Matches in SemOpenAlex for { <https://semopenalex.org/work/W2965112138> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W2965112138 abstract "Image paragraph generation aims to describe an image with a paragraph in natural language. Compared to image captioning with a single sentence, paragraph generation provides more expressive and fine-grained description for storytelling. Existing approaches mainly optimize paragraph generator towards minimizing word-wise cross entropy loss, which neglects linguistic hierarchy of paragraph and results in ``sparse supervision for generator learning. In this paper, we propose a novel Densely Supervised Hierarchical Policy-Value (DHPV) network for effective paragraph generation. We design new hierarchical supervisions consisting of hierarchical rewards and values at both sentence and word levels. The joint exploration of hierarchical rewards and values provides dense supervision cues for learning effective paragraph generator. We propose a new hierarchical policy-value architecture which exploits compositionality at token-to-token and sentence-to-sentence levels simultaneously and can preserve the semantic and syntactic constituent integrity. Extensive experiments on the Stanford image-paragraph benchmark have demonstrated the effectiveness of the proposed DHPV approach with performance improvements over multiple state-of-the-art methods." @default.
- W2965112138 created "2019-08-13" @default.
- W2965112138 creator A5003217535 @default.
- W2965112138 creator A5029102289 @default.
- W2965112138 creator A5030444210 @default.
- W2965112138 creator A5078141810 @default.
- W2965112138 creator A5083715043 @default.
- W2965112138 date "2019-08-01" @default.
- W2965112138 modified "2023-10-14" @default.
- W2965112138 title "Densely Supervised Hierarchical Policy-Value Network for Image Paragraph Generation" @default.
- W2965112138 cites W1687846465 @default.
- W2965112138 cites W1897761818 @default.
- W2965112138 cites W2123024445 @default.
- W2965112138 cites W2302086703 @default.
- W2965112138 cites W2549599535 @default.
- W2965112138 cites W2745461083 @default.
- W2965112138 cites W2890585349 @default.
- W2965112138 cites W2897964062 @default.
- W2965112138 cites W2949376505 @default.
- W2965112138 cites W2963758027 @default.
- W2965112138 cites W648786980 @default.
- W2965112138 doi "https://doi.org/10.24963/ijcai.2019/137" @default.
- W2965112138 hasPublicationYear "2019" @default.
- W2965112138 type Work @default.
- W2965112138 sameAs 2965112138 @default.
- W2965112138 citedByCount "6" @default.
- W2965112138 countsByYear W29651121382020 @default.
- W2965112138 countsByYear W29651121382021 @default.
- W2965112138 countsByYear W29651121382022 @default.
- W2965112138 countsByYear W29651121382023 @default.
- W2965112138 crossrefType "proceedings-article" @default.
- W2965112138 hasAuthorship W2965112138A5003217535 @default.
- W2965112138 hasAuthorship W2965112138A5029102289 @default.
- W2965112138 hasAuthorship W2965112138A5030444210 @default.
- W2965112138 hasAuthorship W2965112138A5078141810 @default.
- W2965112138 hasAuthorship W2965112138A5083715043 @default.
- W2965112138 hasBestOaLocation W29651121381 @default.
- W2965112138 hasConcept C115961682 @default.
- W2965112138 hasConcept C121332964 @default.
- W2965112138 hasConcept C136764020 @default.
- W2965112138 hasConcept C154945302 @default.
- W2965112138 hasConcept C157657479 @default.
- W2965112138 hasConcept C162324750 @default.
- W2965112138 hasConcept C163258240 @default.
- W2965112138 hasConcept C195324797 @default.
- W2965112138 hasConcept C204321447 @default.
- W2965112138 hasConcept C2776187449 @default.
- W2965112138 hasConcept C2777206241 @default.
- W2965112138 hasConcept C2777530160 @default.
- W2965112138 hasConcept C2780992000 @default.
- W2965112138 hasConcept C28490314 @default.
- W2965112138 hasConcept C31170391 @default.
- W2965112138 hasConcept C34447519 @default.
- W2965112138 hasConcept C41008148 @default.
- W2965112138 hasConcept C62520636 @default.
- W2965112138 hasConceptScore W2965112138C115961682 @default.
- W2965112138 hasConceptScore W2965112138C121332964 @default.
- W2965112138 hasConceptScore W2965112138C136764020 @default.
- W2965112138 hasConceptScore W2965112138C154945302 @default.
- W2965112138 hasConceptScore W2965112138C157657479 @default.
- W2965112138 hasConceptScore W2965112138C162324750 @default.
- W2965112138 hasConceptScore W2965112138C163258240 @default.
- W2965112138 hasConceptScore W2965112138C195324797 @default.
- W2965112138 hasConceptScore W2965112138C204321447 @default.
- W2965112138 hasConceptScore W2965112138C2776187449 @default.
- W2965112138 hasConceptScore W2965112138C2777206241 @default.
- W2965112138 hasConceptScore W2965112138C2777530160 @default.
- W2965112138 hasConceptScore W2965112138C2780992000 @default.
- W2965112138 hasConceptScore W2965112138C28490314 @default.
- W2965112138 hasConceptScore W2965112138C31170391 @default.
- W2965112138 hasConceptScore W2965112138C34447519 @default.
- W2965112138 hasConceptScore W2965112138C41008148 @default.
- W2965112138 hasConceptScore W2965112138C62520636 @default.
- W2965112138 hasLocation W29651121381 @default.
- W2965112138 hasOpenAccess W2965112138 @default.
- W2965112138 hasPrimaryLocation W29651121381 @default.
- W2965112138 hasRelatedWork W1957740064 @default.
- W2965112138 hasRelatedWork W2250530145 @default.
- W2965112138 hasRelatedWork W2768287968 @default.
- W2965112138 hasRelatedWork W2962980738 @default.
- W2965112138 hasRelatedWork W2963576560 @default.
- W2965112138 hasRelatedWork W3025136821 @default.
- W2965112138 hasRelatedWork W3035237998 @default.
- W2965112138 hasRelatedWork W3090108315 @default.
- W2965112138 hasRelatedWork W3201291803 @default.
- W2965112138 hasRelatedWork W4246697031 @default.
- W2965112138 isParatext "false" @default.
- W2965112138 isRetracted "false" @default.
- W2965112138 magId "2965112138" @default.
- W2965112138 workType "article" @default.