| |
Records |
Links |
|
Author  |
Albert Gordo; Jose Antonio Rodriguez; Florent Perronnin; Ernest Valveny |
|
| |
Title |
Leveraging category-level labels for instance-level image retrieval |
Type |
Conference Article |
| |
Year |
2012 |
Publication |
25th IEEE Conference on Computer Vision and Pattern Recognition |
Abbreviated Journal |
|
|
| |
Volume |
|
Issue |
|
Pages |
3045-3052 |
|
| |
Keywords |
|
|
| |
Abstract |
In this article, we focus on the problem of large-scale instance-level image retrieval. For efficiency reasons, it is common to represent an image by a fixed-length descriptor which is subsequently encoded into a small number of bits. We note that most encoding techniques include an unsupervised dimensionality reduction step. Our goal in this work is to learn a better subspace in a supervised manner. We especially raise the following question: “can category-level labels be used to learn such a subspace?” To answer this question, we experiment with four learning techniques: the first one is based on a metric learning framework, the second one on attribute representations, the third one on Canonical Correlation Analysis (CCA) and the fourth one on Joint Subspace and Classifier Learning (JSCL). While the first three approaches have been applied in the past to the image retrieval problem, we believe we are the first to show the usefulness of JSCL in this context. In our experiments, we use ImageNet as a source of category-level labels and report retrieval results on two standard dataseis: INRIA Holidays and the University of Kentucky benchmark. Our experimental study shows that metric learning and attributes do not lead to any significant improvement in retrieval accuracy, as opposed to CCA and JSCL. As an example, we report on Holidays an increase in accuracy from 39.3% to 48.6% with 32-dimensional representations. Overall JSCL is shown to yield the best results. |
|
| |
Address |
Providence, Rhode Island |
|
| |
Corporate Author |
|
Thesis |
|
|
| |
Publisher |
IEEE Xplore |
Place of Publication |
|
Editor |
|
|
| |
Language |
|
Summary Language |
|
Original Title |
|
|
| |
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
| |
Series Volume |
|
Series Issue |
|
Edition |
|
|
| |
ISSN |
1063-6919 |
ISBN |
978-1-4673-1226-4 |
Medium |
|
|
| |
Area |
|
Expedition |
|
Conference |
CVPR |
|
| |
Notes |
DAG |
Approved |
no |
|
| |
Call Number |
Admin @ si @ GRP2012 |
Serial |
2050 |
|
| Permanent link to this record |
| |
|
| |
|
Author |
Albert Gordo; Florent Perronnin; Ernest Valveny |
|
| |
Title |
Document classification using multiple views |
Type |
Conference Article |
| |
Year |
2012 |
Publication |
10th IAPR International Workshop on Document Analysis Systems |
Abbreviated Journal |
|
|
| |
Volume |
|
Issue |
|
Pages |
33-37 |
|
| |
Keywords |
|
|
| |
Abstract |
The combination of multiple features or views when representing documents or other kinds of objects usually leads to improved results in classification (and retrieval) tasks. Most systems assume that those views will be available both at training and test time. However, some views may be too `expensive' to be available at test time. In this paper, we consider the use of Canonical Correlation Analysis to leverage `expensive' views that are available only at training time. Experimental results show that this information may significantly improve the results in a classification task. |
|
| |
Address |
Australia |
|
| |
Corporate Author |
|
Thesis |
|
|
| |
Publisher |
IEEE Computer Society Washington |
Place of Publication |
|
Editor |
|
|
| |
Language |
|
Summary Language |
|
Original Title |
|
|
| |
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
| |
Series Volume |
|
Series Issue |
|
Edition |
|
|
| |
ISSN |
|
ISBN |
978-0-7695-4661-2 |
Medium |
|
|
| |
Area |
