Matches in SemOpenAlex for { <https://semopenalex.org/work/W2807345188> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W2807345188 abstract "Face alignment plays an important role for robust face recognition and analysis applications in the wild. While a number of face alignment methods are available, large-pose face alignment remains a very challenging problem due to the ambiguity of facial keypoints in 2D face images. Recent attempts to solve this problem via 3D model fitting show more robustness against large poses and 2D ambiguity, but their accuracy and speed are still limited. We propose a 3D reconstruction based method to quickly and accurately detect 2D facial landmarks and estimate their visibilities. By designing a cascaded multi-task CNN model, we can efficiently reconstruct the 3D face shape, together with pose estimation as an auxiliary task. Finally, the landmarks on 3D shape are projected to the 2D face image to get the 2D landmarks and their visibilities. Experimental results on the challenging 300W-LP, AFLW2000-3D, and AFLW databases show that the proposed approach can be comparable with the state-of-the-art methods and is able to run in real time (32ms per image) on 3.4 GHz CPU." @default.
- W2807345188 created "2018-06-13" @default.
- W2807345188 creator A5028517540 @default.
- W2807345188 creator A5041873456 @default.
- W2807345188 creator A5050297728 @default.
- W2807345188 creator A5083420537 @default.
- W2807345188 creator A5091049278 @default.
- W2807345188 date "2018-05-01" @default.
- W2807345188 modified "2023-10-16" @default.
- W2807345188 title "Face Alignment across Large Pose via MT-CNN Based 3D Shape Reconstruction" @default.
- W2807345188 cites W1536680647 @default.
- W2807345188 cites W1677182931 @default.
- W2807345188 cites W1896424170 @default.
- W2807345188 cites W1935588821 @default.
- W2807345188 cites W1963599662 @default.
- W2807345188 cites W1976948919 @default.
- W2807345188 cites W1990937109 @default.
- W2807345188 cites W1999794899 @default.
- W2807345188 cites W2009431074 @default.
- W2807345188 cites W2012885984 @default.
- W2807345188 cites W2062516103 @default.
- W2807345188 cites W2082149009 @default.
- W2807345188 cites W2111372597 @default.
- W2807345188 cites W2136000821 @default.
- W2807345188 cites W2152826865 @default.
- W2807345188 cites W2153810084 @default.
- W2807345188 cites W2157285372 @default.
- W2807345188 cites W2160126058 @default.
- W2807345188 cites W2166694921 @default.
- W2807345188 cites W2325939864 @default.
- W2807345188 cites W2465108587 @default.
- W2807345188 cites W2731384148 @default.
- W2807345188 cites W2820458630 @default.
- W2807345188 cites W2964014798 @default.
- W2807345188 doi "https://doi.org/10.1109/fg.2018.00039" @default.
- W2807345188 hasPublicationYear "2018" @default.
- W2807345188 type Work @default.
- W2807345188 sameAs 2807345188 @default.
- W2807345188 citedByCount "5" @default.
- W2807345188 countsByYear W28073451882019 @default.
- W2807345188 countsByYear W28073451882020 @default.
- W2807345188 countsByYear W28073451882021 @default.
- W2807345188 countsByYear W28073451882022 @default.
- W2807345188 crossrefType "proceedings-article" @default.
- W2807345188 hasAuthorship W2807345188A5028517540 @default.
- W2807345188 hasAuthorship W2807345188A5041873456 @default.
- W2807345188 hasAuthorship W2807345188A5050297728 @default.
- W2807345188 hasAuthorship W2807345188A5083420537 @default.
- W2807345188 hasAuthorship W2807345188A5091049278 @default.
- W2807345188 hasConcept C144024400 @default.
- W2807345188 hasConcept C153180895 @default.
- W2807345188 hasConcept C154945302 @default.
- W2807345188 hasConcept C2779304628 @default.
- W2807345188 hasConcept C31510193 @default.
- W2807345188 hasConcept C31972630 @default.
- W2807345188 hasConcept C36289849 @default.
- W2807345188 hasConcept C41008148 @default.
- W2807345188 hasConceptScore W2807345188C144024400 @default.
- W2807345188 hasConceptScore W2807345188C153180895 @default.
- W2807345188 hasConceptScore W2807345188C154945302 @default.
- W2807345188 hasConceptScore W2807345188C2779304628 @default.
- W2807345188 hasConceptScore W2807345188C31510193 @default.
- W2807345188 hasConceptScore W2807345188C31972630 @default.
- W2807345188 hasConceptScore W2807345188C36289849 @default.
- W2807345188 hasConceptScore W2807345188C41008148 @default.
- W2807345188 hasLocation W28073451881 @default.
- W2807345188 hasOpenAccess W2807345188 @default.
- W2807345188 hasPrimaryLocation W28073451881 @default.
- W2807345188 hasRelatedWork W1548715306 @default.
- W2807345188 hasRelatedWork W1560697087 @default.
- W2807345188 hasRelatedWork W1989039360 @default.
- W2807345188 hasRelatedWork W2060029454 @default.
- W2807345188 hasRelatedWork W2136321227 @default.
- W2807345188 hasRelatedWork W2136485282 @default.
- W2807345188 hasRelatedWork W2146295394 @default.
- W2807345188 hasRelatedWork W2347601237 @default.
- W2807345188 hasRelatedWork W2545171730 @default.
- W2807345188 hasRelatedWork W2908959303 @default.
- W2807345188 isParatext "false" @default.
- W2807345188 isRetracted "false" @default.
- W2807345188 magId "2807345188" @default.
- W2807345188 workType "article" @default.