Close
Metadata

@InProceedings{AlmeidaJrGuim:2017:CaStHu,
               author = "Almeida, Raquel and Jr, Zenilton K. Goncalves do Patrocinio and 
                         Guimaraes, Silvio Jamil Ferzoli",
          affiliation = "{PUC Minas} and {PUC Minas} and {PUC Minas}",
                title = "A New Pooling Strategy based on Local Feature Distribution: A Case 
                         Study for Human Action Classification",
            booktitle = "Proceedings...",
                 year = "2017",
               editor = "Torchelsen, Rafael Piccin and Nascimento, Erickson Rangel do and 
                         Panozzo, Daniele and Liu, Zicheng and Farias, Myl{\`e}ne and 
                         Viera, Thales and Sacht, Leonardo and Ferreira, Nivan and Comba, 
                         Jo{\~a}o Luiz Dihl and Hirata, Nina and Schiavon Porto, Marcelo 
                         and Vital, Creto and Pagot, Christian Azambuja and Petronetto, 
                         Fabiano and Clua, Esteban and Cardeal, Fl{\'a}vio",
         organization = "Conference on Graphics, Patterns and Images, 30. (SIBGRAPI)",
            publisher = "IEEE Computer Society",
              address = "Los Alamitos",
             keywords = "Mid-level representation, Human action classification, Pooling.",
             abstract = "Mid-level representations are used to map sets of local features 
                         into one global representation for a given media descriptor. In 
                         visual pattern recognition tasks, Bag-of-Words (BoW) is one 
                         popular strategy, among many methods available in literature, due 
                         mainly by the simplicity in concept and implementation. Despite 
                         the overall good results achieved by BoW in many tasks, the method 
                         is unstable in high dimensional feature space and quantization 
                         errors are usually ignored in the final representation. To cope 
                         with these problems, we propose a new pooling function based on 
                         feature points distribution around codewords. We propose to use 
                         the standard deviation associated with each codeword to measure 
                         attribution discrepancy and weight the impact that feature points 
                         will assume in the final representation. The main contribution of 
                         this article is the study of more discriminative representations, 
                         which amplify values of feature points close to codewords border 
                         regions. Experiments were conducted in human action classification 
                         task and results demonstrated that our pooling strategy has 
                         improved the classification rates in 25.6% for UCF Sports dataset 
                         and 21.4% for UCF 11 dataset, with respect to the original pooling 
                         function used in BoW.",
  conference-location = "Niter{\'o}i, RJ",
      conference-year = "Oct. 17-20, 2017",
             language = "en",
           targetfile = "PID4982925.pdf",
        urlaccessdate = "2021, Jan. 21"
}


Close