@inproceedings{fbb97f67b9024fd094de8d7ccbc105ed,
title = "A piggyback representation for action recognition",
abstract = "In video understanding, the spatial patterns formed by local space-time interest points hold discriminative information. We encode these spatial regularities using a word2vec neural network, a recently proposed tool in the field of text processing. Then, building upon recent accumulator based image representation solutions, input videos are represented in a hybrid manner: the appearance of local space time interest points is used to collect and associate the learned descriptors, which capture the spatial patterns. Promising results are shown on recent action recognition benchmarks, using well established methods as the underlying appearance descriptors.",
author = "Lior Wolf and Yair Hanani and Tal Hassner",
note = "Publisher Copyright: {\textcopyright} 2014 IEEE.; 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2014 ; Conference date: 23-06-2014 Through 28-06-2014",
year = "2014",
month = sep,
day = "24",
doi = "10.1109/CVPRW.2014.81",
language = "الإنجليزيّة",
series = "IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops",
publisher = "IEEE Computer Society",
pages = "520--525",
booktitle = "Proceedings - 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2014",
address = "الولايات المتّحدة",
}