Show simple item record

dc.contributor.authorDey, S
dc.contributor.authorDutta, A
dc.contributor.authorGhosh, SK
dc.contributor.authorValveny, E
dc.contributor.authorLlados, J
dc.contributor.authorPal, U
dc.date.accessioned2019-10-16T12:18:23Z
dc.date.issued2018-11-29
dc.description.abstractIn this work we introduce a cross modal image retrieval system that allows both text and sketch as input modalities for the query. A cross-modal deep network architecture is formulated to jointly model the sketch and text input modalities as well as the the image output modality, learning a common embedding between text and images and between sketches and images. In addition, an attention model is used to selectively focus the attention on the different objects of the image, allowing for retrieval with multiple objects in the query. Experiments show that the proposed method performs the best in both single and multiple object image retrieval in standard datasets.en_GB
dc.description.sponsorshipEuropean Union Horizon 2020en_GB
dc.description.sponsorshipCERCA Programme/Generalitat de Catalunyaen_GB
dc.identifier.citation2018 24th International Conference on Pattern Recognition (ICPR), 20-24 August 2019, Beijing, China, pp. 916 - 921en_GB
dc.identifier.doi10.1109/ICPR.2018.8545452
dc.identifier.grantnumber665919en_GB
dc.identifier.grantnumberTIN2015-70924-C2-2-Ren_GB
dc.identifier.grantnumberTIN2014-52072-Pen_GB
dc.identifier.urihttp://hdl.handle.net/10871/39235
dc.language.isoenen_GB
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)en_GB
dc.rights© 2018 IEEEen_GB
dc.titleLearning Cross-Modal Deep Embeddings for Multi-Object Image Retrieval using Text and Sketchen_GB
dc.typeConference paperen_GB
dc.date.available2019-10-16T12:18:23Z
dc.identifier.issn1051-4651
dc.descriptionThis is the author accepted manuscript. The final version is available from IEEE via the DOI in this recorden_GB
dc.rights.urihttp://www.rioxx.net/licenses/all-rights-reserveden_GB
dcterms.dateAccepted2018-04-05
rioxxterms.versionAMen_GB
rioxxterms.licenseref.startdate2018-11-29
rioxxterms.typeConference Paper/Proceeding/Abstracten_GB
refterms.dateFCD2019-10-16T12:15:44Z
refterms.versionFCDAM
refterms.dateFOA2019-10-16T12:18:27Z
refterms.panelBen_GB


Files in this item

This item appears in the following Collection(s)

Show simple item record