Enviaments recents

  • Adaptable multimodal interaction framework for robot-assisted cognitive training 

    Taranovic, Aleksandar; Jevtic, Aleksandar; Torras, Carme (2018)
    Text en actes de congrés
    Accés obert
    The size of the population with cognitive impairment is increasing worldwide, and socially assistive robotics offers a solution to the growing demand for professional carers. Adaptation to users generates more natural, ...
  • Multi-modal joint embedding for fashion product retrieval 

    Rubio Romano, Antonio; Yu, Longlong; Simo Serra, Edgar; Moreno-Noguer, Francesc (Institute of Electrical and Electronics Engineers (IEEE), 2017)
    Text en actes de congrés
    Accés obert
    Finding a product in the fashion world can be a daunting task. Everyday, e-commerce sites are updating with thousands of images and their associated metadata (textual information), deepening the problem, akin to finding a ...
  • Demonstration-free contextualized probabilistic movement primitives, further enhanced with obstacle avoidance 

    Colomé Figueras, Adrià; Torras, Carme (Institute of Electrical and Electronics Engineers (IEEE), 2017)
    Text en actes de congrés
    Accés obert
    Movement Primitives (MPs) have been widely used over the last years for learning robot motion tasks with direct Policy Search (PS) reinforcement learning. Among them, Probabilistic Movement Primitives (ProMPs) are a kind ...
  • Joint coarse-and-fine reasoning for deep optical flow 

    Vaquero Gómez, Víctor; Ros, German; Moreno-Noguer, Francesc; López, Antonio Manuel; Sanfeliu Cortés, Alberto (Institute of Electrical and Electronics Engineers (IEEE), 2017)
    Text en actes de congrés
    Accés obert
    We propose a novel representation for dense pixel-wise estimation tasks using CNNs that boosts accuracy and reduces training time, by explicitly exploiting joint coarse-and-fine reasoning. The coarse reasoning is performed ...
  • Reward-weighted GMM and its application to action-selection in robotized shoe dressing 

    Colomé Figueras, Adrià; Foix Salmerón, Sergi; Alenyà Ribas, Guillem; Torras, Carme (Springer, 2017)
    Text en actes de congrés
    Accés obert
    In the context of assistive robotics, robots need to make multiple decisions. We explore the problem where a robot has multiple choices to perform a task and must select the action that maximizes success probability among ...
  • The breakingNews dataset 

    Ramisa Ayats, Arnau; Yan, Fei; Moreno-Noguer, Francesc; Mikolajczyk, Krystian (2017)
    Text en actes de congrés
    Accés obert
    We present BreakingNews, a novel dataset with approximately 100K news articles including images, text and captions, and enriched with heterogeneous meta-data (e.g. GPS coordinates and popularity metrics). The tenuous ...
  • Software tools for the cognitive development of autonomous robots 

    Jimenez Schlegl, Pablo (2017)
    Text en actes de congrés
    Accés obert
    Robotic systems are evolving towards higher degrees of autonomy. This paper reviews the cognitive tools available nowadays for the fulfilment of abstract or long-term goals as well as for learning and modifying their behaviour.
  • A taxonomy of preferences for physically assistive robots 

    Canal Camprodon, Gerard; Alenyà Ribas, Guillem; Torras, Carme (IEEE Press, 2017)
    Text en actes de congrés
    Accés obert
    Assistive devices and technologies are getting common and some commercial products are starting to be available. However, the deployment of robots able to physically interact with a person in an assistive manner is still ...
  • DUST: dual union of spatio-temporal subspaces for monocular multiple object 3D reconstruction 

    Agudo Martínez, Antonio; Moreno-Noguer, Francesc (Institute of Electrical and Electronics Engineers (IEEE), 2017)
    Text en actes de congrés
    Accés obert
    We present an approach to reconstruct the 3D shape of multiple deforming objects from incomplete 2D trajectories acquired by a single camera. Additionally, we simultaneously provide spatial segmentation (i.e., we identify ...
  • Deconvolutional networks for point-cloud vehicle detection and tracking in driving scenarios 

    Vaquero Gómez, Víctor; del Pino Bastida, Iván; Moreno-Noguer, Francesc; Solà Ortega, Joan; Sanfeliu Cortés, Alberto; Andrade-Cetto, Juan (IEEE Press, 2017)
    Text en actes de congrés
    Accés obert
    Vehicle detection and tracking is a core ingredient for developing autonomous driving applications in urban scenarios. Recent image-based Deep Learning (DL) techniques are obtaining breakthrough results in these perceptive ...
  • Depth-aware convolutional neural networks for accurate 3D pose estimation in RGB-D images 

    Porzi, Lorenzo; Peñate Sánchez, Adrián; Ricci, Elisa; Moreno-Noguer, Francesc (2017)
    Text en actes de congrés
    Accés obert
    Most recent approaches to 3D pose estimation from RGB-D images address the problem in a two-stage pipeline. First, they learn a classifier –typically a random forest– to predict the position of each input pixel on the ...
  • 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 ...

Mostra'n més