@InProceedings{LopesSanValAlmAra:2011:TrLeHu,
author = "Lopes, Ana Paula B. and Santos, Elerson R. da S. and Valle,
Eduardo A. and Almeida, Jussara M. de and Ara{\'u}jo, Arnaldo de
Albuquerque",
affiliation = "Depart. of Computer Science - Universidade Federal de Minas Gerais
(UFMG),Belo Horizonte (MG), Brazil and Depart. of Exact and Tech.
Sciences - Universidade Estadual de Santa Cruz (UESC),ilh{\'e}us,
Brazil and Depart. of Computer Science - Universidade Federal de
Minas Gerais (UFMG),Belo Horizonte (MG), Brazil and Universidade
Estadual de Campinas (UNICAMP), Campinas (SP), Brazil and Depart.
of Computer Science - Universidade Federal de Minas Gerais
(UFMG),Belo Horizonte (MG), Brazil and Depart. of Computer Science
- Universidade Federal de Minas Gerais (UFMG),Belo Horizonte (MG),
Brazil",
title = "Transfer Learning for Human Action Recognition",
booktitle = "Proceedings...",
year = "2011",
editor = "Lewiner, Thomas and Torres, Ricardo",
organization = "Conference on Graphics, Patterns and Images, 24. (SIBGRAPI)",
publisher = "IEEE Computer Society",
address = "Los Alamitos",
keywords = "action recognition, transfer learning, bags-of-visual-features,
video understanding.",
abstract = "To manually collect action samples from realistic videos is a
time-consuming and error-prone task. This is a serious bottleneck
to research related to video understanding, since the large
intra-class variations of such videos demand training sets large
enough to properly encompass those variations. Most authors
dealing with this issue rely on (semi-) automated procedures to
collect additional, generally noisy, examples. In this paper, we
exploit a different approach, based on a Transfer Learning (TL)
technique, to address the target task of action recognition. More
specifically, we propose a framework that transfers the knowledge
about concepts from a previously labeled still image database to
the target action video database. It is assumed that, once
identified in the target action database, these concepts provide
some contextual clues to the action classifier. Our experiments
with Caltech256 and Hollywood2 databases indicate: a) the
feasibility of successfully using transfer learning techniques to
detect concepts and, b) that it is indeed possible to enhance
action recognition with the transferred knowledge of even a few
concepts. In our case, only four concepts were enough to obtain
statistically significant improvements for most actions.",
conference-location = "Macei{\'o}, AL, Brazil",
conference-year = "28-31 Aug. 2011",
doi = "10.1109/SIBGRAPI.2011.41",
url = "http://dx.doi.org/10.1109/SIBGRAPI.2011.41",
language = "en",
ibi = "8JMKD3MGPBW34M/3A3LQGS",
url = "http://urlib.net/ibi/8JMKD3MGPBW34M/3A3LQGS",
targetfile = "PID1979911.pdf",
urlaccessdate = "2024, Apr. 28"
}