Matches in SemOpenAlex for { <https://semopenalex.org/work/W4308236218> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W4308236218 abstract "Research of head pose estimation in computer vision has been at the center of much attention. This work presents a framework based on adaptive graph convolution network (AGCN) to process both 2D and 3D facial landmarks extracted from the input RGB image. The network has a two-streams (teacher/3D-student/2D streams) architecture, trained with a 3D to 2D knowledge distillation training process, to transfer features of the 3D stream to the 2D stream for performance promotion. Several processing modules, such as depth-denoising for detected 3D landmarks, multi-stream fusion in inference, were also proposed for further increase of the prediction performance and robustness of our proposed method. In experiments, we follow standard protocols (in terms of datasets and metrices) to evaluate our performance. Three datasets 300W-LP, AFLW2000 and BIWI were used. The performance is measured in mean absolute error (MAE). We can achieve better performance compared to most of the state-of-the-art methods." @default.
- W4308236218 created "2022-11-09" @default.
- W4308236218 creator A5018255070 @default.
- W4308236218 creator A5053429054 @default.
- W4308236218 creator A5072408542 @default.
- W4308236218 creator A5075960700 @default.
- W4308236218 date "2022-10-16" @default.
- W4308236218 modified "2023-10-14" @default.
- W4308236218 title "3D Head Pose Estimation Based on Graph Convolutional Network from A Single RGB Image" @default.
- W4308236218 cites W2025768430 @default.
- W4308236218 cites W2082308025 @default.
- W4308236218 cites W2087681821 @default.
- W4308236218 cites W2140397781 @default.
- W4308236218 cites W2589255576 @default.
- W4308236218 cites W2923153064 @default.
- W4308236218 cites W2927589841 @default.
- W4308236218 cites W2948058585 @default.
- W4308236218 cites W2957744218 @default.
- W4308236218 cites W2962970060 @default.
- W4308236218 cites W2963644257 @default.
- W4308236218 cites W2963993755 @default.
- W4308236218 cites W2964014798 @default.
- W4308236218 cites W2964320807 @default.
- W4308236218 cites W3010105474 @default.
- W4308236218 cites W3092336341 @default.
- W4308236218 cites W3104792420 @default.
- W4308236218 cites W3119574651 @default.
- W4308236218 cites W3183842024 @default.
- W4308236218 cites W3193885776 @default.
- W4308236218 doi "https://doi.org/10.1109/icip46576.2022.9897519" @default.
- W4308236218 hasPublicationYear "2022" @default.
- W4308236218 type Work @default.
- W4308236218 citedByCount "0" @default.
- W4308236218 crossrefType "proceedings-article" @default.
- W4308236218 hasAuthorship W4308236218A5018255070 @default.
- W4308236218 hasAuthorship W4308236218A5053429054 @default.
- W4308236218 hasAuthorship W4308236218A5072408542 @default.
- W4308236218 hasAuthorship W4308236218A5075960700 @default.
- W4308236218 hasConcept C104317684 @default.
- W4308236218 hasConcept C132525143 @default.
- W4308236218 hasConcept C153180895 @default.
- W4308236218 hasConcept C154945302 @default.
- W4308236218 hasConcept C185592680 @default.
- W4308236218 hasConcept C2776214188 @default.
- W4308236218 hasConcept C31972630 @default.
- W4308236218 hasConcept C41008148 @default.
- W4308236218 hasConcept C52102323 @default.
- W4308236218 hasConcept C55493867 @default.
- W4308236218 hasConcept C63479239 @default.
- W4308236218 hasConcept C80444323 @default.
- W4308236218 hasConcept C81363708 @default.
- W4308236218 hasConcept C82990744 @default.
- W4308236218 hasConceptScore W4308236218C104317684 @default.
- W4308236218 hasConceptScore W4308236218C132525143 @default.
- W4308236218 hasConceptScore W4308236218C153180895 @default.
- W4308236218 hasConceptScore W4308236218C154945302 @default.
- W4308236218 hasConceptScore W4308236218C185592680 @default.
- W4308236218 hasConceptScore W4308236218C2776214188 @default.
- W4308236218 hasConceptScore W4308236218C31972630 @default.
- W4308236218 hasConceptScore W4308236218C41008148 @default.
- W4308236218 hasConceptScore W4308236218C52102323 @default.
- W4308236218 hasConceptScore W4308236218C55493867 @default.
- W4308236218 hasConceptScore W4308236218C63479239 @default.
- W4308236218 hasConceptScore W4308236218C80444323 @default.
- W4308236218 hasConceptScore W4308236218C81363708 @default.
- W4308236218 hasConceptScore W4308236218C82990744 @default.
- W4308236218 hasLocation W43082362181 @default.
- W4308236218 hasOpenAccess W4308236218 @default.
- W4308236218 hasPrimaryLocation W43082362181 @default.
- W4308236218 hasRelatedWork W2035976912 @default.
- W4308236218 hasRelatedWork W2295870746 @default.
- W4308236218 hasRelatedWork W2822883015 @default.
- W4308236218 hasRelatedWork W2900273708 @default.
- W4308236218 hasRelatedWork W2954208830 @default.
- W4308236218 hasRelatedWork W2956571887 @default.
- W4308236218 hasRelatedWork W2997897143 @default.
- W4308236218 hasRelatedWork W3102636071 @default.
- W4308236218 hasRelatedWork W4200151779 @default.
- W4308236218 hasRelatedWork W4386085515 @default.
- W4308236218 isParatext "false" @default.
- W4308236218 isRetracted "false" @default.
- W4308236218 workType "article" @default.