Search For:

Displaying 1-50 out of 73 total
In Memoriam: Mark Everingham
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Andrew Zisserman,John Winn,Andrew Fitzgibbon,Luc Van Gool,Josef Sivic,Chris Williams,David Hogg
Issue Date:November 2012
pp. 2081-2082
Recounts the career and contributions pf Mark Everingham.
 
Finding nemo: Deformable object class modelling using curve matching
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Mukta Prasad, Andrew Fitzgibbon, Andrew Zisserman, Luc Van Gool
Issue Date:June 2010
pp. 1720-1727
An image search for “clownfish” yields many photos of clownfish, each of a different individual of a different 3D shape in a different pose. Yet, to the human observer, this set of images contains enough information to infer the underlying 3D deformable ob...
 
Geodesic star convexity for interactive image segmentation
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Varun Gulshan, Carsten Rother, Antonio Criminisi, Andrew Blake, Andrew Zisserman
Issue Date:June 2010
pp. 3129-3136
In this paper we introduce a new shape constraint for interactive image segmentation. It is an extension of Veksler's [25] star-convexity prior, in two ways: from a single star to multiple stars and from Euclidean rays to Geodesic paths. Global minima of t...
 
Joint Manifold Distance: a new approach to appearance based clustering
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Andrew W. Fitzgibbon, Andrew Zisserman
Issue Date:June 2003
pp. 26
We wish to match sets of images to sets of images where both sets are undergoing various distortions such as viewpoint and lighting changes.<div></div> To this end we have developed a Joint Manifold Distance (JMD) which measures the distance be...
 
Learning epipolar geometry from image sequences
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Yonatan Wexler, Andrew W. Fitzgibbon, Andrew Zisserman
Issue Date:June 2003
pp. 209
We wish to determine the epipolar geometry of a stereo camera pair from image measurements alone. This paper describes a solution to this problem which does not require a parametric model of the camera system, and consequently applies equally well to a wid...
 
Parallax Geometry of Smooth Surfaces in Multiple Views
Found in: Computer Vision, IEEE International Conference on
By Geoff Cross Andrew W. Fitzgibbon, Andrew Zisserman
Issue Date:September 1999
pp. 323
This paper investigates the multiple view geometry of smooth surfaces and a plane, where the plane provides a planar homography mapping between the views. Innovations are made in three areas: first, new solutions are given for the computation of epipolar a...
 
VHS to VRML: 3D Graphical Models from Video Sequences
Found in: Multimedia Computing and Systems, International Conference on
By Andrew Zisserman, Andrew Fitzgibbon, Geoff Cross
Issue Date:June 1999
pp. 9051
We describe a method to completely automatically recover 3D scene structure together with a camera for each frame from a sequence of images acquired by an unknown camera undergoing unknown movement. Previous approaches have used calibration objects or land...
 
Video Google: A Text Retrieval Approach to Object Matching in Videos
Found in: Computer Vision, IEEE International Conference on
By Josef Sivic, Andrew Zisserman
Issue Date:October 2003
pp. 1470
We describe an approach to object and scene retrieval which searches for and localizes all the occurrences of a user outlined object in a video. The object is represented by a set of viewpoint invariant region descriptors so that recognition can proceed su...
 
Image-based rendering using image-based priors
Found in: Computer Vision, IEEE International Conference on
By Andrew Fitzgibbon, Yonatan Wexler, Andrew Zisserman
Issue Date:October 2003
pp. 1176
Given a set of images acquired from known viewpoints, we describe a method for synthesizing the image which would be seen from a new viewpoint. In contrast to existing techniques, which explicity reconstruct the 3D geometry of the scene, we transform the p...
 
Markerless tracking using planar structures in the scene
Found in: Augmented Reality, International Symposium on
By Gilles Simon, Andrew W. Fitzgibbon, Andrew Zisserman
Issue Date:October 2000
pp. 120
We describe a markerless camera tracking system for augmented reality that operates in environments which contain one or more planes. This is a common special case, which we show significantly simplifies tracking. The result is a practical, reliable, visio...
 
