Matches in SemOpenAlex for { <https://semopenalex.org/work/W2896731359> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W2896731359 endingPage "1850" @default.
- W2896731359 startingPage "1850" @default.
- W2896731359 abstract "Image caption generation is attractive research which focuses on generating natural language sentences to describe the visual content of a given image. It is an interdisciplinary subject combining computer vision (CV) and natural language processing (NLP). The existing image captioning methods are mainly focused on generating the final image caption directly, which may lose significant identification information of objects contained in the raw image. Therefore, we propose a new middle-level attribute-based language retouching (MLALR) method to solve this problem. Our proposed MLALR method uses the middle-level attributes predicted from the object regions to retouch the intermediate image description, which is generated by our language generation model. The advantage of our MLALR method is that it can correct descriptive errors in the intermediate image description and make the final image caption more accurate. Moreover, evaluation using benchmark datasets—MSCOCO, Flickr8K, and Flickr30K—validated the impressive performance of our MLALR method with evaluation metrics—BLEU, METEOR, ROUGE-L, CIDEr, and SPICE." @default.
- W2896731359 created "2018-10-26" @default.
- W2896731359 creator A5037558598 @default.
- W2896731359 creator A5044598712 @default.
- W2896731359 creator A5054182752 @default.
- W2896731359 creator A5067196598 @default.
- W2896731359 creator A5090539201 @default.
- W2896731359 date "2018-10-09" @default.
- W2896731359 modified "2023-09-28" @default.
- W2896731359 title "Middle-Level Attribute-Based Language Retouching for Image Caption Generation" @default.
- W2896731359 cites W2131774270 @default.
- W2896731359 cites W2185175083 @default.
- W2896731359 cites W2481240925 @default.
- W2896731359 cites W2508429489 @default.
- W2896731359 cites W2564898401 @default.
- W2896731359 cites W2601380348 @default.
- W2896731359 cites W2735305611 @default.
- W2896731359 cites W2739107216 @default.
- W2896731359 cites W2754689878 @default.
- W2896731359 cites W2790951685 @default.
- W2896731359 cites W639708223 @default.
- W2896731359 cites W68733909 @default.
- W2896731359 doi "https://doi.org/10.3390/app8101850" @default.
- W2896731359 hasPublicationYear "2018" @default.
- W2896731359 type Work @default.
- W2896731359 sameAs 2896731359 @default.
- W2896731359 citedByCount "2" @default.
- W2896731359 countsByYear W28967313592019 @default.
- W2896731359 countsByYear W28967313592022 @default.
- W2896731359 crossrefType "journal-article" @default.
- W2896731359 hasAuthorship W2896731359A5037558598 @default.
- W2896731359 hasAuthorship W2896731359A5044598712 @default.
- W2896731359 hasAuthorship W2896731359A5054182752 @default.
- W2896731359 hasAuthorship W2896731359A5067196598 @default.
- W2896731359 hasAuthorship W2896731359A5090539201 @default.
- W2896731359 hasBestOaLocation W28967313591 @default.
- W2896731359 hasConcept C115961682 @default.
- W2896731359 hasConcept C13280743 @default.
- W2896731359 hasConcept C153180895 @default.
- W2896731359 hasConcept C154945302 @default.
- W2896731359 hasConcept C157657479 @default.
- W2896731359 hasConcept C185798385 @default.
- W2896731359 hasConcept C204321447 @default.
- W2896731359 hasConcept C205649164 @default.
- W2896731359 hasConcept C2781238097 @default.
- W2896731359 hasConcept C31972630 @default.
- W2896731359 hasConcept C41008148 @default.
- W2896731359 hasConceptScore W2896731359C115961682 @default.
- W2896731359 hasConceptScore W2896731359C13280743 @default.
- W2896731359 hasConceptScore W2896731359C153180895 @default.
- W2896731359 hasConceptScore W2896731359C154945302 @default.
- W2896731359 hasConceptScore W2896731359C157657479 @default.
- W2896731359 hasConceptScore W2896731359C185798385 @default.
- W2896731359 hasConceptScore W2896731359C204321447 @default.
- W2896731359 hasConceptScore W2896731359C205649164 @default.
- W2896731359 hasConceptScore W2896731359C2781238097 @default.
- W2896731359 hasConceptScore W2896731359C31972630 @default.
- W2896731359 hasConceptScore W2896731359C41008148 @default.
- W2896731359 hasIssue "10" @default.
- W2896731359 hasLocation W28967313591 @default.
- W2896731359 hasLocation W28967313592 @default.
- W2896731359 hasOpenAccess W2896731359 @default.
- W2896731359 hasPrimaryLocation W28967313591 @default.
- W2896731359 hasRelatedWork W1837097281 @default.
- W2896731359 hasRelatedWork W1966410754 @default.
- W2896731359 hasRelatedWork W2007544051 @default.
- W2896731359 hasRelatedWork W2092957489 @default.
- W2896731359 hasRelatedWork W2363840281 @default.
- W2896731359 hasRelatedWork W2795359650 @default.
- W2896731359 hasRelatedWork W2923366293 @default.
- W2896731359 hasRelatedWork W2975200075 @default.
- W2896731359 hasRelatedWork W3107474891 @default.
- W2896731359 hasRelatedWork W3151908889 @default.
- W2896731359 hasVolume "8" @default.
- W2896731359 isParatext "false" @default.
- W2896731359 isRetracted "false" @default.
- W2896731359 magId "2896731359" @default.
- W2896731359 workType "article" @default.