A. Vedaldi - Publications

Book chapters

Knowing a Good Feature When You See It: Ground Truth and Methodology to Evaluate Local Features for Recognition A. Vedaldi, H. Ling, and S. Soatto, in Computer Vision: Detection, Recognition and Reconstruction, Vol. 285, 27-49, 2010. PDF, BibTeX

@incollection{vedaldi10knowing,
  Author = {A. Vedaldi and H. Ling and S. Soatto},
  Booktitle = {Computer Vision: Detection, Recognition and Reconstruction},
  Editor = {R. Cipolla and S. Battiato and G. M. Farinella},
  Pages = {27-49},
  Publisher = {Springer},
  Title = {Knowing a Good Feature When You See It:
           Ground Truth and Methodology to
           Evaluate Local Features for Recognition},
  Volume = {285},
  Year = {2010}}

Refereed conferences and journals

A Pylon Model for Semantic Segmentation, V. Lempitsky and A. Vedaldi and A. Zisserman, in Proceedings of Advances in Neural Information Processing Systems (NIPS), 2010, PDF, BibTeX

@inproceedings{lempitsky11pylon,
  Author    = {V. Lempitsky and A. Vedaldi
               and A. Zisserman},
  Title     = {A Pylon Model for Semantic Segmentation},
  Booktitle = {Proceedings of Advances in Neural
               Information Processing Systems (NIPS)},
  Year      = {2011}}

The devil is in the details: an evaluation of recent feature encoding methods, K. Chatfield, V. Lempitsky, A. Vedaldi, and A. Zisserman, in Proceedings of the British Machine Vision Conference (BMVC), 2011, PDF, Project, BibTeX

@inproceedings{chatfield11devil,
  Author    = {K. Chatfield and V. Lempitsky and A. Vedaldi and A. Zisserman},
  Title     = {The devil is in the details: an evaluation of
               recent feature encoding methods},
  Booktitle = {Proceedings of the British Machine Vision Conference
               (BMVC)},
  Year      = {2011}}

The Truth About Cats and Dogs, O. Parkhi, A. Vedaldi, C. V. Jawahar, and A. Zisserman, Proceedings of the International Conference on Computer Vision (ICCV), 2011, PDF, BibTeX

@inproceedings{parkhi11truth,
  Author    = {O. Parkhi and A. Vedaldi and C. V. Jawahar and A. Zisserman},
  Title     = {The Truth About Cats and Dogs},
  Booktitle = {Proceedings of the International
               Conference on Computer Vision ({ICCV})},
  Year      = {2011}}

Learning Equivariant Structured Output SVM Regressors, A. Vedaldi, M. Blaschko and A. Zisserman, in Proceedings of the International Conference on Computer Vision (ICCV), 2011, PDF, Poster, BibTeX

@inproceedings{vedaldi11learning,
  Author    = {A. Vedaldi and M. Blashcko and A. Zisserman},
  Title     = {Learning Equivariant Structured Output SVM Regressors},
  Booktitle = {Proceedings of the International
               Conference on Computer Vision ({ICCV})},
  Year      = {2011}}

Efficient Additive Kernels via Explicit Feature Maps, A. Vedaldi and A. Zisserman, in Pattern Analysis and Machine Intelligence, 2011 (to appear), PDF, BibTeX

@article{vedaldi11efficient,
  Author    = {A. Vedaldi and A. Zisserman},
  Title     = {Efficient Additive Kernels via Explicit Feature Maps},
  Journal   = {Pattern Analysis and Machine Intellingence},
  Year      = {2011}}

A coarse-to-fine approach for fast deformable object detection, M. Pedersoli, A. Vedaldi, and J. Gonzàlez, in Proceedings of the IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2011, PDF, BibTeX

@inproceedings{pedersoli11coarse,
  Author    = {M. Pedersoli and A. Vedaldi and J. Gonz{\`a}lez},
  Title     = {A coarse-to-fine approach for fast deformable object detection},
  Booktitle = {Proceedings of the {IEEE} Conf.
               on Computer Vision and Pattern Recognition ({CVPR}),
  Year      = {2011}}

