Recent Submissions

  • Adapting the smart python agent development environment for parallel computing 

    Gnatyshak, Dmitry (Universitat Politècnica de Catalunya, 2019-04-15)
    Master thesis
    Open Access
    Covenantee:  Universitat Rovira i Virgili / Universitat de Barcelona
  • 3D hand reconstruction from RGB-D/RGB video frames in real-time 

    Toda Mas, Aleix (Universitat Politècnica de Catalunya, 2019-04-30)
    Master thesis
    Open Access
    Covenantee:  École polytechnique fédérale de Lausanne
    We present a pipeline able to extract 3D real-world measurements from RGB-D images with high accuracy in real-time. A new method bottom-up multi-person for hand-body pose detection evolved from OpenPifPaf has been presented. ...
  • Deep learning superresolution 

    Mazagatos Pérez, Santiago (Universitat Politècnica de Catalunya, 2019-04-24)
    Master thesis
    Open Access
    [...] In this work the author makes use of state-of-the-art Super-Resolution methods and denoising methods to try and create a comprehensive solution for all use cases related to digital art restoration.
  • Towards more informative hospital benchmarking with deeper data analysis 

    Oganesian, Suren Karenovich (Universitat Politècnica de Catalunya, 2019-04)
    Master thesis
    Restricted access - confidentiality agreement
  • Quantum machine learning 

    Riu I Vicente, Jordi (Universitat Politècnica de Catalunya, 2019-04-14)
    Master thesis
    Open Access
    We use reinforcement learning techniques to optimize the Quantum Approximate Optimization Algorithm when applied to the MaxCut problem. We explore Q-learning based techniques both for continuous and discrete action ...
  • A Human Shape-Motion Predictor with Deep Learning 

    Romero Mérida, Antonio (Universitat Politècnica de Catalunya, 2019-04-24)
    Master thesis
    Open Access
    The objective of this work is to obtain an end-to-end solution which predicts human motion and shape from a given video by extracting its pose in the Wild. Given incomplete human motion sequences our goal is to predict and ...
  • Evaluating the Robustness of GAN-Based Inverse Reinforcement Learning Algorithms 

    Heidecke, Johannes (Universitat Politècnica de Catalunya, 2019-01-15)
    Master thesis
    Open Access
    Covenantee:  Universitat de Barcelona / Universitat Rovira i Virgili
    We evaluate the robustness of reward functions learned with IRL, when transferred to similar tasks. We exceed state of the art results for one benchmark task and solve another one for the first time. Modifications are ...
  • Multiple attribute analysis for deep learning based apparent personality analysis 

    Pérez Principi, Ricardo Darío (Universitat Politècnica de Catalunya, 2019-01)
    Master thesis
    Open Access
    En este trabajo, abordamos el problema de la estimación de la personalidad aparente, es decir, la estimación de la impresión que personas tienen con sobre la personalidad de otra persona. El reconocimiento de rasgos de ...
  • Analysis of speeches in the Spanish Parliament 

    Wang, Zhizhao (Universitat Politècnica de Catalunya, 2018)
    Master thesis
    Open Access
    First part: classification of political speeches' titles; second part: extracting the information of politicians' characteristics from the biographies and measuring the correlation between the characteristics and the ...
  • Incorporation of models in automatic requirement dependencies detection 

    Borrull Baraut, Ricard (Universitat Politècnica de Catalunya, 2018-10-11)
    Master thesis
    Open Access
    Covenantee:  Universitat de Barcelona / Universitat Rovira i Virgili. Escola Tècnica Superior d'Enginyeria
    In this work, an approach to the automatic detection of dependencies in NL requirements is presented. The approach is based on an ontology containing knowledge defining dependency relations between requirements. In order ...
  • A Python implementation for discriminative multivariate data visualization using a Grand Tour of manifold learning nonlinear methods 

    Astudillo Aguilar, Angel (Universitat Politècnica de Catalunya, 2018-10)
    Master thesis
    Open Access
    In this work has been implemented the manifold grand tour with a GTM structureas a way to improve the intuitiveness of the visualization of the GTM manifold. It is done travelling across each point of the GTM structure and ...
  • Learning aerial social force model for drone navigation 

    Coll Gomila, Carles (Universitat Politècnica de Catalunya, 2018-10-15)
    Master thesis
    Open Access
    Es presenta un nou mètode per controlar el vol d'un drone, l'objectiu del qual és acompanyar una persona. Consisteix en una xarxa neuronal que s'entrena a partir de trajectòries d'exemple proporcionades per un humà. També ...

View more