Matches in SemOpenAlex for { <https://semopenalex.org/work/W2792565491> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W2792565491 abstract "Advancements in convolutional neural networks (CNNs) have made significant strides toward achieving high performance levels on multiple object recognition tasks. While some approaches utilize information from the entire scene to propose regions of interest, the task of interpreting a particular region or object is still performed independently of other objects and features in the image. Here we demonstrate that a scene's 'gist' can significantly contribute to how well humans can recognize objects. These findings are consistent with the notion that humans foveate on an object and incorporate information from the periphery to aid in recognition. We use a biologically inspired two-part convolutional neural network ('GistNet') that models the fovea and periphery to provide a proof-of-principle demonstration that computational object recognition can significantly benefit from the gist of the scene as contextual information. Our model yields accuracy improvements of up to 50% in certain object categories when incorporating contextual gist, while only increasing the original model size by 5%. This proposed model mirrors our intuition about how the human visual system recognizes objects, suggesting specific biologically plausible constraints to improve machine vision and building initial steps towards the challenge of scene understanding." @default.
- W2792565491 created "2018-03-29" @default.
- W2792565491 creator A5002340225 @default.
- W2792565491 creator A5017527118 @default.
- W2792565491 creator A5081541767 @default.
- W2792565491 date "2018-03-05" @default.
- W2792565491 modified "2023-09-28" @default.
- W2792565491 title "Learning Scene Gist with Convolutional Neural Networks to Improve Object Recognition" @default.
- W2792565491 cites W1522301498 @default.
- W2792565491 cites W1532257412 @default.
- W2792565491 cites W1566135517 @default.
- W2792565491 cites W1686810756 @default.
- W2792565491 cites W1904365287 @default.
- W2792565491 cites W2016053056 @default.
- W2792565491 cites W2091845343 @default.
- W2792565491 cites W2102022426 @default.
- W2792565491 cites W2113466552 @default.
- W2792565491 cites W2166761907 @default.
- W2792565491 cites W2208025604 @default.
- W2792565491 cites W2288122362 @default.
- W2792565491 cites W2432917172 @default.
- W2792565491 cites W2556967412 @default.
- W2792565491 cites W2604800731 @default.
- W2792565491 cites W2606609115 @default.
- W2792565491 cites W2963703618 @default.
- W2792565491 doi "https://doi.org/10.48550/arxiv.1803.01967" @default.
- W2792565491 hasPublicationYear "2018" @default.
- W2792565491 type Work @default.
- W2792565491 sameAs 2792565491 @default.
- W2792565491 citedByCount "1" @default.
- W2792565491 countsByYear W27925654912019 @default.
- W2792565491 crossrefType "posted-content" @default.
- W2792565491 hasAuthorship W2792565491A5002340225 @default.
- W2792565491 hasAuthorship W2792565491A5017527118 @default.
- W2792565491 hasAuthorship W2792565491A5081541767 @default.
- W2792565491 hasBestOaLocation W27925654911 @default.
- W2792565491 hasConcept C132010649 @default.
- W2792565491 hasConcept C142724271 @default.
- W2792565491 hasConcept C153180895 @default.
- W2792565491 hasConcept C154945302 @default.
- W2792565491 hasConcept C15744967 @default.
- W2792565491 hasConcept C16930146 @default.
- W2792565491 hasConcept C188147891 @default.
- W2792565491 hasConcept C2775922572 @default.
- W2792565491 hasConcept C2781238097 @default.
- W2792565491 hasConcept C31972630 @default.
- W2792565491 hasConcept C41008148 @default.
- W2792565491 hasConcept C50644808 @default.
- W2792565491 hasConcept C64876066 @default.
- W2792565491 hasConcept C71924100 @default.
- W2792565491 hasConcept C81363708 @default.
- W2792565491 hasConceptScore W2792565491C132010649 @default.
- W2792565491 hasConceptScore W2792565491C142724271 @default.
- W2792565491 hasConceptScore W2792565491C153180895 @default.
- W2792565491 hasConceptScore W2792565491C154945302 @default.
- W2792565491 hasConceptScore W2792565491C15744967 @default.
- W2792565491 hasConceptScore W2792565491C16930146 @default.
- W2792565491 hasConceptScore W2792565491C188147891 @default.
- W2792565491 hasConceptScore W2792565491C2775922572 @default.
- W2792565491 hasConceptScore W2792565491C2781238097 @default.
- W2792565491 hasConceptScore W2792565491C31972630 @default.
- W2792565491 hasConceptScore W2792565491C41008148 @default.
- W2792565491 hasConceptScore W2792565491C50644808 @default.
- W2792565491 hasConceptScore W2792565491C64876066 @default.
- W2792565491 hasConceptScore W2792565491C71924100 @default.
- W2792565491 hasConceptScore W2792565491C81363708 @default.
- W2792565491 hasLocation W27925654911 @default.
- W2792565491 hasOpenAccess W2792565491 @default.
- W2792565491 hasPrimaryLocation W27925654911 @default.
- W2792565491 hasRelatedWork W1528044252 @default.
- W2792565491 hasRelatedWork W1531683208 @default.
- W2792565491 hasRelatedWork W1912506516 @default.
- W2792565491 hasRelatedWork W2009052148 @default.
- W2792565491 hasRelatedWork W2200925278 @default.
- W2792565491 hasRelatedWork W2328068029 @default.
- W2792565491 hasRelatedWork W2330829846 @default.
- W2792565491 hasRelatedWork W2350353705 @default.
- W2792565491 hasRelatedWork W2363840281 @default.
- W2792565491 hasRelatedWork W2372904789 @default.
- W2792565491 isParatext "false" @default.
- W2792565491 isRetracted "false" @default.
- W2792565491 magId "2792565491" @default.
- W2792565491 workType "article" @default.