Matches in SemOpenAlex for { <https://semopenalex.org/work/W2078115833> ?p ?o ?g. }
Showing items 1 to 53 of
53
with 100 items per page.
- W2078115833 abstract "Image annotation has been widely investigated to discover the semantics of an image. However, most of the existing algorithms focus on noun tags (e.g. concepts and objects). Since an image is a snapshot of the real world event, annotating images with verbs will enable richer understanding of an image. In this paper, we propose a data-driven approach to verb oriented image annotation. At first, we obtain verb candidates by generating search queries for a given image with initial noun tags and establishing a sentence corpus from those queries. We utilize visualness to filter tags which are not visually presentable (e.g. pain) and differentiate tags into two categories (i.e. scene based and object based) to impose linguistic rules in verb extraction. Then we further re-rank the candidate verbs with the tag context discovered from the images which are both semantically and visually similar to the given image in the MIRFlickr dataset. Our experimental results from user study demonstrate that our proposed approach is promising." @default.
- W2078115833 created "2016-06-24" @default.
- W2078115833 creator A5022985434 @default.
- W2078115833 creator A5078315542 @default.
- W2078115833 creator A5080318646 @default.
- W2078115833 creator A5081130490 @default.
- W2078115833 date "2012-10-29" @default.
- W2078115833 modified "2023-10-16" @default.
- W2078115833 title "What is happening" @default.
- W2078115833 cites W1983705368 @default.
- W2078115833 cites W2042178278 @default.
- W2078115833 cites W2134930802 @default.
- W2078115833 cites W2137251014 @default.
- W2078115833 cites W2172231696 @default.
- W2078115833 cites W2497237364 @default.
- W2078115833 doi "https://doi.org/10.1145/2393347.2396387" @default.
- W2078115833 hasPublicationYear "2012" @default.
- W2078115833 type Work @default.
- W2078115833 sameAs 2078115833 @default.
- W2078115833 citedByCount "1" @default.
- W2078115833 countsByYear W20781158332016 @default.
- W2078115833 crossrefType "proceedings-article" @default.
- W2078115833 hasAuthorship W2078115833A5022985434 @default.
- W2078115833 hasAuthorship W2078115833A5078315542 @default.
- W2078115833 hasAuthorship W2078115833A5080318646 @default.
- W2078115833 hasAuthorship W2078115833A5081130490 @default.
- W2078115833 hasConcept C2779527642 @default.
- W2078115833 hasConcept C41008148 @default.
- W2078115833 hasConcept C52119013 @default.
- W2078115833 hasConcept C554144382 @default.
- W2078115833 hasConcept C95457728 @default.
- W2078115833 hasConceptScore W2078115833C2779527642 @default.
- W2078115833 hasConceptScore W2078115833C41008148 @default.
- W2078115833 hasConceptScore W2078115833C52119013 @default.
- W2078115833 hasConceptScore W2078115833C554144382 @default.
- W2078115833 hasConceptScore W2078115833C95457728 @default.
- W2078115833 hasLocation W20781158331 @default.
- W2078115833 hasOpenAccess W2078115833 @default.
- W2078115833 hasPrimaryLocation W20781158331 @default.
- W2078115833 hasRelatedWork W2240749523 @default.
- W2078115833 hasRelatedWork W2281462793 @default.
- W2078115833 hasRelatedWork W2284511461 @default.
- W2078115833 hasRelatedWork W2368538948 @default.
- W2078115833 hasRelatedWork W2414401146 @default.
- W2078115833 hasRelatedWork W2748952813 @default.
- W2078115833 hasRelatedWork W2790008319 @default.
- W2078115833 hasRelatedWork W2899084033 @default.
- W2078115833 hasRelatedWork W4234792686 @default.
- W2078115833 hasRelatedWork W574712782 @default.
- W2078115833 isParatext "false" @default.
- W2078115833 isRetracted "false" @default.
- W2078115833 magId "2078115833" @default.
- W2078115833 workType "article" @default.