Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387025942> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W4387025942 endingPage "1086" @default.
- W4387025942 startingPage "1080" @default.
- W4387025942 abstract "Abstract When performing visual inspections of bridges, experts collect photographs of defects to assess the overall condition of the structure and schedule maintenance plans. Such inspections are labor‐intensive, and computer vision‐based systems are being investigated as automated tools to assist the experts in their inspections. An important aspect however remains to ensure the representativeness of the data accounting for the sheer size, complexity and variety of the bridge components and defects being reported. Here, we perform a multi‐label classification on a dataset (SOFIA dataset) that consists of 139,455 images of types of bridge components and defects among which 53,805 are labeled (13 classes for each type). The dataset containing class imbalance and noisy labeling is processed using visual embedding computed from unsupervised deep learning methods. A combination of class‐balancing techniques is investigated on the state‐of‐the‐art Vision Transformer model. Interclass relations, which determine whether a class of defect should be part of a class of bridge component, are implemented with an additional filtering step. The whole method is also deployed on the CODEBRIM benchmark dataset resulting in an improved accuracy score." @default.
- W4387025942 created "2023-09-26" @default.
- W4387025942 creator A5030590180 @default.
- W4387025942 creator A5031718058 @default.
- W4387025942 creator A5044490044 @default.
- W4387025942 creator A5092937579 @default.
- W4387025942 creator A5092937580 @default.
- W4387025942 date "2023-09-01" @default.
- W4387025942 modified "2023-09-26" @default.
- W4387025942 title "Automatic Multi‐label Classification of Bridge Components and Defects Based on Inspection Photographs" @default.
- W4387025942 cites W2194775991 @default.
- W4387025942 cites W2896969435 @default.
- W4387025942 cites W2944666600 @default.
- W4387025942 cites W2963351448 @default.
- W4387025942 cites W2963691377 @default.
- W4387025942 cites W2964118266 @default.
- W4387025942 cites W4200321210 @default.
- W4387025942 cites W4206706211 @default.
- W4387025942 cites W4308234037 @default.
- W4387025942 cites W4312877479 @default.
- W4387025942 doi "https://doi.org/10.1002/cepa.2072" @default.
- W4387025942 hasPublicationYear "2023" @default.
- W4387025942 type Work @default.
- W4387025942 citedByCount "0" @default.
- W4387025942 crossrefType "journal-article" @default.
- W4387025942 hasAuthorship W4387025942A5030590180 @default.
- W4387025942 hasAuthorship W4387025942A5031718058 @default.
- W4387025942 hasAuthorship W4387025942A5044490044 @default.
- W4387025942 hasAuthorship W4387025942A5092937579 @default.
- W4387025942 hasAuthorship W4387025942A5092937580 @default.
- W4387025942 hasBestOaLocation W43870259421 @default.
- W4387025942 hasConcept C100776233 @default.
- W4387025942 hasConcept C119857082 @default.
- W4387025942 hasConcept C121332964 @default.
- W4387025942 hasConcept C124101348 @default.
- W4387025942 hasConcept C126322002 @default.
- W4387025942 hasConcept C13280743 @default.
- W4387025942 hasConcept C153180895 @default.
- W4387025942 hasConcept C154945302 @default.
- W4387025942 hasConcept C15744967 @default.
- W4387025942 hasConcept C168167062 @default.
- W4387025942 hasConcept C168820333 @default.
- W4387025942 hasConcept C174348530 @default.
- W4387025942 hasConcept C185798385 @default.
- W4387025942 hasConcept C205649164 @default.
- W4387025942 hasConcept C2777212361 @default.
- W4387025942 hasConcept C31258907 @default.
- W4387025942 hasConcept C37381756 @default.
- W4387025942 hasConcept C41008148 @default.
- W4387025942 hasConcept C71924100 @default.
- W4387025942 hasConcept C77805123 @default.
- W4387025942 hasConcept C97355855 @default.
- W4387025942 hasConceptScore W4387025942C100776233 @default.
- W4387025942 hasConceptScore W4387025942C119857082 @default.
- W4387025942 hasConceptScore W4387025942C121332964 @default.
- W4387025942 hasConceptScore W4387025942C124101348 @default.
- W4387025942 hasConceptScore W4387025942C126322002 @default.
- W4387025942 hasConceptScore W4387025942C13280743 @default.
- W4387025942 hasConceptScore W4387025942C153180895 @default.
- W4387025942 hasConceptScore W4387025942C154945302 @default.
- W4387025942 hasConceptScore W4387025942C15744967 @default.
- W4387025942 hasConceptScore W4387025942C168167062 @default.
- W4387025942 hasConceptScore W4387025942C168820333 @default.
- W4387025942 hasConceptScore W4387025942C174348530 @default.
- W4387025942 hasConceptScore W4387025942C185798385 @default.
- W4387025942 hasConceptScore W4387025942C205649164 @default.
- W4387025942 hasConceptScore W4387025942C2777212361 @default.
- W4387025942 hasConceptScore W4387025942C31258907 @default.
- W4387025942 hasConceptScore W4387025942C37381756 @default.
- W4387025942 hasConceptScore W4387025942C41008148 @default.
- W4387025942 hasConceptScore W4387025942C71924100 @default.
- W4387025942 hasConceptScore W4387025942C77805123 @default.
- W4387025942 hasConceptScore W4387025942C97355855 @default.
- W4387025942 hasIssue "5" @default.
- W4387025942 hasLocation W43870259421 @default.
- W4387025942 hasOpenAccess W4387025942 @default.
- W4387025942 hasPrimaryLocation W43870259421 @default.
- W4387025942 hasRelatedWork W112744582 @default.
- W4387025942 hasRelatedWork W1485630101 @default.
- W4387025942 hasRelatedWork W1966301419 @default.
- W4387025942 hasRelatedWork W2095239229 @default.
- W4387025942 hasRelatedWork W2379533788 @default.
- W4387025942 hasRelatedWork W2464523393 @default.
- W4387025942 hasRelatedWork W2498017833 @default.
- W4387025942 hasRelatedWork W2622932135 @default.
- W4387025942 hasRelatedWork W2961085424 @default.
- W4387025942 hasRelatedWork W4306674287 @default.
- W4387025942 hasVolume "6" @default.
- W4387025942 isParatext "false" @default.
- W4387025942 isRetracted "false" @default.
- W4387025942 workType "article" @default.