loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Paper Unlock

Authors: Diane Larlus and Frédéric Jurie

Affiliation: LEAR Group, INPG-CNRS, INRIA Rhône-Alpes, France

Keyword(s): Object segmentation, Latent aspect models.

Related Ontology Subjects/Areas/Topics: Computer Vision, Visualization and Computer Graphics ; Image and Video Analysis ; Segmentation and Grouping

Abstract: We propose a new method for learning to segment objects in images. This method is based on a latent variables model used for representing images and objects, inspired by the LDA model. Like the LDA model, our model is capable of automatically discovering which visual information comes from which object. We extend LDA by considering that images are made of multiple overlapping regions, treated as distinct documents, giving more chance to small objects to be discovered. This model is extremely well suited for assigning image patches to objects (even if they are small), and therefore for segmenting objects. We apply this method on objects belonging to categories with high intra-class variations and strong viewpoint changes.

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 18.204.214.205

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Larlus, D. and Jurie, F. (2007). CATEGORY LEVEL OBJECT SEGMENTATION - Learning to Segment Objects with Latent Aspect Models. In Proceedings of the Second International Conference on Computer Vision Theory and Applications (VISIGRAPP 2007) - Volume 2: VISAPP; ISBN 978-972-8865-74-0; ISSN 2184-4321, SciTePress, pages 122-127. DOI: 10.5220/0002050201220127

@conference{visapp07,
author={Diane Larlus. and Frédéric Jurie.},
title={CATEGORY LEVEL OBJECT SEGMENTATION - Learning to Segment Objects with Latent Aspect Models},
booktitle={Proceedings of the Second International Conference on Computer Vision Theory and Applications (VISIGRAPP 2007) - Volume 2: VISAPP},
year={2007},
pages={122-127},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002050201220127},
isbn={978-972-8865-74-0},
issn={2184-4321},
}

TY - CONF

JO - Proceedings of the Second International Conference on Computer Vision Theory and Applications (VISIGRAPP 2007) - Volume 2: VISAPP
TI - CATEGORY LEVEL OBJECT SEGMENTATION - Learning to Segment Objects with Latent Aspect Models
SN - 978-972-8865-74-0
IS - 2184-4321
AU - Larlus, D.
AU - Jurie, F.
PY - 2007
SP - 122
EP - 127
DO - 10.5220/0002050201220127
PB - SciTePress