Adaptive hierarchical contexts for object recognition with conditional mixture of trees

Billy Peralta, Pablo Espinace, Alvaro Soto

Resultado de la investigación: Paper

2 Citas (Scopus)

Resumen

Robust category-level object recognition is currently a major goal for the computer vision community. Intra-class and pose variations, as well as, background clutter and partial occlusions are some of the main difficulties to achieve this goal. Contextual information, in the form of object co-occurrences and spatial constraints, has been successfully applied to improve object recognition performance, however, previous work considers only fixed contextual relations that do not depend of the type of scene under inspection. In this work, we present a method that learns adaptive conditional relationships that depend on the type of scene being analyzed. In particular, we propose a model based on a conditional mixture of trees that is able to capture contextual relationships among objects using global information about a scene. Our experiments show that the adaptive specialization of contextual relationships improves object recognition accuracy outperforming previous state-of-the-art approaches.

Idioma originalEnglish
DOI
EstadoPublished - 1 ene 2012
Evento2012 23rd British Machine Vision Conference, BMVC 2012 - Guildford, Surrey, United Kingdom
Duración: 3 sep 20127 sep 2012

Conference

Conference2012 23rd British Machine Vision Conference, BMVC 2012
PaísUnited Kingdom
CiudadGuildford, Surrey
Período3/09/127/09/12

Huella dactilar

Object recognition
Computer vision
Inspection
Experiments

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Citar esto

Peralta, B., Espinace, P., & Soto, A. (2012). Adaptive hierarchical contexts for object recognition with conditional mixture of trees. Papel presentado en 2012 23rd British Machine Vision Conference, BMVC 2012, Guildford, Surrey, United Kingdom. https://doi.org/10.5244/C.26.121
Peralta, Billy ; Espinace, Pablo ; Soto, Alvaro. / Adaptive hierarchical contexts for object recognition with conditional mixture of trees. Papel presentado en 2012 23rd British Machine Vision Conference, BMVC 2012, Guildford, Surrey, United Kingdom.
@conference{5d9e434a21cd4f639f2c898d5764b6fd,
title = "Adaptive hierarchical contexts for object recognition with conditional mixture of trees",
abstract = "Robust category-level object recognition is currently a major goal for the computer vision community. Intra-class and pose variations, as well as, background clutter and partial occlusions are some of the main difficulties to achieve this goal. Contextual information, in the form of object co-occurrences and spatial constraints, has been successfully applied to improve object recognition performance, however, previous work considers only fixed contextual relations that do not depend of the type of scene under inspection. In this work, we present a method that learns adaptive conditional relationships that depend on the type of scene being analyzed. In particular, we propose a model based on a conditional mixture of trees that is able to capture contextual relationships among objects using global information about a scene. Our experiments show that the adaptive specialization of contextual relationships improves object recognition accuracy outperforming previous state-of-the-art approaches.",
author = "Billy Peralta and Pablo Espinace and Alvaro Soto",
year = "2012",
month = "1",
day = "1",
doi = "10.5244/C.26.121",
language = "English",
note = "2012 23rd British Machine Vision Conference, BMVC 2012 ; Conference date: 03-09-2012 Through 07-09-2012",

}

Peralta, B, Espinace, P & Soto, A 2012, 'Adaptive hierarchical contexts for object recognition with conditional mixture of trees' Papel presentado en 2012 23rd British Machine Vision Conference, BMVC 2012, Guildford, Surrey, United Kingdom, 3/09/12 - 7/09/12, . https://doi.org/10.5244/C.26.121

Adaptive hierarchical contexts for object recognition with conditional mixture of trees. / Peralta, Billy; Espinace, Pablo; Soto, Alvaro.

2012. Papel presentado en 2012 23rd British Machine Vision Conference, BMVC 2012, Guildford, Surrey, United Kingdom.

Resultado de la investigación: Paper

TY - CONF

T1 - Adaptive hierarchical contexts for object recognition with conditional mixture of trees

AU - Peralta, Billy

AU - Espinace, Pablo

AU - Soto, Alvaro

PY - 2012/1/1

Y1 - 2012/1/1

N2 - Robust category-level object recognition is currently a major goal for the computer vision community. Intra-class and pose variations, as well as, background clutter and partial occlusions are some of the main difficulties to achieve this goal. Contextual information, in the form of object co-occurrences and spatial constraints, has been successfully applied to improve object recognition performance, however, previous work considers only fixed contextual relations that do not depend of the type of scene under inspection. In this work, we present a method that learns adaptive conditional relationships that depend on the type of scene being analyzed. In particular, we propose a model based on a conditional mixture of trees that is able to capture contextual relationships among objects using global information about a scene. Our experiments show that the adaptive specialization of contextual relationships improves object recognition accuracy outperforming previous state-of-the-art approaches.

AB - Robust category-level object recognition is currently a major goal for the computer vision community. Intra-class and pose variations, as well as, background clutter and partial occlusions are some of the main difficulties to achieve this goal. Contextual information, in the form of object co-occurrences and spatial constraints, has been successfully applied to improve object recognition performance, however, previous work considers only fixed contextual relations that do not depend of the type of scene under inspection. In this work, we present a method that learns adaptive conditional relationships that depend on the type of scene being analyzed. In particular, we propose a model based on a conditional mixture of trees that is able to capture contextual relationships among objects using global information about a scene. Our experiments show that the adaptive specialization of contextual relationships improves object recognition accuracy outperforming previous state-of-the-art approaches.

UR - http://www.scopus.com/inward/record.url?scp=84898441498&partnerID=8YFLogxK

U2 - 10.5244/C.26.121

DO - 10.5244/C.26.121

M3 - Paper

ER -

Peralta B, Espinace P, Soto A. Adaptive hierarchical contexts for object recognition with conditional mixture of trees. 2012. Papel presentado en 2012 23rd British Machine Vision Conference, BMVC 2012, Guildford, Surrey, United Kingdom. https://doi.org/10.5244/C.26.121