Mostra el registre d'ítem simple
2D–3D geometric fusion network using multi-neighbourhood graph convolution for RGB-D indoor scene classification
dc.contributor.author | Mosella Montoro, Albert |
dc.contributor.author | Ruiz Hidalgo, Javier |
dc.contributor.other | Universitat Politècnica de Catalunya. Doctorat en Teoria del Senyal i Comunicacions |
dc.contributor.other | Universitat Politècnica de Catalunya. Departament de Teoria del Senyal i Comunicacions |
dc.date.accessioned | 2021-05-31T14:32:16Z |
dc.date.available | 2023-12-01T01:30:47Z |
dc.date.issued | 2021-12 |
dc.identifier.citation | Mosella, A.; Ruiz-Hidalgo, J. 2D–3D geometric fusion network using multi-neighbourhood graph convolution for RGB-D indoor scene classification. "Information fusion", Desembre 2021, vol. 76, p. 46-54. |
dc.identifier.issn | 1566-2535 |
dc.identifier.uri | http://hdl.handle.net/2117/346435 |
dc.description.abstract | Multi-modal fusion has been proved to help enhance the performance of scene classification tasks. This paper presents a 2D-3D Fusion stage that combines 3D Geometric Features with 2D Texture Features obtained by 2D Convolutional Neural Networks. To get a robust 3D Geometric embedding, a network that uses two novel layers is proposed. The first layer, Multi-Neighbourhood Graph Convolution, aims to learn a more robust geometric descriptor of the scene combining two different neighbourhoods: one in the Euclidean space and the other in the Feature space. The second proposed layer, Nearest Voxel Pooling, improves the performance of the well-known Voxel Pooling. Experimental results, using NYU-Depth-V2 and SUN RGB-D datasets, show that the proposed method outperforms the current state-of-the-art in RGB-D indoor scene classification task. |
dc.description.sponsorship | This work was supported by Secretary of Universities and Research of the Generalitat de Catalunya and the European Social Fund via a PhD grant (FI2018) in the framework of project TEC2016-75976-R, financed by the Ministerio de Economía, Industria y Competitividad and the European Regional Development Fund (ERDF). |
dc.format.extent | 9 p. |
dc.language.iso | eng |
dc.publisher | Elsevier |
dc.subject.lcsh | Neural networks (Computer science) |
dc.subject.lcsh | Multisensor data fusion |
dc.subject.other | Convolutional Graph Neural Network |
dc.subject.other | Multi-modal fusion |
dc.subject.other | Multi-Neighbourhood Graph Neural Network |
dc.subject.other | Indoor scene classification |
dc.subject.other | RGB-D |
dc.title | 2D–3D geometric fusion network using multi-neighbourhood graph convolution for RGB-D indoor scene classification |
dc.type | Article |
dc.subject.lemac | Xarxes neuronals (Informàtica) |
dc.subject.lemac | Fusió d'imatges |
dc.contributor.group | Universitat Politècnica de Catalunya. GPI - Grup de Processament d'Imatge i Vídeo |
dc.identifier.doi | 10.1016/j.inffus.2021.05.002 |
dc.description.peerreviewed | Peer Reviewed |
dc.relation.publisherversion | https://www.sciencedirect.com/science/article/pii/S1566253521001032 |
dc.rights.access | Open Access |
local.identifier.drac | 31757795 |
dc.description.version | Postprint (author's final draft) |
dc.relation.projectid | info:eu-repo/grantAgreement/MINECO/2PE/TEC2016-75976-R |
local.citation.author | Mosella, A.; Ruiz-Hidalgo, J. |
local.citation.publicationName | Information fusion |
local.citation.volume | 76 |
local.citation.startingPage | 46 |
local.citation.endingPage | 54 |
Fitxers d'aquest items
Aquest ítem apareix a les col·leccions següents
-
Articles de revista [2.526]
-
Articles de revista [211]
-
Articles de revista [118]