Show simple item record

dc.contributor.author Silberer, Carina
dc.contributor.author Pinkal, Manfred
dc.date.accessioned 2018-12-18T12:21:17Z
dc.date.available 2018-12-18T12:21:17Z
dc.date.issued 2018
dc.identifier.citation Silberer C, Pinkal M. Grounding semantic roles in images. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing; 2018 Oct 31 - Nov 4; Brussels, Belgium. Stroudsburg (PA): Association for Computational Linguistics; 2018. p. 2616–26.
dc.identifier.uri http://hdl.handle.net/10230/36137
dc.description Comunicació presentada a la 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP 2018), celebrada del 31 d'octubre al 4 de novembre de 2018 a Brussel·les, Bèlgica.
dc.description.abstract We address the task of visual semantic role labeling (vSRL), the identification of the participants of a situation or event in a visual scene, and their labeling with their semantic relations to the event or situation. We render candidate participants as image regions of objects, and train a model which learns to ground roles in the regions which depict the corresponding participant. Experimental results demonstrate that we can train a vSRL model without reliance on prohibitive image-based role annotations, by utilizing noisy data which we extract automatically from image captions using a linguistic SRL system. Furthermore, our model induces frame–semantic visual representations, and their comparison to previous work on supervised visual verb sense disambiguation yields overall better results.
dc.description.sponsorship We thank the anonymous reviewers, Leonie Harter, Christine Sch¨afer, Michael Roth, Gemma Boleda, Anna Rohrbach and Bernt Schiele. This research was supported by the German Research Foundation (DFG EXC 285), by the European Research Council (ERC Horizon 2020 grant agreement No 715154), and the Spanish Ramon y Cajal programme (grant RYC-2015-18907).
dc.format.mimetype application/pdf
dc.language.iso eng
dc.publisher ACL (Association for Computational Linguistics)
dc.relation.ispartof Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing; 2018 Oct 31 - Nov 4; Brussels, Belgium. Stroudsburg (PA): Association for Computational Linguistics; 2018. p. 2616–26.
dc.rights © ACL, Creative Commons Attribution 4.0 License
dc.rights.uri http://creativecommons.org/licenses/by/4.0/
dc.title Grounding semantic roles in images
dc.type info:eu-repo/semantics/conferenceObject
dc.relation.projectID info:eu-repo/grantAgreement/EC/H2020/715154
dc.rights.accessRights info:eu-repo/semantics/openAccess
dc.type.version info:eu-repo/semantics/publishedVersion

Thumbnail

This item appears in the following Collection(s)

Show simple item record

Search DSpace


Advanced Search

Browse

My Account

Statistics

In collaboration with Compliant to Partaking