Matches in SemOpenAlex for { <https://semopenalex.org/work/W2346425926> ?p ?o ?g. }
- W2346425926 endingPage "277" @default.
- W2346425926 startingPage "261" @default.
- W2346425926 abstract "Visual Question Answering (VQA) is the task of taking as input an image and a free-form natural language question about the image, and producing an accurate answer. In this work we view VQA as a “feature extraction” module to extract image and caption representations. We employ these representations for the task of image-caption ranking. Each feature dimension captures (imagines) whether a fact (question-answer pair) could plausibly be true for the image and caption. This allows the model to interpret images and captions from a wide variety of perspectives. We propose score-level and representation-level fusion models to incorporate VQA knowledge in an existing state-of-the-art VQA-agnostic image-caption ranking model. We find that incorporating and reasoning about consistency between images and captions significantly improves performance. Concretely, our model improves state-of-the-art on caption retrieval by 7.1 % and on image retrieval by 4.4 % on the MSCOCO dataset." @default.
- W2346425926 created "2016-06-24" @default.
- W2346425926 creator A5050342343 @default.
- W2346425926 creator A5083014172 @default.
- W2346425926 date "2016-01-01" @default.
- W2346425926 modified "2023-10-18" @default.
- W2346425926 title "Leveraging Visual Question Answering for Image-Caption Ranking" @default.
- W2346425926 cites W141352744 @default.
- W2346425926 cites W1584193343 @default.
- W2346425926 cites W1585779673 @default.
- W2346425926 cites W1597421340 @default.
- W2346425926 cites W1861492603 @default.
- W2346425926 cites W1864464506 @default.
- W2346425926 cites W1891689858 @default.
- W2346425926 cites W1895989618 @default.
- W2346425926 cites W1897761818 @default.
- W2346425926 cites W1905533542 @default.
- W2346425926 cites W1905882502 @default.
- W2346425926 cites W1916445035 @default.
- W2346425926 cites W1924121366 @default.
- W2346425926 cites W1933349210 @default.
- W2346425926 cites W1956340063 @default.
- W2346425926 cites W1957706851 @default.
- W2346425926 cites W1982185844 @default.
- W2346425926 cites W1995628331 @default.
- W2346425926 cites W2033365921 @default.
- W2346425926 cites W2047956997 @default.
- W2346425926 cites W2056120433 @default.
- W2346425926 cites W2063153269 @default.
- W2346425926 cites W2064675550 @default.
- W2346425926 cites W2066134726 @default.
- W2346425926 cites W2077069816 @default.
- W2346425926 cites W2079789819 @default.
- W2346425926 cites W2097117768 @default.
- W2346425926 cites W2098411764 @default.
- W2346425926 cites W2103490241 @default.
- W2346425926 cites W2108598243 @default.
- W2346425926 cites W2118696714 @default.
- W2346425926 cites W2126448884 @default.
- W2346425926 cites W2128856065 @default.
- W2346425926 cites W2142192571 @default.
- W2346425926 cites W2145215286 @default.
- W2346425926 cites W2147414309 @default.
- W2346425926 cites W2196779496 @default.
- W2346425926 cites W2294130536 @default.
- W2346425926 cites W3143107425 @default.
- W2346425926 cites W343636949 @default.
- W2346425926 cites W48884151 @default.
- W2346425926 doi "https://doi.org/10.1007/978-3-319-46475-6_17" @default.
- W2346425926 hasPublicationYear "2016" @default.
- W2346425926 type Work @default.
- W2346425926 sameAs 2346425926 @default.
- W2346425926 citedByCount "61" @default.
- W2346425926 countsByYear W23464259262016 @default.
- W2346425926 countsByYear W23464259262017 @default.
- W2346425926 countsByYear W23464259262018 @default.
- W2346425926 countsByYear W23464259262019 @default.
- W2346425926 countsByYear W23464259262020 @default.
- W2346425926 countsByYear W23464259262021 @default.
- W2346425926 countsByYear W23464259262022 @default.
- W2346425926 countsByYear W23464259262023 @default.
- W2346425926 crossrefType "book-chapter" @default.
- W2346425926 hasAuthorship W2346425926A5050342343 @default.
- W2346425926 hasAuthorship W2346425926A5083014172 @default.
- W2346425926 hasBestOaLocation W23464259262 @default.
- W2346425926 hasConcept C115961682 @default.
- W2346425926 hasConcept C136197465 @default.
- W2346425926 hasConcept C138885662 @default.
- W2346425926 hasConcept C154945302 @default.
- W2346425926 hasConcept C157657479 @default.
- W2346425926 hasConcept C162324750 @default.
- W2346425926 hasConcept C1667742 @default.
- W2346425926 hasConcept C17744445 @default.
- W2346425926 hasConcept C187736073 @default.
- W2346425926 hasConcept C189430467 @default.
- W2346425926 hasConcept C199539241 @default.
- W2346425926 hasConcept C202444582 @default.
- W2346425926 hasConcept C204321447 @default.
- W2346425926 hasConcept C23123220 @default.
- W2346425926 hasConcept C2776359362 @default.
- W2346425926 hasConcept C2776401178 @default.
- W2346425926 hasConcept C2776436953 @default.
- W2346425926 hasConcept C2780451532 @default.
- W2346425926 hasConcept C33676613 @default.
- W2346425926 hasConcept C33923547 @default.
- W2346425926 hasConcept C41008148 @default.
- W2346425926 hasConcept C41895202 @default.
- W2346425926 hasConcept C44291984 @default.
- W2346425926 hasConcept C52622490 @default.
- W2346425926 hasConcept C94625758 @default.
- W2346425926 hasConceptScore W2346425926C115961682 @default.
- W2346425926 hasConceptScore W2346425926C136197465 @default.
- W2346425926 hasConceptScore W2346425926C138885662 @default.
- W2346425926 hasConceptScore W2346425926C154945302 @default.
- W2346425926 hasConceptScore W2346425926C157657479 @default.
- W2346425926 hasConceptScore W2346425926C162324750 @default.
- W2346425926 hasConceptScore W2346425926C1667742 @default.
- W2346425926 hasConceptScore W2346425926C17744445 @default.