Ara es mostren els items 1-20 de 964

    • 2D to 3D body pose estimation for sign language with Deep Learning 

      Perez Granero, Pol (Universitat Politècnica de Catalunya, 2020-06)
      Treball Final de Grau
      Accés obert
      This project aims at leveraging the challenge of using 3D poses for Sign Language translation or animation by transforming 2D pose datasets into 3D ones. The goal is, using a 3D dataset of American Sign Language, to train ...
    • 2D–3D geometric fusion network using multi-neighbourhood graph convolution for RGB-D indoor scene classification 

      Mosella Montoro, Albert; Ruiz Hidalgo, Javier (Elsevier, 2021-12)
      Article
      Accés obert
      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 ...
    • 3D car detection with LIDAR 

      Fernandez López, Christian (Universitat Politècnica de Catalunya, 2019-06)
      Treball Final de Grau
      Accés obert
      Realitzat a/amb:   Ficosa Electronics
      En esta tesis se propone entrenar una red neuronal para la detección de coches, utilizando sólo puntos de un LIDAR de 32 canales de la base de datos de NuScenes. El objetivo es conseguir el reconocimiento de coches frontales ...
    • 3D convolutional neural networks for brain tumor segmentation 

      Casamitjana Díaz, Adrià; Puch Giner, Santi; Aduriz Saiz, Asier; Sayrol Clols, Elisa; Vilaplana Besler, Verónica (2016)
      Comunicació de congrés
      Accés restringit per política de l'editorial
      This paper presents our work on applying 3D Convolutional Networks for brain tumor segmentation for the BRATS challenge. We are currently experimenting with different 3D fully convolutional architectures. We present ...
    • 3D convolutional neural networks for brain tumor segmentation: a comparison of multi-resolution architectures 

      Casamitjana Díaz, Adrià; Puch Giner, Santi; Aduriz Saiz, Asier; Vilaplana Besler, Verónica (Springer, 2017-04-24)
      Capítol de llibre
      Accés obert
    • 3D Face recognition with stereo automotive cameras 

      Tura Vecino, Biel (Universitat Politècnica de Catalunya, 2019-06)
      Treball Final de Grau
      Accés restringit per acord de confidencialitat
      The automotive sector is experiencing a rapid change that will influence the way in which we will use cars. One of the main concerns of this new wave of automotive research regards the security of future vehicles, being ...
    • 3D point cloud correspondences using deep learning 

      Rica Palma, Javier de la (Universitat Politècnica de Catalunya, 2018-05)
      Treball Final de Grau
      Accés obert
      The main goal of the project is to find correspondences between points in two 3D point clouds using deep learning. A deep learning network is trained to select key points and find correspondences between two point clouds ...
    • 3D point cloud correspondences using graph neural networks 

      Gimenez Arnal, Mario (Universitat Politècnica de Catalunya, 2018-10-17)
      Treball Final de Grau
      Accés obert
      The purpose of this project is the study of neural networks, their training and application together with the creation of a database appropriate to the system. Specically, the 3D convolutional networks applied to a database ...
    • 3D pose estimation using convolutional neural networks 

      Rubio Romano, Antonio (Universitat Politècnica de Catalunya, 2015-10)
      Projecte Final de Màster Oficial
      Accés obert
      The present Master Thesis describes a new Pose Estimation method based on Convolutional Neural Networks (CNN). This method divides the three-dimensional space in several regions and, given an input image, returns the ...
    • A 3D Terrain Generator: Enhancing Robotics Simulations with GANs 

      Arellano Garcia, Silvia (Universitat Politècnica de Catalunya, 2023-07-06)
      Treball Final de Grau
      Accés obert
      Realitzat a/amb:   Aalto-yliopisto
      Simulation is essential in robotics to evaluate models and techniques in a controlled setting before conducting experiments on tangible agents. However, developing simulation environments can be a challenging and time-consuming ...
    • A benchmark for graph neural networks for computer network modeling 

      Carol Bosch, Sergi (Universitat Politècnica de Catalunya, 2019-06-27)
      Projecte Final de Màster Oficial
      Accés obert
      Today, network operators still lack functional network models able to make accurate predictions of end-to-end Key Performance Indicators (e.g., delay).This thesis introduces the benchmark for computer network modeling using ...
    • A BF16 FMA is all you need for DNN training 

