Show simple item record

dc.rights.licenseAl consultar y hacer uso de este recurso, está aceptando las condiciones de uso establecidas por los autores.es_CO
dc.contributor.advisorArbeláez Escalante, Pablo Andrés 
dc.contributor.authorRomero Vergara, Andrés Felipe 
dc.coverage.spatialBogotáes_CO
dc.date.accessioned2018-09-28T10:56:43Z
dc.date.available2018-09-28T10:56:43Z
dc.date.issued2017es_CO
dc.identifier.urihttp://hdl.handle.net/1992/13826
dc.descriptionilustraciones a color, fotoses_CO
dc.descriptionIncluye referencias bibliográficases_CO
dc.descriptiontextoes_CO
dc.descriptioncomputadoraes_CO
dc.descriptionrecurso en líneaes_CO
dc.description.abstractWe propose a novel deep convolutional neural network architecture to study the problem of action unit detection. We leverage recent gains in large-scale object recognition by formulating the task of predicting the presence of a specific action unit in a still image as simple image-level binary classification. We first train a convolutional encoder on the problem of multi-view emotion recognition as a high-level representation of facial expressions. We show that our architecture generalizes across views, ethnicity, gender and age by merging and training jointly on three standard emotion recognition datasets: CK+, Bosphorus and RafD. Our system is the first fully multi-view emotion recognizer proposed in the literature. We then extend this shared learned representation with fully-connected layers trained to detect individual action units. Our approach is conceptually simpler and yet significantly more accurate than the best methods based on the dominant paradigm for the study of this problem, which relies on facial landmark detection as an intermediate task. We conduct experiments on the BP4D dataset, the largest and most challenging benchmark currently available for action unit detection, and report an absolute improvement of 16% over the previous state-of-the-artes_CO
dc.formatapplication/pdfes_CO
dc.format.extent19 hojases_CO
dc.language.isoenges_CO
dc.sourceinstname:Universidad de los Andeses_CO
dc.sourcereponame:Repositorio Institucional Sénecaes_CO
dc.titleFacial action unit detection with convolutional neural networkses_CO
dc.typemasterThesises_CO
dc.publisher.programMaestría en Ingeniería Biomédicaes_CO
dc.rights.accessRightsopenAccess
dc.subject.keywordRedes neurales (Computadores) - Investigacioneses_CO
dc.subject.keywordProcesamiento de imágenes - Investigacioneses_CO
dc.subject.keywordSistemas de reconocimiento de configuraciones - Investigacioneses_CO
dc.subject.keywordExpresión facial - Procesamiento de imágenes - Investigacioneses_CO
dc.creator.degreeTesis (Magíster en Ingeniería Biomédica) -- Universidad de los Andeses_CO
dc.identifier.urlhttp://biblioteca.uniandes.edu.co/acepto201699.php?id=9628.pdfes_CO
dc.publisher.facultyFacultad de Ingenieríaes_CO
dc.publisher.departmentDepartamento de Ingeniería Biomédicaes_CO
dc.type.versionpublishedVersion


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record