Afficher la notice abrégée

A hybrid transformer with domain adaptation using interpretability techniques for the application to the detection of risk situations

dc.rights.licenseopenen_US
hal.structure.identifierLaboratoire Bordelais de Recherche en Informatique [LaBRI]
dc.contributor.authorMALLICK, Rupayan
hal.structure.identifierLaboratoire Bordelais de Recherche en Informatique [LaBRI]
dc.contributor.authorBENOIS PINEAU, Jenny
IDREF: 074466992
hal.structure.identifierLaboratoire Bordelais de Recherche en Informatique [LaBRI]
dc.contributor.authorZEMMARI, Akka
IDREF: 157264491
dc.contributor.authorGUERDA, Kamel
hal.structure.identifierLaboratoire Bordelais de Recherche en Informatique [LaBRI]
dc.contributor.authorMANSENCAL, Boris
hal.structure.identifierBordeaux population health [BPH]
dc.contributor.authorAMIEVA, Helene
dc.contributor.authorMIDDLETON, Laura
dc.date.accessioned2024-06-21T09:44:11Z
dc.date.available2024-06-21T09:44:11Z
dc.date.issued2024-03-11
dc.identifier.issn1573-7721en_US
dc.identifier.urihttps://oskar-bordeaux.fr/handle/20.500.12278/200607
dc.description.abstractEnMultimedia approaches are strongly required in multi-modal data processing for the detection and recognition of specific events in the data. Hybrid architectures with time series and image/video inputs in the framework of twin CNNs have shown increased performances compared to mono-modal approaches. Pre-trained models have been used in transfer learning to fine-tune the last few layers in the network. This often leads to distribution shifts in the domain. In a real-world scenario, the distribution shifts between the source and target domains can yield poor classification results. With interpretable techniques used in deep neural networks, important features can be highlighted not only for trained models but also reinforced in the training process. Hence the initialization of the target domain model can be performed with improved weights. During data transfer between datasets, the dimensions of the data are also different. We propose a method for model transfer with the adaptation of data dimension and improved initialization with interpretability approaches.
dc.language.isoENen_US
dc.title.enA hybrid transformer with domain adaptation using interpretability techniques for the application to the detection of risk situations
dc.title.alternativeMultimedia Tools and Applicationsen_US
dc.typeArticle de revueen_US
dc.identifier.doi10.1007/s11042-024-18687-xen_US
dc.subject.halSciences du Vivant [q-bio]/Santé publique et épidémiologieen_US
bordeaux.journalMultimedia Tools and Applicationsen_US
bordeaux.hal.laboratoriesBordeaux Population Health Research Center (BPH) - UMR 1219en_US
bordeaux.institutionUniversité de Bordeauxen_US
bordeaux.institutionINSERMen_US
bordeaux.institutionBordeaux INP
bordeaux.institutionCNRS
bordeaux.teamACTIVE_BPHen_US
bordeaux.peerReviewedouien_US
bordeaux.inpressnonen_US
hal.popularnonen_US
hal.audienceInternationaleen_US
hal.exportfalse
dc.rights.ccPas de Licence CCen_US
bordeaux.COinSctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.jtitle=Multimedia%20Tools%20and%20Applications&rft.date=2024-03-11&rft.eissn=1573-7721&rft.issn=1573-7721&rft.au=MALLICK,%20Rupayan&BENOIS%20PINEAU,%20Jenny&ZEMMARI,%20Akka&GUERDA,%20Kamel&MANSENCAL,%20Boris&rft.genre=article


Fichier(s) constituant ce document

FichiersTailleFormatVue

Il n'y a pas de fichiers associés à ce document.

Ce document figure dans la(les) collection(s) suivante(s)

Afficher la notice abrégée