Multi-Label Object Categorization Using Histograms of Global Relations

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

Publikation: Kapitel i bog/rapport/konference-proceedingKonferencebidrag i proceedingsForskningpeer review


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.
TitelInternational Conference on 3D Vision (3DV)
RedaktørerMichael Brown, Jana Kosecka, Christian Theobalt
Publikationsdato20. nov. 2015
ISBN (Elektronisk)9781467383325
StatusUdgivet - 20. nov. 2015
BegivenhedInternational Conference on 3D Vision - Lyon, Frankrig
Varighed: 19. okt. 201522. okt. 2015


KonferenceInternational Conference on 3D Vision


Dyk ned i forskningsemnerne om 'Multi-Label Object Categorization Using Histograms of Global Relations'. Sammen danner de et unikt fingeraftryk.