@InProceedings{EscherDrewBem:2021:FaSpTr,
author = "Escher, Rafael Molossi and Drews-Jr, Paulo and Bem, Rodrigo
Andrade de",
affiliation = "{Federal University of Rio Grande } and {Federal University of Rio
Grande } and {Federal University of Rio Grande}",
title = "Fast Spatial-Temporal Transformer Network",
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, Video Inpainting, Reformer Networks, Transformer
Networks.",
abstract = "In computer vision, the restoration of missing regions in an image
can be tackled with image inpainting techniques. Neural networks
that perform inpainting in videos require the extraction of
information from neighboring frames to obtain a temporally
coherent result. The state-of-the-art methods for video inpainting
are mainly based on Transformer Networks, which rely on attention
mechanisms to handle temporal input data. However, such networks
are highly costly, requiring considerable computational power for
training and testing, which hinders its use on modest computing
platforms. In this context, our goal is to reduce the
computational complexity of state-ofthe-art video inpainting
methods, improving performance and facilitating its use in low-end
GPUs. Therefore, we introduce the Fast Spatio-Temporal Transformer
Network (FastSTTN), an extension of the Spatio-Temporal
Transformer Network (STTN) in which the adoption of Reversible
Layers reduces memory usage up to 7 times and execution time by
approximately 2.2 times, while maintaining state-of-the-art video
inpainting accuracy.",
conference-location = "Gramado, RS, Brazil (virtual)",
conference-year = "18-22 Oct. 2021",
doi = "10.1109/SIBGRAPI54419.2021.00018",
url = "http://dx.doi.org/10.1109/SIBGRAPI54419.2021.00018",
language = "en",
ibi = "8JMKD3MGPEW34M/45CUSQ5",
url = "http://urlib.net/ibi/8JMKD3MGPEW34M/45CUSQ5",
targetfile = "FastSTTN___SIBGRAPI_2021.pdf",
urlaccessdate = "2024, May 06"
}