2023 - [i41]Ori Ram, Yoav Levine, Itay Dalmedigos, Dor Muhlgay, Amnon Shashua, Kevin Leyton-Brown, Yoav Shoham:
In-Context Retrieval-Augmented Language Models. CoRR abs/2302.00083 (2023) - [i40]Noam Wies, Yoav Levine, Amnon Shashua:
The Learnability of In-Context Learning. CoRR abs/2303.07895 (2023) - [i39]Yotam Wolf, Noam Wies, Yoav Levine, Amnon Shashua:
Fundamental Limitations of Alignment in Large Language Models. CoRR abs/2304.11082 (2023) - [i38]Eliya Segev, Maya Alroy, Ronen Katsir, Noam Wies, Ayana Shenhav, Yael Ben-Oren, David Zar, Oren Tadmor, Jacob Bitterman, Amnon Shashua, Tal Rosenwein:
Align With Purpose: Optimize Desired Properties in CTC Models with a General Plug-and-Play Framework. CoRR abs/2307.01715 (2023) - [i37]Dor Muhlgay, Ori Ram, Inbal Magar, Yoav Levine, Nir Ratner, Yonatan Belinkov, Omri Abend, Kevin Leyton-Brown, Amnon Shashua, Yoav Shoham:
Generating Benchmarks for Factuality Evaluation of Language Models. CoRR abs/2307.06908 (2023) - 2022
- [c83]Yoav Levine, Noam Wies, Daniel Jannai, Dan Navon, Yedid Hoshen, Amnon Shashua:
The Inductive Bias of In-Context Learning: Rethinking Pretraining Example Design. ICLR 2022 - [i36]Noam Wies, Yoav Levine, Amnon Shashua:
Sub-Task Decomposition Enables Learning in Sequence to Sequence Tasks. CoRR abs/2204.02892 (2022) - [i35]Yoav Levine, Itay Dalmedigos, Ori Ram, Yoel Zeldes, Daniel Jannai, Dor Muhlgay, Yoni Osin, Opher Lieber, Barak Lenz, Shai Shalev-Shwartz, Amnon Shashua, Kevin Leyton-Brown, Yoav Shoham:
Standing on the Shoulders of Giant Frozen Language Models. CoRR abs/2204.10019 (2022) - [i34]Ehud Karpas, Omri Abend, Yonatan Belinkov, Barak Lenz, Opher Lieber, Nir Ratner, Yoav Shoham, Hofit Bata, Yoav Levine, Kevin Leyton-Brown, Dor Muhlgay, Noam Rozen, Erez Schwartz, Gal Shachaf, Shai Shalev-Shwartz, Amnon Shashua, Moshe Tennenholtz:
MRKL Systems: A modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoning. CoRR abs/2205.00445 (2022) - [i33]Nir Ratner, Yoav Levine, Yonatan Belinkov, Ori Ram, Omri Abend, Ehud Karpas, Amnon Shashua, Kevin Leyton-Brown, Yoav Shoham:
Parallel Context Windows Improve In-Context Learning of Large Language Models. CoRR abs/2212.10947 (2022) - 2021
- [c82]Noam Wies, Yoav Levine, Daniel Jannai, Amnon Shashua:
Which transformer architecture fits my data? A vocabulary bottleneck in self-attention. ICML 2021: 11170-11181 - [i32]Or Sharir, Amnon Shashua, Giuseppe Carleo:
Neural tensor contractions and the expressive power of deep neural quantum states. CoRR abs/2103.10293 (2021) - [i31]Noam Wies, Yoav Levine, Daniel Jannai, Amnon Shashua:
Which transformer architecture fits my data? A vocabulary bottleneck in self-attention. CoRR abs/2105.03928 (2021) - [i30]Yoav Levine, Noam Wies, Daniel Jannai, Dan Navon, Yedid Hoshen, Amnon Shashua:
The Inductive Bias of In-Context Learning: Rethinking Pretraining Example Design. CoRR abs/2110.04541 (2021) - 2020
