@InProceedings{KuhnMore:2021:DaFiCl,
               author = "Kuhn, Daniel M. and Moreira, Viviane P.",
          affiliation = "{Institute of Informatics - UFRGS } and {Institute of Informatics 
                         - UFRGS}",
                title = "BRCars: a Dataset for Fine-Grained Classification of Car Images",
            booktitle = "Proceedings...",
                 year = "2021",
               editor = "Paiva, Afonso and Menotti, David and Baranoski, Gladimir V. G. and 
                         Proen{\c{c}}a, Hugo Pedro and Junior, Antonio Lopes Apolinario 
                         and Papa, Jo{\~a}o Paulo and Pagliosa, Paulo and dos Santos, 
                         Thiago Oliveira and e S{\'a}, Asla Medeiros and da Silveira, 
                         Thiago Lopes Trugillo and Brazil, Emilio Vital and Ponti, Moacir 
                         A. and Fernandes, Leandro A. F. and Avila, Sandra",
         organization = "Conference on Graphics, Patterns and Images, 34. (SIBGRAPI)",
            publisher = "IEEE Computer Society",
              address = "Los Alamitos",
             keywords = "fine-grained computer vision, car model classification.",
             abstract = "Fine-grained computer vision tasks refer to the ability of 
                         distinguishing objects that belong to the same parent class, 
                         differentiating themselves by subtle visual elements. Image 
                         classification in car models is considered a fine-grained 
                         classification task. In this work, we introduce BRCars, a dataset 
                         that seeks to replicate the main challenges inherent to the task 
                         of classifying car images in many practical applications. BRCars 
                         contains around 300K images collected from a Brazilian car 
                         advertising website. The images correspond to 52K car instances 
                         and are distributed among 427 different models. The images are 
                         both from the exterior and the interior of the cars and present an 
                         unbalanced distribution across the different models. In addition, 
                         they are characterized by a lack of standardization in terms of 
                         perspective. We adopted a semi-automated annotation pipeline with 
                         the help of the new CLIP neural network, which enabled 
                         distinguishing thousands of images among different perspectives 
                         using textual queries. Experiments with standard deep learning 
                         classifiers were performed to serve as baseline results for future 
                         work on this topic. BRCars dataset is available at 
                         https://github.com/danimtk/brcars-dataset.",
  conference-location = "Gramado, RS, Brazil (virtual)",
      conference-year = "18-22 Oct. 2021",
                  doi = "10.1109/SIBGRAPI54419.2021.00039",
                  url = "http://dx.doi.org/10.1109/SIBGRAPI54419.2021.00039",
             language = "en",
                  ibi = "8JMKD3MGPEW34M/45CTUK5",
                  url = "http://urlib.net/ibi/8JMKD3MGPEW34M/45CTUK5",
           targetfile = "SIBGRAPI_2021_cars_classifiction.pdf",
        urlaccessdate = "2024, May 06"
}