Matches in SemOpenAlex for { <https://semopenalex.org/work/W2961090131> ?p ?o ?g. }
- W2961090131 abstract "Localizing facial landmarks is a fundamental step in facial image analysis. However, the problem continues to be challenging in condition of large variations caused by pose disparity, illumination, expression and occlusion. In this paper, we propose a coarse-to-fine framework which joints stacked hourglass network and salient region attention refinement for robust face alignment. To achieve this, we firstly develop a multi-scale region learning module (MSL) to analyze the structure and texture information at different facial region and extract strong discriminative deep feature. Then we employ a novel convolutional neural network named stacked hourglass network (SHN) for heatmap regression and initial facial landmarks prediction. Moreover, we present a salient region attention module (SRA) to extract precise feature based on the heatmap regression, and the filtered feature is used for landmarks refinement. The extensive experimental results on two public datasets, including 300W and COFW, confirm the validity of our model." @default.
- W2961090131 created "2019-07-23" @default.
- W2961090131 creator A5029203943 @default.
- W2961090131 creator A5067937579 @default.
- W2961090131 date "2019-05-01" @default.
- W2961090131 modified "2023-09-24" @default.
- W2961090131 title "Stacked Hourglass Network Joint with Salient Region Attention Refinement for Face Alignment" @default.
- W2961090131 cites W1682276745 @default.
- W2961090131 cites W1896424170 @default.
- W2961090131 cites W1915668717 @default.
- W2961090131 cites W1976948919 @default.
- W2961090131 cites W1990937109 @default.
- W2961090131 cites W2005264304 @default.
- W2961090131 cites W2036868818 @default.
- W2961090131 cites W2038952578 @default.
- W2961090131 cites W2058961190 @default.
- W2961090131 cites W2087681821 @default.
- W2961090131 cites W2090530238 @default.
- W2961090131 cites W2097117768 @default.
- W2961090131 cites W2111372597 @default.
- W2961090131 cites W2152826865 @default.
- W2961090131 cites W2157285372 @default.
- W2961090131 cites W2165731615 @default.
- W2961090131 cites W2166694921 @default.
- W2961090131 cites W2172532449 @default.
- W2961090131 cites W2194775991 @default.
- W2961090131 cites W2210580011 @default.
- W2961090131 cites W2238285753 @default.
- W2961090131 cites W2283863529 @default.
- W2961090131 cites W2430562337 @default.
- W2961090131 cites W2436394355 @default.
- W2961090131 cites W2437557374 @default.
- W2961090131 cites W2474575620 @default.
- W2961090131 cites W2491353998 @default.
- W2961090131 cites W2518965973 @default.
- W2961090131 cites W2557290168 @default.
- W2961090131 cites W2559117000 @default.
- W2961090131 cites W2605701576 @default.
- W2961090131 cites W2736728583 @default.
- W2961090131 cites W2798898313 @default.
- W2961090131 cites W2887748972 @default.
- W2961090131 cites W2952074561 @default.
- W2961090131 cites W2963253045 @default.
- W2961090131 cites W2963559058 @default.
- W2961090131 cites W2963789946 @default.
- W2961090131 cites W2964014798 @default.
- W2961090131 cites W2964105113 @default.
- W2961090131 cites W3101998545 @default.
- W2961090131 doi "https://doi.org/10.1109/fg.2019.8756590" @default.
- W2961090131 hasPublicationYear "2019" @default.
- W2961090131 type Work @default.
- W2961090131 sameAs 2961090131 @default.
- W2961090131 citedByCount "1" @default.
- W2961090131 countsByYear W29610901312022 @default.
- W2961090131 crossrefType "proceedings-article" @default.
- W2961090131 hasAuthorship W2961090131A5029203943 @default.
- W2961090131 hasAuthorship W2961090131A5067937579 @default.
- W2961090131 hasConcept C127413603 @default.
- W2961090131 hasConcept C127532173 @default.
- W2961090131 hasConcept C137878579 @default.
- W2961090131 hasConcept C138496976 @default.
- W2961090131 hasConcept C144024400 @default.
- W2961090131 hasConcept C154945302 @default.
- W2961090131 hasConcept C15744967 @default.
- W2961090131 hasConcept C166957645 @default.
- W2961090131 hasConcept C18555067 @default.
- W2961090131 hasConcept C205778803 @default.
- W2961090131 hasConcept C2779304628 @default.
- W2961090131 hasConcept C2780719617 @default.
- W2961090131 hasConcept C31972630 @default.
- W2961090131 hasConcept C36289849 @default.
- W2961090131 hasConcept C41008148 @default.
- W2961090131 hasConcept C66938386 @default.
- W2961090131 hasConcept C95457728 @default.
- W2961090131 hasConceptScore W2961090131C127413603 @default.
- W2961090131 hasConceptScore W2961090131C127532173 @default.
- W2961090131 hasConceptScore W2961090131C137878579 @default.
- W2961090131 hasConceptScore W2961090131C138496976 @default.
- W2961090131 hasConceptScore W2961090131C144024400 @default.
- W2961090131 hasConceptScore W2961090131C154945302 @default.
- W2961090131 hasConceptScore W2961090131C15744967 @default.
- W2961090131 hasConceptScore W2961090131C166957645 @default.
- W2961090131 hasConceptScore W2961090131C18555067 @default.
- W2961090131 hasConceptScore W2961090131C205778803 @default.
- W2961090131 hasConceptScore W2961090131C2779304628 @default.
- W2961090131 hasConceptScore W2961090131C2780719617 @default.
- W2961090131 hasConceptScore W2961090131C31972630 @default.
- W2961090131 hasConceptScore W2961090131C36289849 @default.
- W2961090131 hasConceptScore W2961090131C41008148 @default.
- W2961090131 hasConceptScore W2961090131C66938386 @default.
- W2961090131 hasConceptScore W2961090131C95457728 @default.
- W2961090131 hasLocation W29610901311 @default.
- W2961090131 hasOpenAccess W2961090131 @default.
- W2961090131 hasPrimaryLocation W29610901311 @default.
- W2961090131 hasRelatedWork W187484614 @default.
- W2961090131 hasRelatedWork W1899364738 @default.
- W2961090131 hasRelatedWork W1955116508 @default.
- W2961090131 hasRelatedWork W2103413230 @default.
- W2961090131 hasRelatedWork W2136321227 @default.
- W2961090131 hasRelatedWork W2170790090 @default.