Ir al contenido (pulsa Retorno)

Universitat Politècnica de Catalunya

    • Català
    • Castellano
    • English
    • LoginRegisterLog in (no UPC users)
  • mailContact Us
  • world English 
    • Català
    • Castellano
    • English
  • userLogin   
      LoginRegisterLog in (no UPC users)

UPCommons. Global access to UPC knowledge

Banner header
69.058 UPC E-Prints
You are here:
View Item 
  •   DSpace Home
  • E-prints
  • Instituts de recerca
  • IRI - Institut de Robòtica i Informàtica Industrial, CSIC-UPC
  • Ponències/Comunicacions de congressos
  • View Item
  •   DSpace Home
  • E-prints
  • Instituts de recerca
  • IRI - Institut de Robòtica i Informàtica Industrial, CSIC-UPC
  • Ponències/Comunicacions de congressos
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

3D CNNs on distance matrices for human action recognition

Thumbnail
View/Open
1954-3D-CNNs-on-distance-matrices-for-human-action-recognition.pdf (1,660Mb)
 
10.1145/3123266.3123299
 
  View UPCommons Usage Statistics
  LA Referencia / Recolecta stats
Includes usage data since 2022
Cita com:
hdl:2117/114317

Show full item record
Hernández Ruiz, Alejandro José
Porzi, Lorenzo
Rota Bulò, Samuel
Moreno-Noguer, FrancescMés informació
Document typeConference report
Defense date2017
Rights accessOpen Access
Attribution-NonCommercial-NoDerivs 3.0 Spain
This work is protected by the corresponding intellectual and industrial property rights. Except where otherwise noted, its contents are licensed under a Creative Commons license : Attribution-NonCommercial-NoDerivs 3.0 Spain
Abstract
In 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.
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. 
URIhttp://hdl.handle.net/2117/114317
DOI10.1145/3123266.3123299
Publisher versionhttps://dl.acm.org/citation.cfm?doid=3123266.3123299
Collections
  • IRI - Institut de Robòtica i Informàtica Industrial, CSIC-UPC - Ponències/Comunicacions de congressos [609]
  • ROBiri - Grup de Percepció i Manipulació Robotitzada de l'IRI - Ponències/Comunicacions de congressos [283]
  View UPCommons Usage Statistics

Show full item record

FilesDescriptionSizeFormatView
1954-3D-CNNs-on ... man-action-recognition.pdf1,660MbPDFView/Open

Browse

This CollectionBy Issue DateAuthorsOther contributionsTitlesSubjectsThis repositoryCommunities & CollectionsBy Issue DateAuthorsOther contributionsTitlesSubjects

© UPC Obrir en finestra nova . Servei de Biblioteques, Publicacions i Arxius

info.biblioteques@upc.edu

  • About This Repository
  • Metadata under:Metadata under CC0
  • Contact Us
  • Send Feedback
  • Privacy Settings
  • Inici de la pàgina