Multi-Label Object Categorization Using Histograms of Global Relations

Wail Mustafa, Hanchen Xiong, Dirk Kraft, Sandor Szedmak, Justus Piater, Norbert Krüger

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

Abstract

In this paper, we present an object categorization system capable of assigning multiple and related categories for novel objects using multi-label learning. In this system, objects are described using global geometric relations of 3D features. We propose using the Joint SVM method for learning and we investigate the extraction of hierarchical clusters as a higher-level description of objects to assist the learning. We make comparisons with other multi-label learning approaches as well as single-label approaches (including a state-of-the-art methods using different object descriptors). The experiments are carried out on a dataset of 100 objects belonging to 13 visual and action-related categories. The results indicate that multi-label methods are able to identify the relation between the dependent categories and hence perform categorization accordingly. It is also found that extracting hierarchical clusters does not lead to gain in the system's performance. The results also show that using histograms of global relations to describe objects leads to fast learning in terms of the number of samples required for training.
Original languageEnglish
Title of host publicationInternational Conference on 3D Vision (3DV)
PublisherIEEE
Publication date2015
Pages309-317
DOIs
Publication statusPublished - 2015
Externally publishedYes
EventInternational Conference on 3D Vision - Lyon, France
Duration: 19 Oct 201522 Oct 2015

Conference

ConferenceInternational Conference on 3D Vision
CountryFrance
CityLyon
Period19/10/201522/10/2015

Fingerprint Dive into the research topics of 'Multi-Label Object Categorization Using Histograms of Global Relations'. Together they form a unique fingerprint.

Cite this