Depth-From-Recognition: Inferring Meta-data by Cognitive Feedback

A. Thomas; V. Ferrari; B. Leibe; T. Tuytelaars; L. Van Gool

doi:10.1109/ICCV.2007.4408831

Depth-From-Recognition: Inferring Meta-data by Cognitive Feedback

A. Thomas, V. Ferrari, B. Leibe, T. Tuytelaars, L. Van Gool

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract / Description of output

Thanks to recent progress in category-level object recognition, we have now come to a point where these techniques have gained sufficient maturity and accuracy to succesfully feed back their output to other processes. This is what we refer to as cognitive feedback. In this paper, we study one particular form of cognitive feedback, where the ability to recognize objects of a given category is exploited to infer meta-data such as depth cues, 3D points, or object decomposition in images of previously unseen object instances. Our approach builds on the implicit shape model of Leibe and Schiele, and extends it to transfer annotations from training images to test images. Experimental results validate the viability of our approach.

Original language	English
Title of host publication	Computer Vision, 2007. ICCV 2007. IEEE 11th International Conference on
Pages	1-8
Number of pages	8
ISBN (Electronic)	978-1-4244-1631-8
DOIs	https://doi.org/10.1109/ICCV.2007.4408831
Publication status	Published - 1 Oct 2007

Keywords / Materials (for Non-textual outputs)

image recognition
object recognition
Leibe-Schiele implicit shape model
category-level object recognition
cognitive feedback
depth-from-recognition
metadata
Buildings
Feedback
Feeds
Humans
Image recognition
Layout
Object detection
Object recognition
Shape
Testing

Access to Document

10.1109/ICCV.2007.4408831

Thomas et al 2007 Depth from recognitionAccepted author manuscript, 597 KB

http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=4408831

Cite this

@inproceedings{89d575ccc1a7405ea670edfc441905f6,

title = "Depth-From-Recognition: Inferring Meta-data by Cognitive Feedback",

abstract = "Thanks to recent progress in category-level object recognition, we have now come to a point where these techniques have gained sufficient maturity and accuracy to succesfully feed back their output to other processes. This is what we refer to as cognitive feedback. In this paper, we study one particular form of cognitive feedback, where the ability to recognize objects of a given category is exploited to infer meta-data such as depth cues, 3D points, or object decomposition in images of previously unseen object instances. Our approach builds on the implicit shape model of Leibe and Schiele, and extends it to transfer annotations from training images to test images. Experimental results validate the viability of our approach.",

keywords = "image recognition, object recognition, Leibe-Schiele implicit shape model, category-level object recognition, cognitive feedback, depth-from-recognition, metadata, Buildings, Feedback, Feeds, Humans, Image recognition, Layout, Object detection, Object recognition, Shape, Testing",

author = "A. Thomas and V. Ferrari and B. Leibe and T. Tuytelaars and {Van Gool}, L.",

year = "2007",

month = oct,

day = "1",

doi = "10.1109/ICCV.2007.4408831",

language = "English",

isbn = "978-1-4244-1630-1 ",

pages = "1--8",

booktitle = "Computer Vision, 2007. ICCV 2007. IEEE 11th International Conference on",

}

TY - GEN

T1 - Depth-From-Recognition: Inferring Meta-data by Cognitive Feedback

AU - Thomas, A.

AU - Ferrari, V.

AU - Leibe, B.

AU - Tuytelaars, T.

AU - Van Gool, L.

PY - 2007/10/1

Y1 - 2007/10/1

N2 - Thanks to recent progress in category-level object recognition, we have now come to a point where these techniques have gained sufficient maturity and accuracy to succesfully feed back their output to other processes. This is what we refer to as cognitive feedback. In this paper, we study one particular form of cognitive feedback, where the ability to recognize objects of a given category is exploited to infer meta-data such as depth cues, 3D points, or object decomposition in images of previously unseen object instances. Our approach builds on the implicit shape model of Leibe and Schiele, and extends it to transfer annotations from training images to test images. Experimental results validate the viability of our approach.

AB - Thanks to recent progress in category-level object recognition, we have now come to a point where these techniques have gained sufficient maturity and accuracy to succesfully feed back their output to other processes. This is what we refer to as cognitive feedback. In this paper, we study one particular form of cognitive feedback, where the ability to recognize objects of a given category is exploited to infer meta-data such as depth cues, 3D points, or object decomposition in images of previously unseen object instances. Our approach builds on the implicit shape model of Leibe and Schiele, and extends it to transfer annotations from training images to test images. Experimental results validate the viability of our approach.

KW - image recognition

KW - object recognition

KW - Leibe-Schiele implicit shape model

KW - category-level object recognition

KW - cognitive feedback

KW - depth-from-recognition

KW - metadata

KW - Buildings

KW - Feedback

KW - Feeds

KW - Humans

KW - Image recognition

KW - Layout

KW - Object detection

KW - Object recognition

KW - Shape

KW - Testing

U2 - 10.1109/ICCV.2007.4408831

DO - 10.1109/ICCV.2007.4408831

M3 - Conference contribution

SN - 978-1-4244-1630-1

SP - 1

EP - 8

BT - Computer Vision, 2007. ICCV 2007. IEEE 11th International Conference on

ER -

Depth-From-Recognition: Inferring Meta-data by Cognitive Feedback

Abstract / Description of output

Keywords / Materials (for Non-textual outputs)

Access to Document

Fingerprint

Cite this