Academic Positions

  • 2019

    Member of the Master Thesis Evaluation Committee

    Annual Catalan Meeting on Computer Vision

  • 2019

    Professor at Postgradute Course in Artificial Intelligence with Deep Learning

    Universitat Politècnica de Catalunya

  • 2018

    Assistant Professor of Digital Image Processing

    Universitat Politècnica de Catalunya

  • 2018

    Member of the Master Thesis Evaluation Committee

    Annual Catalan Meeting on Computer Vision

  • 2018

    Deep Learning Master Thesis Advisor

    Universitat Politècnica de Catalunya

Education & Training

  • Ph.D. Present

    PhD in Multidimensional Scene Understanding using Deep learning

    Universitat Politècnica de Catalunya

  • MSc 2017

    MSc in Computer Vision

    Universitat Autonoma de Barcelona

  • BSc 2015

    BSc in Audiovisual Systems Engineering

    Universitat Politècnica de Catalunya

Grants

  • 2018
    PhD Fellowship from Catalonia Government

Research Summary

Currently I am working on methodologies to process three-dimensional point clouds using deep learning techniques with the goal of understanding the information inherent on such data. To accomplish this, I am currently focusing on the following applications:

  • Scene Categorization
  • Image Retrieval
  • Semantic Segmentation
  • Instance Segmentation

Furthermore, I am interested in prediction algorithms applied to different fields such as: weather pronostics, market studies, software testing and so on. Additionally, I am also interested in the speech recognition and emotion analysis fields.

Interests

  • Artificial Intelligence
  • Machine Learning
  • Deep Learning
  • Convolutional Neural Networks
  • Recurrent Neural networks
  • Graph Neural networks
  • Computer Vision
  • Three-Dimensional Scene Understanding
  • Semantic Segmentation
  • Instance Segmentation
  • Object Detection
  • Image Retrieval
  • Autonomous Driving

Publications

Residual Attention Graph Convolutional Network for Geometric 3D Scene Classification

Albert Mosella-Montoro, Javier Ruiz-Hidalgo
Conference Papers Mosella-Montoro, Albert and Ruiz-Hidalgo, Javier, “Residual Attention Graph Convolutional Network for Geometric 3D Scene Classification”, in IEEE Conference on Computer Vision Workshop (ICCVW), Seoul, Korea, 2019.

Abstract

Geometric 3D scene classification is a very challenging task. Current methodologies extract the geometric information using only a depth channel provided by an RGB-D 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.

Hybrid Cosine Based Convolutional Neural Networks

Adrià Ciurana, Albert Mosella-Montoro, Javier Ruiz-Hidalgo
Misc Adrià Ciurana, Albert Mosella-Montoro, Javier Ruiz-Hidalgo, "Hybrid Cosine Based Convolutional Neural Networks", arXiv:1904.01987 (2019).

Abstract

Convolutional neural networks (CNNs) have demonstrated their capability to solve different kind of problems in a very huge number of applications. However, CNNs are limited for their computational and storage requirements. These limitations make difficult to implement these kind of neural networks on embedded devices such as mobile phones, smart cameras or advanced driving assistance systems. In this paper, we present a novel layer named Hybrid Cosine Based Convolution that replaces standard convolutional layers using cosine basis to generate filter weights. The proposed layers provide several advantages: faster convergence in training, the receptive field can be increased at no cost and substantially reduce the number of parameters. We evaluate our proposed layers on three competitive classification tasks where our proposed layers can achieve similar (and in some cases better) performances than VGG and ResNet architectures.

Contact & Meet Me

I would be happy to talk to you if you need my assistance in your research or whether you need support for your company. I am always open to collaborating with the industry in order to do a knowledge transfer of my investigation and create products with it. If you are interested in a research collaboration, please use my academic e-mail to contact me. For other topics, please use the second e-mail provided. In both cases you can reach me in skype.