Matches in SemOpenAlex for { <https://semopenalex.org/work/W2010164951> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W2010164951 abstract "Parameterized Appearance Models, such as Active Appearance Models (AAM), Morphable Models, or Boosted Appearance Models, have been extensively used for face alignment. Discriminative methods learn a mapping function between appearance features and shape parameters. Different mapping functions have been studied in the literature, including linear regression, which has proved to perform well when close to the true solution. Despite its easiness, it still suffers from two major drawbacks: 1) It takes the whole data without highlighting relations among different regions of the face, and 2) it is computationally expensive both in time and memory. In this paper, we analyze the covariance of the training data, and propose a way to find related information. By clustering those patches that are related, we reach a noise-reduced regression matrix. Then, we construct a clean mapping matrix, with reduced dimensionality, taking only the relevant training information. Experiments show that this method outperforms linear regression for face alignment." @default.
- W2010164951 created "2016-06-24" @default.
- W2010164951 creator A5023727222 @default.
- W2010164951 creator A5025644152 @default.
- W2010164951 creator A5037470203 @default.
- W2010164951 date "2013-01-01" @default.
- W2010164951 modified "2023-09-24" @default.
- W2010164951 title "Blockwise Linear Regression for Face Alignment" @default.
- W2010164951 cites W1978099323 @default.
- W2010164951 cites W2005310385 @default.
- W2010164951 cites W2032558548 @default.
- W2010164951 cites W2045965808 @default.
- W2010164951 cites W2046399019 @default.
- W2010164951 cites W2053290137 @default.
- W2010164951 cites W2069258060 @default.
- W2010164951 cites W2076017598 @default.
- W2010164951 cites W2114171253 @default.
- W2010164951 cites W2116083845 @default.
- W2010164951 cites W2118508489 @default.
- W2010164951 cites W2133401711 @default.
- W2010164951 cites W2138406903 @default.
- W2010164951 cites W2149476927 @default.
- W2010164951 cites W2152826865 @default.
- W2010164951 cites W2172532449 @default.
- W2010164951 cites W2296659146 @default.
- W2010164951 cites W25944667 @default.
- W2010164951 cites W2868041278 @default.
- W2010164951 cites W3097096317 @default.
- W2010164951 cites W96226593 @default.
- W2010164951 doi "https://doi.org/10.5244/c.27.85" @default.
- W2010164951 hasPublicationYear "2013" @default.
- W2010164951 type Work @default.
- W2010164951 sameAs 2010164951 @default.
- W2010164951 citedByCount "0" @default.
- W2010164951 crossrefType "proceedings-article" @default.
- W2010164951 hasAuthorship W2010164951A5023727222 @default.
- W2010164951 hasAuthorship W2010164951A5025644152 @default.
- W2010164951 hasAuthorship W2010164951A5037470203 @default.
- W2010164951 hasBestOaLocation W20101649511 @default.
- W2010164951 hasConcept C105795698 @default.
- W2010164951 hasConcept C111030470 @default.
- W2010164951 hasConcept C11413529 @default.
- W2010164951 hasConcept C119857082 @default.
- W2010164951 hasConcept C144024400 @default.
- W2010164951 hasConcept C153180895 @default.
- W2010164951 hasConcept C154945302 @default.
- W2010164951 hasConcept C185142706 @default.
- W2010164951 hasConcept C2779304628 @default.
- W2010164951 hasConcept C31510193 @default.
- W2010164951 hasConcept C33923547 @default.
- W2010164951 hasConcept C36289849 @default.
- W2010164951 hasConcept C41008148 @default.
- W2010164951 hasConcept C48921125 @default.
- W2010164951 hasConcept C73555534 @default.
- W2010164951 hasConcept C83546350 @default.
- W2010164951 hasConcept C97931131 @default.
- W2010164951 hasConceptScore W2010164951C105795698 @default.
- W2010164951 hasConceptScore W2010164951C111030470 @default.
- W2010164951 hasConceptScore W2010164951C11413529 @default.
- W2010164951 hasConceptScore W2010164951C119857082 @default.
- W2010164951 hasConceptScore W2010164951C144024400 @default.
- W2010164951 hasConceptScore W2010164951C153180895 @default.
- W2010164951 hasConceptScore W2010164951C154945302 @default.
- W2010164951 hasConceptScore W2010164951C185142706 @default.
- W2010164951 hasConceptScore W2010164951C2779304628 @default.
- W2010164951 hasConceptScore W2010164951C31510193 @default.
- W2010164951 hasConceptScore W2010164951C33923547 @default.
- W2010164951 hasConceptScore W2010164951C36289849 @default.
- W2010164951 hasConceptScore W2010164951C41008148 @default.
- W2010164951 hasConceptScore W2010164951C48921125 @default.
- W2010164951 hasConceptScore W2010164951C73555534 @default.
- W2010164951 hasConceptScore W2010164951C83546350 @default.
- W2010164951 hasConceptScore W2010164951C97931131 @default.
- W2010164951 hasLocation W20101649511 @default.
- W2010164951 hasOpenAccess W2010164951 @default.
- W2010164951 hasPrimaryLocation W20101649511 @default.
- W2010164951 hasRelatedWork W1889383825 @default.
- W2010164951 hasRelatedWork W1976581533 @default.
- W2010164951 hasRelatedWork W1990937109 @default.
- W2010164951 hasRelatedWork W2052317792 @default.
- W2010164951 hasRelatedWork W2146099898 @default.
- W2010164951 hasRelatedWork W2255794050 @default.
- W2010164951 hasRelatedWork W2344361766 @default.
- W2010164951 hasRelatedWork W2520042076 @default.
- W2010164951 hasRelatedWork W2592282254 @default.
- W2010164951 hasRelatedWork W2736728583 @default.
- W2010164951 hasRelatedWork W2736754949 @default.
- W2010164951 hasRelatedWork W2768890224 @default.
- W2010164951 hasRelatedWork W2891775095 @default.
- W2010164951 hasRelatedWork W2913141361 @default.
- W2010164951 hasRelatedWork W3000589903 @default.
- W2010164951 hasRelatedWork W3016892155 @default.
- W2010164951 hasRelatedWork W3105578499 @default.
- W2010164951 hasRelatedWork W3133681769 @default.
- W2010164951 hasRelatedWork W3198178648 @default.
- W2010164951 hasRelatedWork W96226593 @default.
- W2010164951 isParatext "false" @default.
- W2010164951 isRetracted "false" @default.
- W2010164951 magId "2010164951" @default.
- W2010164951 workType "article" @default.