FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2760103357> ?p ?o ?g. }

• W2760103357 abstract "We introduce a general-purpose conditioning method for neural networks called FiLM: Feature-wise Linear Modulation. FiLM layers influence neural network computation via a simple, feature-wise affine transformation based on conditioning information. We show that FiLM layers are highly effective for visual reasoning - answering image-related questions which require a multi-step, high-level process - a task which has proven difficult for standard deep learning methods that do not explicitly model reasoning. Specifically, we show on visual reasoning tasks that FiLM layers 1) halve state-of-the-art error for the CLEVR benchmark, 2) modulate features in a coherent manner, 3) are robust to ablations and architectural modifications, and 4) generalize well to challenging, new data from few examples or even zero-shot." @default.
• W2760103357 created "2017-10-06" @default.
• W2760103357 creator A5024394972 @default.
• W2760103357 creator A5031185465 @default.
• W2760103357 creator A5084438979 @default.
• W2760103357 creator A5085748370 @default.
• W2760103357 creator A5091112967 @default.
• W2760103357 date "2018-04-29" @default.
• W2760103357 modified "2023-10-14" @default.
• W2760103357 title "FiLM: Visual Reasoning with a General Conditioning Layer" @default.
• W2760103357 cites W1924770834 @default.
• W2760103357 cites W1934264538 @default.
• W2760103357 cites W2025653905 @default.
• W2760103357 cites W2064675550 @default.
• W2760103357 cites W2117539524 @default.
• W2760103357 cites W2127795553 @default.
• W2760103357 cites W2187089797 @default.
• W2760103357 cites W2194775991 @default.
• W2760103357 cites W2230472587 @default.
• W2760103357 cites W2463565445 @default.
• W2760103357 cites W2560647685 @default.
• W2760103357 cites W2560730294 @default.
• W2760103357 cites W2561715562 @default.
• W2760103357 cites W2613526370 @default.
• W2760103357 cites W2613904329 @default.
• W2760103357 cites W2620076854 @default.
• W2760103357 cites W2622672190 @default.
• W2760103357 cites W2624614404 @default.
• W2760103357 cites W2734498959 @default.
• W2760103357 cites W2737615485 @default.
• W2760103357 cites W2737766105 @default.
• W2760103357 cites W2752782242 @default.
• W2760103357 cites W2949117887 @default.
• W2760103357 cites W2949382160 @default.
• W2760103357 cites W2950133940 @default.
• W2760103357 cites W2950761309 @default.
• W2760103357 cites W2951619830 @default.
• W2760103357 cites W2951697117 @default.
• W2760103357 cites W2952246170 @default.
• W2760103357 cites W2952339051 @default.
• W2760103357 cites W2953054324 @default.
• W2760103357 cites W2953326374 @default.
• W2760103357 cites W2962716332 @default.
• W2760103357 cites W2963245493 @default.
• W2760103357 cites W2963280294 @default.
• W2760103357 cites W2963636093 @default.
• W2760103357 cites W2963684088 @default.
• W2760103357 cites W2963954913 @default.
• W2760103357 cites W2964118342 @default.
• W2760103357 cites W2964121744 @default.
• W2760103357 doi "https://doi.org/10.1609/aaai.v32i1.11671" @default.
• W2760103357 hasPublicationYear "2018" @default.
• W2760103357 type Work @default.
• W2760103357 sameAs 2760103357 @default.
• W2760103357 citedByCount "395" @default.
• W2760103357 countsByYear W27601033572017 @default.
• W2760103357 countsByYear W27601033572018 @default.
• W2760103357 countsByYear W27601033572019 @default.
• W2760103357 countsByYear W27601033572020 @default.
• W2760103357 countsByYear W27601033572021 @default.
• W2760103357 countsByYear W27601033572022 @default.
• W2760103357 countsByYear W27601033572023 @default.
• W2760103357 crossrefType "journal-article" @default.
• W2760103357 hasAuthorship W2760103357A5024394972 @default.
• W2760103357 hasAuthorship W2760103357A5031185465 @default.
• W2760103357 hasAuthorship W2760103357A5084438979 @default.
• W2760103357 hasAuthorship W2760103357A5085748370 @default.
• W2760103357 hasAuthorship W2760103357A5091112967 @default.
• W2760103357 hasBestOaLocation W27601033571 @default.
• W2760103357 hasConcept C104317684 @default.
• W2760103357 hasConcept C111472728 @default.
• W2760103357 hasConcept C11413529 @default.
• W2760103357 hasConcept C115961682 @default.
• W2760103357 hasConcept C127413603 @default.
• W2760103357 hasConcept C13280743 @default.
• W2760103357 hasConcept C138885662 @default.
• W2760103357 hasConcept C153180895 @default.
• W2760103357 hasConcept C154945302 @default.
• W2760103357 hasConcept C178790620 @default.
• W2760103357 hasConcept C185592680 @default.
• W2760103357 hasConcept C185798385 @default.
• W2760103357 hasConcept C201995342 @default.
• W2760103357 hasConcept C204241405 @default.
• W2760103357 hasConcept C205649164 @default.
• W2760103357 hasConcept C2524010 @default.
• W2760103357 hasConcept C2776401178 @default.
• W2760103357 hasConcept C2777508537 @default.
• W2760103357 hasConcept C2779227376 @default.
• W2760103357 hasConcept C2780451532 @default.
• W2760103357 hasConcept C2780586882 @default.
• W2760103357 hasConcept C33923547 @default.
• W2760103357 hasConcept C41008148 @default.
• W2760103357 hasConcept C41895202 @default.
• W2760103357 hasConcept C45374587 @default.
• W2760103357 hasConcept C50644808 @default.
• W2760103357 hasConcept C55493867 @default.
• W2760103357 hasConcept C92757383 @default.
• W2760103357 hasConceptScore W2760103357C104317684 @default.
• W2760103357 hasConceptScore W2760103357C111472728 @default.
• W2760103357 hasConceptScore W2760103357C11413529 @default.

• next