Matches in SemOpenAlex for { <https://semopenalex.org/work/W4308236273> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W4308236273 abstract "Recovering 3D geometry from a single-view 2D face image is an ill-posed task full of various challenges, especially under occlusion conditions commonly seen with large poses, while partial facial information missing makes the burden much heavier. Although existing methods could solve this problem in the end-to-end fashion, they still have limited performance in the occluded scenes. It is intuitively for many methods to depress the influence of those occluded regions for reconstruction. But we propose an occlusion-sensitive weighting mechanism for balancing the contributions among occluded and non-occluded regions. Meanwhile, considering no dataset contains various occlusions for learning, the data augmentation technique is exploited to expand the training dataset, which further facilitates the learning of the occlusion-sensitive deep network. Extensive experiments on two challenging datasets validate the advanced performance of our method for both 3D face reconstruction and face alignment. <sup xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>1</sup>" @default.
- W4308236273 created "2022-11-09" @default.
- W4308236273 creator A5005674481 @default.
- W4308236273 creator A5009887822 @default.
- W4308236273 creator A5021604612 @default.
- W4308236273 creator A5034985240 @default.
- W4308236273 creator A5037677450 @default.
- W4308236273 date "2022-10-16" @default.
- W4308236273 modified "2023-10-06" @default.
- W4308236273 title "Exploring Occlusion-Sensitive Deep Network for Single-View 3D Face Reconstruction" @default.
- W4308236273 cites W2012885984 @default.
- W4308236273 cites W2168722300 @default.
- W4308236273 cites W2237250383 @default.
- W4308236273 cites W2265959009 @default.
- W4308236273 cites W2560722161 @default.
- W4308236273 cites W2963253045 @default.
- W4308236273 cites W2964014798 @default.
- W4308236273 cites W2990935086 @default.
- W4308236273 cites W2995982174 @default.
- W4308236273 cites W3163434270 @default.
- W4308236273 cites W3182318349 @default.
- W4308236273 doi "https://doi.org/10.1109/icip46576.2022.9897209" @default.
- W4308236273 hasPublicationYear "2022" @default.
- W4308236273 type Work @default.
- W4308236273 citedByCount "2" @default.
- W4308236273 countsByYear W43082362732023 @default.
- W4308236273 crossrefType "proceedings-article" @default.
- W4308236273 hasAuthorship W4308236273A5005674481 @default.
- W4308236273 hasAuthorship W4308236273A5009887822 @default.
- W4308236273 hasAuthorship W4308236273A5021604612 @default.
- W4308236273 hasAuthorship W4308236273A5034985240 @default.
- W4308236273 hasAuthorship W4308236273A5037677450 @default.
- W4308236273 hasConcept C108583219 @default.
- W4308236273 hasConcept C126838900 @default.
- W4308236273 hasConcept C141379421 @default.
- W4308236273 hasConcept C144024400 @default.
- W4308236273 hasConcept C153180895 @default.
- W4308236273 hasConcept C154945302 @default.
- W4308236273 hasConcept C162324750 @default.
- W4308236273 hasConcept C164705383 @default.
- W4308236273 hasConcept C183115368 @default.
- W4308236273 hasConcept C187736073 @default.
- W4308236273 hasConcept C2776268601 @default.
- W4308236273 hasConcept C2779304628 @default.
- W4308236273 hasConcept C2780451532 @default.
- W4308236273 hasConcept C31510193 @default.
- W4308236273 hasConcept C31972630 @default.
- W4308236273 hasConcept C36289849 @default.
- W4308236273 hasConcept C41008148 @default.
- W4308236273 hasConcept C71924100 @default.
- W4308236273 hasConceptScore W4308236273C108583219 @default.
- W4308236273 hasConceptScore W4308236273C126838900 @default.
- W4308236273 hasConceptScore W4308236273C141379421 @default.
- W4308236273 hasConceptScore W4308236273C144024400 @default.
- W4308236273 hasConceptScore W4308236273C153180895 @default.
- W4308236273 hasConceptScore W4308236273C154945302 @default.
- W4308236273 hasConceptScore W4308236273C162324750 @default.
- W4308236273 hasConceptScore W4308236273C164705383 @default.
- W4308236273 hasConceptScore W4308236273C183115368 @default.
- W4308236273 hasConceptScore W4308236273C187736073 @default.
- W4308236273 hasConceptScore W4308236273C2776268601 @default.
- W4308236273 hasConceptScore W4308236273C2779304628 @default.
- W4308236273 hasConceptScore W4308236273C2780451532 @default.
- W4308236273 hasConceptScore W4308236273C31510193 @default.
- W4308236273 hasConceptScore W4308236273C31972630 @default.
- W4308236273 hasConceptScore W4308236273C36289849 @default.
- W4308236273 hasConceptScore W4308236273C41008148 @default.
- W4308236273 hasConceptScore W4308236273C71924100 @default.
- W4308236273 hasFunder F4320321001 @default.
- W4308236273 hasFunder F4320321543 @default.
- W4308236273 hasFunder F4320322769 @default.
- W4308236273 hasLocation W43082362731 @default.
- W4308236273 hasOpenAccess W4308236273 @default.
- W4308236273 hasPrimaryLocation W43082362731 @default.
- W4308236273 hasRelatedWork W1775397219 @default.
- W4308236273 hasRelatedWork W1899364738 @default.
- W4308236273 hasRelatedWork W2103413230 @default.
- W4308236273 hasRelatedWork W2139960062 @default.
- W4308236273 hasRelatedWork W2161437355 @default.
- W4308236273 hasRelatedWork W2347601237 @default.
- W4308236273 hasRelatedWork W2765462099 @default.
- W4308236273 hasRelatedWork W2897995864 @default.
- W4308236273 hasRelatedWork W2908959303 @default.
- W4308236273 hasRelatedWork W43171467 @default.
- W4308236273 isParatext "false" @default.
- W4308236273 isRetracted "false" @default.
- W4308236273 workType "article" @default.