VLFeat - An open and portable library of computer vision algorithms, A. Vedaldi and B. Fulkerson, in Proceedings of the 18th annual ACM international conference on Multimedia, 2010, PDF, BibTeX

@inproceedings{vedaldi10vlfeat,
  Author    = {A. Vedaldi and B. Fulkerson},
  Title     = {VLFeat -- An open and portable library of computer
               vision algorithms},
  Booktitle = {Proceedings of the 18th annual {ACM} international
               conference on Multimedia},
  Year      = {2010}}

Winner of the ACM Open Source Software Competition (2010)

Simultaneous Object Detection and Ranking with Weak Supervision, M. B. Blaschko and A. Vedaldi and A. Zisserman, in Proceedings of Advances in Neural Information Processing Systems (NIPS), 2010, PDF, BibTeX

@inproceedings{blaschko10simultaneous,
  Author    = {M. B. Blaschko and A. Vedaldi
               and A. Zisserman},
  Title     = {Simultaneous Object Detection and Ranking
               with Weak Supervision},
  Booktitle = {Proceedings of Advances in Neural
               Information Processing Systems (NIPS)},
  Year      = {2010}}

Generalized RBF feature maps for efficient detection, V. Sreekanth, A. Vedaldi, C. V. Jawahar, and A. Zisserman, in Proceedings of the British Machine Vision Conference (BMVC), 2010 (oral presentation), PDF, BibTeX

@inproceedings{sreekanth10generalized,
  Author    = {V. Sreekanth and A. Vedaldi and
               C. V. Jawahar and A. Zisserman},
  Title     = {Generalized {RBF} feature maps for efficient detection},
  Booktitle = {Proceedings of the British Machine Vision Conference
               (BMVC)},
  Year      = {2010}}

Efficient Additive Kernels via Explicit Feature Maps, A. Vedaldi and A. Zisserman, in Proceedings of the IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2010, PDF, BibTeX, Poster

@inproceedings{vedaldi10efficient,
  Author    = {A. Vedaldi and A. Zisserman},
  Title     = {Efficient Additive Kernels via
               Explicit Feature Maps},
  Booktitle = {Proceedings of the IEEE Conf. on
               Computer Vision and Pattern Recognition (CVPR)},
  Year      = {2010}}

Structured output regression for detection with partial occulsion, A. Vedaldi and A. Zisserman in Proceedings of Advances in Neural Information Processing Systems (NIPS), 2009, PDF, BibTeX

@inproceedings{vedaldi09structured,
  Author    = {A. Vedaldi and A. Zisserman},
  Title     = {Structured output regression for detection with
               partial occulsion},
  Booktitle = {Proceedings of Advances in Neural
               Information Processing Systems (NIPS)},
  Year      = {2009}}

Multiple Kernels for Object Detection, A. Vedaldi, V. Gulshan, M. Varma, and A. Zisserman, in Proceedings of the International Conference on Computer Vision (ICCV), 2009, PDF, BibTeX

@inproceedings{vedaldi09multiple,
  Author    = {A. Vedaldi and V. Gulshan and M. Varma and A. Zisserman},
  Title     = {Multiple Kernels for Object Detection},
  Booktitle = {Proceedings of the International
               Conference on Computer Vision ({ICCV})},
  Year      = {2009}}

Winner of the PASCAL Visual Object Classification challenge (2009)

Class Segmentation and Object Localization with Superpixel Neighborhoods, B. Fulkerson, A. Vedaldi, and S. Soatto, in Proceedings of the International Conference on Computer Vision (ICCV), 2009, PDF, BibTeX

@inproceedings{fulkerson08localizing,
  Author    = {B. Fulkerson and A. Vedaldi and S. Soatto},
  Title     = {Class Segmentation and Object
               Localization with Superpixel Neighborhoods},
  Booktitle = {Proceedings of the International
               Conference on Computer Vision ({ICCV})},
  Year      = {2009}}

Localizing Objects With Smart Dictionaries, B. Fulkerson, A. Vedaldi, and S. Soatto, in Proceedings of the European Conference on Computer Vision (ECCV), 2008, PDF, BibTeX

