Matches in SemOpenAlex for { <https://semopenalex.org/work/W2973082566> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W2973082566 endingPage "280" @default.
- W2973082566 startingPage "267" @default.
- W2973082566 abstract "Human body parsing remains a challenging problem in natural scenes due to multi-instance and inter-part semantic confusions as well as occlusions. This paper proposes a novel approach to decomposing multiple human bodies into semantic part regions in unconstrained environments. Specifically we propose a convolutional neural network (CNN) architecture which comprises of novel semantic and contour attention mechanisms across feature hierarchy to resolve the semantic ambiguities and boundary localization issues related to semantic body parsing. We further propose to encode estimated pose as higher-level contextual information which is combined with local semantic cues in a novel graphical model in a principled manner. In this proposed model, the lower-level semantic cues can be recursively updated by propagating higher-level contextual information from estimated pose and vice versa across the graph, so as to alleviate erroneous pose information and pixel level predictions. We further propose an optimization technique to efficiently derive the solutions. Our proposed method achieves the state-of-art results on the challenging Pascal Person-Part dataset." @default.
- W2973082566 created "2019-09-19" @default.
- W2973082566 creator A5023084225 @default.
- W2973082566 creator A5036188652 @default.
- W2973082566 date "2019-01-01" @default.
- W2973082566 modified "2023-09-23" @default.
- W2973082566 title "Graph-Boosted Attentive Network for Semantic Body Parsing" @default.
- W2973082566 cites W1511842291 @default.
- W2973082566 cites W1901129140 @default.
- W2973082566 cites W1903029394 @default.
- W2973082566 cites W1978098473 @default.
- W2973082566 cites W1999416389 @default.
- W2973082566 cites W2002951941 @default.
- W2973082566 cites W2083118758 @default.
- W2973082566 cites W2089995859 @default.
- W2973082566 cites W2097998671 @default.
- W2973082566 cites W2104408738 @default.
- W2973082566 cites W2109253138 @default.
- W2973082566 cites W2115091888 @default.
- W2973082566 cites W2118246710 @default.
- W2973082566 cites W2150579614 @default.
- W2973082566 cites W2153410696 @default.
- W2973082566 cites W2169374938 @default.
- W2973082566 cites W2309415944 @default.
- W2973082566 cites W2382036597 @default.
- W2973082566 cites W2406445210 @default.
- W2973082566 cites W2415731916 @default.
- W2973082566 cites W2741928574 @default.
- W2973082566 cites W2755066373 @default.
- W2973082566 cites W2788024025 @default.
- W2973082566 cites W2799166040 @default.
- W2973082566 cites W2896249043 @default.
- W2973082566 cites W2920548993 @default.
- W2973082566 cites W2962820340 @default.
- W2973082566 cites W2962891704 @default.
- W2973082566 cites W2963344496 @default.
- W2973082566 cites W2963736028 @default.
- W2973082566 cites W2963758239 @default.
- W2973082566 cites W2963805953 @default.
- W2973082566 cites W2963935758 @default.
- W2973082566 cites W2963948108 @default.
- W2973082566 cites W2964070329 @default.
- W2973082566 cites W2964309882 @default.
- W2973082566 cites W56385144 @default.
- W2973082566 cites W582195991 @default.
- W2973082566 doi "https://doi.org/10.1007/978-3-030-30508-6_22" @default.
- W2973082566 hasPublicationYear "2019" @default.
- W2973082566 type Work @default.
- W2973082566 sameAs 2973082566 @default.
- W2973082566 citedByCount "0" @default.
- W2973082566 crossrefType "book-chapter" @default.
- W2973082566 hasAuthorship W2973082566A5023084225 @default.
- W2973082566 hasAuthorship W2973082566A5036188652 @default.
- W2973082566 hasConcept C132525143 @default.
- W2973082566 hasConcept C154945302 @default.
- W2973082566 hasConcept C186644900 @default.
- W2973082566 hasConcept C204321447 @default.
- W2973082566 hasConcept C41008148 @default.
- W2973082566 hasConcept C80444323 @default.
- W2973082566 hasConceptScore W2973082566C132525143 @default.
- W2973082566 hasConceptScore W2973082566C154945302 @default.
- W2973082566 hasConceptScore W2973082566C186644900 @default.
- W2973082566 hasConceptScore W2973082566C204321447 @default.
- W2973082566 hasConceptScore W2973082566C41008148 @default.
- W2973082566 hasConceptScore W2973082566C80444323 @default.
- W2973082566 hasLocation W29730825661 @default.
- W2973082566 hasOpenAccess W2973082566 @default.
- W2973082566 hasPrimaryLocation W29730825661 @default.
- W2973082566 hasRelatedWork W1552159754 @default.
- W2973082566 hasRelatedWork W1806995473 @default.
- W2973082566 hasRelatedWork W1930331324 @default.
- W2973082566 hasRelatedWork W1978971213 @default.
- W2973082566 hasRelatedWork W2151447942 @default.
- W2973082566 hasRelatedWork W2167662847 @default.
- W2973082566 hasRelatedWork W2502722637 @default.
- W2973082566 hasRelatedWork W2903680434 @default.
- W2973082566 hasRelatedWork W85349525 @default.
- W2973082566 hasRelatedWork W1551406738 @default.
- W2973082566 isParatext "false" @default.
- W2973082566 isRetracted "false" @default.
- W2973082566 magId "2973082566" @default.
- W2973082566 workType "book-chapter" @default.