Show simple item record

dc.contributor.authorLe, Nam
dc.contributor.authorBredin, Herve
dc.contributor.authorSergent, Gabriel
dc.contributor.authorIndia Massana, Miquel Àngel
dc.contributor.authorLópez-Otero, Paula
dc.contributor.authorBarras, Claude
dc.contributor.authorGuinaudeau, Camille
dc.contributor.authorGravier, Guillaume
dc.contributor.authorBarbosa da Fonseca, Gabriel
dc.contributor.authorLyon Freire, Izabela
dc.contributor.authorPatrocinio Jr., Zenilton
dc.contributor.authorJamil F. Guimarães, Silvio
dc.contributor.authorMartí Juan, Gerard
dc.contributor.authorMorros Rubió, Josep Ramon
dc.contributor.authorHernando Pericás, Francisco Javier
dc.contributor.authorDocio-Fernández, Laura
dc.contributor.authorGarcía-Mateo, Carmen
dc.contributor.authorMeignier, Sylvain
dc.contributor.authorOdobez, Jean-Marc
dc.contributor.otherUniversitat Politècnica de Catalunya. Departament de Teoria del Senyal i Comunicacions
dc.date.accessioned2017-12-19T11:12:46Z
dc.date.issued2017
dc.identifier.citationLe, N., Bredin, H., Sergent, G., India, M., López-Otero, P., Barras, C., Guinaudeau, C., Gravier, G., Barbosa da Fonseca, G., Lyon Freire, I., Patrocinio Jr., Z., Jamil F. Guimarães, S., Marti, G., Morros, J.R., Hernando, J., Docio-Fernández, L., García-Mateo, C., Meignier, S., Odobez, J. Towards large scale multimedia indexing: a case study on person discovery in broadcast news. A: International Workshop on Content-Based Multimedia Indexing. "Proceedings of the 15th International Workshop on Content-Based Multimedia Indexing, CBMI 2017, Florence, Italy, June 19-21, 2017". Firenze: Association for Computing Machinery (ACM), 2017, p. 1-6.
dc.identifier.isbn978-1-4503-5333-5
dc.identifier.urihttp://hdl.handle.net/2117/112283
dc.description.abstractThe rapid growth of multimedia databases and the human interest in their peers make indices representing the location and identity of people in audio-visual documents essential for searching archives. Person discovery in the absence of prior identity knowledge requires accurate association of audio-visual cues and detected names. To this end, we present 3 different strategies to approach this problem: clustering-based naming, verification-based naming, and graph-based naming. Each of these strategies utilizes different recent advances in unsupervised face / speech representation, verification, and optimization. To have a better understanding of the approaches, this paper also provides a quantitative and qualitative comparative study of these approaches using the associated corpus of the Person Discovery challenge at MediaEval 2016. From the results of our experiments, we can observe the pros and cons of each approach, thus paving the way for future promising research directions.
dc.format.extent6 p.
dc.language.isoeng
dc.publisherAssociation for Computing Machinery (ACM)
dc.subjectÀrees temàtiques de la UPC::Informàtica::Sistemes d'informació::Bases de dades
dc.subjectÀrees temàtiques de la UPC::So, imatge i multimèdia
dc.subject.lcshDatabases
dc.subject.lcshAudio-visual materials
dc.subject.lcshCluster
dc.titleTowards large scale multimedia indexing: a case study on person discovery in broadcast news
dc.typeConference report
dc.subject.lemacBases de dades
dc.subject.lemacAudiovisuals
dc.subject.lemacSistemes productius locals
dc.contributor.groupUniversitat Politècnica de Catalunya. GPI - Grup de Processament d'Imatge i Vídeo
dc.contributor.groupUniversitat Politècnica de Catalunya. VEU - Grup de Tractament de la Parla
dc.identifier.doihttps://doi.org/10.1145/3095713.3095732
dc.description.peerreviewedPeer Reviewed
dc.relation.publisherversionhttps://dl.acm.org/citation.cfm?doid=3095713.3095732
dc.rights.accessRestricted access - publisher's policy
drac.iddocument21669987
dc.description.versionPostprint (published version)
dc.relation.projectidinfo:eu-repo/grantAgreement/EC/FP7/611057/EU/EUMSSI- Event Understanding through Multimodal Social Stream Interpretation/EUMSSI
dc.date.lift10000-01-01
upcommons.citation.authorLe, N., Bredin, H., Sergent, G., India, M., López-Otero, P., Barras, C., Guinaudeau, C., Gravier, G., Barbosa da Fonseca, G., Lyon Freire, I., Patrocinio Jr., Z., Jamil F. Guimarães, S., Marti, G., Morros, J.R., Hernando, J., Docio-Fernández, L., García-Mateo, C., Meignier, S., Odobez, J.
upcommons.citation.contributorInternational Workshop on Content-Based Multimedia Indexing
upcommons.citation.pubplaceFirenze
upcommons.citation.publishedtrue
upcommons.citation.publicationNameProceedings of the 15th International Workshop on Content-Based Multimedia Indexing, CBMI 2017, Florence, Italy, June 19-21, 2017
upcommons.citation.startingPage1
upcommons.citation.endingPage6


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

All rights reserved. This work is protected by the corresponding intellectual and industrial property rights. Without prejudice to any existing legal exemptions, reproduction, distribution, public communication or transformation of this work are prohibited without permission of the copyright holder