@inproceedings{fulkerson08localizing,
  Author    = {B.Fulkerson and A. Vedaldi and S. Soatto},
  Title     = {Localizing Objects With Smart Dictionaries},
  Booktitle = {Proceedings of the European
               Conference on Computer Vision ({ECCV})},
  Year      = {2008}}

Quick Shift and Kernel Methods for Mode Seeking, A. Vedaldi and S. Soatto, in Proceedings of the European Conference on Computer Vision (ECCV), 2008, PDF, BibTeX

@inproceedings{vedaldi08quick,
  Author    = {A. Vedaldi and S. Soatto},
  Title     = {Quick Shift and Kernel Methods for Mode Seeking},
  Booktitle = {Proceedings of the European
               Conference on Computer Vision ({ECCV})},
  Year      = {2008}}

Relaxed Matching Kernels for Object Recognition, A. Vedaldi, G. Guidi, and S. Soatto, in Proceedings of the IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2008, PDF, BibTeX

@inproceedings{vedaldi08relaxed,
  Author    = {A. Vedaldi and S. Soatto},
  Title     = {Relaxed Matching Kernels for Object Recognition},
  Booktitle = {Proceedings of the {IEEE} Conf.
               on Computer Vision and Pattern Recognition ({CVPR}),
  Year      = {2008}}

Joint Alignment up to (Lossy) Transformations, A. Vedaldi, G. Guidi, and S. Soatto, in Proceedings of the IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2008, PDF, BibTeX

@inproceedings{vedaldi08joint,
  Author    = {A. Vedaldi and G. Guidi and S. Soatto},
  Title     = {Joint Alignment up to (Lossy) Transforamtions},
  Booktitle = {Proceedings of the {IEEE} Conf.
               on Computer Vision and Pattern Recognition ({CVPR})},
  Year      = {2008}}

Objects in Context, A. Rabinovich, A. Vedaldi, C. Galleguillos, E. Wiewiora, and S. Belongie, in Proceedings of the International Conference on Computer Vision (ICCV), 2007, PDF, BibTeX

@inproceedings{rabinovich07objects,
  Author    = {A. Rabinovich and A. Vedaldi and
               C. Galleguillos and E. Wiewiora and
               S. Belongie},
  Title     = {Objects in Context},
  Booktitle = {Proceedings of the International
               Conference on Computer Vision ({ICCV})},
  Year      = {2007}}

Boosting Invariance and Efficiency in Supervised Learning, A. Vedaldi, P. Favaro, and E. Grisan, in Proceedings of the International Conference on Computer Vision (ICCV), 2007, PDF, BibTeX, code

@inproceedings{vedaldi07boosting,
  Author    = {A. Vedaldi and P. Favaro and E. Grisan},
  Title     = {Boosting Invariance and Efficiency in Supervised Learning},
  Booktitle = {Proceedings of the International
               Conference on Computer Vision ({ICCV})},
  Year      = {2007}}

Moving Forward in Structure From Motion, A. Vedaldi, G. Guidi, and S. Soatto, in Proceedings of the IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2007, PDF, extended PDF, BibTeX

@inproceedings{vedaldi07moving,
  Author    = {A. Vedaldi and G. Guidi and S. Soatto},
  Title     = {Moving Forward in Structure From Motion},
  Booktitle = {Proceedings of the {IEEE} Conf.
               on Computer Vision and Pattern Recognition ({CVPR})},
  Year      = {2007}}

Inertial structure from motion with autocalibration, E. Jones, A. Vedaldi, and S. Soatto, in Proceedings of the Internetional Conference on Computer Vision - Workshop on Dynamical Vision (ICCV Workshop), 2007, PDF, BibTeX

@inproceedings{jones07inertial,
  Author    = {E. Jones and A. Vedaldi and S. Soatto},
  Title     = {Inertial structure from motion with autocalibration},
  Booktitle = {Proceedings of the Internetional Conference on Computer Vision
               - Workshop on Dynamical Vision},
  Year      = {2007}}

A Complexity-Distortion Approach to Joint Pattern Alignment, A. Vedaldi and S. Soatto, in Proceedings of Advances in Neural Information Processing Systems (NIPS'06), 2007, PDF, BibTeX

