Ara es mostren els items 1-20 de 96

  • 3D CNNs on distance matrices for human action recognition 

    Hernández Ruiz, Alejandro José; Porzi, Lorenzo; Rota Bulò, Samuel; Moreno-Noguer, Francesc (2017)
    Text en actes de congrés
    Accés obert
    In this paper we are interested in recognizing human actions from sequences of 3D skeleton data. For this purpose we combine a 3D Convolutional Neural Network with body representations based on Euclidean Distance Matrices ...
  • 3D human pose estimation from a single image via distance matrix regression 

    Moreno-Noguer, Francesc (Institute of Electrical and Electronics Engineers (IEEE), 2017)
    Text en actes de congrés
    Accés obert
    This paper addresses the problem of 3D human pose estimation from a single image. We follow a standard two-step pipeline by first detecting the 2D position of the N body joints, and then using these observations to infer ...
  • 3D human pose tracking priors using geodesic mixture models 

    Simó Serra, Edgar; Torras, Carme; Moreno-Noguer, Francesc (2017-04-01)
    Article
    Accés obert
    We present a novel approach for learning a finite mixture model on a Riemannian manifold in which Euclidean metrics are not applicable and one needs to resort to geodesic distances consistent with the manifold geometry. ...
  • A 3D descriptor to detect task-oriented grasping points in clothing 

    Ramisa Ayats, Arnau; Alenyà Ribas, Guillem; Moreno-Noguer, Francesc; Torras, Carme (2016)
    Article
    Accés obert
    Manipulating textile objects with a robot is a challenging task, especially because the garment perception is difficult due to the endless configurations it can adopt, coupled with a large variety of colors and designs. ...
  • A bayesian approach to simultaneously recover camera pose and non-rigid shape from monocular images 

    Moreno-Noguer, Francesc; Porta Pleite, Josep Maria (2016)
    Article
    Accés obert
    In this paper we bring the tools of the Simultaneous Localization and Map Building (SLAM) problem from a rigid to a deformable domain and use them to simultaneously recover the 3D shape of non-rigid surfaces and the sequence ...
  • Accurate and linear time pose estimation from points and lines 

    Vakhitov, A.; Funke, Jan; Moreno-Noguer, Francesc (2016)
    Text en actes de congrés
    Accés obert
    The Perspective-n-Point (PnP) problem seeks to estimate the pose of a calibrated camera from n 3Dto-2D point correspondences. There are situations, though, where PnP solutions are prone to fail because feature point ...
  • Active perception of deformable objects using 3D cameras 

    Alenyà Ribas, Guillem; Moreno-Noguer, Francesc; Ramisa Ayats, Arnau; Torras, Carme (Escuela Superior de Ingenieros de la Universidad de Sevilla, 2011)
    Text en actes de congrés
    Accés obert
    Perception and manipulation of rigid objects has received a lot of attention, and several solutions have been proposed. In contrast, dealing with deformable objects is a relatively new and challenging task because they ...
  • Active testing search for point cloud matching 

    Amável Pinheiro, Miguel; Sznitman, Raphael; Serradell, Eduard; Kybic, Jan; Moreno-Noguer, Francesc; Fua, Pascal (Springer, 2013)
    Text en actes de congrés
    Accés obert
    We present a general approach for solving the point-cloud matching problem for the case of mildly nonlinear transformations. Our method quickly finds a coarse approximation of the solution by exploring a reduced set of ...
  • 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 ...
  • A joint model for 2D and 3D pose estimation from a single image 

    Simó Serra, Edgar; Quattoni, Ariadna Julieta; Torras, Carme; Moreno-Noguer, Francesc (Institute of Electrical and Electronics Engineers (IEEE), 2013)
    Text en actes de congrés
    Accés restringit per política de l'editorial
    We introduce a novel approach to automatically recover 3D human pose from a single image. Most previous work follows a pipelined approach: initially, a set of 2D features such as edges, joints or silhouettes are detected ...
  • A scalable, efficient, and accurate solution to non-rigid structure from motion 

    Agudo Martínez, Antonio; Moreno-Noguer, Francesc (2018)
    Article
    Accés obert
    Most Non-Rigid Structure from Motion (NRSfM) solutions are based on factorization approaches that allow reconstructing objects parameterized by a sparse set of 3D points. These solutions, however, are low resolution and ...
  • BASS: boundary-aware superpixel segmentation 

    Rubio Romano, Antonio; Yu, Longlong; Simó Serra, Edgar; Moreno-Noguer, Francesc (IEEE Press, 2016)
    Text en actes de congrés
    Accés obert
    We propose a new superpixel algorithm based on exploiting the boundary information of an image, as objects in images can generally be described by their boundaries. Our proposed approach initially estimates the boundaries ...
  • Boosted Random ferns for object detection 

    Villamizar Vergel, Michael Alejandro; Andrade-Cetto, Juan; Sanfeliu Cortés, Alberto; Moreno-Noguer, Francesc (2018-02-01)
    Article
    Accés obert
    In this paper we introduce the Boosted Random Ferns (BRFs) to rapidly build discriminative classifiers for learning and detecting object categories. At the core of our approach we use standard random ferns, but we introduce ...
  • Breakingnews: article annotation by image and text processing 

    Ramisa Ayats, Arnau; Yan, Fei; Moreno-Noguer, Francesc; Mikolajczyk, Krystian (Institute of Electrical and Electronics Engineers (IEEE), 2018-05-01)
    Article
    Accés obert
    Building upon recent Deep Neural Network architectures, current approaches lying in the intersection of Computer Vision and Natural Language Processing have achieved unprecedented breakthroughs in tasks like automatic ...
  • Characterization of textile grasping experiments 

    Alenyà Ribas, Guillem; Ramisa Ayats, Arnau; Moreno-Noguer, Francesc; Torras, Carme (2012)
    Text en actes de congrés
    Accés obert
    Grasping highly deformable objects, like textiles, is an emerging area of research that involves both percep- tion and manipulation abilities. As new techniques appear, it becomes essential to design strategies to compare ...
  • Combining geometric and appearance priors for robust homography estimation 

    Serradell, Eduard; Özuysa, Mustafa; Lepetit, Vincent; Fua, Pascal; Moreno-Noguer, Francesc (Springer, 2010)
    Text en actes de congrés
    Accés restringit per política de l'editorial
    Abstract. The homography between pairs of images are typically computed from the correspondence of keypoints, which are established by using image descriptors. When these descriptors are not reliable, either because of ...
  • 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 ...
  • Combining local-physical and global-statistical models for sequential deformable shape from motion 

    Agudo Martínez, Antonio; Moreno-Noguer, Francesc (2017-04-01)
    Article
    Accés obert
    In this paper, we simultaneously estimate camera pose and non-rigid 3D shape from a monocular video, using a sequential solution that combines local and global representations. We model the object as an ensemble of particles, ...
  • DaLI: deformation and light invariant descriptor 

    Simó Serra, Edgar; Torras, Carme; Moreno-Noguer, Francesc (2015-11-01)
    Article
    Accés obert
    Recent advances in 3D shape analysis and recognition have shown that heat diffusion theory can be effectively used to describe local features of deforming and scaling surfaces. In this paper, we show how this description ...
  • Database for 3D human pose estimation from single depth images 

    Arduengo García, Miguel; Alenyà Ribas, Guillem; Moreno-Noguer, Francesc (2016)
    Report de recerca
    Accés obert
    This work is part of the project I-­-DRESS (Assistive interactive robotic system for support in dressing). The specific objective is the detection of human body postures and the tracking of their movements. To this end, ...