Matches in SemOpenAlex for { <https://semopenalex.org/work/W2909519650> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W2909519650 abstract "Railway power supply infrastructure is one of the most important components of railway transportation. As the key step of railway maintenance system, power supply infrastructure defects recognition plays a vital role in the whole defects inspection sub-system. Traditional defects recognition task is performed manually, which is time-consuming and high-labor costing. Inspired by the great success of deep neural networks in dealing with different vision tasks, this paper presents an end-to-end deep network to solve the railway infrastructure defects detection problem. More importantly, this paper is the first work that adopts the idea of deep fine-grained classification to do railway defects detection. We propose a new bilinear deep network named Spatial Transformer And Bilinear Low-Rank (STABLR) model and apply it to railway infrastructure defects detection. The experimental results demonstrate that the proposed method outperforms both hand-craft features based machine learning methods and classic deep neural network methods." @default.
- W2909519650 created "2019-01-25" @default.
- W2909519650 creator A5014466286 @default.
- W2909519650 creator A5049609631 @default.
- W2909519650 creator A5050390965 @default.
- W2909519650 creator A5063629854 @default.
- W2909519650 creator A5065946561 @default.
- W2909519650 date "2018-12-01" @default.
- W2909519650 modified "2023-10-16" @default.
- W2909519650 title "Railway Infrastructure Defects Recognition using Fine-grained Deep Convolutional Neural Networks" @default.
- W2909519650 cites W1588043677 @default.
- W2909519650 cites W1955942245 @default.
- W2909519650 cites W2054831422 @default.
- W2909519650 cites W2076327099 @default.
- W2909519650 cites W2104657103 @default.
- W2909519650 cites W2117539524 @default.
- W2909519650 cites W2133059825 @default.
- W2909519650 cites W2161969291 @default.
- W2909519650 cites W2183341477 @default.
- W2909519650 cites W2194775991 @default.
- W2909519650 cites W2219903032 @default.
- W2909519650 cites W2480364715 @default.
- W2909519650 cites W2555875178 @default.
- W2909519650 cites W2731821979 @default.
- W2909519650 cites W2740620254 @default.
- W2909519650 cites W2765268259 @default.
- W2909519650 cites W2765906533 @default.
- W2909519650 cites W2779475642 @default.
- W2909519650 cites W2963037989 @default.
- W2909519650 cites W2963066927 @default.
- W2909519650 cites W4239510810 @default.
- W2909519650 cites W4250878893 @default.
- W2909519650 cites W4255391993 @default.
- W2909519650 cites W4298082496 @default.
- W2909519650 doi "https://doi.org/10.1109/dicta.2018.8615868" @default.
- W2909519650 hasPublicationYear "2018" @default.
- W2909519650 type Work @default.
- W2909519650 sameAs 2909519650 @default.
- W2909519650 citedByCount "6" @default.
- W2909519650 countsByYear W29095196502020 @default.
- W2909519650 countsByYear W29095196502022 @default.
- W2909519650 countsByYear W29095196502023 @default.
- W2909519650 crossrefType "proceedings-article" @default.
- W2909519650 hasAuthorship W2909519650A5014466286 @default.
- W2909519650 hasAuthorship W2909519650A5049609631 @default.
- W2909519650 hasAuthorship W2909519650A5050390965 @default.
- W2909519650 hasAuthorship W2909519650A5063629854 @default.
- W2909519650 hasAuthorship W2909519650A5065946561 @default.
- W2909519650 hasConcept C108583219 @default.
- W2909519650 hasConcept C119857082 @default.
- W2909519650 hasConcept C144133560 @default.
- W2909519650 hasConcept C154945302 @default.
- W2909519650 hasConcept C162853370 @default.
- W2909519650 hasConcept C164624739 @default.
- W2909519650 hasConcept C2984842247 @default.
- W2909519650 hasConcept C41008148 @default.
- W2909519650 hasConcept C50644808 @default.
- W2909519650 hasConcept C52622490 @default.
- W2909519650 hasConcept C81363708 @default.
- W2909519650 hasConceptScore W2909519650C108583219 @default.
- W2909519650 hasConceptScore W2909519650C119857082 @default.
- W2909519650 hasConceptScore W2909519650C144133560 @default.
- W2909519650 hasConceptScore W2909519650C154945302 @default.
- W2909519650 hasConceptScore W2909519650C162853370 @default.
- W2909519650 hasConceptScore W2909519650C164624739 @default.
- W2909519650 hasConceptScore W2909519650C2984842247 @default.
- W2909519650 hasConceptScore W2909519650C41008148 @default.
- W2909519650 hasConceptScore W2909519650C50644808 @default.
- W2909519650 hasConceptScore W2909519650C52622490 @default.
- W2909519650 hasConceptScore W2909519650C81363708 @default.
- W2909519650 hasLocation W29095196501 @default.
- W2909519650 hasOpenAccess W2909519650 @default.
- W2909519650 hasPrimaryLocation W29095196501 @default.
- W2909519650 hasRelatedWork W2279398222 @default.
- W2909519650 hasRelatedWork W2337926734 @default.
- W2909519650 hasRelatedWork W2915754718 @default.
- W2909519650 hasRelatedWork W3011074480 @default.
- W2909519650 hasRelatedWork W3133861977 @default.
- W2909519650 hasRelatedWork W3156786002 @default.
- W2909519650 hasRelatedWork W4287009405 @default.
- W2909519650 hasRelatedWork W4299822940 @default.
- W2909519650 hasRelatedWork W4311257506 @default.
- W2909519650 hasRelatedWork W4366492315 @default.
- W2909519650 isParatext "false" @default.
- W2909519650 isRetracted "false" @default.
- W2909519650 magId "2909519650" @default.
- W2909519650 workType "article" @default.