Matches in SemOpenAlex for { <https://semopenalex.org/work/W2900363265> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W2900363265 abstract "Automatically describing the content of an image is a challenging task in computer vision that connects the machine learning and natural language processing. In this paper, we present a framework, based on modeling image context, to generate natural sentences describing an image, which consists of two parts: relation modeling and description generating. By modeling the mapping from image spatial context to the logical relationship between objects, the former is trained to maximize the likelihood of the target linguistics phrase describing the relationship between object given the training image. By taking the the advantages of the syntactic-tree based method, the latter takes the predicted relationships as key ingredients to facilitate the image description generation within tree-growth process. We conduct extensive experimental evaluations on MS COCO dataset. Our framework outperforms the state-of-the-art methods. The results demonstrates that our framework provides robust and significant improvements for the relationship prediction between objects and the image description generation." @default.
- W2900363265 created "2018-11-16" @default.
- W2900363265 creator A5008154497 @default.
- W2900363265 creator A5023931221 @default.
- W2900363265 creator A5058293888 @default.
- W2900363265 creator A5060963494 @default.
- W2900363265 date "2018-07-01" @default.
- W2900363265 modified "2023-09-25" @default.
- W2900363265 title "Image Description Generation by Modeling the Relationship Between Objects" @default.
- W2900363265 cites W1596746947 @default.
- W2900363265 cites W1614282981 @default.
- W2900363265 cites W1668438657 @default.
- W2900363265 cites W1895577753 @default.
- W2900363265 cites W2011511325 @default.
- W2900363265 cites W2049705550 @default.
- W2900363265 cites W2097117768 @default.
- W2900363265 cites W2101105183 @default.
- W2900363265 cites W2110933980 @default.
- W2900363265 cites W2112912048 @default.
- W2900363265 cites W2149172860 @default.
- W2900363265 cites W2296385829 @default.
- W2900363265 cites W2300242332 @default.
- W2900363265 cites W2591644541 @default.
- W2900363265 cites W2594494421 @default.
- W2900363265 cites W2594843439 @default.
- W2900363265 cites W2737599761 @default.
- W2900363265 cites W2766666366 @default.
- W2900363265 cites W2962706528 @default.
- W2900363265 cites W62621907 @default.
- W2900363265 cites W68733909 @default.
- W2900363265 cites W8316075 @default.
- W2900363265 doi "https://doi.org/10.1109/icwapr.2018.8521291" @default.
- W2900363265 hasPublicationYear "2018" @default.
- W2900363265 type Work @default.
- W2900363265 sameAs 2900363265 @default.
- W2900363265 citedByCount "0" @default.
- W2900363265 crossrefType "proceedings-article" @default.
- W2900363265 hasAuthorship W2900363265A5008154497 @default.
- W2900363265 hasAuthorship W2900363265A5023931221 @default.
- W2900363265 hasAuthorship W2900363265A5058293888 @default.
- W2900363265 hasAuthorship W2900363265A5060963494 @default.
- W2900363265 hasConcept C113174947 @default.
- W2900363265 hasConcept C115961682 @default.
- W2900363265 hasConcept C119857082 @default.
- W2900363265 hasConcept C124101348 @default.
- W2900363265 hasConcept C134306372 @default.
- W2900363265 hasConcept C151730666 @default.
- W2900363265 hasConcept C153180895 @default.
- W2900363265 hasConcept C154945302 @default.
- W2900363265 hasConcept C183322885 @default.
- W2900363265 hasConcept C195324797 @default.
- W2900363265 hasConcept C199360897 @default.
- W2900363265 hasConcept C204321447 @default.
- W2900363265 hasConcept C25343380 @default.
- W2900363265 hasConcept C2776224158 @default.
- W2900363265 hasConcept C2779343474 @default.
- W2900363265 hasConcept C2781238097 @default.
- W2900363265 hasConcept C33923547 @default.
- W2900363265 hasConcept C41008148 @default.
- W2900363265 hasConcept C86803240 @default.
- W2900363265 hasConcept C98045186 @default.
- W2900363265 hasConceptScore W2900363265C113174947 @default.
- W2900363265 hasConceptScore W2900363265C115961682 @default.
- W2900363265 hasConceptScore W2900363265C119857082 @default.
- W2900363265 hasConceptScore W2900363265C124101348 @default.
- W2900363265 hasConceptScore W2900363265C134306372 @default.
- W2900363265 hasConceptScore W2900363265C151730666 @default.
- W2900363265 hasConceptScore W2900363265C153180895 @default.
- W2900363265 hasConceptScore W2900363265C154945302 @default.
- W2900363265 hasConceptScore W2900363265C183322885 @default.
- W2900363265 hasConceptScore W2900363265C195324797 @default.
- W2900363265 hasConceptScore W2900363265C199360897 @default.
- W2900363265 hasConceptScore W2900363265C204321447 @default.
- W2900363265 hasConceptScore W2900363265C25343380 @default.
- W2900363265 hasConceptScore W2900363265C2776224158 @default.
- W2900363265 hasConceptScore W2900363265C2779343474 @default.
- W2900363265 hasConceptScore W2900363265C2781238097 @default.
- W2900363265 hasConceptScore W2900363265C33923547 @default.
- W2900363265 hasConceptScore W2900363265C41008148 @default.
- W2900363265 hasConceptScore W2900363265C86803240 @default.
- W2900363265 hasConceptScore W2900363265C98045186 @default.
- W2900363265 hasLocation W29003632651 @default.
- W2900363265 hasOpenAccess W2900363265 @default.
- W2900363265 hasPrimaryLocation W29003632651 @default.
- W2900363265 hasRelatedWork W1538473846 @default.
- W2900363265 hasRelatedWork W1580052303 @default.
- W2900363265 hasRelatedWork W159132833 @default.
- W2900363265 hasRelatedWork W2134486566 @default.
- W2900363265 hasRelatedWork W2283261054 @default.
- W2900363265 hasRelatedWork W2592109610 @default.
- W2900363265 hasRelatedWork W2761417937 @default.
- W2900363265 hasRelatedWork W2765382140 @default.
- W2900363265 hasRelatedWork W2948139051 @default.
- W2900363265 hasRelatedWork W2952844618 @default.
- W2900363265 isParatext "false" @default.
- W2900363265 isRetracted "false" @default.
- W2900363265 magId "2900363265" @default.
- W2900363265 workType "article" @default.