Matches in SemOpenAlex for { <https://semopenalex.org/work/W2987703048> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W2987703048 endingPage "4656" @default.
- W2987703048 startingPage "4656" @default.
- W2987703048 abstract "This work presents a deep learning method for scene description. (1) Background: This method is part of a larger system, called BlindSys, that assists the visually impaired in an indoor environment. The method detects the presence of certain objects, regardless of their position in the scene. This problem is also known as image multi-labeling. (2) Methods: Our proposed deep learning solution is based on a light-weight pre-trained CNN called SqueezeNet. We improved the SqueezeNet architecture by resetting the last convolutional layer to free weights, replacing its activation function from a rectified linear unit (ReLU) to a LeakyReLU, and adding a BatchNormalization layer thereafter. We also replaced the activation functions at the output layer from softmax to linear functions. These adjustments make up the main contributions in this work. (3) Results: The proposed solution is tested on four image multi-labeling datasets representing different indoor environments. It has achieved results better than state-of-the-art solutions both in terms of accuracy and processing time. (4) Conclusions: The proposed deep CNN is an effective solution for predicting the presence of objects in a scene and can be successfully used as a module within BlindSys." @default.
- W2987703048 created "2019-11-22" @default.
- W2987703048 creator A5030617821 @default.
- W2987703048 creator A5052594698 @default.
- W2987703048 creator A5052654920 @default.
- W2987703048 creator A5054237841 @default.
- W2987703048 date "2019-11-01" @default.
- W2987703048 modified "2023-09-27" @default.
- W2987703048 title "Helping the Visually Impaired See via Image Multi-labeling Based on SqueezeNet CNN" @default.
- W2987703048 cites W2022508996 @default.
- W2987703048 cites W2031506269 @default.
- W2987703048 cites W2055085016 @default.
- W2987703048 cites W2076063813 @default.
- W2987703048 cites W2112796928 @default.
- W2987703048 cites W2117287331 @default.
- W2987703048 cites W2136922672 @default.
- W2987703048 cites W2155217764 @default.
- W2987703048 cites W2163922914 @default.
- W2987703048 cites W2203224402 @default.
- W2987703048 cites W2304245051 @default.
- W2987703048 cites W2413409465 @default.
- W2987703048 cites W2528333963 @default.
- W2987703048 cites W2582278192 @default.
- W2987703048 cites W2605995529 @default.
- W2987703048 cites W2618530766 @default.
- W2987703048 cites W2769764785 @default.
- W2987703048 cites W2795778833 @default.
- W2987703048 cites W639708223 @default.
- W2987703048 doi "https://doi.org/10.3390/app9214656" @default.
- W2987703048 hasPublicationYear "2019" @default.
- W2987703048 type Work @default.
- W2987703048 sameAs 2987703048 @default.
- W2987703048 citedByCount "21" @default.
- W2987703048 countsByYear W29877030482020 @default.
- W2987703048 countsByYear W29877030482021 @default.
- W2987703048 countsByYear W29877030482022 @default.
- W2987703048 countsByYear W29877030482023 @default.
- W2987703048 crossrefType "journal-article" @default.
- W2987703048 hasAuthorship W2987703048A5030617821 @default.
- W2987703048 hasAuthorship W2987703048A5052594698 @default.
- W2987703048 hasAuthorship W2987703048A5052654920 @default.
- W2987703048 hasAuthorship W2987703048A5054237841 @default.
- W2987703048 hasBestOaLocation W29877030481 @default.
- W2987703048 hasConcept C108583219 @default.
- W2987703048 hasConcept C115961682 @default.
- W2987703048 hasConcept C153180895 @default.
- W2987703048 hasConcept C154945302 @default.
- W2987703048 hasConcept C178790620 @default.
- W2987703048 hasConcept C185592680 @default.
- W2987703048 hasConcept C188441871 @default.
- W2987703048 hasConcept C2779227376 @default.
- W2987703048 hasConcept C31972630 @default.
- W2987703048 hasConcept C41008148 @default.
- W2987703048 hasConcept C81363708 @default.
- W2987703048 hasConceptScore W2987703048C108583219 @default.
- W2987703048 hasConceptScore W2987703048C115961682 @default.
- W2987703048 hasConceptScore W2987703048C153180895 @default.
- W2987703048 hasConceptScore W2987703048C154945302 @default.
- W2987703048 hasConceptScore W2987703048C178790620 @default.
- W2987703048 hasConceptScore W2987703048C185592680 @default.
- W2987703048 hasConceptScore W2987703048C188441871 @default.
- W2987703048 hasConceptScore W2987703048C2779227376 @default.
- W2987703048 hasConceptScore W2987703048C31972630 @default.
- W2987703048 hasConceptScore W2987703048C41008148 @default.
- W2987703048 hasConceptScore W2987703048C81363708 @default.
- W2987703048 hasFunder F4320335045 @default.
- W2987703048 hasIssue "21" @default.
- W2987703048 hasLocation W29877030481 @default.
- W2987703048 hasOpenAccess W2987703048 @default.
- W2987703048 hasPrimaryLocation W29877030481 @default.
- W2987703048 hasRelatedWork W2621864722 @default.
- W2987703048 hasRelatedWork W2732542196 @default.
- W2987703048 hasRelatedWork W2738221750 @default.
- W2987703048 hasRelatedWork W2758063741 @default.
- W2987703048 hasRelatedWork W2883041339 @default.
- W2987703048 hasRelatedWork W2913997398 @default.
- W2987703048 hasRelatedWork W2977314777 @default.
- W2987703048 hasRelatedWork W3000978536 @default.
- W2987703048 hasRelatedWork W3156786002 @default.
- W2987703048 hasRelatedWork W564581980 @default.
- W2987703048 hasVolume "9" @default.
- W2987703048 isParatext "false" @default.
- W2987703048 isRetracted "false" @default.
- W2987703048 magId "2987703048" @default.
- W2987703048 workType "article" @default.