- [c81]Yoav Levine, Barak Lenz, Or Dagan, Ori Ram, Dan Padnos, Or Sharir, Shai Shalev-Shwartz, Amnon Shashua, Yoav Shoham:
SenseBERT: Driving Some Sense into BERT. ACL 2020: 4656-4667 - [c80]Yoav Levine, Noam Wies, Or Sharir, Hofit Bata, Amnon Shashua:
Limits to Depth Efficiencies of Self-Attention. NeurIPS 2020 - [i29]Shai Shalev-Shwartz, Shaked Shammah, Amnon Shashua:
On the Ethics of Building AI in a Responsible Manner. CoRR abs/2004.04644 (2020) - [i28]Yoav Levine, Noam Wies, Or Sharir, Hofit Bata, Amnon Shashua:
Limits to Depth Efficiencies of Self-Attention. CoRR abs/2006.12467 (2020)
2010 – 2019
- 2019
- [i27]Shai Shalev-Shwartz, Shaked Shammah, Amnon Shashua:
Vision Zero: on a Provable Method for Eliminating Roadway Accidents without Compromising Traffic Throughput. CoRR abs/1901.05022 (2019) - [i26]Or Sharir, Yoav Levine, Noam Wies, Giuseppe Carleo, Amnon Shashua:
Deep autoregressive models for the efficient variational simulation of many-body quantum systems. CoRR abs/1902.04057 (2019) - [i25]Yoav Levine, Barak Lenz, Or Dagan, Dan Padnos, Or Sharir, Shai Shalev-Shwartz, Amnon Shashua, Yoav Shoham:
SenseBERT: Driving Some Sense into BERT. CoRR abs/1908.05646 (2019) - 2018
- [c79]Or Sharir, Amnon Shashua:
Sum-Product-Quotient Networks. AISTATS 2018: 529-537 - [c78]Nadav Cohen, Ronen Tamari, Amnon Shashua:
Boosting Dilated Convolutional Networks with Mixed Tensor Decompositions. ICLR 2018 - [c77]Yoav Levine, Or Sharir, Amnon Shashua:
Benefits of Depth for Long-Term Memory of Recurrent Networks. ICLR (Workshop) 2018 - [c76]Yoav Levine, David Yakira, Nadav Cohen, Amnon Shashua:
Deep Learning and Quantum Entanglement: Fundamental Connections with Implications to Network Design. ICLR (Poster) 2018 - [c75]Or Sharir, Amnon Shashua:
On the Expressive Power of Overlapping Architectures of Deep Learning. ICLR (Poster) 2018 - [i24]Yoav Levine, Or Sharir, Nadav Cohen, Amnon Shashua:
Bridging Many-Body Quantum Physics and Deep Learning via Tensor Networks. CoRR abs/1803.09780 (2018) - 2017
- [c74]Nadav Cohen, Amnon Shashua:
Inductive Bias of Deep Convolutional Networks through Pooling Geometry. ICLR (Poster) 2017 - [i23]Or Sharir, Amnon Shashua:
On the Expressive Power of Overlapping Operations of Deep Networks. CoRR abs/1703.02065 (2017) - [i22]Nadav Cohen, Ronen Tamari, Amnon Shashua:
Boosting Dilated Convolutional Networks with Mixed Tensor Decompositions. CoRR abs/1703.06846 (2017) - [i21]Yoav Levine, David Yakira, Nadav Cohen, Amnon Shashua:
Deep Learning and Quantum Entanglement: Fundamental Connections with Implications to Network Design. CoRR abs/1704.01552 (2017) - [i20]Nadav Cohen, Or Sharir, Yoav Levine, Ronen Tamari, David Yakira, Amnon Shashua:
Analysis and Design of Convolutional Networks via Hierarchical Tensor Decompositions. CoRR abs/1705.02302 (2017) - [i19]Shai Shalev-Shwartz, Shaked Shammah, Amnon Shashua:
On a Formal Model of Safe and Scalable Self-driving Cars. CoRR abs/1708.06374 (2017) - [i18]Or Sharir, Amnon Shashua:
Sum-Product-Quotient Networks. CoRR abs/1710.04404 (2017) - [i17]Yoav Levine, Or Sharir, Amnon Shashua:
Benefits of Depth for Long-Term Memory of Recurrent Networks. CoRR abs/1710.09431 (2017) - 2016
- [c73]Nadav Cohen, Or Sharir, Amnon Shashua:
On the Expressive Power of Deep Learning: A Tensor Analysis. COLT 2016: 698-728 - [c72]Nadav Cohen, Or Sharir, Amnon Shashua:
Deep SimNets. CVPR 2016: 4782-4791 - [c71]Nadav Cohen, Amnon Shashua:
Convolutional Rectifier Networks as Generalized Tensor Decompositions. ICML 2016: 955-963 - [c70]Oren Tadmor, Tal Rosenwein, Shai Shalev-Shwartz, Yonatan Wexler, Amnon Shashua:
Learning a Metric Embedding for Face Recognition using the Multibatch Method. NIPS 2016: 1388-1389 - [i16]Shai Shalev-Shwartz, Nir Ben-Zrihem, Aviad Cohen, Amnon Shashua:
Long-term Planning by Short-term Prediction. CoRR abs/1602.01580 (2016) - [i15]Nadav Cohen, Amnon Shashua:
Convolutional Rectifier Networks as Generalized Tensor Decompositions. CoRR abs/1603.00162 (2016) - [i14]Shai Shalev-Shwartz, Amnon Shashua:
On the Sample Complexity of End-to-end Training vs. Semantic Abstraction Training. CoRR abs/1604.06915 (2016) - [i13]Nadav Cohen, Amnon Shashua:
Inductive Bias of Deep Convolutional Networks through Pooling Geometry. CoRR abs/1605.06743 (2016) - [i12]Oren Tadmor, Yonatan Wexler, Tal Rosenwein, Shai Shalev-Shwartz, Amnon Shashua:
Learning a Metric Embedding for Face Recognition using the Multibatch Method. CoRR abs/1605.07270 (2016) - [i11]Shai Shalev-Shwartz, Shaked Shammah, Amnon Shashua:
Safe, Multi-Agent, Reinforcement Learning for Autonomous Driving. CoRR abs/1610.03295 (2016) - [i10]Or Sharir, Ronen Tamari, Nadav Cohen, Amnon Shashua:
Tensorial Mixture Models. CoRR abs/1610.04167 (2016) - 2015
- [i9]Nadav Cohen, Or Sharir, Amnon Shashua:
Deep SimNets. CoRR abs/1506.03059 (2015) - [i8]Nadav Cohen, Or Sharir, Amnon Shashua:
On the Expressive Power of Deep Learning: A Tensor Analysis. CoRR abs/1509.05009 (2015) - 2014
- [i7]Nadav Cohen, Amnon Shashua:
SimNets: A Generalization of Convolutional Networks. CoRR abs/1410.0781 (2014) - 2012
- [c69]Tamir Hazan, Jian Peng, Amnon Shashua:
Tightening Fractional Covering Upper Bounds on the Partition Function for High-Order Region Graphs. UAI 2012: 356-366 - [i6]Tamir Hazan, Amnon Shashua:
Convergent Message-Passing Algorithms for Inference over General Graphs with Convex Free Energies. CoRR abs/1206.3262 (2012) - [i5]Tamir Hazan, Jian Peng, Amnon Shashua:
Tightening Fractional Covering Upper Bounds on the Partition Function for High-Order Region Graphs. CoRR abs/1210.4881 (2012) - 2011
- [c68]Shai Shalev-Shwartz, Yonatan Wexler, Amnon Shashua:
ShareBoost: Efficient multiclass learning with feature sharing. NIPS 2011: 1179-1187 - [i4]Shai Shalev-Shwartz, Yonatan Wexler, Amnon Shashua:
