Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/43464
DC FieldValueLanguage
dc.contributorDepartment of Computing-
dc.creatorXie, X-
dc.creatorYang, L-
dc.creatorZheng, WS-
dc.date.accessioned2016-06-07T06:16:22Z-
dc.date.available2016-06-07T06:16:22Z-
dc.identifier.issn1077-3142-
dc.identifier.urihttp://hdl.handle.net/10397/43464-
dc.language.isoenen_US
dc.publisherAcademic Pressen_US
dc.subjectGraph modelen_US
dc.subjectMaterial recognitionen_US
dc.subjectMulti-label learningen_US
dc.subjectObject recognitionen_US
dc.titleLearning object-specific DAGs for multi-label material recognitionen_US
dc.typeJournal/Magazine Articleen_US
dc.identifier.spage183-
dc.identifier.epage190-
dc.identifier.volume143-
dc.identifier.doi10.1016/j.cviu.2015.11.018-
dcterms.abstractA real-world object surface often consists of multiple materials. Recognizing surface materials is important because it significantly benefits understanding the quality and functionality of the object. However, identifying multiple materials on a surface from a single photograph is very challenging because different materials are often interweaved together and hard to be segmented for separate identification. To address this problem, we present a multi-label learning framework for identifying multiple materials of a real-world object surface without a segmentation for each of them. We find that there are potential correlations between materials and that correlations are relevant to object category. For example, a surface of monitor likely consists of plastic and glasses rather than wood or stone. It motivates us to learn the correlations of material labels locally on each semantic object cluster. To this end, samples are semantically grouped according to their object categories. For each group of samples, we employ a Directed Acyclic Graph (DAG) to encode the conditional dependencies of material labels. These object-specific DAGs are then used for assisting the inference of surface materials. The key enabler of the proposed method is that the object recognition provides a semantic cue for material recognition by formulating an object-specific DAG learning. We test our method on the ALOT database and show consistent improvements over the state-of-the-arts.-
dcterms.bibliographicCitationComputer vision and image understanding, 2016, v. 143, p. 183-190-
dcterms.isPartOfComputer vision and image understanding-
dcterms.issued2016-
dc.identifier.scopus2-s2.0-84954323385-
Appears in Collections:Journal/Magazine Article
Access
View full-text via PolyU eLinks SFX Query
Show simple item record

SCOPUSTM   
Citations

3
Last Week
0
Last month
Citations as of Sep 6, 2020

WEB OF SCIENCETM
Citations

3
Last Week
0
Last month
Citations as of Oct 29, 2020

Page view(s)

144
Last Week
6
Last month
Citations as of Oct 25, 2020

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.