      Osorio Ríos, John Haiber; Armejach Sanosa, Adrià; Petit, Eric; Henry, Greg; Casas, Marc (Institute of Electrical and Electronics Engineers (IEEE), 2022-07-01)
      Article
      Accés obert
      Fused Multiply-Add (FMA) functional units constitute a fundamental hardware component to train Deep Neural Networks (DNNs). Its silicon area grows quadratically with the mantissa bit count of the computer number format, ...
    • A closer look at referring expressions for video object segmentation 

      Bellver Bueno, Míriam; Ventura Royo, Carles; Silberer, Carina; Kazakos, Ioannis; Torres Viñals, Jordi; Giró Nieto, Xavier (2023-01)
      Article
      Accés obert
      The task of Language-guided Video Object Segmentation (LVOS) aims at generating binary masks for an object referred by a linguistic expression. When this expression unambiguously describes an object in the scene, it is ...
    • A communication infrastructure for emulating large-scale neural networks models 

      Barrera, A.G.; Moreno Aróstegui, Juan Manuel (Springer, 2012)
      Text en actes de congrés
      Accés restringit per política de l'editorial
      This paper presents the SEPELYNS architecture that permits to in- terconnect multiple spiking neurons focused on hardware implementations. SEPELYNS can connect millions of neur ons with thousands of synapses per neuron ...
    • A comparative study of different gradient approximations for Restricted Boltzmann Machines 

      Ji, Lihong (Universitat Politècnica de Catalunya, 2023-06-29)
      Projecte Final de Màster Oficial
      Accés obert
      Realitzat a/amb:   Universitat Rovira i Virgili. Escola Tècnica Superior d'Enginyeria / Universitat de Barcelona. Facultat de Matemàtiques i Informàtica
      This project consists of the theoretical study of Restricted Boltzmann Machines(RBMs) and focuses on the gradient approximations of RBMs. RBMs suffer from the dilemma of accurate learning with the exact gradient. Based on ...
    • A Comprehensive survey on deep future frame video prediction 

      Selva Castelló, Javier (Universitat Politècnica de Catalunya, 2018-01-25)
      Projecte Final de Màster Oficial
      Accés obert
      Realitzat a/amb:   Universitat de Barcelona
      El present projecte planteja l'estudi comprensiu i extens per a la tasca de predicció de fotogrames donada una seqüència de vídeo. Mitjançant l'anàlisi de l'estat de l'art en generació d'imatges, xarxes convolucionals i ...
    • A Convolutional Neural Network for the automatic diagnosis of collagen VI-related muscular dystrophies 

      Rodríguez Bazaga, Adrián; Roldán Molina, Mónica; Badosa Gallego, Maria del Carmen; Jiménez Mallebrera, Cecilia; Porta Pleite, Josep Maria (2019-12-01)
      Article
      Accés obert
      The development of machine learning systems for the diagnosis of rare diseases is challenging, mainly due to the lack of data to study them. This paper surmounts this obstacle and presents the first Computer-Aided Diagnosis ...
    • A cross-layer review of deep learning frameworks to ease their optimization and reuse 

      Tabani, Hamid; Pujol Torramorell, Roger; Abella Ferrer, Jaume; Cazorla Almeida, Francisco Javier (Institute of Electrical and Electronics Engineers (IEEE), 2020)
      Text en actes de congrés
      Accés obert
      Machine learning and especially Deep Learning (DL) approaches are at the heart of many domains, from computer vision and speech processing to predicting trajectories in autonomous driving and data science. Those approaches ...
    • A Deep learning method for optimal stopping problems 

      Boix Torres, Andreu (Universitat Politècnica de Catalunya, 2023-07)
      Treball Final de Grau
      Accés obert
      L’objectiu principal d’aquest treball és complementar els fonaments teòrics i implementar el model de Deep Learning presentat a l’article anomenat “Deep Optimal Stopping”, de Becker et al, publicat al Journal of Machine ...
    • A digital memristor emulator for FPGA-based artificial neural networks 

      Vourkas, Ioanis; Abusleme, A.; Ntinas, V.; Sirakoulis, Georgios Ch.; Rubio Sola, Jose Antonio (Institute of Electrical and Electronics Engineers (IEEE), 2016)
      Text en actes de congrés
      Accés restringit per política de l'editorial
      FPGAs are reconfigurable electronic platforms, well-suited to implement complex artificial neural networks (ANNs). To this end, the compact hardware (HW) implementation of artificial synapses is an important step to obtain ...