ShareBoost: Efficient Multiclass Learning with Feature Sharing. CoRR abs/1109.0820 (2011) - 2010
- [j20]Tamir Hazan, Amnon Shashua:
Norm-Product Belief Propagation: Primal-Dual Message-Passing for Approximate Inference. IEEE Trans. Inf. Theory 56(12): 6294-6316 (2010) - [c67]Simon Polak, Amnon Shashua:
The Semi-explicit Shape Model for Multi-object Detection and Classification. ECCV (2) 2010: 336-349 - [c66]Gideon P. Stein, Yoram Gdalyahu, Amnon Shashua:
Stereo-Assist: Top-down stereo for driver assistance systems. Intelligent Vehicles Symposium 2010: 723-730 - [i3]Amnon Shashua, Gabi Pragier:
The Latent Bernoulli-Gauss Model for Data Analysis. CoRR abs/1007.0660 (2010)
2000 – 2009
- 2009
- [i2]Tamir Hazan, Amnon Shashua:
Norm-Product Belief Propagation: Primal-Dual Message-Passing for Approximate Inference. CoRR abs/0903.3127 (2009) - [i1]Amnon Shashua:
Introduction to Machine Learning: Class Notes 67577. CoRR abs/0904.3664 (2009) - 2008
- [c65]Tamir Hazan, Amit Man, Amnon Shashua:
A Parallel Decomposition Solver for SVM: Distributed dual ascend using Fenchel Duality. CVPR 2008 - [c64]Ron Zass, Amnon Shashua:
Probabilistic graph and hypergraph matching. CVPR 2008 - [c63]Tamir Hazan, Amnon Shashua:
Convergent Message-Passing Algorithms for Inference over General Graphs with Convex Free Energies. UAI 2008: 264-273 - 2007
- [c62]Tamir Hazan, Roee Hardoon, Amnon Shashua:
pLSA for Sparse Arrays With Tsallis Pseudo-Additive Divergence: Noise Robustness and Algorithm. ICCV 2007: 1-8 - [c61]Simon Polak, Amnon Shashua:
Latent Model Clustering and Applications to Visual Recognition. ICCV 2007: 1-8 - 2006
- [j19]Richard Mason, Jim Radford, Deepak Kumar, Robert Walters, Brian Fulkerson, Eagle Jones, David Caldwell, Jason Meltzer, Yaniv Alon, Amnon Shashua, Hiroshi Hattori, Emilio Frazzoli, Stefano Soatto:
The Golem Group/University of California at Los Angeles autonomous ground vehicle in the DARPA grand challenge. J. Field Robotics 23(8): 527-553 (2006) - [c60]Yaniv Alon, Andras Ferencz, Amnon Shashua:
Off-road Path Following using Region Classification and Geometric Projection Constraints. CVPR (1) 2006: 689-696 - [c59]Amnon Shashua, Ron Zass, Tamir Hazan:
Multi-way Clustering Using Super-Symmetric Non-negative Tensor Factorization. ECCV (4) 2006: 595-608 - [c58]Ron Zass, Amnon Shashua:
Nonnegative Sparse PCA. NIPS 2006: 1561-1568 - [c57]Ron Zass, Amnon Shashua:
Doubly Stochastic Normalization for Spectral Clustering. NIPS 2006: 1569-1576 - 2005
- [j18]Lior Wolf, Amnon Shashua:
Feature Selection for Unsupervised and Supervised Inference: The Emergence of Sparsity in a Weight-Based Approach. J. Mach. Learn. Res. 6: 1855-1887 (2005) - [c56]Gideon P. Stein, Elchanan Rushinek, Gaby Hayun, Amnon Shashua:
A Computer Vision System on a Chip: a case study from the automotive domain. CVPR Workshops 2005: 130 - [c55]Lior Wolf, Amnon Shashua, Sayan Mukherjee:
