Recent Submissions

  • Textual visual semantic dataset for text spotting 

    Sabir, Ahmed; Moreno-Noguer, Francesc; Padró, Lluís (Institute of Electrical and Electronics Engineers (IEEE), 2020)
    Conference report
    Open Access
    Text Spotting in the wild consists of detecting and recognizing text appearing in images (e.g. signboards, traffic signals or brands in clothing or objects). This is a challenging problem due to the complexity of the context ...
  • Zoom control to compensate camera translation within a robot egomotion estimation approach 

    Alenyà Ribas, Guillem; Torras, Carme (2007)
    Conference report
    Open Access
    Zoom control has not received the attention one would expect in view of how it enriches the competences of a vision system. The possibility of changing the size of object projections not only permits analysing objects at ...
  • Visually-guided robot navigation: from artificial to natural landmarks 

    Celaya Llover, Enric; Albarral Garcia, Jose Luis; Jimenez Schlegl, Pablo; Torras, Carme (2007)
    Conference report
    Open Access
    Landmark-based navigation in unknown unstructured environments is far from solved. The bottleneck nowadays seems to be the fast detection of reliable visual references in the image stream as the robot moves. In our research, ...
  • Natural landmark detection for visually-guided robot navigation 

    Celaya Llover, Enric; Albarral Garcia, Jose Luis; Jimenez Schlegl, Pablo; Torras, Carme (2007)
    Conference report
    Open Access
    The main difficulty to attain fully autonomous robot navigation outdoors is the fast detection of reliable visual references, and their subsequent characterization as landmarks for immediate and unambiguous recognition. ...
  • Outdoor landmark-view recognition based on bipartite-graph matching and logistic regression 

    Todt, Eduardo; Torras, Carme (Institute of Electrical and Electronics Engineers (IEEE), 2007)
    Conference report
    Open Access
    This paper describes the extraction of visual landmarks from outdoor images for mobile robot applications. The concept of group of landmarks, called landmark-view, is introduced, aggregating the most relevant landmarks ...
  • Exploiting single-cycle symmetries in branch-and-prune algorithms 

    Ruiz de Angulo García, Vicente; Torras, Carme (2007)
    Conference report
    Open Access
    As a first attempt to exploit symmetries in continuous constraint problems, we focus on permutations of the variables consisting of one single cycle. We propose a procedure that takes advantage of these symmetries by ...
  • Human motion prediction via spatio-temporal inpainting 

    Hernández Ruiz, Alejandro José; Gall, Juergen; Moreno-Noguer, Francesc (Institute of Electrical and Electronics Engineers (IEEE), 2019)
    Conference report
    Open Access
    We propose a Generative Adversarial Network (GAN) to forecast 3D human motion given a sequence of past 3D skeleton poses. While recent GANs have shown promising results, they can only forecast plausible motion over relatively ...
  • Unsupervised image-to-video clothing transfer 

    Pumarola Peris, Albert; Goswami, Vedanuj; Vicente, Francisco; De La Torre, Fernando; Moreno-Noguer, Francesc (2019)
    Conference report
    Open Access
    We present a system to photo-realistically transfer the clothing of a person in a reference image into another person in an unconstrained image or video. Our architecture is based on a GAN equipped with a physical memory ...
  • 3DPeople: modeling the geometry of dressed humans 

    Pumarola Peris, Albert; Sánchez Riera, Jordi; Choi, Gary; Sanfeliu Cortés, Alberto; Moreno-Noguer, Francesc (2019)
    Conference report
    Open Access
    Recent advances in 3D human shape estimation build upon parametric representations that model very well the shape of the naked body, but are not appropriate to represent the clothing geometry. In this paper, we present an ...
  • Human-robot collaborative navigation search using social reward sources 

    Dalmasso Blanch, Marc; Garrell Zulueta, Anais; Jimenez Schlegl, Pablo; Sanfeliu Cortés, Alberto (2019)
    Conference report
    Open Access
    This paper proposes a Social Reward Sources (SRS) design for a Human-Robot Collaborative Navigation (HRCN) task: human-robot collaborative search. It is a flexible approach capable of handling the collaborative task, ...
  • Anticipatory science fiction to foster ethical debates on AI and robotics 

    Torras, Carme (2019)
    Conference report
    Open Access
    The influence that hyperconnectivity and our increasing interaction with machines will have on the evolution of society and on people’s daily lives is difficult to predict. Thus, when trying to anticipate the potential ...
  • Enhancing text spotting with a language model and visual context information 

    Sabir, Ahmed; Moreno-Noguer, Francesc; Padró, Lluís (IOS Press, 2018)
    Conference report
    Open Access
    This paper addresses the problem of detecting and recognizing text in images acquired ‘in the wild’. This is a severely under-constrained problem which needs to tackle a number of challenges including large occlusions, ...

View more