Matches in SemOpenAlex for { <https://semopenalex.org/work/W2982163989> ?p ?o ?g. }
- W2982163989 endingPage "171284" @default.
- W2982163989 startingPage "171272" @default.
- W2982163989 abstract "Extracting object skeleton and its scale features in natural images is helpful for object detection and recognition in computer vision. In order to advance the location accuracy of object skeleton pixels, a new method via multi-task and variable coefficient loss function is proposed in this paper. Adopting the hierarchical integration mechanism to mutually refine captured features at different network layers; a specific variable coefficient loss function is designed for multi-class imbalanced data handling problem, such as the skeleton pixels in natural images are always far less than the non-skeleton pixels; the regression algorithm is an added deep learning branch in the skeleton extraction network assisting the improvement of recognition accuracy. Besides, not only the skeleton pixels and its classification can be obtained, but also its scales are predicted without disturbing skeleton acquisition process. The experimental results verify that both the skeleton accuracy and the generalization abilities are promoted benefiting from the regression task and the new loss function in the new method, as satisfactory results are achieved on three public datasets, i.e., SK-LARGE, SK-SMALL, and WH-SYMMAX, which are indicated by F-measures and precision/recall curves. The results further demonstrate that the proposed method is superior to the best skeleton extraction method available currently." @default.
- W2982163989 created "2019-11-01" @default.
- W2982163989 creator A5008240552 @default.
- W2982163989 creator A5011596136 @default.
- W2982163989 creator A5080841116 @default.
- W2982163989 date "2019-01-01" @default.
- W2982163989 modified "2023-09-24" @default.
- W2982163989 title "An Improved Skeleton Extraction Method via Multi-Task and Variable Coefficient Loss Function in Natural Images" @default.
- W2982163989 cites W1567302070 @default.
- W2982163989 cites W1658853941 @default.
- W2982163989 cites W1745334888 @default.
- W2982163989 cites W174734558 @default.
- W2982163989 cites W1903029394 @default.
- W2982163989 cites W1967790662 @default.
- W2982163989 cites W1988452762 @default.
- W2982163989 cites W1989066343 @default.
- W2982163989 cites W2014988088 @default.
- W2982163989 cites W2038517424 @default.
- W2982163989 cites W2058256495 @default.
- W2982163989 cites W2091806358 @default.
- W2982163989 cites W2099673295 @default.
- W2982163989 cites W2144506857 @default.
- W2982163989 cites W2154576060 @default.
- W2982163989 cites W2160306297 @default.
- W2982163989 cites W2217188300 @default.
- W2982163989 cites W2253429366 @default.
- W2982163989 cites W2412782625 @default.
- W2982163989 cites W2508457857 @default.
- W2982163989 cites W2518902831 @default.
- W2982163989 cites W2554408731 @default.
- W2982163989 cites W2574253917 @default.
- W2982163989 cites W2591692311 @default.
- W2982163989 cites W2630750947 @default.
- W2982163989 cites W2738854914 @default.
- W2982163989 cites W2768854046 @default.
- W2982163989 cites W2787262181 @default.
- W2982163989 cites W2892046417 @default.
- W2982163989 cites W2914992758 @default.
- W2982163989 cites W2917663261 @default.
- W2982163989 cites W2946490545 @default.
- W2982163989 cites W2963722952 @default.
- W2982163989 cites W2964216471 @default.
- W2982163989 cites W2965815071 @default.
- W2982163989 cites W3098538019 @default.
- W2982163989 cites W4241071816 @default.
- W2982163989 cites W845365781 @default.
- W2982163989 doi "https://doi.org/10.1109/access.2019.2949269" @default.
- W2982163989 hasPublicationYear "2019" @default.
- W2982163989 type Work @default.
- W2982163989 sameAs 2982163989 @default.
- W2982163989 citedByCount "3" @default.
- W2982163989 countsByYear W29821639892021 @default.
- W2982163989 countsByYear W29821639892023 @default.
- W2982163989 crossrefType "journal-article" @default.
- W2982163989 hasAuthorship W2982163989A5008240552 @default.
- W2982163989 hasAuthorship W2982163989A5011596136 @default.
- W2982163989 hasAuthorship W2982163989A5080841116 @default.
- W2982163989 hasBestOaLocation W29821639891 @default.
- W2982163989 hasConcept C134306372 @default.
- W2982163989 hasConcept C14036430 @default.
- W2982163989 hasConcept C153180895 @default.
- W2982163989 hasConcept C154945302 @default.
- W2982163989 hasConcept C160633673 @default.
- W2982163989 hasConcept C177148314 @default.
- W2982163989 hasConcept C18969341 @default.
- W2982163989 hasConcept C199360897 @default.
- W2982163989 hasConcept C2781238097 @default.
- W2982163989 hasConcept C31972630 @default.
- W2982163989 hasConcept C33923547 @default.
- W2982163989 hasConcept C41008148 @default.
- W2982163989 hasConcept C50644808 @default.
- W2982163989 hasConcept C52622490 @default.
- W2982163989 hasConcept C78458016 @default.
- W2982163989 hasConcept C86803240 @default.
- W2982163989 hasConceptScore W2982163989C134306372 @default.
- W2982163989 hasConceptScore W2982163989C14036430 @default.
- W2982163989 hasConceptScore W2982163989C153180895 @default.
- W2982163989 hasConceptScore W2982163989C154945302 @default.
- W2982163989 hasConceptScore W2982163989C160633673 @default.
- W2982163989 hasConceptScore W2982163989C177148314 @default.
- W2982163989 hasConceptScore W2982163989C18969341 @default.
- W2982163989 hasConceptScore W2982163989C199360897 @default.
- W2982163989 hasConceptScore W2982163989C2781238097 @default.
- W2982163989 hasConceptScore W2982163989C31972630 @default.
- W2982163989 hasConceptScore W2982163989C33923547 @default.
- W2982163989 hasConceptScore W2982163989C41008148 @default.
- W2982163989 hasConceptScore W2982163989C50644808 @default.
- W2982163989 hasConceptScore W2982163989C52622490 @default.
- W2982163989 hasConceptScore W2982163989C78458016 @default.
- W2982163989 hasConceptScore W2982163989C86803240 @default.
- W2982163989 hasFunder F4320322927 @default.
- W2982163989 hasFunder F4320326839 @default.
- W2982163989 hasFunder F4320326981 @default.
- W2982163989 hasFunder F4320335777 @default.
- W2982163989 hasLocation W29821639891 @default.
- W2982163989 hasOpenAccess W2982163989 @default.
- W2982163989 hasPrimaryLocation W29821639891 @default.
- W2982163989 hasRelatedWork W121273120 @default.