%0 Conference Proceedings
%4 sid.inpe.br/sibgrapi/2018/10.17.11.39
%2 sid.inpe.br/sibgrapi/2018/10.17.11.39.27
%T Comparison of deep convolutional networks for action recognition in videos
%D 2018
%A Kovaleski, Patrícia de Andrade,
%A Nunes, Leonardo de Oliveira,
%A Silva, Eduardo Antônio Barros da,
%@affiliation Federal University of Rio de Janeiro
%@affiliation Microsoft
%@affiliation Federal University of Rio de Janeiro
%E Ross, Arun,
%E Gastal, Eduardo S. L.,
%E Jorge, Joaquim A.,
%E Queiroz, Ricardo L. de,
%E Minetto, Rodrigo,
%E Sarkar, Sudeep,
%E Papa, João Paulo,
%E Oliveira, Manuel M.,
%E Arbeláez, Pablo,
%E Mery, Domingo,
%E Oliveira, Maria Cristina Ferreira de,
%E Spina, Thiago Vallin,
%E Mendes, Caroline Mazetto,
%E Costa, Henrique Sérgio Gutierrez,
%E Mejail, Marta Estela,
%E Geus, Klaus de,
%E Scheer, Sergio,
%B Conference on Graphics, Patterns and Images, 31 (SIBGRAPI)
%C Foz do Iguaçu, PR, Brazil
%8 29 Oct.-1 Nov. 2018
%I Sociedade Brasileira de Computação
%J Porto Alegre
%S Proceedings
%K action recognition, deep convolutional networks, deep learning.
%X This work presents the implementation of deep convolutional networks for action recognition in videos based on the well-known two-stream architecture, that is composed of a temporal and a spatial stream. The development was done in order to replicate the one reported in the original paper using the Microsoft Cognitive Toolkit (CNTK). Different experiments were made in order to evaluate the performance of the two-stream in a public dataset when trained for different base network architectures and input data modality.
%@language en
%3 comparison-deep-convolutional-final.pdf