| HAL-Inria | Publications, software ... of Inria's scientists |
Conference papers
Understanding Objects in Detail with Fine-grained Attributes
Andrea Vedaldi
1
Siddarth Mahendran
2
Stavros Tsogkas
3, 4
Subhransu Maji
5
Ross B. Girshick
6
Juho Kannala
7
Esa Rahtu
8
Iasonas Kokkinos
3, 4
Matthew B. Blaschko
3, 4
David Weiss
9
Ben Taskar
10
Karen Simonyan
1
Naomi Saphra
11
Sammy Mohamed
12
3
GALEN - Organ Modeling through Extraction, Representation and Understanding of Medical Image Content
Ecole Centrale Paris, Inria Saclay - Ile de France
Andrea Vedaldi 1
Author
Siddarth Mahendran 2
Author
Stavros Tsogkas 3, 4
Author Employer institution : Ecole Centrale Paris
Subhransu Maji 5
Author
Naomi Saphra 11
Author
Sammy Mohamed 12
Author
1
Department of Engineering Science (Department of Engineering Science University of Oxford Parks Road OXFORD OX1 3PJ UK - United Kingdom)
- University of Oxford [Oxford] (Wellington Square, Oxford OX1 2JD - United Kingdom)
2
CIS - Center for Imaging Science (301 Clark Hall - Johns Hopkins University - 3400 North Charles Street - Baltimore MD 21218-2686 - United States)
- JHU - Johns Hopkins University (Baltimore, Maryland 410-516-8000 - United States)
3
GALEN - Organ Modeling through Extraction, Representation and Understanding of Medical Image Content (Laboratoire MAS Ecole Centrale de Paris Grande Voie des Vignes 92295 Chatenay-Malabry Cedex - France)
- Ecole Centrale Paris (France)
- Inria Saclay - Ile de France (1 rue Honoré d'Estienne d'Orves
Bâtiment Alan Turing
Campus de l'École Polytechnique
91120 Palaiseau - France)
- Inria - Institut National de Recherche en Informatique et en Automatique (Domaine de Voluceau Rocquencourt - BP 105 78153 Le Chesnay Cedex - France)
4
CVN - Centre de vision numérique (CentraleSupélec - Bâtiment Bouygues - 3 rue Joliot Curie - 91190 GIF-SUR-YVETTE - France)
- Inria - Institut National de Recherche en Informatique et en Automatique (Domaine de Voluceau Rocquencourt - BP 105 78153 Le Chesnay Cedex - France)
- CentraleSupélec (3, rue Joliot Curie, Plateau de Moulon, 91192 GIF-SUR-YVETTE Cedex - France)
5
Toyota Technological Institute (France)
- TTIC - Toyota Technological Institute at Chicago [Chicago] (6045 S. Kenwood Ave. Chicago, Illinois 60637 - United States)
6
Department of Computer Science, University of Chicago (United States)
- University of Chicago (Edward H. Levi Hall 5801 South Ellis Avenue Chicago, Illinois 60637 - United States)
7
CMV - Center for Machine Vision Research (P.O Box 4500 FI-90014 University of Oulu - Finland)
- University of Oulu (Oulu Finland - Finland)
8
MVG - Machine Vision Group (Machine Vision Group Department of Electrical and Information Engineering P.O.Box 4500 FI-90014 University of Oulu Finland - Finland)
- University of Oulu (Oulu Finland - Finland)
9
Google Inc. (United States)
10
CSE - Department of Computer Science & Engineering (Computer Science & Engineering University of Washington Box 352350 Seattle, WA 98195-2350 (206) 543-1695 voice, (206) 543-2969 FAX - United States)
- University of Washington [Seattle] (Seattle, Washington 98105 - United States)
11
JHU - Johns Hopkins University (Baltimore, Maryland 410-516-8000 - United States)
12
SBU - Stony Brook University [SUNY] (100 Nicolls Road, Stony Brook, NY 11794 - United States)
- SUNY - State University of New York (United States)
Abstract : We study the problem of understanding objects in detail, intended as recognizing a wide array of fine-grained object attributes. To this end, we introduce a dataset of 7,413 airplanes annotated in detail with parts and their attributes, leveraging images donated by airplane spotters and crowd-sourcing both the design and collection of the detailed annotations. We provide a number of insights that should help researchers interested in designing fine-grained datasets for other basic level categories. We show that the collected data can be used to study the relation between part detection and attribute prediction by diagnosing the performance of classifiers that pool information from different parts of an object. We note that the prediction of certain attributes can benefit substantially from accurate part detection. We also show that, differently from previous results in object detection, employing a large number of part templates can improve detection accuracy at the expenses of detection speed. We finally propose a coarse-to-fine approach to speed up detection through a hierarchical cascade algorithm.
Document type :
Conference papers
Complete list of metadata
https://hal.inria.fr/hal-00981125
Contributor : Matthew Blaschko <>
Submitted on : Monday, April 21, 2014 - 2:53:38 AM
Last modification on : Thursday, July 9, 2020 - 4:06:04 PM
Long-term archiving on: : Monday, April 10, 2017 - 3:58:15 PM
Contributor : Matthew Blaschko <>
Submitted on : Monday, April 21, 2014 - 2:53:38 AM
Last modification on : Thursday, July 9, 2020 - 4:06:04 PM
Long-term archiving on: : Monday, April 10, 2017 - 3:58:15 PM
File
OIDcvpr.pdf
Files produced by the author(s)
Identifiers
- HAL Id : hal-00981125, version 1
- DOI : 10.1109/CVPR.2014.463
Citation
Andrea Vedaldi, Siddarth Mahendran, Stavros Tsogkas, Subhransu Maji, Ross B. Girshick, et al.. Understanding Objects in Detail with Fine-grained Attributes. IEEE Conference on Computer Vision and Pattern Recognition, Jun 2014, Columbus, United States. ⟨10.1109/CVPR.2014.463⟩. ⟨hal-00981125⟩
Metrics
Record views
742
Files downloads