@inproceedings{vedaldi07complexity,
  Author     = {A. Vedaldi and S. Soatto},
  Title      = {A Complexity-Distrotion Approach to Joint Pattern Alignment},
  Booktitle  = {Advances in Neural Information Processing Systems 19},
  Editor     = {B. Sch\:{o}lkopf and J.C. Platt and T. Hofmann},
  Publisher  = {MIT Press},
  Address    = {Cambridge, MA},
  Year       = {2007}}

Local Features, All Grown Up, A. Vedaldi and S. Soatto, in Proceedings of the IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), pp. 1753-1760, 2006. PDF, BibTeX

@inproceedings{vedaldi06local,
  Author    = {A. Vedaldi and S. Soatto},
  Title     = {Local Features, All Grown Up},
  Booktitle = {Proceedings of the {IEEE} Conf.
               on Computer Vision and Pattern Recognition ({CVPR})},
  Pages     = {1753-1760},
  Year      = {2006}}

Viewpoint Induced Deformation Statistics and the Design of Viewpoint Invariant Features: Singularities and Occlusions, A. Vedaldi and S. Soatto, in Proceedings of the European Conference on Computer Vision (ECCV), Vol. 2, 374 ff., 2006. PDF, BibTeX

@inproceedings{vedaldi06viewpoint,
  Author    = {A. Vedaldi and S. Soatto},
  Title     = {Viewpoint Induced Deformation Statistics and
               the Design of Viewpoint Invariant Features:
               Singularities and Occlusions},
  Booktitle = {Proceedings of the European
                Conference on Computer Vision ({ECCV})},
  Volume    = {2},
  Pages     = {374},
  Year      = {2006}}

Features for recognition: Viewpoint invariance for non-planar scenes, A. Vedaldi and S. Soatto, in Proceedings of the International Conference on Computer Vision (ICCV), Vol. 2, 1474-1481, 2005. PDF, Tech. Report, BibTeX

@inproceedings{vedaldi05features,
  Author    = {A. Vedaldi and S. Soatto},
  Title     = {Features for Recognition:
               Viewpoint Invariance for Non-Planar Scenes},
  Booktitle = {Proceedings of the International
                  Conference on Computer Vision (ICCV)},
  Volume    = {2},
  Pages     = {1474--1481},
  Year      = {2005}}

KALMANSAC: Robust filtering by consensus, A. Vedaldi, H. Jin, P. Favaro, and S. Soatto, in Proceedings of the International Conference on Computer Vision (ICCV), Vol. 1, 633-640, 2005. PDF, BibTeX

@inproceedings{vedaldi05kalmansac,
  Author    = {A. Vedaldi and H. Jin and P. Favaro and S. Soatto},
  Title     = {{KALMANSAC}: Robust Filtering by Consensus},
  Booktitle = {Proceedings of the International
               Conference on Computer Vision (ICCV)},
  Volume    = {1},
  Pages     = {633--640},
  Year      = {2005}}

Other publications

Invariant Representations and Learning for Computer Vision, A. Vedaldi, Ph.D. thesis, UCLA, 2008. PDF, BibTeX

@phdthesis{vedaldi08invariant,
	Author = {A. Vedaldi},
	School = {University of California at Los Angeles},
	Title  = {Invariant Representations and Learning
               for Computer Vision},
	Year   = {2008},
}

An open implementation of the SIFT detector and descriptor, A. Vedaldi, UCLA CSD Tech. Report 070012, 2006. PDF, BibTeX

@techreport{vedaldi07open,
	Author = {A. Vedaldi},
	Institution = {{UCLA CSD}},
	Number = {070012},
	Title = {An open implementation of the {SIFT} detector and descriptor},
	Year = {2007}}

Viewpoint invariance for non-planar scenes, A. Vedaldi and S. Soatto, in UCLA CSD Tech. Report 050012, 2005. PDF, BibTeX

@techreport{vedaldiTR05viewpoint,
	Author = {A. Vedaldi and S. Soatto},
	Institution = {{UCLA} {CSD}},
	Number = {050012},
	Title = {On Viewpoint Invariance for Non-Planar Scenes},
	Year = {2005}}

Andrea Vedaldi

Book chapters

Refereed conferences and journals

Other publications