FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2273038706> ?p ?o ?g. }

• W2273038706 abstract "The complex compositional structure of language makes problems at the intersection of vision and language challenging. But language also provides a strong prior that can result in good superficial performance, without the underlying models truly understanding the visual content. This can hinder progress in pushing state of art in the computer vision aspects of multi-modal AI. In this paper, we address binary Visual Question Answering (VQA) on abstract scenes. We formulate this problem as visual verification of concepts inquired in the questions. Specifically, we convert the question to a tuple that concisely summarizes the visual concept to be detected in the image. If the concept can be found in the image, the answer to the question is yes, and otherwise no. Abstract scenes play two roles (1) They allow us to focus on the high-level semantics of the VQA task as opposed to the low-level recognition problems, and perhaps more importantly, (2) They provide us the modality to balance the dataset such that language priors are controlled, and the role of vision is essential. In particular, we collect fine-grained pairs of scenes for every question, such that the answer to the question is yes for one scene, and no for the other for the exact same question. Indeed, language priors alone do not perform better than chance on our balanced dataset. Moreover, our proposed approach matches the performance of a state-of-the-art VQA approach on the unbalanced dataset, and outperforms it on the balanced dataset." @default.
• W2273038706 created "2016-06-24" @default.
• W2273038706 creator A5011052950 @default.
• W2273038706 creator A5014035752 @default.
• W2273038706 creator A5024021293 @default.
• W2273038706 creator A5029360035 @default.
• W2273038706 creator A5050342343 @default.
• W2273038706 date "2015-11-16" @default.
• W2273038706 modified "2023-10-16" @default.
• W2273038706 title "Yin and Yang: Balancing and Answering Binary Visual Questions" @default.
• W2273038706 cites W141352744 @default.
• W2273038706 cites W1488163396 @default.
• W2273038706 cites W1514535095 @default.
• W2273038706 cites W1527575280 @default.
• W2273038706 cites W1706899115 @default.
• W2273038706 cites W1734113335 @default.
• W2273038706 cites W1895641373 @default.
• W2273038706 cites W1895989618 @default.
• W2273038706 cites W1982185844 @default.
• W2273038706 cites W1983927101 @default.
• W2273038706 cites W1986330201 @default.
• W2273038706 cites W1996418862 @default.
• W2273038706 cites W2047956997 @default.
• W2273038706 cites W2058556535 @default.
• W2273038706 cites W2090243146 @default.
• W2273038706 cites W2108598243 @default.
• W2273038706 cites W2112055291 @default.
• W2273038706 cites W2125436846 @default.
• W2273038706 cites W2131726681 @default.
• W2273038706 cites W2153332911 @default.
• W2273038706 cites W2156163116 @default.
• W2273038706 cites W2159243025 @default.
• W2273038706 cites W2167187514 @default.
• W2273038706 cites W2196779496 @default.
• W2273038706 cites W2250861254 @default.
• W2273038706 cites W2402268235 @default.
• W2273038706 cites W2949218037 @default.
• W2273038706 cites W2949769367 @default.
• W2273038706 cites W2950761309 @default.
• W2273038706 cites W2951183276 @default.
• W2273038706 cites W2951619830 @default.
• W2273038706 cites W2951805548 @default.
• W2273038706 cites W2951912364 @default.
• W2273038706 cites W2952246170 @default.
• W2273038706 cites W2953049742 @default.
• W2273038706 doi "https://doi.org/10.48550/arxiv.1511.05099" @default.
• W2273038706 hasPublicationYear "2015" @default.
• W2273038706 type Work @default.
• W2273038706 sameAs 2273038706 @default.
• W2273038706 citedByCount "23" @default.
• W2273038706 countsByYear W22730387062015 @default.
• W2273038706 countsByYear W22730387062016 @default.
• W2273038706 countsByYear W22730387062017 @default.
• W2273038706 countsByYear W22730387062018 @default.
• W2273038706 countsByYear W22730387062019 @default.
• W2273038706 countsByYear W22730387062020 @default.
• W2273038706 countsByYear W22730387062021 @default.
• W2273038706 crossrefType "posted-content" @default.
• W2273038706 hasAuthorship W2273038706A5011052950 @default.
• W2273038706 hasAuthorship W2273038706A5014035752 @default.
• W2273038706 hasAuthorship W2273038706A5024021293 @default.
• W2273038706 hasAuthorship W2273038706A5029360035 @default.
• W2273038706 hasAuthorship W2273038706A5050342343 @default.
• W2273038706 hasBestOaLocation W22730387061 @default.
• W2273038706 hasConcept C107673813 @default.
• W2273038706 hasConcept C115961682 @default.
• W2273038706 hasConcept C118615104 @default.
• W2273038706 hasConcept C118930307 @default.
• W2273038706 hasConcept C120665830 @default.
• W2273038706 hasConcept C121332964 @default.
• W2273038706 hasConcept C127413603 @default.
• W2273038706 hasConcept C146978453 @default.
• W2273038706 hasConcept C154945302 @default.
• W2273038706 hasConcept C162324750 @default.
• W2273038706 hasConcept C177769412 @default.
• W2273038706 hasConcept C184337299 @default.
• W2273038706 hasConcept C187736073 @default.
• W2273038706 hasConcept C192209626 @default.
• W2273038706 hasConcept C199360897 @default.
• W2273038706 hasConcept C204321447 @default.
• W2273038706 hasConcept C2780451532 @default.
• W2273038706 hasConcept C33923547 @default.
• W2273038706 hasConcept C41008148 @default.
• W2273038706 hasConcept C44291984 @default.
• W2273038706 hasConcept C64543145 @default.
• W2273038706 hasConceptScore W2273038706C107673813 @default.
• W2273038706 hasConceptScore W2273038706C115961682 @default.
• W2273038706 hasConceptScore W2273038706C118615104 @default.
• W2273038706 hasConceptScore W2273038706C118930307 @default.
• W2273038706 hasConceptScore W2273038706C120665830 @default.
• W2273038706 hasConceptScore W2273038706C121332964 @default.
• W2273038706 hasConceptScore W2273038706C127413603 @default.
• W2273038706 hasConceptScore W2273038706C146978453 @default.
• W2273038706 hasConceptScore W2273038706C154945302 @default.
• W2273038706 hasConceptScore W2273038706C162324750 @default.
• W2273038706 hasConceptScore W2273038706C177769412 @default.
• W2273038706 hasConceptScore W2273038706C184337299 @default.
• W2273038706 hasConceptScore W2273038706C187736073 @default.
• W2273038706 hasConceptScore W2273038706C192209626 @default.
• W2273038706 hasConceptScore W2273038706C199360897 @default.

• next