Scipediacontent: Scipediacontent moved page Draft Content 676343935 to Souza et al 2016a

2020-10-14T12:32:20Z

Scipediacontent moved page Draft Content 676343935 to Souza et al 2016a

Scipediacontent: Created page with " == 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 l..."

2020-10-14T12:32:17Z

Created page with " == 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 l..."

New page

== 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 Deep learning, although a breakthrough for image classification and showing promise for videos, has still not clearly superseded action recognition methods using hand-crafted features, even when training on massive datasets.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.

Document type: Part of book or chapter of book

== Full document ==
<pdf>Media:Draft_Content_676343935-beopen566-7973-document.pdf</pdf>

== Original document ==

The different versions of the original document can be found in:

* [http://arxiv.org/abs/1608.07138 http://arxiv.org/abs/1608.07138]

* [https://elib.dlr.de/107744/1/deSouza_Sympathy_for_the_details_ECCV_2016_paper.pdf https://elib.dlr.de/107744/1/deSouza_Sympathy_for_the_details_ECCV_2016_paper.pdf]

← Older revision	Revision as of 12:32, 14 October 2020
(No difference)

Souza et al 2016a - Revision history

Scipediacontent: Scipediacontent moved page Draft Content 676343935 to Souza et al 2016a

Scipediacontent: Created page with " == 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 l..."