Maintaining Multiple Motion Model Hypotheses Over Many Views to Recover Matching and Structure
Found in: Computer Vision, IEEE International Conference on
By Phil Torr, Andrew W. Fitzgibbon, Andrew Zisserman
Issue Date:January 1998
pp. 485
In order to recover structure from images it is desirable to use many views to obtain the best possible estimates. However, whilst recovering projective structure and motion from such extended sequences problems arise that are not apparent from a general v...
 
Extremely Low Bit-Rate Nearest Neighbor Search Using a Set Compression Tree
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Relja Arandjelovic,Andrew Zisserman
Issue Date:December 2014
pp. 1-1
The goal of this work is a data structure to support approximate nearest neighbor search on very large scale sets of vector descriptors. The criteria we wish to optimize are: (i) that the memory footprint of the representation should be very small (so that...
 
Symbiotic Segmentation and Part Localization for Fine-Grained Categorization
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Yuning Chai,Victor Lempitsky,Andrew Zisserman
Issue Date:December 2013
pp. 321-328
We propose a new method for the task of fine-grained visual categorization. The method builds a model of the base-level category that can be fitted to images, producing high-quality foreground segmentation and mid-level part localizations. The model can be...
 
Smooth object retrieval using a bag of boundaries
Found in: Computer Vision, IEEE International Conference on
By Relja Arandjelovic,Andrew Zisserman
Issue Date:November 2011
pp. 375-382
We describe a scalable approach to 3D smooth object retrieval which searches for and localizes all the occurrences of a user outlined object in a dataset of images in real time. The approach is illustrated on sculptures.
 
Tabula rasa: Model transfer for object category detection
Found in: Computer Vision, IEEE International Conference on
By Yusuf Aytar,Andrew Zisserman
Issue Date:November 2011
pp. 2252-2259
Our objective is transfer training of a discriminatively trained object category detector, in order to reduce the number of training images required. To this end we propose three transfer learning formulations where a template learnt previously for other c...
 
BiCoS: A Bi-level co-segmentation method for image classification
Found in: Computer Vision, IEEE International Conference on
By Yuning Chai,Victor Lempitsky,Andrew Zisserman
Issue Date:November 2011
pp. 2579-2586
The objective of this paper is the unsupervised segmentation of image training sets into foreground and background in order to improve image classification performance. To this end we introduce a new scalable, alternation-based algorithm for co-segmentatio...
 
Learning equivariant structured output SVM regressors
Found in: Computer Vision, IEEE International Conference on
By Andrea Vedaldi,Matthew Blaschko,Andrew Zisserman
Issue Date:November 2011
pp. 959-966
Equivariance and invariance are often desired properties of a computer vision system. However, currently available strategies generally rely on virtual sampling, leaving open the question of how many samples are necessary, on the use of invariant feature r...
 
Efficient Additive Kernels via Explicit Feature Maps
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Andrea Vedaldi,Andrew Zisserman
Issue Date:March 2012
pp. 480-492
Large scale nonlinear support vector machines (SVMs) can be approximated by linear ones using a suitable feature map. The linear SVMs are in general much faster to learn and evaluate (test) than the original nonlinear SVMs. This work introduces explicit fe...
 
Efficient additive kernels via explicit feature maps
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Andrea Vedaldi, Andrew Zisserman
Issue Date:June 2010
pp. 3539-3546
Maji and Berg [13] have recently introduced an explicit feature map approximating the intersection kernel. This enables efficient learning methods for linear kernels to be applied to the non-linear intersection kernel, expanding the applicability of this m...
 
Non-uniform deblurring for shaken images
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Oliver Whyte, Josef Sivic, Andrew Zisserman, Jean Ponce
Issue Date:June 2010
pp. 491-498
Blur from camera shake is mostly due to the 3D rotation of the camera, resulting in a blur kernel that can be significantly non-uniform across the image. However, most current deblurring methods model the observed image as a convolution of a sharp image wi...
 
