@article {aMosella-Montoro21, title = {2D{\textendash}3D Geometric Fusion network using Multi-Neighbourhood Graph Convolution for RGB-D indoor scene classification}, journal = {Information Fusion}, volume = {76}, year = {2021}, month = {12/2021}, chapter = {46-54}, 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.\ 

https://imatge-upc.github.io/munegc/

}, doi = {10.1016/j.inffus.2021.05.002}, url = {https://imatge-upc.github.io/munegc/}, author = {Mosella-Montoro, Albert and Ruiz-Hidalgo, J.} }