Matches in SemOpenAlex for { <https://semopenalex.org/work/W2806281999> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W2806281999 abstract "Contour detection plays an important role in a wide range of applications such as image segmentation, object detection, shape matching, scene understanding, etc. In this study, we conduct a comprehensive analysis of contour detection using existing convolutional neural network (CNN) architectures. Given that contour detection can be considered as a classification task (e.g., contour or non-contour), six types of pretrained CNN (trained on ImageNet dataset) are individually used for domain-specific fine-tuning on contour dataset. The contour detection can then be achieved by sliding-window strategy, in which each image window (corresponding to a local patch) is used to extract features followed by classification. The features extraction is implemented by extracting the activation vectors from the fully-connected layers (except for the classification layer) of a fine-tuned CNN. Random forest classifier is adopted to predict whether the central pixel of a local patch is passed by contour or not. Experiments on a widely-used dataset called Berkeley Segmentation Data Set (BSDS500) demonstrate that fine-tuning technique can significantly improve the performance of contour detection." @default.
- W2806281999 created "2018-06-13" @default.
- W2806281999 creator A5011090035 @default.
- W2806281999 creator A5031949326 @default.
- W2806281999 creator A5045545412 @default.
- W2806281999 creator A5053727718 @default.
- W2806281999 creator A5054999570 @default.
- W2806281999 date "2018-02-26" @default.
- W2806281999 modified "2023-09-26" @default.
- W2806281999 title "A Comparative Study for Contour Detection Using Deep Convolutional Neural Networks" @default.
- W2806281999 cites W1849277567 @default.
- W2806281999 cites W1976047850 @default.
- W2806281999 cites W1976526581 @default.
- W2806281999 cites W2051732316 @default.
- W2806281999 cites W2107333657 @default.
- W2806281999 cites W2110158442 @default.
- W2806281999 cites W2119823327 @default.
- W2806281999 cites W2151049637 @default.
- W2806281999 cites W2165914352 @default.
- W2806281999 cites W2253590344 @default.
- W2806281999 cites W2962966523 @default.
- W2806281999 cites W2963173190 @default.
- W2806281999 cites W845365781 @default.
- W2806281999 doi "https://doi.org/10.1145/3195106.3195145" @default.
- W2806281999 hasPublicationYear "2018" @default.
- W2806281999 type Work @default.
- W2806281999 sameAs 2806281999 @default.
- W2806281999 citedByCount "1" @default.
- W2806281999 countsByYear W28062819992019 @default.
- W2806281999 crossrefType "proceedings-article" @default.
- W2806281999 hasAuthorship W2806281999A5011090035 @default.
- W2806281999 hasAuthorship W2806281999A5031949326 @default.
- W2806281999 hasAuthorship W2806281999A5045545412 @default.
- W2806281999 hasAuthorship W2806281999A5053727718 @default.
- W2806281999 hasAuthorship W2806281999A5054999570 @default.
- W2806281999 hasConcept C102392041 @default.
- W2806281999 hasConcept C111919701 @default.
- W2806281999 hasConcept C112353826 @default.
- W2806281999 hasConcept C115961682 @default.
- W2806281999 hasConcept C124504099 @default.
- W2806281999 hasConcept C153180895 @default.
- W2806281999 hasConcept C154945302 @default.
- W2806281999 hasConcept C160633673 @default.
- W2806281999 hasConcept C2776151529 @default.
- W2806281999 hasConcept C2778751112 @default.
- W2806281999 hasConcept C31972630 @default.
- W2806281999 hasConcept C41008148 @default.
- W2806281999 hasConcept C50644808 @default.
- W2806281999 hasConcept C52622490 @default.
- W2806281999 hasConcept C75294576 @default.
- W2806281999 hasConcept C81363708 @default.
- W2806281999 hasConcept C89600930 @default.
- W2806281999 hasConcept C95623464 @default.
- W2806281999 hasConceptScore W2806281999C102392041 @default.
- W2806281999 hasConceptScore W2806281999C111919701 @default.
- W2806281999 hasConceptScore W2806281999C112353826 @default.
- W2806281999 hasConceptScore W2806281999C115961682 @default.
- W2806281999 hasConceptScore W2806281999C124504099 @default.
- W2806281999 hasConceptScore W2806281999C153180895 @default.
- W2806281999 hasConceptScore W2806281999C154945302 @default.
- W2806281999 hasConceptScore W2806281999C160633673 @default.
- W2806281999 hasConceptScore W2806281999C2776151529 @default.
- W2806281999 hasConceptScore W2806281999C2778751112 @default.
- W2806281999 hasConceptScore W2806281999C31972630 @default.
- W2806281999 hasConceptScore W2806281999C41008148 @default.
- W2806281999 hasConceptScore W2806281999C50644808 @default.
- W2806281999 hasConceptScore W2806281999C52622490 @default.
- W2806281999 hasConceptScore W2806281999C75294576 @default.
- W2806281999 hasConceptScore W2806281999C81363708 @default.
- W2806281999 hasConceptScore W2806281999C89600930 @default.
- W2806281999 hasConceptScore W2806281999C95623464 @default.
- W2806281999 hasLocation W28062819991 @default.
- W2806281999 hasOpenAccess W2806281999 @default.
- W2806281999 hasPrimaryLocation W28062819991 @default.
- W2806281999 hasRelatedWork W1485614034 @default.
- W2806281999 hasRelatedWork W2536634271 @default.
- W2806281999 hasRelatedWork W2613186388 @default.
- W2806281999 hasRelatedWork W2734888972 @default.
- W2806281999 hasRelatedWork W2738461075 @default.
- W2806281999 hasRelatedWork W2739874619 @default.
- W2806281999 hasRelatedWork W2913302899 @default.
- W2806281999 hasRelatedWork W4225852842 @default.
- W2806281999 hasRelatedWork W4312857205 @default.
- W2806281999 hasRelatedWork W2187221949 @default.
- W2806281999 isParatext "false" @default.
- W2806281999 isRetracted "false" @default.
- W2806281999 magId "2806281999" @default.
- W2806281999 workType "article" @default.