Dr Andrea Vedaldi
Department of Engineering Science E-mail abpnm8@r.postjobfree.com
University of Oxford WWW http://www.vlfeat.org/~vedaldi
Parks Road, Oxford, UK Tel. +44-186*-***-***
OX1 3PJ
Research Interests
Visual object detection, image classi cation, large scale machine learning and kernel methods.
Professional Experience
University of Oxford, University Lecturer in Engineering Science
Oxford, UK, since 9/12.
University of Oxford, Tutorial Fellow in New College
Oxford, UK, since 9/12.
University of Oxford, Junior Research Fellow
Oxford, UK, 8/08 8/12
A liated with the Visual Geometry Group of Andrew Zisserman
Education
University of California at Los Angeles, Doctor of Philosophy
Dept. of Computer Science
Los Angeles, California, 5/05 6/08
Thesis: Invariant representations and learning for computer vision
Committee: Alan Yuille, Song-Chun Zhu, Luiminita Vese, Serge Belongie, Stefano Soatto (chair)
University of California at Los Angeles, Master of Science
Dept. of Computer Sicence
Los Angeles, California, 7/03 5/05
G.P.A. 4/4
Advisor: Stefano Soatto
University of Padua, Laurea in Ingegneria Informatica (MSc equivalent)
Dept. of Information Engineering,
Padua, Italy, 9/98 4/03
Thesis: Modelli setocastici per il riconoscimento di sistemi di gesti complessi
Highest honors
Advisor: Ruggero Frezza
Funding
Xerox Foundation UAC Grant, 90,000 USD, 2012-14.
PASCAL Harvest Grant for VLFeat, 21,420 EUR, 2012-13.
1
Awards and Fellowships
Outstanding Reviewer Award, IEEE Conference on Computer Vision and Pattern Recognition (CVPR),
2012.
Outstanding Reviewer Award, IEEE Conference on Computer Vision and Pattern Recognition (CVPR),
2011.
W. W. Spooner Junior Research Fellow, New College, Oxford, 2011.
Oxford Violette and Samuel Glasstone Research Fellowships in Science, 2010.
Winner of the ACM Multimedia Open Source Software Competition for VLFeat, with Brian Fulkerson,
at the ACM international conference on Multimedia, 2010.
Winner of the PASCAL Visual Object Classi cation Challenge for object detection, with V. Gulshan, M.
Varma, and A. Zisserman, at the International Conference on Computer Vision (ICCV), 2009.
Outstanding Doctor of Philosophy in Computer Science, The Henry Samueli School of Engineering and
Applied Science, University of California Los Angeles, 2008.
Outstanding Master of Science in Computer Science, The Henry Samueli School of Engineering and
Applied Science, University of California Los Angeles, 2005.
Professional Activities
Team leader. Johns Hopkins CLSP Summer Research Workshop Towards a Detailed Understanding of
Objects and Scenes in Natural Images, June 11 August 7 2012, in collaboration with Subhransu Maji,
Matthew Blaschko, Iasonas Kokkinos, Ben Taskar.
Tutorials. Additive Kernels and Explicit Embeddings for Large Scale Computer Vision Problems at
the European Conference on Computer Vision (ECCV), 2012.
Modern features: advances, applications, and software at the European Conference on Computer Vision
(ECCV), 2012.
VLFeat: An Open and Portable Library of Computer Vision Algorithms at the European Conference on
Computer Vision (ECCV), 2010.
VLFeat: An Open and Portable Library of Computer Vision Algorithms, with Brian Fulkerson, at the
IEEE international conference on Computer Vision and Pattern Recognition (CVPR), 2010.
Area Chair. International Conference on Computer Vision (ICCV), 2011, British Machine Vision
Conference (BMVC), 2012, Computer Vision and Pattern Recognition (CVPR) 2013.
Reviewer: international conferences. IEEE Conference on Computer Vision and Pattern Recognition
(CVPR) 2005 2012, European Conference on Computer Vision (ECCV) 2006, 2008, 2010, 2012,
International Conference on Computer Vision (ICCV) 2005, 2007, 2009, International Conference on Neural
Information Processing Systems (NIPS) 2007 12, International Conference on Robotics Science and
Systems 2012.
Reviewer: international journals. IEEE Transactions on Pattern Analysis and Machine Intelligence
(TPAMI), International Journal on Computer Vision (IJCV), IEEE Transactions on Image Processing
(TIP), Computer Vision and Image Understanding (CVIU), Neurocomputing.
2
Reviewer: national conferences. Indian Conference on Computer Vision, Graphics & Image
Processing (ICCVGP).
Reviewer: funding schemes. Vienna Science and Technology Fund (WWTF) 2011, CHIST-ERA 2012.