CLAROS - Bringing Classical Art to a Global Public
Found in: e-Science and Grid Computing, International Conference on
By Donna Kurtz, Greg Parker, David Shotton, Graham Klyne, Florian Schroff, Andrew Zisserman, Yorick Wilks
Issue Date:December 2009
pp. 20-27
CLAROS (Classical Art Research Online Services; www.clarosweb.org) is an international interdisciplinary research initiative led by the University of Oxford (Humanities and Mathematics and Physical Sciences), hosted by the Oxford e-Research Centre (OeRC, w...
 
Automated Flower Classification over a Large Number of Classes
Found in: Computer Vision, Graphics & Image Processing, Indian Conference on
By Maria-Elena Nilsback, Andrew Zisserman
Issue Date:December 2008
pp. 722-729
We investigate to what extent combinations of features can improve classification performance on a large dataset of similar classes. To this end we introduce a 103 class flower dataset. We compute four different features for the flowers, each describing di...
 
Object Mining Using a Matching Graph on Very Large Image Collections
Found in: Computer Vision, Graphics & Image Processing, Indian Conference on
By James Philbin, Andrew Zisserman
Issue Date:December 2008
pp. 738-745
Automatic organization of large, unordered image collections is an extremely challenging problem with many potential applications. Often, what is required is that images taken in the same place, of the same thing, or of the same person be conceptually grou...
 
A Statistical Approach to Material Classification Using Image Patch Exemplars
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Manik Varma, Andrew Zisserman
Issue Date:November 2009
pp. 2032-2047
In this paper, we investigate material classification from single images obtained under unknown viewpoint and illumination. It is demonstrated that materials can be classified using the joint distribution of intensity values over extremely compact neighbor...
 
Lost in quantization: Improving particular object retrieval in large scale image databases
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By James Philbin, Ondrej Chum, Michael Isard, Josef Sivic, Andrew Zisserman
Issue Date:June 2008
pp. 1-8
The state of the art in visual object retrieval from large databases is achieved by systems that are inspired by text retrieval. A key component of these approaches is that local regions of images are characterized using high-dimensional descriptors which ...
 
Unsupervised discovery of visual object class hierarchies
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Josef Sivic, Bryan C. Russell, Andrew Zisserman, William T. Freeman, Alexei A. Efros
Issue Date:June 2008
pp. 1-8
Objects in the world can be arranged into a hierarchy based on their semantic meaning (e.g. organism — animal — feline — cat). What about defining a hierarchy based on the visual appearance of objects? This paper investigates ways to automatically discover...
 
Discriminative learned dictionaries for local image analysis
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Julien Mairal, Francis Bach, Jean Ponce, Guillermo Sapiro, Andrew Zisserman
Issue Date:June 2008
pp. 1-8
Sparse signal models have been the focus of much recent research, leading to (or improving upon) state-of-the-art results in signal, image, and video restoration. This article extends this line of research into a novel framework for local image discriminat...
 
Progressive search space reduction for human pose estimation
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Vittorio Ferrari, Manuel Marin-Jimenez, Andrew Zisserman
Issue Date:June 2008
pp. 1-8
The objective of this paper is to estimate 2D human pose as a spatial configuration of body parts in TV and movie video shots. Such video material is uncontrolled and extremely challenging.
 
Efficient Visual Search of Videos Cast as Text Retrieval
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Josef Sivic, Andrew Zisserman
Issue Date:April 2009
pp. 591-606
We describe an approach to object retrieval which searches for and localizes all the occurrences of an object in a video, given a query image of the object. The object is represented by a set of viewpoint invariant region descriptors so that recognition ca...
 
Image Classification using Random Forests and Ferns
Found in: Computer Vision, IEEE International Conference on
By Anna Bosch, Andrew Zisserman, Xavier Munoz
Issue Date:October 2007
pp. 1-8
We explore the problem of classifying images by the object categories they contain in the case of a large number of object categories. To this end we combine three ingredients: (i) shape and appearance representations that support spatial pyramid matching ...
 
