@InProceedings{CaetanoMeloSantSchw:2017:AcReBa,
author = "Caetano, Carlos and Melo, Victor H. C. de and Santos, Jefersson A.
dos and Schwartz, William Robson",
affiliation = "{Universidade Federal de Minas Gerais} and {Universidade Federal
de Minas Gerais} and {Universidade Federal de Minas Gerais} and
{Universidade Federal de Minas Gerais}",
title = "Activity Recognition based on a Magnitude-Orientation Stream
Network",
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 = "Magnitude, Orientation, Stream Network, Convolutional Neural
Networks.",
abstract = "The temporal component of videos provides an important clue for
activity recognition, as a number of activities can be reliably
recognized based on the motion information. In view of that, this
work proposes a novel temporal stream for two-stream convolutional
networks based on images computed from the optical flow magnitude
and orientation, named Magnitude-Orientation Stream (MOS), to
learn the motion in a better and richer manner. Our method applies
simple nonlinear transformations on the vertical and horizontal
components of the optical flow to generate input images for the
temporal stream. Experimental results, carried on two well-known
datasets (HMDB51 and UCF101), demonstrate that using our proposed
temporal stream as input to existing neural network architectures
can improve their performance for activity recognition. Results
demonstrate that our temporal stream provides complementary
information able to improve the classical two-stream methods,
indicating the suitability of our approach to be used as a
temporal video representation.",
conference-location = "Niter{\'o}i, RJ, Brazil",
conference-year = "17-20 Oct. 2017",
doi = "10.1109/SIBGRAPI.2017.13",
url = "http://dx.doi.org/10.1109/SIBGRAPI.2017.13",
language = "en",
ibi = "8JMKD3MGPAW/3PF6LMS",
url = "http://urlib.net/ibi/8JMKD3MGPAW/3PF6LMS",
targetfile = "main Certified by IEEE PDF eXpress.pdf",
urlaccessdate = "2024, Apr. 29"
}