@conference {cRuiz-Hidalgo19, title = {Residual Attention Graph Convolutional Network for Geometric 3D Scene Classification}, booktitle = {IEEE Conference on Computer Vision Workshop (ICCVW)}, year = {2019}, month = {11/2019}, publisher = {IEEE}, organization = {IEEE}, address = {Seoul, Korea}, abstract = {

Geometric 3D scene classification is a very challenging task. Current methodologies extract the geometric information using only a depth channel provided by an RGBD sensor. These kinds of methodologies introduce possible errors due to missing local geometric context in the depth channel. This work proposes a novel Residual Attention Graph Convolutional Network that exploits the intrinsic geometric context inside a 3D space without using any kind of point features, allowing the use of organized or unorganized 3D data. Experiments are done in NYU Depth v1 and SUN-RGBD datasets to study the different configurations and to demonstrate the effectiveness of the proposed method. Experimental results show that the proposed method outperforms current state-of-the-art in geometric 3D scene classification tasks.\ 

}, doi = {10.1109/ICCVW.2019.00507}, url = {https://imatge-upc.github.io/ragc/}, author = {Mosella-Montoro, Albert and Ruiz-Hidalgo, J.} }