Advising
PhD
Omkar Parkhi
University of Oxford (2011 present)
Co-supervised with Andrew Zisserman
Mircea Cimpoi
University of Oxford (2011 present)
Co-supervised with Andrew Zisserman
Marco Pedersoli
University of Barcelona (2011)
Co-supervised with Jordi Gon`lez
a
MSc and MEng
Mayank Juneja
MSc student, International Institute of Information Technology - Hyderabad (2009 present)
Co-supervised with C. V. Jawahar and Andrew Zisserman
Max Jaderberg
MEng, 4yp, University of Oxford (2011 present)
Co-supervised with Andrew Zisserman
John Cant
MEng, 4py, University of Oxford (2010 2011)
Co-supervised with Andrew Zisserman
Omkar Parkhi
MSc student, International Institute of Information Technology - Hyderabad (2008 2011)
Co-supervised with C. V. Jawahar and Andrew Zisserman
Vempati Sreekanth
MSc, International Institute of Information Technology - Hyderabad (2010)
Co-supervised with C. V. Jawahar and Andrew Zisserman
Other
Michal Spisiak
BMath, 3yp, University of Oxford (2011 12)
Teaching
College teaching. Collections: New College, Trinity 2012. Tutorials: New College, 1P2, Op. Amp.
Circuits, 2012.
Lectures. 4th year C4B Computer Vision course (two lectures), Oxford, 2010. Various lectures on
Computer Vision and Computer Graphics, UCLA, 2005 08.
3
Example classes and labs. 4th year C19 Machine Learning example classes, Oxford, 2012 Computer
Vision example classes, Oxford, 2009 10. 3rd year Information Engineering Labs (III year B4) on
Computer Vision, Oxford, 2009 12. Teaching Assistant, Computer Graphics, UCLA, 2005.
Academic development
Attended the following seminars and courses: Introduction to Academic Policy and Practice,
Introduction to Teaching at Oxford, Student Support and Welfare / Academic Life at Oxford:
university and college roles and responsibilities, Research Student Supervision, The UK Research
Environment: funding and conduct of research, Admissions Interviewing course, Admissions
Interviewing Practice, Oxford, 2012.
Software Projects
Main author of the VLFeat library of computer vision algorithms (http://www.vlfeat.org/). The library
is a popular tool for fast prototyping in computer vision research.
Presentations
Semantic image analysis with structure and kernels, Max Planck Institute, Saarbr cken, Germany, 2011.
u
E cient Structured Modeling for the Interpretation of Images, CIS Seminar, Johns Hopkins University,
Baltimore, US, 2011.
Multiple and fast kernels for the detection of visual object categories, invited talk at the Workshop on
Kernels and Distances for Computer Vision, in conjunction with the International Conference on Computer
Vision (ICCV), Barcelona, 2011.
E cient Structured Modeling for the Interpretation of Images, LCSR/ERC Seminar, Johns Hopkins
University, Baltimore, US, 2011.
E cient Additive Kernels via Explicit Feature Maps, CIS Seminar, Johns Hopkins University, Baltimore,
US, 2010.
E cient Additive Kernels via Explicit Feature Maps, seminar, University of Edinburgh, UK, 2010.
E cient Additive Kernels via Explicit Feature Maps, seminar, Heriot-Watt University, Edinburgh, UK,
2010.
A Tale of Two Object Detectors, CS seminar, University of California at San Diego (UCSD), San Diego,
US, 2010.
Multiple kernels for Object Classi cation and Detection, invited talk at the PASCAL VOC Challenge
Workshop, in conjunction with the International Conference on Computer Vision (ICCV), Kyoto, Japan,
2009.
Multiple kernels for Object Classi cation and Detection, invited talk at the Indian Institute of
Information Technology (IIIT), Hyderabad, 2009.
The design and implementation of the SIFT feature detector and descriptor, invited talk at the Indian
Institute of Information Technology (IIIT), Hyderabad, 2009.
Invariant Representation and Learning for Computer Vision, seminar, University of Oxford, UK, 2008.
Invariant Representation and Learning for Computer Vision, seminar, Ecole Centrale, Paris, 2008.
Viewpoint Invariant Features: Why it works, what to do when it does not, seminar, Univeristy of Padova,
Italy, 2007.
4
Viewpoint Invariant Features: Why it works, what to do when it does not, seminar, Univeristy of San
Diego (UCSD), US, 2007.
Viewpoint Invariant Features: Why it works, what to do when it does not, seminar, Univeristy of
California at Berkeley, US, 2007.
Publications
Remark. The major computer vision publication avenues are ICCV, ECCV, CVPR, and NIPS (acceptance
rates: oral