@InProceedings{CesardeSouza2016,
author="Cesar de Souza
and Adrien Gaidon
and Eleonora Vig
and Antonio Lopez",
title="Sympathy for the Details: Dense Trajectories and Hybrid Classification Architectures for Action Recognition",
booktitle="14th European Conference on Computer Vision",
year="2016",
pages="697--716",
abstract="Action recognition in videos is a challenging task due to the complexity of the spatio-temporal patterns to model and the difficulty to acquire and learn on large quantities of video data. Deep learning, although a breakthrough for image classification and showing promise for videos, has still not clearly superseded action recognition methods using hand-crafted features, even when training on massive datasets. In this paper, we introduce hybrid video classification architectures based on carefully designed unsupervised representations of hand-crafted spatio-temporal features classified by supervised deep networks. As we show in our experiments on five popular benchmarks for action recognition, our hybrid model combines the best of both worlds: it is data efficient (trained on 150 to 10000 short clips) and yet improves significantly on the state of the art, including recent deep models trained on millions of manually labelled images and videos.",
optnote="ADAS; 600.076; 600.085",
optnote="exported from refbase (http://refbase.cvc.uab.es/show.php?record=2824), last updated on Thu, 20 Jan 2022 11:30:22 +0100",
doi="10.1007/978-3-319-46478-7_43",
file=":http://refbase.cvc.uab.es/files/SGV2016.pdf:PDF"
}