Matches in SemOpenAlex for { <https://semopenalex.org/work/W3041291503> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W3041291503 endingPage "470" @default.
- W3041291503 startingPage "457" @default.
- W3041291503 abstract "Abstract Human parsing, which is a task of labeling pixels in human images into different fine-grained semantic parts, has achieved significant progress during the past decade. However, there are still several challenges in human parsing, due to occlusions, varying poses and similar appearance between the left/right parts. To tackle these problems, a Human Kinematic Skeleton Graph Layer (HKSGL) is proposed to augment regular neural networks with human kinematic skeleton information. The HKSGL has two major components: kinematic skeleton graph and interconnected modular neural layer. The kinematic skeleton graph is a user pre-defined skeleton graph, which models the interconnection between different semantic parts. Then the skeleton graph is passed to the interconnected modular neural layer composed of a set of modular blocks corresponding to different semantic parts. The HKSGL is a lightweight, low costs layer which can be easily attached to any existing neural networks. To demonstrate the power of our HKSGL, a new dataset on human parsing in occlusions is also collected, termed the RAP-Occ. Extensive experiments have been performed on four datasets on human parsing, including the LIP, the CIHP, the ATR and the RAP-Occ. And two popular baselines i.e., the Deeplab V3+ and the CE2P, are agumented by the proposed HKSGL. Competitive performance of the augmented models has been achieved over in comparison with state-of-the-art methods." @default.
- W3041291503 created "2020-07-16" @default.
- W3041291503 creator A5000051451 @default.
- W3041291503 creator A5006178794 @default.
- W3041291503 creator A5055478558 @default.
- W3041291503 creator A5078748099 @default.
- W3041291503 date "2020-11-01" @default.
- W3041291503 modified "2023-10-17" @default.
- W3041291503 title "Kinematic skeleton graph augmented network for human parsing" @default.
- W3041291503 cites W1973255633 @default.
- W3041291503 cites W2031489346 @default.
- W3041291503 cites W2049768550 @default.
- W3041291503 cites W2052055672 @default.
- W3041291503 cites W2074621908 @default.
- W3041291503 cites W2117539524 @default.
- W3041291503 cites W2412782625 @default.
- W3041291503 cites W2605951450 @default.
- W3041291503 cites W2892923422 @default.
- W3041291503 cites W2898491875 @default.
- W3041291503 cites W2948080642 @default.
- W3041291503 cites W2963224792 @default.
- W3041291503 cites W2963881378 @default.
- W3041291503 cites W2963978393 @default.
- W3041291503 cites W2964252655 @default.
- W3041291503 doi "https://doi.org/10.1016/j.neucom.2020.07.002" @default.
- W3041291503 hasPublicationYear "2020" @default.
- W3041291503 type Work @default.
- W3041291503 sameAs 3041291503 @default.
- W3041291503 citedByCount "7" @default.
- W3041291503 countsByYear W30412915032021 @default.
- W3041291503 countsByYear W30412915032022 @default.
- W3041291503 countsByYear W30412915032023 @default.
- W3041291503 crossrefType "journal-article" @default.
- W3041291503 hasAuthorship W3041291503A5000051451 @default.
- W3041291503 hasAuthorship W3041291503A5006178794 @default.
- W3041291503 hasAuthorship W3041291503A5055478558 @default.
- W3041291503 hasAuthorship W3041291503A5078748099 @default.
- W3041291503 hasConcept C121332964 @default.
- W3041291503 hasConcept C132525143 @default.
- W3041291503 hasConcept C154945302 @default.
- W3041291503 hasConcept C186644900 @default.
- W3041291503 hasConcept C18969341 @default.
- W3041291503 hasConcept C199360897 @default.
- W3041291503 hasConcept C2777846634 @default.
- W3041291503 hasConcept C31972630 @default.
- W3041291503 hasConcept C39920418 @default.
- W3041291503 hasConcept C41008148 @default.
- W3041291503 hasConcept C74650414 @default.
- W3041291503 hasConcept C80444323 @default.
- W3041291503 hasConceptScore W3041291503C121332964 @default.
- W3041291503 hasConceptScore W3041291503C132525143 @default.
- W3041291503 hasConceptScore W3041291503C154945302 @default.
- W3041291503 hasConceptScore W3041291503C186644900 @default.
- W3041291503 hasConceptScore W3041291503C18969341 @default.
- W3041291503 hasConceptScore W3041291503C199360897 @default.
- W3041291503 hasConceptScore W3041291503C2777846634 @default.
- W3041291503 hasConceptScore W3041291503C31972630 @default.
- W3041291503 hasConceptScore W3041291503C39920418 @default.
- W3041291503 hasConceptScore W3041291503C41008148 @default.
- W3041291503 hasConceptScore W3041291503C74650414 @default.
- W3041291503 hasConceptScore W3041291503C80444323 @default.
- W3041291503 hasLocation W30412915031 @default.
- W3041291503 hasOpenAccess W3041291503 @default.
- W3041291503 hasPrimaryLocation W30412915031 @default.
- W3041291503 hasRelatedWork W2119189625 @default.
- W3041291503 hasRelatedWork W2144724818 @default.
- W3041291503 hasRelatedWork W2209601329 @default.
- W3041291503 hasRelatedWork W2319494172 @default.
- W3041291503 hasRelatedWork W234978900 @default.
- W3041291503 hasRelatedWork W2360758025 @default.
- W3041291503 hasRelatedWork W2372015780 @default.
- W3041291503 hasRelatedWork W2377558231 @default.
- W3041291503 hasRelatedWork W2810934349 @default.
- W3041291503 hasRelatedWork W3020058237 @default.
- W3041291503 hasVolume "413" @default.
- W3041291503 isParatext "false" @default.
- W3041291503 isRetracted "false" @default.
- W3041291503 magId "3041291503" @default.
- W3041291503 workType "article" @default.