Gene Selection via a Spectral Approach. CVPR Workshops 2005: 140 - [c54]Tamir Hazan, Simon Polak, Amnon Shashua:
Sparse Image Coding Using a 3D Non-Negative Tensor Factorization. ICCV 2005: 50-57 - [c53]Ron Zass, Amnon Shashua:
A Unifying Approach to Hard and Probabilistic Clustering. ICCV 2005: 294-301 - [c52]Amnon Shashua, Tamir Hazan:
Non-negative tensor factorization with applications to statistics and computer vision. ICML 2005: 792-799 - 2004
- [j17]Jeremy Yermiyahou Kaminski, Amnon Shashua:
Multiple View Geometry of General Algebraic Curves. Int. J. Comput. Vis. 56(3): 195-219 (2004) - [c51]Amnon Shashua, Lior Wolf:
Kernel Feature Selection with Side Data Using a Spectral Approach. ECCV (3) 2004: 39-53 - [c50]Amnon Shashua, Tamir Hazan:
Algebraic Set Kernels with Application to Inference Over Local Image Representations. NIPS 2004: 1257-1264 - 2003
- [j16]Lior Wolf, Amnon Shashua:
Learning over Sets using Kernel Principal Angles. J. Mach. Learn. Res. 4: 913-931 (2003) - [c49]Lior Wolf, Amnon Shashua:
Kernel Principal Angles for Classification Machines with Applications to Image Sequence Interpretation. CVPR (1) 2003: 635-642 - [c48]Lior Wolf, Amnon Shashua:
Feature Selection for Unsupervised and Supervised Inference: the Emergence of Sparsity in a Weighted-based Approach. ICCV 2003: 378-384 - 2002
- [j15]Lior Wolf, Amnon Shashua:
On Projection Matrices Pk-> P2k=3, ..., 6, and their Applications in Computer Vision. Int. J. Comput. Vis. 48(1): 53-67 (2002) - [j14]Kiriakos N. Kutulakos, Amnon Shashua:
Guest Editorial. Int. J. Comput. Vis. 49(2-3): 99-100 (2002) - [c47]Anat Levin, Amnon Shashua:
Revisiting Single-View Shape Tensors: Theory and Applications. ECCV (2) 2002: 399-414 - [c46]Anat Levin, Amnon Shashua:
Principal Component Analysis over Continuous Subspaces and Intersection of Half-Spaces. ECCV (3) 2002: 635-650 - [c45]Amnon Shashua, Anat Levin, Shai Avidan:
Manifold Pursuit: A New Approach to Appearance Based Recognition. ICPR (3) 2002: 590-594 - [c44]Amnon Shashua, Anat Levin:
Ranking with Large Margin Principle: Two Approaches. NIPS 2002: 937-944 - 2001
- [j13]Shai Avidan, Amnon Shashua:
Threading Fundamental Matrices. IEEE Trans. Pattern Anal. Mach. Intell. 23(1): 73-77 (2001) - [j12]Amnon Shashua, Tammy Riklin-Raviv:
The Quotient Image: Class-Based Re-Rendering and Recognition with Varying Illuminations. IEEE Trans. Pattern Anal. Mach. Intell. 23(2): 129-139 (2001) - [j11]Amnon Shashua, Yonatan Wexler:
Q-Warping: Direct Computation of Quadratic Reference Surfaces. IEEE Trans. Pattern Anal. Mach. Intell. 23(8): 920-925 (2001) - [c43]Amnon Shashua, Anat Levin:
Linear Image Coding for Regression and Classification using the Tensor-rank Principle. CVPR (1) 2001: 42-49 - [c42]Lior Wolf, Amnon Shashua:
Two-body Segmentation from Two Perspective Views. CVPR (1) 2001: 263-270 - [c41]Anat Levin, Lior Wolf, Amnon Shashua:
