@InProceedings{GuoIshwKonr:2009:AcReVi,
               author = "Guo, Kai and Ishwar, Prakash and Konrad, Janusz",
          affiliation = "{Boston University} and {Boston University} and {Boston 
                         University}",
                title = "Action recognition in video by covariance matching of silhouette 
                         tunnels",
            booktitle = "Proceedings...",
                 year = "2009",
               editor = "Nonato, Luis Gustavo and Scharcanski, Jacob",
         organization = "Brazilian Symposium on Computer Graphics and Image Processing, 22. 
                         (SIBGRAPI)",
            publisher = "IEEE Computer Society",
              address = "Los Alamitos",
             keywords = "video analysis, action recognition, silhouette tunnel, covariance 
                         matching, generalized eigenvalues.",
             abstract = "Action recognition is a challenging problem in video analytics due 
                         to event complexity, variations in imaging conditions, and intra- 
                         and inter-individual action-variability. Central to these 
                         challenges is the way one models actions in video, i.e., action 
                         representation. In this paper, an action is viewed as a temporal 
                         sequence of local shape-deformations of centroid-centered object 
                         silhouettes, i.e., the shape of the centroid-centered object 
                         silhouette tunnel. Each action is represented by the empirical 
                         covariance matrix of a set of 13-dimensional normalized geometric 
                         feature vectors that capture the shape of the silhouette tunnel. 
                         The similarity of two actions is measured in terms of a Riemannian 
                         metric between their covariance matrices. The silhouette tunnel of 
                         a test video is broken into short overlapping segments and each 
                         segment is classified using a dictionary of labeled action 
                         covariance matrices and the nearest neighbor rule. On a database 
                         of 90 short video sequences this attains a correct classification 
                         rate of 97%, which is very close to the state-of-the-art, at 
                         almost 5-fold reduced computational cost. Majority-vote fusion of 
                         segment decisions achieves 100% classification rate.",
  conference-location = "Rio de Janeiro, RJ, Brazil",
      conference-year = "11-14 Oct. 2009",
                  doi = "10.1109/SIBGRAPI.2009.29",
                  url = "http://dx.doi.org/10.1109/SIBGRAPI.2009.29",
             language = "en",
                  ibi = "8JMKD3MGPBW4/35S6KT8",
                  url = "http://urlib.net/ibi/8JMKD3MGPBW4/35S6KT8",
           targetfile = "IEEE-PID949748_final_submission.pdf",
        urlaccessdate = "2024, Apr. 29"
}