FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2891021031> ?p ?o ?g. }

• W2891021031 abstract "We marry two powerful ideas: deep representation learning for visual recognition and language understanding, and symbolic program execution for reasoning. Our neural-symbolic visual question answering (NS-VQA) system first recovers a structural scene representation from the image and a program trace from the question. It then executes the program on the scene representation to obtain an answer. Incorporating symbolic structure as prior knowledge offers three unique advantages. First, executing programs on a symbolic space is more robust to long program traces; our model can solve complex reasoning tasks better, achieving an accuracy of 99.8% on the CLEVR dataset. Second, the model is more data- and memory-efficient: it performs well after learning on a small number of training data; it can also encode an image into a compact representation, requiring less storage than existing methods for offline question answering. Third, symbolic program execution offers full transparency to the reasoning process; we are thus able to interpret and diagnose each execution step." @default.
• W2891021031 created "2018-09-27" @default.
• W2891021031 creator A5010972658 @default.
• W2891021031 creator A5013834379 @default.
• W2891021031 creator A5032574264 @default.
• W2891021031 creator A5040877128 @default.
• W2891021031 creator A5071093940 @default.
• W2891021031 creator A5085020955 @default.
• W2891021031 date "2018-10-04" @default.
• W2891021031 modified "2023-09-23" @default.
• W2891021031 title "Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding" @default.
• W2891021031 cites W1691728462 @default.
• W2891021031 cites W1902237438 @default.
• W2891021031 cites W1933349210 @default.
• W2891021031 cites W2064675550 @default.
• W2891021031 cites W2119717200 @default.
• W2891021031 cites W2147336195 @default.
• W2891021031 cites W2151498684 @default.
• W2891021031 cites W2161002933 @default.
• W2891021031 cites W2188956040 @default.
• W2891021031 cites W2194775991 @default.
• W2891021031 cites W2250539671 @default.
• W2891021031 cites W2471094925 @default.
• W2891021031 cites W2480004914 @default.
• W2891021031 cites W2550100435 @default.
• W2891021031 cites W2550120381 @default.
• W2891021031 cites W2560730294 @default.
• W2891021031 cites W2561715562 @default.
• W2891021031 cites W2565639579 @default.
• W2891021031 cites W2736019926 @default.
• W2891021031 cites W2739010165 @default.
• W2891021031 cites W2771052642 @default.
• W2891021031 cites W2785578203 @default.
• W2891021031 cites W2962716332 @default.
• W2891021031 cites W2962878980 @default.
• W2891021031 cites W2962933067 @default.
• W2891021031 cites W2963069010 @default.
• W2891021031 cites W2963143606 @default.
• W2891021031 cites W2963223524 @default.
• W2891021031 cites W2963224792 @default.
• W2891021031 cites W2963264829 @default.
• W2891021031 cites W2963477107 @default.
• W2891021031 cites W2963565420 @default.
• W2891021031 cites W2963668159 @default.
• W2891021031 cites W2963683806 @default.
• W2891021031 cites W2963705779 @default.
• W2891021031 cites W2963722138 @default.
• W2891021031 cites W2963907629 @default.
• W2891021031 cites W2963921132 @default.
• W2891021031 cites W2963929497 @default.
• W2891021031 cites W2963948515 @default.
• W2891021031 cites W2963951231 @default.
• W2891021031 cites W2963954913 @default.
• W2891021031 cites W2964036520 @default.
• W2891021031 cites W2964224049 @default.
• W2891021031 cites W2964245290 @default.
• W2891021031 cites W2964252535 @default.
• W2891021031 cites W2964308564 @default.
• W2891021031 doi "https://doi.org/10.48550/arxiv.1810.02338" @default.
• W2891021031 hasPublicationYear "2018" @default.
• W2891021031 type Work @default.
• W2891021031 sameAs 2891021031 @default.
• W2891021031 citedByCount "22" @default.
• W2891021031 countsByYear W28910210312018 @default.
• W2891021031 countsByYear W28910210312019 @default.
• W2891021031 countsByYear W28910210312020 @default.
• W2891021031 countsByYear W28910210312021 @default.
• W2891021031 countsByYear W28910210312023 @default.
• W2891021031 crossrefType "posted-content" @default.
• W2891021031 hasAuthorship W2891021031A5010972658 @default.
• W2891021031 hasAuthorship W2891021031A5013834379 @default.
• W2891021031 hasAuthorship W2891021031A5032574264 @default.
• W2891021031 hasAuthorship W2891021031A5040877128 @default.
• W2891021031 hasAuthorship W2891021031A5071093940 @default.
• W2891021031 hasAuthorship W2891021031A5085020955 @default.
• W2891021031 hasBestOaLocation W28910210311 @default.
• W2891021031 hasConcept C11171543 @default.
• W2891021031 hasConcept C119857082 @default.
• W2891021031 hasConcept C138885662 @default.
• W2891021031 hasConcept C154945302 @default.
• W2891021031 hasConcept C15744967 @default.
• W2891021031 hasConcept C161301231 @default.
• W2891021031 hasConcept C17744445 @default.
• W2891021031 hasConcept C199360897 @default.
• W2891021031 hasConcept C199539241 @default.
• W2891021031 hasConcept C204321447 @default.
• W2891021031 hasConcept C2776095079 @default.
• W2891021031 hasConcept C2776359362 @default.
• W2891021031 hasConcept C2780233690 @default.
• W2891021031 hasConcept C38652104 @default.
• W2891021031 hasConcept C41008148 @default.
• W2891021031 hasConcept C41895202 @default.
• W2891021031 hasConcept C44291984 @default.
• W2891021031 hasConcept C75291252 @default.
• W2891021031 hasConcept C94625758 @default.
• W2891021031 hasConcept C98045186 @default.
• W2891021031 hasConceptScore W2891021031C11171543 @default.
• W2891021031 hasConceptScore W2891021031C119857082 @default.
• W2891021031 hasConceptScore W2891021031C138885662 @default.
• W2891021031 hasConceptScore W2891021031C154945302 @default.

• next