Conference paper Open Access

Global Flow and Temporal-shape Descriptors for Human Action Recognition from 3D Reconstruction Data

Papadopoulos, Georgios Th.; Daras, Petros


MARC21 XML Export

<?xml version='1.0' encoding='UTF-8'?>
<record xmlns="http://www.loc.gov/MARC21/slim">
  <leader>00000nam##2200000uu#4500</leader>
  <datafield tag="041" ind1=" " ind2=" ">
    <subfield code="a">eng</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">Action recognition</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">3D reconstruction</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">3D  flow</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">3D shape</subfield>
  </datafield>
  <controlfield tag="005">20200120174601.0</controlfield>
  <controlfield tag="001">1087115</controlfield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Centre for Research and Technology Hellas</subfield>
    <subfield code="a">Daras, Petros</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">1093926</subfield>
    <subfield code="z">md5:d276f6e3b8dbbc96c2449fed850dfd99</subfield>
    <subfield code="u">https://zenodo.org/record/1087115/files/mldm-camera-ready.pdf</subfield>
  </datafield>
  <datafield tag="542" ind1=" " ind2=" ">
    <subfield code="l">open</subfield>
  </datafield>
  <datafield tag="260" ind1=" " ind2=" ">
    <subfield code="c">2017-07-15</subfield>
  </datafield>
  <datafield tag="909" ind1="C" ind2="O">
    <subfield code="p">openaire</subfield>
    <subfield code="o">oai:zenodo.org:1087115</subfield>
  </datafield>
  <datafield tag="100" ind1=" " ind2=" ">
    <subfield code="u">Centre for Research and Technology Hellas</subfield>
    <subfield code="a">Papadopoulos, Georgios Th.</subfield>
  </datafield>
  <datafield tag="245" ind1=" " ind2=" ">
    <subfield code="a">Global Flow and Temporal-shape Descriptors for Human Action Recognition from 3D Reconstruction Data</subfield>
  </datafield>
  <datafield tag="536" ind1=" " ind2=" ">
    <subfield code="c">700367</subfield>
    <subfield code="a">Detecting and ANalysing TErrorist-related online contents and financing activities</subfield>
  </datafield>
  <datafield tag="540" ind1=" " ind2=" ">
    <subfield code="u">https://creativecommons.org/licenses/by/4.0/legalcode</subfield>
    <subfield code="a">Creative Commons Attribution 4.0 International</subfield>
  </datafield>
  <datafield tag="650" ind1="1" ind2="7">
    <subfield code="a">cc-by</subfield>
    <subfield code="2">opendefinition.org</subfield>
  </datafield>
  <datafield tag="520" ind1=" " ind2=" ">
    <subfield code="a">&lt;p&gt;In this paper, global-level view-invariant descriptors for human action recognition using 3D reconstruction data are proposed. 3D reconstruction techniques are employed for addressing two of the most challenging issues related to human action recognition in the general case, namely view-variance and the presence of (self-) occlusions. Initially, a set of calibrated Kinect sensors are employed for producing a 3D reconstruction of the performing subjects. Subsequently, a 3D flow field is estimated for every captured frame. For performing action recognition, a novel global 3D flow descriptor is introduced, which achieves to efficiently encode the global motion characteristics in a compact way, while also incorporating spatial distribution related information. Additionally, a new global temporal-shape descriptor that extends the notion of 3D shape descriptions for action recognition, by including temporal information, is also proposed. The latter descriptor efficiently addresses the inherent problems of temporal alignment and compact representation, while also being robust in the presence of noise. Experimental results using public datasets demonstrate the efficiency of the proposed approach.&lt;/p&gt;</subfield>
  </datafield>
  <datafield tag="773" ind1=" " ind2=" ">
    <subfield code="n">doi</subfield>
    <subfield code="i">isVersionOf</subfield>
    <subfield code="a">10.5281/zenodo.1087114</subfield>
  </datafield>
  <datafield tag="024" ind1=" " ind2=" ">
    <subfield code="a">10.5281/zenodo.1087115</subfield>
    <subfield code="2">doi</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">publication</subfield>
    <subfield code="b">conferencepaper</subfield>
  </datafield>
</record>
99
49
views
downloads
All versions This version
Views 9999
Downloads 4949
Data volume 53.6 MB53.6 MB
Unique views 9797
Unique downloads 4848

Share

Cite as