IS = { zkontrolovano 02 Feb 2010 },
  UPDATE  = { 2009-08-18 },
  author =      {Thurau, Christian and Hlav{\'a}{\v c}, V{\'a}clav},
  title =       {Recognizing human actions by their pose},
  year =        {2009},
  month =       {July},
  pages =       {169-192},
  editor =      {Cremers, Daniel and Rosenhahn, Bodo and Yuille, Alan L. and Schmidt, Frank R.},
  booktitle =   {Statistical and Geometrical Approaches to Visual Motion Analysis},
  publisher =   {Springer Verlag},
  address =     {Berlin, Germany},
  isbn =        {978-3-642-03060-4},
  isbn =        {0302-9743},
  volume =      {5604},
  series =      {Lecture Notes in Computer Science},
  book_pages =  {322},
  annote = {The topic of human action recognition from image sequences
    gained increasing interest throughout the last
    years. Interestingly, the majority of approaches are restricted to
    dynamic motion features and therefore not universally
    applicable. In this paper, we propose to recognize human actions
    by evaluating a distribution over a set of predefined static poses
    which we refer to as pose primitives. We aim at a generally
    applicable approach that also works in still images, or for images
    taken from a moving camera. Experimental validation takes varying
    video sequence lengths into account and emphasizes the possibility
    for action recognition from single images, which we believe is an
    often overlooked but nevertheless important aspect of action
    recognition.  The proposed approach uses a set of training video
    sequences to estimate pose and action class representations. To
    incorporate the local temporal context of poses, atomic
    subsequences of poses using ngram expressions are explored. Action
    classes can be represented by histograms of poses primitive
    n-grams which allows for action recognition by means of histogram
    comparison. Although the suggested action recognition method is
    independent of the underlying low-level representation of poses,
    representations remain important for targeting practical problems.
    Thus, to deal with common problems in video based action
    recognition, e.g. articulated poses and cluttered background, a
    recently introduced Histogram of Oriented Gradient based
    descriptor is extended using a non-negative matrix factorization
  keywords =    {human detection, video analytics, computer vision, 
                 motion detection},
  authorship =  {50-50},
  edition =     {1},
  project =     {MRTN-CT-2004-005439, MSM6840770038, ICT-215078 DIPLECS },
  psurl       = {[PostScript, 1.65 MB] },