|
Expedition |
|
Conference |
DAS |
|
| |
Notes |
DAG |
Approved |
no |
|
| |
Call Number |
Admin @ si @ GPV2012 |
Serial |
2049 |
|
| Permanent link to this record |
| |
|
| |
|
Author |
Albert Clapes; Miguel Reyes; Sergio Escalera |
|
| |
Title |
User Identification and Object Recognition in Clutter Scenes Based on RGB-Depth Analysis |
Type |
Conference Article |
| |
Year |
2012 |
Publication |
7th Conference on Articulated Motion and Deformable Objects |
Abbreviated Journal |
|
|
| |
Volume |
7378 |
Issue |
|
Pages |
1-11 |
|
| |
Keywords |
|
|
| |
Abstract |
We propose an automatic system for user identification and object recognition based on multi-modal RGB-Depth data analysis. We model a RGBD environment learning a pixel-based background Gaussian distribution. Then, user and object candidate regions are detected and recognized online using robust statistical approaches over RGBD descriptions. Finally, the system saves the historic of user-object assignments, being specially useful for surveillance scenarios. The system has been evaluated on a novel data set containing different indoor/outdoor scenarios, objects, and users, showing accurate recognition and better performance than standard state-of-the-art approaches. |
|
| |
Address |
Mallorca |
|
| |
Corporate Author |
|
Thesis |
|
|
| |
Publisher |
Springer Berlin Heidelberg |
Place of Publication |
|
Editor |
|
|
| |
Language |
|
Summary Language |
|
Original Title |
|
|
| |
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
LNCS |
|
| |
Series Volume |
|
Series Issue |
|
Edition |
|
|
| |
ISSN |
0302-9743 |
ISBN |
978-3-642-31566-4 |
Medium |
|
|
| |
Area |
|
Expedition |
|
Conference |
AMDO |
|
| |
Notes |
HUPBA;MILAB |
Approved |
no |
|
| |
Call Number |
Admin @ si @ CRE2012 |
Serial |
2010 |
|
| Permanent link to this record |
| |
|
| |
|
Author |
Albert Andaluz; Francesc Carreras; Cristina Santa Marta;Debora Gil |
|
| |
Title |
Myocardial torsion estimation with Tagged-MRI in the OsiriX platform |
Type |
Conference Article |
| |
Year |
2012 |
Publication |
ISBI Workshop on Open Source Medical Image Analysis software |
Abbreviated Journal |
|
|
| |
Volume |
|
Issue |
|
Pages |
|
|
| |
Keywords |
|
|
| |
Abstract |
Myocardial torsion (MT) plays a crucial role in the assessment of the functionality of the
left ventricle. For this purpose, the IAM group at the CVC has developed the Harmonic Phase Flow (HPF) plugin for the Osirix DICOM platform . We have validated its funcionalty on sequences acquired using different protocols and including healthy and pathological cases. Results show similar torsion trends for SPAMM acquisitions, with pathological cases introducing expected deviations from the ground truth. Finally, we provide the plugin free of charge at http://iam.cvc.uab.es |
|
| |
Address |
Barcelona, Spain |
|
| |
Corporate Author |
|
Thesis |
|
|
| |
Publisher |
IEEE |
Place of Publication |
|
Editor |
Wiro Niessen (Erasmus MC) and Marc Modat (UCL) |
|
| |
Language |
|
Summary Language |
|
Original Title |
|
|
| |
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
| |
Series Volume |
|
Series Issue |
|
Edition |
|
|
| |
ISSN |
|
ISBN |
|
Medium |
|
|
| |
Area |
|
Expedition |
|
Conference |
ISBI |
|
| |
Notes |
IAM |
Approved |
no |
|
| |
Call Number |
IAM @ iam @ ACS2012 |
Serial |
1900 |
|
| Permanent link to this record |
| |
|
| |
|
Author |
Albert Andaluz |
|
| |
Title |
Harmonic Phase Flow: User's guide |
Type |
Manual |
| |
Year |
2012 |
Publication |
CVC |
Abbreviated Journal |
|
|
| |
Volume |
|
Issue |
|
Pages |
|
|
| |
Keywords |
|
|
| |
Abstract |
HPF is a plugin for the computation of clinical scores under Osirix.
This manual provides a basic guide for experienced clinical staff. Chapter 1 provides the theoretical background in which this plugin is based.
