Matches in SemOpenAlex for { <https://semopenalex.org/work/W1694858705> ?p ?o ?g. }
- W1694858705 abstract "This paper proposes a novel framework for generating lingual descriptions of indoor scenes. Whereas substantial efforts have been made to tackle this problem, previous approaches focusing primarily on generating a single sentence for each image, which is not sufficient for describing complex scenes. We attempt to go beyond this, by generating coherent descriptions with multiple sentences. Our approach is distinguished from conventional ones in several aspects: (1) a 3D visual parsing system that jointly infers objects, attributes, and relations; (2) a generative grammar learned automatically from training text; and (3) a text generation algorithm that takes into account the coherence among sentences. Experiments on the augmented NYU-v2 dataset show that our framework can generate natural descriptions with substantially higher ROGUE scores compared to those produced by the baseline." @default.
- W1694858705 created "2016-06-24" @default.
- W1694858705 creator A5010087030 @default.
- W1694858705 creator A5038385949 @default.
- W1694858705 creator A5058557954 @default.
- W1694858705 creator A5070642269 @default.
- W1694858705 date "2015-02-27" @default.
- W1694858705 modified "2023-09-23" @default.
- W1694858705 title "Generating Multi-Sentence Lingual Descriptions of Indoor Scenes" @default.
- W1694858705 cites W125693051 @default.
- W1694858705 cites W1527575280 @default.
- W1694858705 cites W1584193343 @default.
- W1694858705 cites W1858383477 @default.
- W1694858705 cites W1895577753 @default.
- W1694858705 cites W1995820507 @default.
- W1694858705 cites W1996430422 @default.
- W1694858705 cites W2017814585 @default.
- W1694858705 cites W2046382188 @default.
- W1694858705 cites W2048343491 @default.
- W1694858705 cites W2062955551 @default.
- W1694858705 cites W2066134726 @default.
- W1694858705 cites W2066813062 @default.
- W1694858705 cites W2079937789 @default.
- W1694858705 cites W2086842362 @default.
- W1694858705 cites W2101105183 @default.
- W1694858705 cites W2106624428 @default.
- W1694858705 cites W2109586012 @default.
- W1694858705 cites W2110933980 @default.
- W1694858705 cites W2111161343 @default.
- W1694858705 cites W2122180654 @default.
- W1694858705 cites W2136985729 @default.
- W1694858705 cites W2149172860 @default.
- W1694858705 cites W2149536503 @default.
- W1694858705 cites W2152571752 @default.
- W1694858705 cites W2152984213 @default.
- W1694858705 cites W2157487986 @default.
- W1694858705 cites W2159243025 @default.
- W1694858705 cites W2167905777 @default.
- W1694858705 cites W2251041941 @default.
- W1694858705 cites W2296385829 @default.
- W1694858705 cites W2949559657 @default.
- W1694858705 cites W2949769367 @default.
- W1694858705 cites W2951183276 @default.
- W1694858705 cites W2951619830 @default.
- W1694858705 cites W2951805548 @default.
- W1694858705 cites W2963811219 @default.
- W1694858705 doi "https://doi.org/10.48550/arxiv.1503.00064" @default.
- W1694858705 hasPublicationYear "2015" @default.
- W1694858705 type Work @default.
- W1694858705 sameAs 1694858705 @default.
- W1694858705 citedByCount "4" @default.
- W1694858705 countsByYear W16948587052016 @default.
- W1694858705 countsByYear W16948587052018 @default.
- W1694858705 countsByYear W16948587052019 @default.
- W1694858705 crossrefType "posted-content" @default.
- W1694858705 hasAuthorship W1694858705A5010087030 @default.
- W1694858705 hasAuthorship W1694858705A5038385949 @default.
- W1694858705 hasAuthorship W1694858705A5058557954 @default.
- W1694858705 hasAuthorship W1694858705A5070642269 @default.
- W1694858705 hasBestOaLocation W16948587051 @default.
- W1694858705 hasConcept C105795698 @default.
- W1694858705 hasConcept C111368507 @default.
- W1694858705 hasConcept C12725497 @default.
- W1694858705 hasConcept C127313418 @default.
- W1694858705 hasConcept C138885662 @default.
- W1694858705 hasConcept C154945302 @default.
- W1694858705 hasConcept C167966045 @default.
- W1694858705 hasConcept C186644900 @default.
- W1694858705 hasConcept C204321447 @default.
- W1694858705 hasConcept C26022165 @default.
- W1694858705 hasConcept C2777530160 @default.
- W1694858705 hasConcept C2781181686 @default.
- W1694858705 hasConcept C33923547 @default.
- W1694858705 hasConcept C39890363 @default.
- W1694858705 hasConcept C41008148 @default.
- W1694858705 hasConcept C41895202 @default.
- W1694858705 hasConceptScore W1694858705C105795698 @default.
- W1694858705 hasConceptScore W1694858705C111368507 @default.
- W1694858705 hasConceptScore W1694858705C12725497 @default.
- W1694858705 hasConceptScore W1694858705C127313418 @default.
- W1694858705 hasConceptScore W1694858705C138885662 @default.
- W1694858705 hasConceptScore W1694858705C154945302 @default.
- W1694858705 hasConceptScore W1694858705C167966045 @default.
- W1694858705 hasConceptScore W1694858705C186644900 @default.
- W1694858705 hasConceptScore W1694858705C204321447 @default.
- W1694858705 hasConceptScore W1694858705C26022165 @default.
- W1694858705 hasConceptScore W1694858705C2777530160 @default.
- W1694858705 hasConceptScore W1694858705C2781181686 @default.
- W1694858705 hasConceptScore W1694858705C33923547 @default.
- W1694858705 hasConceptScore W1694858705C39890363 @default.
- W1694858705 hasConceptScore W1694858705C41008148 @default.
- W1694858705 hasConceptScore W1694858705C41895202 @default.
- W1694858705 hasLocation W16948587051 @default.
- W1694858705 hasOpenAccess W1694858705 @default.
- W1694858705 hasPrimaryLocation W16948587051 @default.
- W1694858705 hasRelatedWork W159132833 @default.
- W1694858705 hasRelatedWork W1978971213 @default.
- W1694858705 hasRelatedWork W2100833569 @default.
- W1694858705 hasRelatedWork W2250523280 @default.
- W1694858705 hasRelatedWork W2251733251 @default.