Matches in SemOpenAlex for { <https://semopenalex.org/work/W2577157695> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W2577157695 abstract "Collecting and labeling various and relevant data for training automatic facial information prediction systems is both hard and time-consuming. As a consequence, available data is often of limited size compared to the difficulty of the prediction tasks. This makes overfitting a particularly important issue in several face-related machine learning applications. In this PhD, we introduce a novel method for multi-dimensional label regression, namely Hard Multi-Task Metric Learning for Kernel Regression (H-MT-MLKR). Our proposed method has been designed taking a particular focus on overfitting reduction. The Metric Learning for Kernel Regression method (MLKR) that has been proposed by Kilian Q. Weinberger in 2007 aims at learning a subspace for minimizing the quadratic training error of a Nadaraya-Watson estimator. In our method, we extend MLKR for multi-dimensional label regression by adding a novel multi-task regularization that reduces the degrees of freedom of the learned model along with potential overfitting. We evaluate our regression method on two different applications, namely landmark localization and Action Unit intensity prediction. We also present our work on automatic emotion prediction in a continuous space which is based on the Nadaraya-Watson estimator as well. Two of our frameworks let us win international data science challenges, namely the Audio-Visual Emotion Challenge (AVEC’12) and the fully continuous Facial Expression Recognition and Analysis challenge (FERA’15)." @default.
- W2577157695 created "2017-01-26" @default.
- W2577157695 creator A5054982466 @default.
- W2577157695 date "2016-03-08" @default.
- W2577157695 modified "2023-09-27" @default.
- W2577157695 title "Reading Faces. Using Hard Multi-Task Metric Learning for Kernel Regression" @default.
- W2577157695 hasPublicationYear "2016" @default.
- W2577157695 type Work @default.
- W2577157695 sameAs 2577157695 @default.
- W2577157695 citedByCount "0" @default.
- W2577157695 crossrefType "dissertation" @default.
- W2577157695 hasAuthorship W2577157695A5054982466 @default.
- W2577157695 hasConcept C105795698 @default.
- W2577157695 hasConcept C114614502 @default.
- W2577157695 hasConcept C119857082 @default.
- W2577157695 hasConcept C122280245 @default.
- W2577157695 hasConcept C12267149 @default.
- W2577157695 hasConcept C127413603 @default.
- W2577157695 hasConcept C153180895 @default.
- W2577157695 hasConcept C154945302 @default.
- W2577157695 hasConcept C176217482 @default.
- W2577157695 hasConcept C185429906 @default.
- W2577157695 hasConcept C200695384 @default.
- W2577157695 hasConcept C21547014 @default.
- W2577157695 hasConcept C22019652 @default.
- W2577157695 hasConcept C33923547 @default.
- W2577157695 hasConcept C41008148 @default.
- W2577157695 hasConcept C50644808 @default.
- W2577157695 hasConcept C70518039 @default.
- W2577157695 hasConcept C74193536 @default.
- W2577157695 hasConcept C83546350 @default.
- W2577157695 hasConceptScore W2577157695C105795698 @default.
- W2577157695 hasConceptScore W2577157695C114614502 @default.
- W2577157695 hasConceptScore W2577157695C119857082 @default.
- W2577157695 hasConceptScore W2577157695C122280245 @default.
- W2577157695 hasConceptScore W2577157695C12267149 @default.
- W2577157695 hasConceptScore W2577157695C127413603 @default.
- W2577157695 hasConceptScore W2577157695C153180895 @default.
- W2577157695 hasConceptScore W2577157695C154945302 @default.
- W2577157695 hasConceptScore W2577157695C176217482 @default.
- W2577157695 hasConceptScore W2577157695C185429906 @default.
- W2577157695 hasConceptScore W2577157695C200695384 @default.
- W2577157695 hasConceptScore W2577157695C21547014 @default.
- W2577157695 hasConceptScore W2577157695C22019652 @default.
- W2577157695 hasConceptScore W2577157695C33923547 @default.
- W2577157695 hasConceptScore W2577157695C41008148 @default.
- W2577157695 hasConceptScore W2577157695C50644808 @default.
- W2577157695 hasConceptScore W2577157695C70518039 @default.
- W2577157695 hasConceptScore W2577157695C74193536 @default.
- W2577157695 hasConceptScore W2577157695C83546350 @default.
- W2577157695 hasLocation W25771576951 @default.
- W2577157695 hasOpenAccess W2577157695 @default.
- W2577157695 hasPrimaryLocation W25771576951 @default.
- W2577157695 hasRelatedWork W1495279923 @default.
- W2577157695 hasRelatedWork W1527106129 @default.
- W2577157695 hasRelatedWork W1553692878 @default.
- W2577157695 hasRelatedWork W1592227380 @default.
- W2577157695 hasRelatedWork W1991469820 @default.
- W2577157695 hasRelatedWork W2115403315 @default.
- W2577157695 hasRelatedWork W2124049598 @default.
- W2577157695 hasRelatedWork W2133675239 @default.
- W2577157695 hasRelatedWork W2141199622 @default.
- W2577157695 hasRelatedWork W2151386286 @default.
- W2577157695 hasRelatedWork W2218060551 @default.
- W2577157695 hasRelatedWork W2405171085 @default.
- W2577157695 hasRelatedWork W2578519904 @default.
- W2577157695 hasRelatedWork W2727412051 @default.
- W2577157695 hasRelatedWork W2736208942 @default.
- W2577157695 hasRelatedWork W2928496594 @default.
- W2577157695 hasRelatedWork W2952715980 @default.
- W2577157695 hasRelatedWork W2972997310 @default.
- W2577157695 hasRelatedWork W3082369885 @default.
- W2577157695 hasRelatedWork W3092900959 @default.
- W2577157695 isParatext "false" @default.
- W2577157695 isRetracted "false" @default.
- W2577157695 magId "2577157695" @default.
- W2577157695 workType "dissertation" @default.