Next, in chapter 2 we provide basic instructions for installing and uninstalling this plugin. chapter 3we shows a step-by-step scenario to compute clinical scores from tagged-MRI images with HPF. Finally, in chapter 4 we provide a quick guide for plugin developers |
|
| |
Address |
Bellaterra, Barcelona (Spain) |
|
| |
Corporate Author |
Computer Vision Center |
Thesis |
|
|
| |
Publisher |
CVC |
Place of Publication |
Barcelona |
Editor |
|
|
| |
Language |
english |
Summary Language |
english |
Original Title |
|
|
| |
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
| |
Series Volume |
|
Series Issue |
|
Edition |
|
|
| |
ISSN |
|
ISBN |
|
Medium |
|
|
| |
Area |
|
Expedition |
|
Conference |
|
|
| |
Notes |
IAM |
Approved |
no |
|
| |
Call Number |
IAM @ iam @ And2012 |
Serial |
1863 |
|
| Permanent link to this record |
| |
|
| |
|
Author |
Adriana Romero; Simeon Petkov; Carlo Gatta; M.Sabate; Petia Radeva |
|
| |
Title |
Efficient automatic segmentation of vessels |
Type |
Conference Article |
| |
Year |
2012 |
Publication |
16th Conference on Medical Image Understanding and Analysis |
Abbreviated Journal |
|
|
| |
Volume |
|
Issue |
|
Pages |
|
|
| |
Keywords |
|
|
| |
Abstract |
|
|
| |
Address |
Swansea, United Kingdom |
|
| |
Corporate Author |
|
Thesis |
|
|
| |
Publisher |
|
Place of Publication |
|
Editor |
|
|
| |
Language |
|
Summary Language |
|
Original Title |
|
|
| |
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
| |
Series Volume |
|
Series Issue |
|
Edition |
|
|
| |
ISSN |
|
ISBN |
|
Medium |
|
|
| |
Area |
|
Expedition |
|
Conference |
MIUA |
|
| |
Notes |
MILAB |
Approved |
no |
|
| |
Call Number |
Admin @ si @ |
Serial |
2137 |
|
| Permanent link to this record |
| |
|
| |
|
Author |
Adela Barbulescu; Wenjuan Gong; Jordi Gonzalez; Thomas B. Moeslund; Xavier Roca |
|
| |
Title |
3D Human Pose Estimation Using 2D Body Part Detectors |
Type |
Conference Article |
| |
Year |
2012 |
Publication |
21st International Conference on Pattern Recognition |
Abbreviated Journal |
|
|
| |
Volume |
|
Issue |
|
Pages |
2484 - 2487 |
|
| |
Keywords |
|
|
| |
Abstract |
Automatic 3D reconstruction of human poses from monocular images is a challenging and popular topic in the computer vision community, which provides a wide range of applications in multiple areas. Solutions for 3D pose estimation involve various learning approaches, such as support vector machines and Gaussian processes, but many encounter difficulties in cluttered scenarios and require additional input data, such as silhouettes, or controlled camera settings. We present a framework that is capable of estimating the 3D pose of a person from single images or monocular image sequences without requiring background information and which is robust to camera variations. The framework models the non-linearity present in human pose estimation as it benefits from flexible learning approaches, including a highly customizable 2D detector. Results on the HumanEva benchmark show how they perform and influence the quality of the 3D pose estimates. |
|
| |
Address |
Tsubuka, Japan |
|
| |
Corporate Author |
|
Thesis |
|
|
| |
Publisher |
|
Place of Publication |
|
Editor |
|
|
| |
Language |
|
Summary Language |
|
Original Title |
|
|
| |
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
| |
Series Volume |
|
Series Issue |
|
Edition |
|
|
| |
ISSN |
1051-4651 |
ISBN |
978-1-4673-2216-4 |
Medium |
|
|
| |
Area |
|
Expedition |
|
Conference |
ICPR |
|
| |
Notes |
ISE |
Approved |
no |
|
| |
Call Number |
Admin @ si @ BGG2012 |
Serial |
2172 |
|
| Permanent link to this record |
