no code implementations • CVPR 2022 • Albert Mosella-Montoro, Javier Ruiz-Hidalgo
Whereas previous methods pre-compute handcrafted features that relate the mesh and the skeleton or assume a fixed topology of the skeleton, the proposed method extracts this information in an end-to-end learnable fashion by jointly learning the best relationship between mesh vertices and skeleton joints.
no code implementations • 23 Sep 2020 • Albert Mosella-Montoro, Javier Ruiz-Hidalgo
Multi-modal fusion has been proved to help enhance the performance of scene classification tasks.
no code implementations • 30 Sep 2019 • Albert Mosella-Montoro, Javier Ruiz-Hidalgo
Geometric 3D scene classification is a very challenging task.
no code implementations • 3 Apr 2019 • Adrià Ciurana, Albert Mosella-Montoro, Javier Ruiz-Hidalgo
Convolutional neural networks (CNNs) have demonstrated their capability to solve different kind of problems in a very huge number of applications.