Matches in SemOpenAlex for { <https://semopenalex.org/work/W2936250137> ?p ?o ?g. }
- W2936250137 endingPage "516" @default.
- W2936250137 startingPage "496" @default.
- W2936250137 abstract "Abstract A scene graph provides a powerful intermediate knowledge structure for various visual tasks, including semantic image retrieval, image captioning, and visual question answering. In this paper, the task of predicting a scene graph for an image is formulated as two connected problems, ie, recognizing the relationship triplets, structured as < subject‐predicate‐object >, and constructing the scene graph from the recognized relationship triplets. For relationship triplet recognition, we develop a novel hierarchical recurrent neural network with visual attention mechanism. This model is composed of two attention‐based recurrent neural networks in a hierarchical organization. The first network generates a topic vector for each relationship triplet, whereas the second network predicts each word in that relationship triplet given the topic vector. This approach successfully captures the compositional structure and contextual dependency of an image and the relationship triplets describing its scene. For scene graph construction, an entity localization approach to determine the graph structure is presented with the assistance of available attention information. Then, the procedures for automatically converting the generated relationship triplets into a scene graph are clarified through an algorithm. Extensive experimental results on two widely used data sets verify the feasibility of the proposed approach." @default.
- W2936250137 created "2019-04-25" @default.
- W2936250137 creator A5011407685 @default.
- W2936250137 creator A5028635794 @default.
- W2936250137 creator A5030064573 @default.
- W2936250137 creator A5074639024 @default.
- W2936250137 creator A5081117163 @default.
- W2936250137 date "2019-03-22" @default.
- W2936250137 modified "2023-10-14" @default.
- W2936250137 title "A hierarchical recurrent approach to predict scene graphs from a visual‐attention‐oriented perspective" @default.
- W2936250137 cites W2068397385 @default.
- W2936250137 cites W2077069816 @default.
- W2936250137 cites W2101298495 @default.
- W2936250137 cites W2115613106 @default.
- W2936250137 cites W2122710056 @default.
- W2936250137 cites W2123432324 @default.
- W2936250137 cites W2125238156 @default.
- W2936250137 cites W2250673545 @default.
- W2936250137 cites W2251849926 @default.
- W2936250137 cites W2277195237 @default.
- W2936250137 cites W2313903725 @default.
- W2936250137 cites W2479423890 @default.
- W2936250137 cites W2506483933 @default.
- W2936250137 cites W2549599535 @default.
- W2936250137 cites W2564898401 @default.
- W2936250137 cites W2575842049 @default.
- W2936250137 cites W2579549467 @default.
- W2936250137 cites W2607855566 @default.
- W2936250137 cites W2737024909 @default.
- W2936250137 cites W2741263162 @default.
- W2936250137 cites W2750938222 @default.
- W2936250137 cites W2753661786 @default.
- W2936250137 cites W2763314014 @default.
- W2936250137 cites W2776212699 @default.
- W2936250137 cites W2778940641 @default.
- W2936250137 cites W2781833237 @default.
- W2936250137 cites W2810482788 @default.
- W2936250137 cites W2883112830 @default.
- W2936250137 cites W2889924266 @default.
- W2936250137 cites W2891894830 @default.
- W2936250137 cites W2894469712 @default.
- W2936250137 cites W2962779575 @default.
- W2936250137 cites W2963093690 @default.
- W2936250137 cites W2963184176 @default.
- W2936250137 cites W2963649796 @default.
- W2936250137 cites W2963650529 @default.
- W2936250137 cites W2963762755 @default.
- W2936250137 cites W3101840568 @default.
- W2936250137 cites W3122238731 @default.
- W2936250137 cites W3138558418 @default.
- W2936250137 cites W7746136 @default.
- W2936250137 doi "https://doi.org/10.1111/coin.12202" @default.
- W2936250137 hasPublicationYear "2019" @default.
- W2936250137 type Work @default.
- W2936250137 sameAs 2936250137 @default.
- W2936250137 citedByCount "14" @default.
- W2936250137 countsByYear W29362501372020 @default.
- W2936250137 countsByYear W29362501372021 @default.
- W2936250137 countsByYear W29362501372022 @default.
- W2936250137 countsByYear W29362501372023 @default.
- W2936250137 crossrefType "journal-article" @default.
- W2936250137 hasAuthorship W2936250137A5011407685 @default.
- W2936250137 hasAuthorship W2936250137A5028635794 @default.
- W2936250137 hasAuthorship W2936250137A5030064573 @default.
- W2936250137 hasAuthorship W2936250137A5074639024 @default.
- W2936250137 hasAuthorship W2936250137A5081117163 @default.
- W2936250137 hasConcept C115961682 @default.
- W2936250137 hasConcept C12713177 @default.
- W2936250137 hasConcept C132525143 @default.
- W2936250137 hasConcept C153180895 @default.
- W2936250137 hasConcept C154945302 @default.
- W2936250137 hasConcept C157657479 @default.
- W2936250137 hasConcept C179372163 @default.
- W2936250137 hasConcept C204321447 @default.
- W2936250137 hasConcept C205711294 @default.
- W2936250137 hasConcept C2993807640 @default.
- W2936250137 hasConcept C31972630 @default.
- W2936250137 hasConcept C36464697 @default.
- W2936250137 hasConcept C41008148 @default.
- W2936250137 hasConcept C80444323 @default.
- W2936250137 hasConceptScore W2936250137C115961682 @default.
- W2936250137 hasConceptScore W2936250137C12713177 @default.
- W2936250137 hasConceptScore W2936250137C132525143 @default.
- W2936250137 hasConceptScore W2936250137C153180895 @default.
- W2936250137 hasConceptScore W2936250137C154945302 @default.
- W2936250137 hasConceptScore W2936250137C157657479 @default.
- W2936250137 hasConceptScore W2936250137C179372163 @default.
- W2936250137 hasConceptScore W2936250137C204321447 @default.
- W2936250137 hasConceptScore W2936250137C205711294 @default.
- W2936250137 hasConceptScore W2936250137C2993807640 @default.
- W2936250137 hasConceptScore W2936250137C31972630 @default.
- W2936250137 hasConceptScore W2936250137C36464697 @default.
- W2936250137 hasConceptScore W2936250137C41008148 @default.
- W2936250137 hasConceptScore W2936250137C80444323 @default.
- W2936250137 hasFunder F4320321001 @default.
- W2936250137 hasFunder F4320335777 @default.
- W2936250137 hasIssue "3" @default.
- W2936250137 hasLocation W29362501371 @default.