Show simple item record

dc.contributor.authorHernández Ruiz, Alejandro José
dc.contributor.authorPorzi, Lorenzo
dc.contributor.authorRota Bulò, Samuel
dc.contributor.authorMoreno-Noguer, Francesc
dc.contributor.otherInstitut de Robòtica i Informàtica Industrial
dc.date.accessioned2018-02-20T21:36:42Z
dc.date.available2018-02-20T21:36:42Z
dc.date.issued2017
dc.identifier.citationHernandez, A., Porzi, L., Rota, S., Moreno-Noguer, F. 3D CNNs on distance matrices for human action recognition. A: ACM Conference on Multimedia Conference. "Proceedings of the 25th ACM Conference on Multimedia". Mountain view: 2017, p. 1087-1095.
dc.identifier.urihttp://hdl.handle.net/2117/114317
dc.description.abstractIn this paper we are interested in recognizing human actions from sequences of 3D skeleton data. For this purpose we combine a 3D Convolutional Neural Network with body representations based on Euclidean Distance Matrices (EDMs), which have been recently shown to be very effective to capture the geometric structure of the human pose. One inherent limitation of the EDMs, however, is that they are defined up to a permutation of the skeleton joints, i.e., randomly shuffling the ordering of the joints yields many different representations. In oder to address this issue we introduce a novel architecture that simultaneously, and in an end-to-end manner, learns an optimal transformation of the joints, while optimizing the rest of parameters of the convolutional network. The proposed approach achieves state-of-the-art results on 3 benchmarks, including the recent NTU RGB-D dataset, for which we improve on previous LSTM-based methods by more than 10 percentage points, also surpassing other CNN-based methods while using almost 1000 times fewer parameters.
dc.format.extent9 p.
dc.language.isoeng
dc.rightsAttribution-NonCommercial-NoDerivs 3.0 Spain
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/3.0/es/
dc.subjectÀrees temàtiques de la UPC::Informàtica::Automàtica i control
dc.subject.otherpattern recognition
dc.subject.other3d convolutional neural networks
dc.subject.otheractivity recognition
dc.subject.otherdeep learning
dc.subject.otherhuman action recognition
dc.title3D CNNs on distance matrices for human action recognition
dc.typeConference report
dc.contributor.groupUniversitat Politècnica de Catalunya. ROBiri - Grup de Robòtica de l'IRI
dc.identifier.doi10.1145/3123266.3123299
dc.description.peerreviewedPeer Reviewed
dc.subject.inspecClassificació INSPEC::Pattern recognition
dc.relation.publisherversionhttps://dl.acm.org/citation.cfm?doid=3123266.3123299
dc.rights.accessOpen Access
local.identifier.drac21977149
dc.description.versionPostprint (author's final draft)
dc.relation.projectidinfo:eu-repo/grantAgreement/MINECO/PE2017-2021/MDM-2016-0600
local.citation.authorHernandez, A.; Porzi, L.; Rota, S.; Moreno-Noguer, F.
local.citation.contributorACM Conference on Multimedia Conference
local.citation.pubplaceMountain view
local.citation.publicationNameProceedings of the 25th ACM Conference on Multimedia
local.citation.startingPage1087
local.citation.endingPage1095


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

Attribution-NonCommercial-NoDerivs 3.0 Spain
Except where otherwise noted, content on this work is licensed under a Creative Commons license : Attribution-NonCommercial-NoDerivs 3.0 Spain