Total Recall: Automatic Query Expansion with a Generative Feature Model for Object Retrieval
Found in: Computer Vision, IEEE International Conference on
By Ondrej Chum, James Philbin, Josef Sivic, Michael Isard, Andrew Zisserman
Issue Date:October 2007
pp. 1-8
Given a query image of an object, our objective is to retrieve all instances of that object in a large (1M+) image database. We adopt the bag-of-visual-words architecture which has proven successful in achieving high precision at low recall. Unfortunately,...
 
Scene Classification Using a Hybrid Generative/Discriminative Approach
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Anna Bosch, Andrew Zisserman, Xavier Muñoz
Issue Date:April 2008
pp. 712-727
We investigate whether dimensionality reduction using a latent generative model is beneficial forthe task of weakly supervised scene classification. In detail we are given a set of labelled images ofscenes (e.g. coast, forest, city, river, etc) and our obj...
 
An Exemplar Model for Learning Object Classes
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Ondrej Chum, Andrew Zisserman
Issue Date:June 2007
pp. 1-8
We introduce an exemplar model that can learn and generate a region of interest around class instances in a training set, given only a set of images containing the visual class. The model is scale and translation invariant. In the training phase, image reg...
 
Object retrieval with large vocabularies and fast spatial matching
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By James Philbin, Ondrej Chum, Michael Isard, Josef Sivic, Andrew Zisserman
Issue Date:June 2007
pp. 1-8
In this paper, we present a large-scale object retrieval system. The user supplies a query object by selecting a region of a query image, and the system returns a ranked list of images that contain the same object, retrieved from a large corpus. We demonst...
 
Tracking People by Learning Their Appearance
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Deva Ramanan, David A. Forsyth, Andrew Zisserman
Issue Date:January 2007
pp. 65-81
An open vision problem is to automatically track the articulations of people from a video sequence. This problem is difficult because one needs to determine both the number of people in each frame and estimate their configurations. But, finding people and ...
 
A Visual Vocabulary for Flower Classification
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Maria-Elena Nilsback, Andrew Zisserman
Issue Date:June 2006
pp. 1447-1454
We investigate to what extent ?bag of visual words? models can be used to distinguish categories which have significant visual similarity. To this end we develop and optimize a nearest neighbour classifier architecture, which is evaluated on a very challen...
 
Using Multiple Segmentations to Discover Objects and their Extent in Image Collections
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Bryan C. Russell, William T. Freeman, Alexei A. Efros, Josef Sivic, Andrew Zisserman
Issue Date:June 2006
pp. 1605-1614
Given a large dataset of images, we seek to automatically determine the visually similar object and scene classes together with their image segmentation. To achieve this we combine two ideas: (i) that a set of segmented objects can be partitioned into visu...
 
Incremental learning of object detectors using a visual shape alphabet
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Andreas Opelt, Axel Pinz, Andrew Zisserman
Issue Date:June 2006
pp. 3-10
<p>We address the problem of multiclass object detection. Our aims are to enable models for new categories to benefit from the detectors built previously for other categories, and for the complexity of the multiclass system to grow sublinearly with t...
 
Regression and Classification Approaches to Eye Localization in Face Images
Found in: Automatic Face and Gesture Recognition, IEEE International Conference on
By Mark Everingham, Andrew Zisserman
Issue Date:April 2006
pp. 441-448
We address the task of accurately localizing the eyes in face images extracted by a face detector, an important problem to be solved because of the negative effect of poor localization on face recognition accuracy. We investigate three approaches to the ta...
 
Estimating the Affine Transformation between Textures
Found in: Digital Image Computing: Techniques and Applications
By Angeline M. Loh, Andrew Zisserman
Issue Date:December 2005
pp. 67
A method is presented that solves the affine transformation between two images of the same texture. This problem is encountered in many areas of Computer Vision such as object retexturing and it is an essential part of many Shape-from-Texture algorithms. T...
 
