Skip to main content

5 Result(s)

within Xavier Roca Remove this filter Natural Language Processing (NLP) Remove this filter

and

  1. No Access

    Chapter and Conference Paper

    Automatic Learning of Conceptual Knowledge in Image Sequences for Human Behavior Interpretation

    This work describes an approach for the interpretation and explanation of human behavior in image sequences, within the context of a Cognitive Vision System. The information source is the geometrical data obtaine...

    Pau Baiget, Carles Fernández, Xavier Roca… in Pattern Recognition and Image Analysis (2007)

  2. No Access

    Chapter and Conference Paper

    Natural Language Descriptions of Human Behavior from Video Sequences

    This contribution addresses the generation of textual descriptions in several natural languages for evaluation of human behavior in video sequences. The problem is tackled by converting geometrical information...

    Carles Fernández Tena, Pau Baiget… in KI 2007: Advances in Artificial Intelligen… (2007)

  3. No Access

    Chapter and Conference Paper

    A 3D Dynamic Model of Human Actions for Probabilistic Image Tracking

    In this paper we present a method suitable to be used for human tracking as a temporal prior in a particle filtering framework such as CONDENSATION [5]. This method is for predicting feasible human postures given...

    Ignasi Rius, Daniel Rowe, Jordi Gonzàlez… in Pattern Recognition and Image Analysis (2005)

  4. No Access

    Chapter and Conference Paper

    Probabilistic Image-Based Tracking: Improving Particle Filtering

    Condensation is a widely-used tracking algorithm based on particle filters. Although some results have been achieved, it has several unpleasant behaviours. In this paper, we highlight the...

    Daniel Rowe, Ignasi Rius, Jordi Gonzàlez… in Pattern Recognition and Image Analysis (2005)

  5. No Access

    Chapter and Conference Paper

    Multiple Model Approach to Deformable Shape Tracking

    This paper describes a new proposal for tracking deformable objects in video sequences using multiple shape models of heterogeneous dimensionality. This models are generated unsupervisedly from a training sequ...

    Daniel Ponsa, Xavier Roca in Pattern Recognition and Image Analysis (2003)