Matches in SemOpenAlex for { <https://semopenalex.org/work/W2886770200> ?p ?o ?g. }
- W2886770200 abstract "Face alignment could be widely used in face recognition, expression recognition, face-based AR applications etc. Cascaded-regression-based face alignment algorithms have been popular in recent years for their low computational costs and impressive results in uncontrolled scenarios. Unfortunately, the size of the trained model is quite large for cascaded-regression-based methods which makes it unsuitable for commercial applications on mobile phones. In this study, the authors proposed a data compression method for the trained model of the supervised descent method (SDM). Firstly, the distribution of the model data was estimated using a non-parametric method. Then an adaptive quantisation algorithm was proposed to quantise the model data. Finally, their adaptive quantisation algorithm was tightly coupled with the SDM training process to fine tune the results. The quantitative experimental results proved that their proposed method could compress the data model to <20% of its original size without hurting the performances. The proposed method has been integrated into a mobile AR application, subjective evaluations proved that the proposed compression method could provide similar visual effects compared with the uncompressed counterpart." @default.
- W2886770200 created "2018-08-22" @default.
- W2886770200 creator A5031146697 @default.
- W2886770200 creator A5047980519 @default.
- W2886770200 creator A5063227132 @default.
- W2886770200 creator A5084459839 @default.
- W2886770200 creator A5090038584 @default.
- W2886770200 date "2018-10-16" @default.
- W2886770200 modified "2023-10-17" @default.
- W2886770200 title "Model compression of SDM‐based face alignment for mobile applications" @default.
- W2886770200 cites W1946919140 @default.
- W2886770200 cites W1976948919 @default.
- W2886770200 cites W1977821862 @default.
- W2886770200 cites W2006902452 @default.
- W2886770200 cites W2038952578 @default.
- W2886770200 cites W2087681821 @default.
- W2886770200 cites W2090530238 @default.
- W2886770200 cites W2111372597 @default.
- W2886770200 cites W2130563197 @default.
- W2886770200 cites W2151103935 @default.
- W2886770200 cites W2152826865 @default.
- W2886770200 cites W2157285372 @default.
- W2886770200 cites W2300242332 @default.
- W2886770200 cites W2465108587 @default.
- W2886770200 cites W2474575620 @default.
- W2886770200 cites W2533542587 @default.
- W2886770200 cites W2962714886 @default.
- W2886770200 cites W2964014798 @default.
- W2886770200 cites W3104792420 @default.
- W2886770200 doi "https://doi.org/10.1049/joe.2018.8294" @default.
- W2886770200 hasPublicationYear "2018" @default.
- W2886770200 type Work @default.
- W2886770200 sameAs 2886770200 @default.
- W2886770200 citedByCount "0" @default.
- W2886770200 crossrefType "journal-article" @default.
- W2886770200 hasAuthorship W2886770200A5031146697 @default.
- W2886770200 hasAuthorship W2886770200A5047980519 @default.
- W2886770200 hasAuthorship W2886770200A5063227132 @default.
- W2886770200 hasAuthorship W2886770200A5084459839 @default.
- W2886770200 hasAuthorship W2886770200A5090038584 @default.
- W2886770200 hasBestOaLocation W28867702001 @default.
- W2886770200 hasConcept C105795698 @default.
- W2886770200 hasConcept C111919701 @default.
- W2886770200 hasConcept C117251300 @default.
- W2886770200 hasConcept C124101348 @default.
- W2886770200 hasConcept C144024400 @default.
- W2886770200 hasConcept C153180895 @default.
- W2886770200 hasConcept C154945302 @default.
- W2886770200 hasConcept C159985019 @default.
- W2886770200 hasConcept C162478608 @default.
- W2886770200 hasConcept C180016635 @default.
- W2886770200 hasConcept C192562407 @default.
- W2886770200 hasConcept C202474056 @default.
- W2886770200 hasConcept C2779304628 @default.
- W2886770200 hasConcept C31510193 @default.
- W2886770200 hasConcept C33923547 @default.
- W2886770200 hasConcept C36289849 @default.
- W2886770200 hasConcept C41008148 @default.
- W2886770200 hasConcept C65483669 @default.
- W2886770200 hasConcept C78548338 @default.
- W2886770200 hasConcept C98045186 @default.
- W2886770200 hasConceptScore W2886770200C105795698 @default.
- W2886770200 hasConceptScore W2886770200C111919701 @default.
- W2886770200 hasConceptScore W2886770200C117251300 @default.
- W2886770200 hasConceptScore W2886770200C124101348 @default.
- W2886770200 hasConceptScore W2886770200C144024400 @default.
- W2886770200 hasConceptScore W2886770200C153180895 @default.
- W2886770200 hasConceptScore W2886770200C154945302 @default.
- W2886770200 hasConceptScore W2886770200C159985019 @default.
- W2886770200 hasConceptScore W2886770200C162478608 @default.
- W2886770200 hasConceptScore W2886770200C180016635 @default.
- W2886770200 hasConceptScore W2886770200C192562407 @default.
- W2886770200 hasConceptScore W2886770200C202474056 @default.
- W2886770200 hasConceptScore W2886770200C2779304628 @default.
- W2886770200 hasConceptScore W2886770200C31510193 @default.
- W2886770200 hasConceptScore W2886770200C33923547 @default.
- W2886770200 hasConceptScore W2886770200C36289849 @default.
- W2886770200 hasConceptScore W2886770200C41008148 @default.
- W2886770200 hasConceptScore W2886770200C65483669 @default.
- W2886770200 hasConceptScore W2886770200C78548338 @default.
- W2886770200 hasConceptScore W2886770200C98045186 @default.
- W2886770200 hasFunder F4320321001 @default.
- W2886770200 hasLocation W28867702001 @default.
- W2886770200 hasOpenAccess W2886770200 @default.
- W2886770200 hasPrimaryLocation W28867702001 @default.
- W2886770200 hasRelatedWork W2096340988 @default.
- W2886770200 hasRelatedWork W2203580091 @default.
- W2886770200 hasRelatedWork W2269861582 @default.
- W2886770200 hasRelatedWork W2347419900 @default.
- W2886770200 hasRelatedWork W2518328974 @default.
- W2886770200 hasRelatedWork W2573076041 @default.
- W2886770200 hasRelatedWork W2789828580 @default.
- W2886770200 hasRelatedWork W2885251243 @default.
- W2886770200 hasRelatedWork W2964571041 @default.
- W2886770200 hasRelatedWork W2986455168 @default.
- W2886770200 hasRelatedWork W3002249742 @default.
- W2886770200 hasRelatedWork W3006122767 @default.
- W2886770200 hasRelatedWork W3013785883 @default.
- W2886770200 hasRelatedWork W3044714827 @default.
- W2886770200 hasRelatedWork W3120577895 @default.