FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W1735396802> ?p ?o ?g. }

• W1735396802 abstract "This thesis proposes a novel unified boosting framework. We apply this framework to the several face processing tasks, face detection, facial feature localisation, and pose classification, and use the same boosting algorithm and the same pool of features (local binary features). This is in contrast with the standard approaches that make use of a variety of features and models, for example AdaBoost, cascades of boosted classifiers and Active Appearance Models. The unified boosting framework covers multivariate classification and regression problems and it is achieved by interpreting boosting as optimization in the functional space of the weak learners. Thus a wide range of smooth loss functions can be optimized with the same algorithm. There are two general optimization strategies we propose that extend recent works on TaylorBoost and Variational AdaBoost. The first proposition is an empirical expectation formulation that minimizes the average loss and the second is a variational formulation that includes an additional penalty for large variations between predictions. These two boosting formulations are used to train real-time models using local binary features. This is achieved using look-up-tables as weak learners and multi-block Local Binary Patterns as features. The resulting boosting algorithms are simple, efficient and easily scalable with the available resources. Furthermore, we introduce a novel coarse-to-fine feature selection method to handle high resolution models and a bootstrapping algorithm to sample representative training data from very large pools of data. The proposed approach is evaluated for several face processing tasks. These tasks include frontal face detection (binary classification), facial feature localization (multivariate regression) and pose estimation (multivariate classification). Several studies are performed to assess different optimization algorithms, bootstrapping parametrizations and feature sharing methods (for the multivariate case). The results show good performance for all of these tasks. In addition to this, two other contributions are presented. First, we propose a context-based model for removing the false alarms generated by a given generic face detector. Second, we propose a new face detector that predicts the Jaccard distance between the current location and the ground truth. This allows us to formulate the face detection problem as a regression task." @default.
• W1735396802 created "2016-06-24" @default.
• W1735396802 creator A5036252593 @default.
• W1735396802 date "2012-01-01" @default.
• W1735396802 modified "2023-09-23" @default.
• W1735396802 title "Multivariate Boosting with Look-up Tables for Face Processing" @default.
• W1735396802 doi "https://doi.org/10.5075/epfl-thesis-5374" @default.
• W1735396802 hasPublicationYear "2012" @default.
• W1735396802 type Work @default.
• W1735396802 sameAs 1735396802 @default.
• W1735396802 citedByCount "1" @default.
• W1735396802 countsByYear W17353968022017 @default.
• W1735396802 crossrefType "journal-article" @default.
• W1735396802 hasAuthorship W1735396802A5036252593 @default.
• W1735396802 hasConcept C119857082 @default.
• W1735396802 hasConcept C12267149 @default.
• W1735396802 hasConcept C141404830 @default.
• W1735396802 hasConcept C148483581 @default.
• W1735396802 hasConcept C153180895 @default.
• W1735396802 hasConcept C154945302 @default.
• W1735396802 hasConcept C31510193 @default.
• W1735396802 hasConcept C41008148 @default.
• W1735396802 hasConcept C46686674 @default.
• W1735396802 hasConcept C66905080 @default.
• W1735396802 hasConcept C95623464 @default.
• W1735396802 hasConceptScore W1735396802C119857082 @default.
• W1735396802 hasConceptScore W1735396802C12267149 @default.
• W1735396802 hasConceptScore W1735396802C141404830 @default.
• W1735396802 hasConceptScore W1735396802C148483581 @default.
• W1735396802 hasConceptScore W1735396802C153180895 @default.
• W1735396802 hasConceptScore W1735396802C154945302 @default.
• W1735396802 hasConceptScore W1735396802C31510193 @default.
• W1735396802 hasConceptScore W1735396802C41008148 @default.
• W1735396802 hasConceptScore W1735396802C46686674 @default.
• W1735396802 hasConceptScore W1735396802C66905080 @default.
• W1735396802 hasConceptScore W1735396802C95623464 @default.
• W1735396802 hasLocation W17353968021 @default.
• W1735396802 hasOpenAccess W1735396802 @default.
• W1735396802 hasPrimaryLocation W17353968021 @default.
• W1735396802 hasRelatedWork W1255322248 @default.
• W1735396802 hasRelatedWork W1555325287 @default.
• W1735396802 hasRelatedWork W1584608784 @default.
• W1735396802 hasRelatedWork W1607790861 @default.
• W1735396802 hasRelatedWork W165429482 @default.
• W1735396802 hasRelatedWork W1997754250 @default.
• W1735396802 hasRelatedWork W2026629623 @default.
• W1735396802 hasRelatedWork W2031265081 @default.
• W1735396802 hasRelatedWork W2044849712 @default.
• W1735396802 hasRelatedWork W2049324684 @default.
• W1735396802 hasRelatedWork W2051065934 @default.
• W1735396802 hasRelatedWork W2097062438 @default.
• W1735396802 hasRelatedWork W2122702209 @default.
• W1735396802 hasRelatedWork W2166016745 @default.
• W1735396802 hasRelatedWork W2299646912 @default.
• W1735396802 hasRelatedWork W2334892849 @default.
• W1735396802 hasRelatedWork W2344769595 @default.
• W1735396802 hasRelatedWork W2914907652 @default.
• W1735396802 hasRelatedWork W3006991460 @default.
• W1735396802 hasRelatedWork W3046500874 @default.
• W1735396802 isParatext "false" @default.
• W1735396802 isRetracted "false" @default.
• W1735396802 magId "1735396802" @default.
• W1735396802 workType "article" @default.