Conference paper Open Access

# Near-Duplicate Video Retrieval with Deep Metric Learning

Kordopatis-Zilos, Giorgos; Papadopoulos, Symeon; Patras, Ioannis; Kompatsiaris, Yiannis

### DataCite XML Export

<?xml version='1.0' encoding='utf-8'?>
<identifier identifierType="DOI">10.5281/zenodo.852351</identifier>
<creators>
<creator>
<creatorName>Kordopatis-Zilos, Giorgos</creatorName>
<givenName>Giorgos</givenName>
<familyName>Kordopatis-Zilos</familyName>
<affiliation>CERTH-ITI</affiliation>
</creator>
<creator>
<givenName>Symeon</givenName>
<affiliation>CERTH-ITI</affiliation>
</creator>
<creator>
<creatorName>Patras, Ioannis</creatorName>
<givenName>Ioannis</givenName>
<familyName>Patras</familyName>
<affiliation>CERTH-ITI</affiliation>
</creator>
<creator>
<creatorName>Kompatsiaris, Yiannis</creatorName>
<givenName>Yiannis</givenName>
<familyName>Kompatsiaris</familyName>
<affiliation>CERTH-ITI</affiliation>
</creator>
</creators>
<titles>
<title>Near-Duplicate Video Retrieval with Deep Metric Learning</title>
</titles>
<publisher>Zenodo</publisher>
<publicationYear>2017</publicationYear>
<subjects>
<subject>Near-Duplicate</subject>
<subject>Video Retrieval</subject>
<subject>Deep Metric Learning</subject>
</subjects>
<dates>
<date dateType="Issued">2017-10-23</date>
</dates>
<resourceType resourceTypeGeneral="Text">Conference paper</resourceType>
<alternateIdentifiers>
<alternateIdentifier alternateIdentifierType="url">https://zenodo.org/record/852351</alternateIdentifier>
</alternateIdentifiers>
<relatedIdentifiers>
<relatedIdentifier relatedIdentifierType="DOI" relationType="IsVersionOf">10.5281/zenodo.852350</relatedIdentifier>
<relatedIdentifier relatedIdentifierType="URL" relationType="IsPartOf">https://zenodo.org/communities/invid-h2020</relatedIdentifier>
</relatedIdentifiers>
<rightsList>
<rights rightsURI="info:eu-repo/semantics/openAccess">Open Access</rights>
</rightsList>
<descriptions>
<description descriptionType="Abstract">&lt;p&gt;This work addresses the problem of Near-Duplicate Video Retrieval (NDVR). We propose an effective video-level NDVR scheme based on deep metric learning that leverages Convolutional Neural Network (CNN) features from intermediate layers to generate discriminative global video representations in tandem with a Deep Metric Learning (DML) framework with two fusion variations, trained to approximate an embedding function for accurate distance calculation between two near-duplicate videos. In contrast to most state-of-the-art methods, which exploit information deriving from the same source of data for both development and evaluation (which usually results to dataset-specific solutions), the proposed model is fed during training with sampled triplets generated from an independent dataset and is thoroughly tested on the widely used CC WEB VIDEO dataset, using two popular deep CNN architectures (AlexNet, GoogleNet). We demonstrate that the proposed approach achieves outstanding performance against the state-of-the-art, either with or without access to the evaluation dataset.&lt;/p&gt;</description>
</descriptions>
<fundingReferences>
<fundingReference>
<funderName>European Commission</funderName>
<funderIdentifier funderIdentifierType="Crossref Funder ID">10.13039/501100000780</funderIdentifier>
<awardNumber awardURI="info:eu-repo/grantAgreement/EC/H2020/687786/">687786</awardNumber>
<awardTitle>In Video Veritas – Verification of Social Media Video Content for the News Industry</awardTitle>
</fundingReference>
</fundingReferences>
</resource>

145
105
views