@InProceedings{VieiraOliv:2021:GaEsVi,
author = "Vieira, Gabriel Lefundes and Oliveira, Luciano",
affiliation = "{Federal University of Bahia } and {Federal University of Bahia}",
title = "Gaze estimation via self-attention augmented convolutions",
booktitle = "Proceedings...",
year = "2021",
editor = "Paiva, Afonso and Menotti, David and Baranoski, Gladimir V. G. and
Proen{\c{c}}a, Hugo Pedro and Junior, Antonio Lopes Apolinario
and Papa, Jo{\~a}o Paulo and Pagliosa, Paulo and dos Santos,
Thiago Oliveira and e S{\'a}, Asla Medeiros and da Silveira,
Thiago Lopes Trugillo and Brazil, Emilio Vital and Ponti, Moacir
A. and Fernandes, Leandro A. F. and Avila, Sandra",
organization = "Conference on Graphics, Patterns and Images, 34. (SIBGRAPI)",
publisher = "IEEE Computer Society",
address = "Los Alamitos",
keywords = "deep learning, gaze estimation, attention-augmented
convolutions.",
abstract = "Although recently deep learning methods have boosted the accuracy
of appearance-based gaze estimation, there is still room for
improvement in the network architectures for this particular task.
Hence we propose here a novel network architecture grounded on
self-attention augmented convolutions to improve the quality of
the learned features during the training of a shallower residual
network. The rationale is that self-attention mechanism can help
outperform deeper architectures by learning dependencies between
distant regions in full-face images. This mechanism can also
create better and more spatially-aware feature representations
derived from the face and eye images before gaze regression. We
dubbed our framework ARes-gaze, which explores our
Attention-augmented ResNet (ARes-14) as twin convolutional
backbones. In our experiments, results showed a decrease of the
average angular error by 2.38% when compared to state-of-the-art
methods on the MPIIFaceGaze data set, while achieving a
second-place on the EyeDiap data set. It is noteworthy that our
proposed framework was the only one to reach high accuracy
simultaneously on both data sets.",
conference-location = "Gramado, RS, Brazil (virtual)",
conference-year = "18-22 Oct. 2021",
doi = "10.1109/SIBGRAPI54419.2021.00016",
url = "http://dx.doi.org/10.1109/SIBGRAPI54419.2021.00016",
language = "en",
ibi = "8JMKD3MGPEW34M/45CPHC5",
url = "http://urlib.net/ibi/8JMKD3MGPEW34M/45CPHC5",
targetfile = "gaze_attention_sibgrapi_2021_CAMERA_READY(1).pdf",
urlaccessdate = "2024, May 06"
}