dc.contributor.author | Dey, S | |
dc.contributor.author | Dutta, A | |
dc.contributor.author | Ghosh, SK | |
dc.contributor.author | Valveny, E | |
dc.contributor.author | Llados, J | |
dc.contributor.author | Pal, U | |
dc.date.accessioned | 2019-10-16T12:18:23Z | |
dc.date.issued | 2018-11-29 | |
dc.description.abstract | In 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.sponsorship | European Union Horizon 2020 | en_GB |
dc.description.sponsorship | CERCA Programme/Generalitat de Catalunya | en_GB |
dc.identifier.citation | 2018 24th International Conference on Pattern Recognition (ICPR), 20-24 August 2019, Beijing, China, pp. 916 - 921 | en_GB |
dc.identifier.doi | 10.1109/ICPR.2018.8545452 | |
dc.identifier.grantnumber | 665919 | en_GB |
dc.identifier.grantnumber | TIN2015-70924-C2-2-R | en_GB |
dc.identifier.grantnumber | TIN2014-52072-P | en_GB |
dc.identifier.uri | http://hdl.handle.net/10871/39235 | |
dc.language.iso | en | en_GB |
dc.publisher | Institute of Electrical and Electronics Engineers (IEEE) | en_GB |
dc.rights | © 2018 IEEE | en_GB |
dc.title | Learning Cross-Modal Deep Embeddings for Multi-Object Image Retrieval using Text and Sketch | en_GB |
dc.type | Conference paper | en_GB |
dc.date.available | 2019-10-16T12:18:23Z | |
dc.identifier.issn | 1051-4651 | |
dc.description | This is the author accepted manuscript. The final version is available from IEEE via the DOI in this record | en_GB |
dc.rights.uri | http://www.rioxx.net/licenses/all-rights-reserved | en_GB |
dcterms.dateAccepted | 2018-04-05 | |
rioxxterms.version | AM | en_GB |
rioxxterms.licenseref.startdate | 2018-11-29 | |
rioxxterms.type | Conference Paper/Proceeding/Abstract | en_GB |
refterms.dateFCD | 2019-10-16T12:15:44Z | |
refterms.versionFCD | AM | |
refterms.dateFOA | 2019-10-16T12:18:27Z | |
refterms.panel | B | en_GB |