Show simple item record

dc.contributor.authorStroud, Jonathan C.
dc.contributor.authorMcCaffrey, Ryan
dc.contributor.authorMihalcea, Rada
dc.contributor.authorDeng, Jia
dc.contributor.authorRussakovsky, Olga
dc.date.accessioned2019-12-22T11:57:02Z
dc.date.available2019-12-22T11:57:02Z
dc.date.issued2019-12-04
dc.identifier.urihttp://hdl.handle.net/10754/660726
dc.description.abstractTemporal grounding entails establishing a correspondence between natural language event descriptions and their visual depictions. Compositional modeling becomes central: we first ground atomic descriptions
dc.description.sponsorshipThis work is partially supported by King Abdullah University of Science and Technology (KAUST) Office of Sponsored Research (OSR) under Award No. OSRCRG2017-3405, and by the Toyota Research Institute (TRI).
dc.publisherarXiv
dc.relation.urlhttps://arxiv.org/pdf/1912.02256
dc.rightsArchived with thanks to arXiv
dc.titleCompositional Temporal Visual Grounding of Natural Language Event Descriptions
dc.typePreprint
dc.eprint.versionPre-print
dc.contributor.institutionUniversity of Michigan
dc.contributor.institutionPrinceton University
dc.identifier.arxivid1912.02256
kaust.grant.numberCRG2017
refterms.dateFOA2019-12-22T11:57:51Z
kaust.acknowledged.supportUnitOffice of Sponsored Research (OSR)


Files in this item

Thumbnail
Name:
Preprintfile1.pdf
Size:
10.24Mb
Format:
PDF
Description:
Pre-print

This item appears in the following Collection(s)

Show simple item record