@InProceedings{MeloSaCaSoPeSc:2018:ObTeSe,
               author = "Melo, Victor Hugo Cunha de and Santos, Jesimon Barreto and Caetano 
                         J{\'u}nior, Carlos Ant{\^o}nio and Souza, J{\'e}ssica Sena de 
                         and Penatti, Ot{\'a}vio Augusto Bizetto and Schwartz, William 
                         Robson",
          affiliation = "Smart Sense Laboratory, Universidade Federal de Minas Gerais and 
                         Smart Sense Laboratory, Universidade Federal de Minas Gerais and 
                         Smart Sense Laboratory, Universidade Federal de Minas Gerais and 
                         Smart Sense Laboratory, Universidade Federal de Minas Gerais and 
                         Advanced Technologies, Samsung Research Institute and Smart Sense 
                         Laboratory, Universidade Federal de Minas Gerais",
                title = "Object-based Temporal Segment Relational Network for Activity 
                         Recognition",
            booktitle = "Proceedings...",
                 year = "2018",
               editor = "Ross, Arun and Gastal, Eduardo S. L. and Jorge, Joaquim A. and 
                         Queiroz, Ricardo L. de and Minetto, Rodrigo and Sarkar, Sudeep and 
                         Papa, Jo{\~a}o Paulo and Oliveira, Manuel M. and Arbel{\'a}ez, 
                         Pablo and Mery, Domingo and Oliveira, Maria Cristina Ferreira de 
                         and Spina, Thiago Vallin and Mendes, Caroline Mazetto and Costa, 
                         Henrique S{\'e}rgio Gutierrez and Mejail, Marta Estela and Geus, 
                         Klaus de and Scheer, Sergio",
         organization = "Conference on Graphics, Patterns and Images, 31. (SIBGRAPI)",
            publisher = "IEEE Computer Society",
              address = "Los Alamitos",
             keywords = "Action recognition, contextual cues, relational reasoning.",
             abstract = "Video understanding is the next frontier of computer vision, in 
                         which activity recognition plays a major role. Despite the recent 
                         improvements in holistic activity recognition, further researching 
                         part-based models such as context may allow us to better 
                         understand what is important for activities and thus improve our 
                         current activity recognition models. This work tackles contextual 
                         cues obtained from object detections, in which we posit that 
                         objects relevant to an action are related to its spatial 
                         arrangement regarding an agent. Based on that, we propose 
                         Egocentric Pyramid to encode such spatial relationships. We 
                         further extend it by proposing a data-centric approach named 
                         Temporal Segment Relational Network (TSRN). Our experiments give 
                         support to the hypothesis that object spatiality provides an 
                         important clue to activity recognition. In addition, our 
                         data-centric approach shows that besides such spatial features, 
                         there may be other important information that further enhances the 
                         object-based activity recognition, such as co-occurrence, relative 
                         size, and temporal information.",
  conference-location = "Foz do Igua{\c{c}}u, PR, Brazil",
      conference-year = "29 Oct.-1 Nov. 2018",
                  doi = "10.1109/SIBGRAPI.2018.00020",
                  url = "http://dx.doi.org/10.1109/SIBGRAPI.2018.00020",
             language = "en",
                  ibi = "8JMKD3MGPAW/3RPBTD2",
                  url = "http://urlib.net/ibi/8JMKD3MGPAW/3RPBTD2",
           targetfile = "Paper ID 98.pdf",
        urlaccessdate = "2024, May 03"
}