Matches in SemOpenAlex for { <https://semopenalex.org/work/W2893171822> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W2893171822 endingPage "62" @default.
- W2893171822 startingPage "49" @default.
- W2893171822 abstract "Keypoint detection is one of the most important pre-processing steps in tasks such as face modeling, recognition and verification. In this paper, we present an iterative method for Keypoint Estimation and Pose prediction of unconstrained faces by Learning Efficient H-CNN Regressors (KEPLER) for addressing the unconstrained face alignment problem. Recent state-of-the-art methods have shown improvements in facial keypoint detection by employing Convolution Neural Networks (CNNs). Although a simple feed forward neural network can learn the mapping between input and output spaces, it does not learn the inherent structural dependencies that well. We present a novel architecture called H-CNN (Heatmap-CNN) acting on an N-dimensional input image which captures informative structured global and local features and thus favors accurate keypoint detecion in in-the wild face images. H-CNN is jointly trained on the visibility, fiducials and 3D-pose of the face. As the iterations proceed, the error decreases making the gradients small and thus requiring efficient training of deep networks to mitigate this. KEPLER performs global corrections in pose and fiducials for the first four iterations followed by local corrections at a later stage. As a by-product, KEPLER also provides robust estimate of 3D pose (pitch, yaw and roll) of the face. We also show that without using any 3D information, KEPLER outperforms recent state-of-the-art methods for alignment on challenging datasets such as AFW [1] and AFLW [2]." @default.
- W2893171822 created "2018-10-05" @default.
- W2893171822 creator A5009101133 @default.
- W2893171822 creator A5062652529 @default.
- W2893171822 creator A5085657325 @default.
- W2893171822 date "2018-11-01" @default.
- W2893171822 modified "2023-10-03" @default.
- W2893171822 title "KEPLER: Simultaneous estimation of keypoints and 3D pose of unconstrained faces in a unified framework by learning efficient H-CNN regressors" @default.
- W2893171822 cites W1677182931 @default.
- W2893171822 cites W1990937109 @default.
- W2893171822 cites W2097117768 @default.
- W2893171822 cites W2151103935 @default.
- W2893171822 cites W2155893237 @default.
- W2893171822 cites W2163808566 @default.
- W2893171822 cites W2963202462 @default.
- W2893171822 cites W2964014798 @default.
- W2893171822 doi "https://doi.org/10.1016/j.imavis.2018.09.009" @default.
- W2893171822 hasPublicationYear "2018" @default.
- W2893171822 type Work @default.
- W2893171822 sameAs 2893171822 @default.
- W2893171822 citedByCount "10" @default.
- W2893171822 countsByYear W28931718222019 @default.
- W2893171822 countsByYear W28931718222020 @default.
- W2893171822 countsByYear W28931718222021 @default.
- W2893171822 countsByYear W28931718222022 @default.
- W2893171822 countsByYear W28931718222023 @default.
- W2893171822 crossrefType "journal-article" @default.
- W2893171822 hasAuthorship W2893171822A5009101133 @default.
- W2893171822 hasAuthorship W2893171822A5062652529 @default.
- W2893171822 hasAuthorship W2893171822A5085657325 @default.
- W2893171822 hasBestOaLocation W28931718221 @default.
- W2893171822 hasConcept C108583219 @default.
- W2893171822 hasConcept C144024400 @default.
- W2893171822 hasConcept C150846664 @default.
- W2893171822 hasConcept C153180895 @default.
- W2893171822 hasConcept C154945302 @default.
- W2893171822 hasConcept C207963374 @default.
- W2893171822 hasConcept C2779304628 @default.
- W2893171822 hasConcept C31972630 @default.
- W2893171822 hasConcept C36289849 @default.
- W2893171822 hasConcept C41008148 @default.
- W2893171822 hasConcept C45347329 @default.
- W2893171822 hasConcept C50644808 @default.
- W2893171822 hasConcept C52102323 @default.
- W2893171822 hasConcept C81363708 @default.
- W2893171822 hasConceptScore W2893171822C108583219 @default.
- W2893171822 hasConceptScore W2893171822C144024400 @default.
- W2893171822 hasConceptScore W2893171822C150846664 @default.
- W2893171822 hasConceptScore W2893171822C153180895 @default.
- W2893171822 hasConceptScore W2893171822C154945302 @default.
- W2893171822 hasConceptScore W2893171822C207963374 @default.
- W2893171822 hasConceptScore W2893171822C2779304628 @default.
- W2893171822 hasConceptScore W2893171822C31972630 @default.
- W2893171822 hasConceptScore W2893171822C36289849 @default.
- W2893171822 hasConceptScore W2893171822C41008148 @default.
- W2893171822 hasConceptScore W2893171822C45347329 @default.
- W2893171822 hasConceptScore W2893171822C50644808 @default.
- W2893171822 hasConceptScore W2893171822C52102323 @default.
- W2893171822 hasConceptScore W2893171822C81363708 @default.
- W2893171822 hasFunder F4320312530 @default.
- W2893171822 hasFunder F4320333051 @default.
- W2893171822 hasLocation W28931718221 @default.
- W2893171822 hasOpenAccess W2893171822 @default.
- W2893171822 hasPrimaryLocation W28931718221 @default.
- W2893171822 hasRelatedWork W1589930024 @default.
- W2893171822 hasRelatedWork W2018638282 @default.
- W2893171822 hasRelatedWork W2103413230 @default.
- W2893171822 hasRelatedWork W2116300362 @default.
- W2893171822 hasRelatedWork W2138569648 @default.
- W2893171822 hasRelatedWork W2360851659 @default.
- W2893171822 hasRelatedWork W2606416966 @default.
- W2893171822 hasRelatedWork W3000866861 @default.
- W2893171822 hasRelatedWork W4312417841 @default.
- W2893171822 hasRelatedWork W4321369474 @default.
- W2893171822 hasVolume "79" @default.
- W2893171822 isParatext "false" @default.
- W2893171822 isRetracted "false" @default.
- W2893171822 magId "2893171822" @default.
- W2893171822 workType "article" @default.