@InProceedings{AndalóPenaTest:2016:TaViCo,
               author = "Andal{\'o}, Fernanda A. and Penatti, Ot{\'a}vio A. B. and 
                         Testoni, Vanessa",
          affiliation = "{Samsung Research Institute} and {Samsung Research Institute} and 
                         {Samsung Research Institute}",
                title = "Transmitting what matters: task-oriented video composition and 
                         compression",
            booktitle = "Proceedings...",
                 year = "2016",
               editor = "Aliaga, Daniel G. and Davis, Larry S. and Farias, Ricardo C. and 
                         Fernandes, Leandro A. F. and Gibson, Stuart J. and Giraldi, Gilson 
                         A. and Gois, Jo{\~a}o Paulo and Maciel, Anderson and Menotti, 
                         David and Miranda, Paulo A. V. and Musse, Soraia and Namikawa, 
                         Laercio and Pamplona, Mauricio and Papa, Jo{\~a}o Paulo and 
                         Santos, Jefersson dos and Schwartz, William Robson and Thomaz, 
                         Carlos E.",
         organization = "Conference on Graphics, Patterns and Images, 29. (SIBGRAPI)",
            publisher = "IEEE Computer Society´s Conference Publishing Services",
              address = "Los Alamitos",
             keywords = "composition, object detection and tracking, video compression, 
                         computer vision applications.",
             abstract = "We present a simple yet effective framework - Transmitting What 
                         Matters (TWM) - to generate compressed videos containing only 
                         relevant objects targeted to specific computer vision tasks, such 
                         as faces for the task of face expression recognition, license 
                         plates for the task of optical character recognition, among 
                         others. TWM takes advantage of the final desired computer vision 
                         task to compose video frames only with the necessary data. The 
                         video frames are compressed and can be stored or transmitted to 
                         powerful servers where extensive and time-consuming tasks can be 
                         performed. We experimentally present the trade-offs between 
                         distortion and bitrate for a wide range of compression levels, and 
                         the impact generated by compression artifacts on the accuracy of 
                         the desired vision task. We show that, for one selected computer 
                         vision task, it is possible to dramatically reduce the amount of 
                         required data to be stored or transmitted, without compromising 
                         accuracy.",
  conference-location = "S{\~a}o Jos{\'e} dos Campos, SP, Brazil",
      conference-year = "4-7 Oct. 2016",
                  doi = "10.1109/SIBGRAPI.2016.019",
                  url = "http://dx.doi.org/10.1109/SIBGRAPI.2016.019",
             language = "en",
                  ibi = "8JMKD3MGPAW/3M5JQ92",
                  url = "http://urlib.net/ibi/8JMKD3MGPAW/3M5JQ92",
           targetfile = "PID4346111.pdf",
        urlaccessdate = "2024, Apr. 28"
}