Enviaments recents

  • Modeling robot's world with minimal effort 

    Villamizar Vergel, Michael Alejandro; Garrell Zulueta, Anais; Sanfeliu Cortés, Alberto; Moreno-Noguer, Francesc (Institute of Electrical and Electronics Engineers (IEEE), 2015)
    Text en actes de congrés
    Accés obert
    We propose an efficient Human Robot Interaction approach to efficiently model the appearance of all relevant objects in robot’s environment. Given an input video stream recorded while the robot is navigating, the user just ...
  • Neuroaesthetics in fashion: modeling the perception of fashionability 

    Simó Serra, Edgar; Fidler, Sanja; Moreno-Noguer, Francesc; Urtasun, Raquel (2015)
    Text en actes de congrés
    Accés obert
    In this paper, we analyze the fashion of clothing of a large social website. Our goal is to learn and predict how fashionable a person looks on a photograph and suggest subtle improvements the user could make to improve ...
  • Learning shape, motion and elastic models in force space 

    Agudo Martínez, Antonio; Moreno-Noguer, Francesc (Institute of Electrical and Electronics Engineers (IEEE), 2015)
    Text en actes de congrés
    Accés obert
    In this paper, we address the problem of simultaneously recovering the 3D shape and pose of a deformable and potentially elastic object from 2D motion. This is a highly ambiguous problem typically tackled by using low-rank ...
  • Lie algebra-based kinematic prior for 3D human pose tracking 

    Simó Serra, Edgar; Torras, Carme; Moreno-Noguer, Francesc (2015)
    Text en actes de congrés
    Accés obert
    We propose a novel kinematic prior for 3D human pose tracking that allows predicting the position in subsequent frames given the current position. We first define a Riemannian manifold that models the pose and extend it ...
  • Teaching grasping points using natural movements 

    Isleyici, Yalim; Alenyà Ribas, Guillem (IOS Press, 2015)
    Text en actes de congrés
    Accés obert
    The research on robots performing every-day tasks at home, has pursued the problem of the manipulation of everyday objects. Among them, grasping a cloth is a challenging task, as the textile is highly-deformable and it is ...
  • A high performance CRF model for clothes parsing 

    Simó Serra, Edgar; Fidler, Sanja; Moreno-Noguer, Francesc; Urtasun, Raquel (Springer, 2014)
    Text en actes de congrés
    Accés obert
    In this paper we tackle the problem of clothing parsing: Our goal is to segment and classify different garments a person is wearing. We frame the problem as the one of inference in a pose-aware Conditional Random Field ...
  • Safe robot execution in model-based reinforcement learning 

    Martínez Martínez, David; Alenyà Ribas, Guillem; Torras, Carme (Institute of Electrical and Electronics Engineers (IEEE), 2015)
    Text en actes de congrés
    Accés obert
    Task learning in robotics requires repeatedly executing the same actions in different states to learn the model of the task. However, in real-world domains, there are usually sequences of actions that, if executed, may ...
  • Matchability prediction for full-search template matching algorithms 

    Peñate Sánchez, Adrián; Porzi, Lorenzo; Moreno-Noguer, Francesc (Institute of Electrical and Electronics Engineers (IEEE), 2015)
    Text en actes de congrés
    Accés obert
    While recent approaches have shown that it is possible to do template matching by exhaustively scanning the parameter space, the resulting algorithms are still quite demanding. In this paper we alleviate the computational ...
  • Combining geometric, textual and visual features for predicting prepositions in image descriptions 

    Ramisa Ayats, Arnau; Wang, Josiah; Lu, Ying; Dellandrea, Emmanuel; Moreno-Noguer, Francesc; Gaizauskas, Robert (2016)
    Text en actes de congrés
    Accés obert
    We investigate the role that geometric, textual and visual features play in the task of predicting a preposition that links two visual entities depicted in an image. The task is an important part of the subsequent process ...
  • Learning probabilistic action models from interpretation transitions 

    Martínez Martínez, David; Ribeiro, Tony; Inoue, Katsumi; Alenyà Ribas, Guillem; Torras, Carme (2015)
    Text en actes de congrés
    Accés obert
    Probabilistic planners are very flexible tools that provide good solutions for difficult tasks. However, they rely on a model of the domain and actions, which they have difficulties to learn for complex tasks. We propose ...

Mostra'n més