Discovering Objects and their Localization in Images
Found in: Computer Vision, IEEE International Conference on
By Josef Sivic, Bryan C. Russell, Alexei A. Efros, Andrew Zisserman, William T. Freeman
Issue Date:October 2005
pp. 370-377
<p>We seek to discover the object categories depicted in a set of unlabelled images. We achieve this using a model developed in the statistical text literature: probabilistic Latent Semantic Analysis (pLSA). In text analysis this is used to discover ...
 
Identifying Individuals in Video by Combining ?Generative? and Discriminative Head Models
Found in: Computer Vision, IEEE International Conference on
By Mark Everingham, Andrew Zisserman
Issue Date:October 2005
pp. 1103-1110
<p>The objective of this work is automatic detection and identification of individuals in unconstrained consumer video, given a minimal number of labelled faces as training data. Whilst much work has been done on (mainly frontal) face detection and r...
 
Strike a Pose: Tracking People by Finding Stylized Poses
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Deva Ramanan, D. A. Forsyth, Andrew Zisserman
Issue Date:June 2005
pp. 271-278
We develop an algorithm for finding and kinematically tracking multiple people in long sequences. Our basic assumption is that people tend to take on certain canonical poses, even when performing unusual activities like throwing a baseball or figure skatin...
 
Tracking People and Recognizing Their Activities
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Deva Ramanan, David Forsyth, Andrew Zisserman
Issue Date:June 2005
pp. 1194
No summary available.
   
Automatic Face Recognition for Film Character Retrieval in Feature-Length Films
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Ognjen Arandjelović, Andrew Zisserman
Issue Date:June 2005
pp. 860-867
The objective of this work is to recognize all the frontal faces of a character in the closed world of a movie or situation comedy, given a small number of query faces. This is challenging because faces in a feature-length film are relatively uncontrolled ...
 
Automated Visual Identification of Characters in Situation Comedies
Found in: Pattern Recognition, International Conference on
By Mark Everingham, Andrew Zisserman
Issue Date:August 2004
pp. 983-986
The objectives of the work described in this paper are simply stated: given examples of a particular person and an unlabelled video, we wish to find every instance of that person in the video and in others. This is an extremely difficult problem because of...
 
Estimating Illumination Direction from Textured Images
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Manik Varma, Andrew Zisserman
Issue Date:July 2004
pp. 179-186
<p>We study the problem of estimating the illuminant?s direction from images of textured surfaces. Given an isotropic, Gaussian random surface with constant albedo, Koenderink and Pont [JOSA 03] developed a theory for recovering the illuminant?s azim...
 
Video Data Mining Using Configurations of Viewpoint Invariant Regions
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Josef Sivic, Andrew Zisserman
Issue Date:July 2004
pp. 488-495
<p>We describe a method for obtaining the principal objects, characters and scenes in a video by measuring the reoccurrence of spatial configurations of viewpoint invariant features. We investigate two aspects of the problem: the scale of the configu...
 
Augmenting Images of Non-Rigid Scenes Using Point and Curve Correspondences
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Adrien Bartoli, Eugénie von Tunzelmann, Andrew Zisserman
Issue Date:July 2004
pp. 699-706
<p>Our goal is to augment images of non-rigid scenes coming from single-camera footage. We do not assume any a priori information about the scene being viewed, such as for example a parameterized 3D model or the motion of the camera. One possible sol...
 
Geometry of Single Axis Motions Using Conic Fitting
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Guang Jiang, Hung-tat Tsui, Long Quan, Andrew Zisserman
Issue Date:October 2003
pp. 1343-1348
<p><b>Abstract</b>—Previous algorithms for recovering 3D geometry from an uncalibrated image sequence of a single axis motion of unknown rotation angles are mainly based on the computation of two-view fundamental matrices and three-view t...
 
 1  2 Next >>