Subir material

Suba sus trabajos a SEDICI, para mejorar notoriamente su visibilidad e impacto

 

Mostrar el registro sencillo del ítem

dc.date.accessioned 2022-08-30T16:59:31Z
dc.date.available 2022-08-30T16:59:31Z
dc.date.issued 2021
dc.identifier.uri http://sedici.unlp.edu.ar/handle/10915/141291
dc.description.abstract The goal of this work is to propose possible improvements on one of the latest models for Video Action Recognition based on currently existing attention mechanisms. We took a model architecture that uses 2 sub-models in paralell: one based on Optical Flow and the other based on the video itself, and proposed the following improvements: adding mixed precision in the training loop, using a Ranger optimizer instead of SGD, and expanding the Attention Mechanism. The video database used for this work was the EGTEA+ that is a action database of first person videos of daily activities. en
dc.format.extent 36-39 es
dc.language en es
dc.subject First Person Vision es
dc.subject Human Computer Interaction es
dc.subject Action Recognition es
dc.subject Attention module es
dc.title An efficient action detection from first person vision with attention model en
dc.type Objeto de conferencia es
sedici.identifier.uri http://50jaiio.sadio.org.ar/pdfs/saiv/SAIV-08.pdf es
sedici.identifier.issn 2683-8990 es
sedici.creator.person Straminsky, Axel es
sedici.creator.person Jacobo, Julio es
sedici.creator.person Buemi, María Elena es
sedici.subject.materias Ciencias Informáticas es
sedici.description.fulltext true es
mods.originInfo.place Sociedad Argentina de Informática e Investigación Operativa es
sedici.subtype Objeto de conferencia es
sedici.rights.license Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0)
sedici.rights.uri http://creativecommons.org/licenses/by-nc-sa/3.0/
sedici.date.exposure 2021-10
sedici.relation.event II Simposio Argentino de Imágenes y Visión (SAIV 2021) - JAIIO 50 (Modalidad virtual) es
sedici.description.peerReview peer-review es


Descargar archivos

Thumbnail
Documento completo
Descargar archivo (228.3Kb) - PDF
Icon
Enlace externo

Este ítem aparece en la(s) siguiente(s) colección(ones)

Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0) Excepto donde se diga explícitamente, este item se publica bajo la siguiente licencia Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0)