Matches in SemOpenAlex for { <https://semopenalex.org/work/W1915668717> ?p ?o ?g. }
- W1915668717 abstract "Cascaded regression approaches have been recently shown to achieve state-of-the-art performance for many computer vision tasks. Beyond its connection to boosting, cascaded regression has been interpreted as a learning-based approach to iterative optimization methods like the Newton's method. However, in prior work, the connection to optimization theory is limited only in learning a mapping from image features to problem parameters. In this paper, we consider the problem of facial deformable model fitting using cascaded regression and make the following contributions: (a) We propose regression to learn a sequence of averaged Jacobian and Hessian matrices from data, and from them descent directions in a fashion inspired by Gauss-Newton optimization. (b) We show that the optimization problem in hand has structure and devise a learning strategy for a cascaded regression approach that takes the problem structure into account. By doing so, the proposed method learns and employs a sequence of averaged Jacobians and descent directions in a subspace orthogonal to the facial appearance variation; hence, we call it Project-Out Cascaded Regression (PO-CR). (c) Based on the principles of PO-CR, we built a face alignment system that produces remarkably accurate results on the challenging iBUG data set outperforming previously proposed systems by a large margin. Code for our system is available from http://www.cs.nott.ac.uk/~yzt/." @default.
- W1915668717 created "2016-06-24" @default.
- W1915668717 creator A5024224610 @default.
- W1915668717 date "2015-06-01" @default.
- W1915668717 modified "2023-10-16" @default.
- W1915668717 title "Project-Out Cascaded Regression with an application to face alignment" @default.
- W1915668717 cites W1678356000 @default.
- W1915668717 cites W1964357740 @default.
- W1915668717 cites W1974744233 @default.
- W1915668717 cites W1976948919 @default.
- W1915668717 cites W1977821862 @default.
- W1915668717 cites W1998294030 @default.
- W1915668717 cites W2006902452 @default.
- W1915668717 cites W2032558548 @default.
- W1915668717 cites W2035379092 @default.
- W1915668717 cites W2036196300 @default.
- W1915668717 cites W2036868818 @default.
- W1915668717 cites W2038952578 @default.
- W1915668717 cites W2076017598 @default.
- W1915668717 cites W2082308025 @default.
- W1915668717 cites W2087681821 @default.
- W1915668717 cites W2101467695 @default.
- W1915668717 cites W2103876808 @default.
- W1915668717 cites W2116277445 @default.
- W1915668717 cites W2121684305 @default.
- W1915668717 cites W2124313187 @default.
- W1915668717 cites W2130563197 @default.
- W1915668717 cites W2133192850 @default.
- W1915668717 cites W2136000821 @default.
- W1915668717 cites W2143451044 @default.
- W1915668717 cites W2149829493 @default.
- W1915668717 cites W2151103935 @default.
- W1915668717 cites W2152826865 @default.
- W1915668717 cites W2157285372 @default.
- W1915668717 cites W2163998463 @default.
- W1915668717 cites W2170800077 @default.
- W1915668717 cites W2187714658 @default.
- W1915668717 cites W2219827282 @default.
- W1915668717 cites W4250589301 @default.
- W1915668717 doi "https://doi.org/10.1109/cvpr.2015.7298989" @default.
- W1915668717 hasPublicationYear "2015" @default.
- W1915668717 type Work @default.
- W1915668717 sameAs 1915668717 @default.
- W1915668717 citedByCount "179" @default.
- W1915668717 countsByYear W19156687172015 @default.
- W1915668717 countsByYear W19156687172016 @default.
- W1915668717 countsByYear W19156687172017 @default.
- W1915668717 countsByYear W19156687172018 @default.
- W1915668717 countsByYear W19156687172019 @default.
- W1915668717 countsByYear W19156687172020 @default.
- W1915668717 countsByYear W19156687172021 @default.
- W1915668717 countsByYear W19156687172022 @default.
- W1915668717 countsByYear W19156687172023 @default.
- W1915668717 crossrefType "proceedings-article" @default.
- W1915668717 hasAuthorship W1915668717A5024224610 @default.
- W1915668717 hasBestOaLocation W19156687172 @default.
- W1915668717 hasConcept C105795698 @default.
- W1915668717 hasConcept C11413529 @default.
- W1915668717 hasConcept C119857082 @default.
- W1915668717 hasConcept C126255220 @default.
- W1915668717 hasConcept C137836250 @default.
- W1915668717 hasConcept C153180895 @default.
- W1915668717 hasConcept C153258448 @default.
- W1915668717 hasConcept C154945302 @default.
- W1915668717 hasConcept C157553263 @default.
- W1915668717 hasConcept C200331156 @default.
- W1915668717 hasConcept C203616005 @default.
- W1915668717 hasConcept C28826006 @default.
- W1915668717 hasConcept C32834561 @default.
- W1915668717 hasConcept C33923547 @default.
- W1915668717 hasConcept C41008148 @default.
- W1915668717 hasConcept C46686674 @default.
- W1915668717 hasConcept C50644808 @default.
- W1915668717 hasConcept C774472 @default.
- W1915668717 hasConcept C83546350 @default.
- W1915668717 hasConceptScore W1915668717C105795698 @default.
- W1915668717 hasConceptScore W1915668717C11413529 @default.
- W1915668717 hasConceptScore W1915668717C119857082 @default.
- W1915668717 hasConceptScore W1915668717C126255220 @default.
- W1915668717 hasConceptScore W1915668717C137836250 @default.
- W1915668717 hasConceptScore W1915668717C153180895 @default.
- W1915668717 hasConceptScore W1915668717C153258448 @default.
- W1915668717 hasConceptScore W1915668717C154945302 @default.
- W1915668717 hasConceptScore W1915668717C157553263 @default.
- W1915668717 hasConceptScore W1915668717C200331156 @default.
- W1915668717 hasConceptScore W1915668717C203616005 @default.
- W1915668717 hasConceptScore W1915668717C28826006 @default.
- W1915668717 hasConceptScore W1915668717C32834561 @default.
- W1915668717 hasConceptScore W1915668717C33923547 @default.
- W1915668717 hasConceptScore W1915668717C41008148 @default.
- W1915668717 hasConceptScore W1915668717C46686674 @default.
- W1915668717 hasConceptScore W1915668717C50644808 @default.
- W1915668717 hasConceptScore W1915668717C774472 @default.
- W1915668717 hasConceptScore W1915668717C83546350 @default.
- W1915668717 hasLocation W19156687171 @default.
- W1915668717 hasLocation W19156687172 @default.
- W1915668717 hasLocation W19156687173 @default.
- W1915668717 hasLocation W19156687174 @default.
- W1915668717 hasOpenAccess W1915668717 @default.
- W1915668717 hasPrimaryLocation W19156687171 @default.