@InProceedings{SadMotMacVieAra:2013:TeMoDe,
               author = "Sad, Dhiego and Mota, Virg{\'{\i}}nia Fernandes and Maciel, Luiz 
                         Maur{\'{\i}}lio and Vieira, Marcelo Bernardes and Ara{\'u}jo, 
                         Arnaldo de Albuquerque",
          affiliation = "{Universidade Federal de Juiz de Fora} and {Universidade Federal 
                         de Minas Gerais} and {Universidade Federal de Juiz de Fora} and 
                         {Universidade Federal de Juiz de Fora} and {Universidade Federal 
                         de Minas Gerais}",
                title = "A Tensor Motion Descriptor Based on Multiple Gradient Estimators",
            booktitle = "Proceedings...",
                 year = "2013",
               editor = "Boyer, Kim and Hirata, Nina and Nedel, Luciana and Silva, 
                         Claudio",
         organization = "Conference on Graphics, Patterns and Images, 26. (SIBGRAPI)",
            publisher = "IEEE Computer Society",
              address = "Los Alamitos",
             keywords = "Multifilter analysis, Motion descriptor, Orientation tensor, Human 
                         action recognition.",
             abstract = "This work presents a novel approach for motion description in 
                         videos using multiple band-pass filters which act as first order 
                         derivative estimators. The filters response on each frame are 
                         coded into individual histograms of gradients to reduce their 
                         dimensionality. They are combined using orientation tensors. No 
                         local features are extracted and no learning is performed, i.e., 
                         the descriptor depends uniquely on the input video. Motion 
                         description can be enhanced even using multiple filters with 
                         similar or overlapping frequency response. For the problem of 
                         human action recognition using the KTH database, our descriptor 
                         achieved the recognition rate of 93.3% using three Daubechies 
                         filters, one extra filter designed to correlate them, two-fold 
                         protocol and a SVM classifier. It is superior to most global 
                         descriptor approaches and fairly comparable to the state- 
                         of-the-art methods.",
  conference-location = "Arequipa, Peru",
      conference-year = "5-8 Aug. 2013",
                  doi = "10.1109/SIBGRAPI.2013.19",
                  url = "http://dx.doi.org/10.1109/SIBGRAPI.2013.19",
             language = "en",
                  ibi = "8JMKD3MGPBW34M/3EEH5B2",
                  url = "http://urlib.net/ibi/8JMKD3MGPBW34M/3EEH5B2",
           targetfile = "paper_sad_114944.pdf",
        urlaccessdate = "2024, Apr. 27"
}