1 Ocak 2021 Dergi makalesi Açık Erişim

Tanisik, Gokhan; Zalluhoglu, Cemil; Ikizler-Cinbis, Nazli

DataCite XML

<?xml version='1.0' encoding='utf-8'?>
<resource xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="http://datacite.org/schema/kernel-4" xsi:schemaLocation="http://datacite.org/schema/kernel-4 http://schema.datacite.org/meta/kernel-4.1/metadata.xsd">
  <identifier identifierType="URL">https://aperta.ulakbim.gov.tr/record/236236</identifier>
  <creators>
    <creator>
      <creatorName>Tanisik, Gokhan</creatorName>
      <givenName>Gokhan</givenName>
      <familyName>Tanisik</familyName>
      <affiliation>Hacettepe Univ, Dept Comp Engn, Ankara, Turkey</affiliation>
    </creator>
    <creator>
      <creatorName>Zalluhoglu, Cemil</creatorName>
      <givenName>Cemil</givenName>
      <familyName>Zalluhoglu</familyName>
      <affiliation>Hacettepe Univ, Dept Comp Engn, Ankara, Turkey</affiliation>
    </creator>
    <creator>
      <creatorName>Ikizler-Cinbis, Nazli</creatorName>
      <givenName>Nazli</givenName>
      <familyName>Ikizler-Cinbis</familyName>
      <affiliation>Hacettepe Univ, Dept Comp Engn, Ankara, Turkey</affiliation>
    </creator>
  </creators>
  <titles>
    <title>Multi-Stream Pose Convolutional Neural Networks For Human Interaction Recognition In Images</title>
  </titles>
  <publisher>Aperta</publisher>
  <publicationYear>2021</publicationYear>
  <dates>
    <date dateType="Issued">2021-01-01</date>
  </dates>
  <resourceType resourceTypeGeneral="Text">Journal article</resourceType>
  <alternateIdentifiers>
    <alternateIdentifier alternateIdentifierType="url">https://aperta.ulakbim.gov.tr/record/236236</alternateIdentifier>
  </alternateIdentifiers>
  <relatedIdentifiers>
    <relatedIdentifier relatedIdentifierType="DOI" relationType="IsIdenticalTo">10.1016/j.image.2021.116265</relatedIdentifier>
  </relatedIdentifiers>
  <rightsList>
    <rights rightsURI="http://www.opendefinition.org/licenses/cc-by">Creative Commons Attribution</rights>
    <rights rightsURI="info:eu-repo/semantics/openAccess">Open Access</rights>
  </rightsList>
  <descriptions>
    <description descriptionType="Abstract">Recognizing human interactions in still images is quite a challenging task since compared to videos, there is only a glimpse of interaction in a single image. This work investigates the role of human poses in recognizing human-human interactions in still images. To this end, a multi-stream convolutional neural network architecture is proposed, which fuses different levels of human pose information to recognize human interactions better. In this context, several pose-based representations are explored. Experimental evaluations in an extended benchmark dataset show that the proposed multi-stream pose Convolutional Neural Network is successful in discriminating a wide range of human-human interactions and human poses when used in conjunction with the overall context provides discriminative cues about human-human interactions.</description>
  </descriptions>
</resource>