Time-varying Shape Tensors for Scenes with Multiply Moving Points. CVPR (1) 2001: 623-630 - [c40]Assaf Zomet, Lior Wolf, Amnon Shashua:
Omni-Rig: Linear Self-Recalibration of a Rig with Varying Internal and External Parameters. ICCV 2001: 135-141 - [c39]Jeremy Yermiyahou Kaminski, Michael Fryers, Amnon Shashua, Mina Teicher:
Multiple View Geometry of Non-planar Algebraic Curves. ICCV 2001: 181-186 - [c38]Lior Wolf, Amnon Shashua:
Affine 3-D Reconstruction from Two Projective Images of Independently Translating Planes. ICCV 2001: 238-244 - [c37]Lior Wolf, Amnon Shashua:
On Projection Matrices and their Applications in Computer Vision. ICCV 2001: 412-419 - [c36]Amnon Shashua, Anat Levin:
Multi-Frame Infinitesimal Motion Model for the Reconstruction of (Dynamic) Scenes with Multiple Linearly Moving Objects. ICCV 2001: 592-599 - 2000
- [j10]Shai Avidan, Amnon Shashua:
Trajectory Triangulation: 3D Reconstruction of Moving Points from a Monocular Image Sequence. IEEE Trans. Pattern Anal. Mach. Intell. 22(4): 348-357 (2000) - [j9]Gideon P. Stein, Amnon Shashua:
Model-Based Brightness Constraints: On Direct Estimation of Structure and Motion. IEEE Trans. Pattern Anal. Mach. Intell. 22(9): 992-1015 (2000) - [c35]Yonatan Wexler, Amnon Shashua:
On the Synthesis of Dynamic Scenes from Reference Views. CVPR 2000: 1576-1581 - [c34]Amnon Shashua, Lior Wolf:
Homography Tensors: On Algebraic Entities that Represent Three Views of Static or Moving Planar Points. ECCV (1) 2000: 507-521 - [c33]Dana Segal, Amnon Shashua:
3D Reconstruction from Tangent-of-Sight Measurements of a Moving Object Seen from a Moving Camera. ECCV (1) 2000: 621-631 - [c32]Jeremy Yermiyahou Kaminski, Amnon Shashua:
On Calibration and Reconstruction from Planar Curves. ECCV (1) 2000: 678-694 - [c31]Amnon Shashua, Lior Wolf:
On the Structure and Properties of the Quadrifocal Tensor. ECCV (1) 2000: 710-724 - [c30]Amnon Shashua, Shai Avidan:
On the Reprojection of 3D and 2D Scenes Without Explicit Model Selection. ECCV (1) 2000: 936-949 - [c29]Lior Wolf, Amnon Shashua, Yonatan Wexler:
Join Tensors: On 3D-to-3D Alignment of Dynamic Sets. ICPR 2000: 1388-1391
1990 – 1999
- 1999
- [j8]Amnon Shashua:
On the Relationship Between the Support Vector Machine for Classification and Sparsified Fisher's Linear Discriminant. Neural Process. Lett. 9(2): 129-139 (1999) - [j7]Gideon P. Stein, Amnon Shashua:
On Degeneracy of Linear Reconstruction From Three Views: Linear Line Complex and Applications. IEEE Trans. Pattern Anal. Mach. Intell. 21(3): 244-251 (1999) - [c28]Yonatan Wexler, Amnon Shashua:
Q-Warping: Direct Computation of Quadratic Reference Surfaces. CVPR 1999: 1333-1338 - [c27]Shai Avidan, Amnon Shashua:
Trajectory Triangulation of Lines: Reconstruction of a 3D point Moving along a Line from a Monocular Image Sequence. CVPR 1999: 2062-2066 - [c26]