An efficient action detection from first person vision with attention model

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...

Descripción completa

Detalles Bibliográficos
Autores principales: Straminsky, Axel, Jacobo, Julio, Buemi, María Elena
Formato: Objeto de conferencia
Lenguaje:Inglés
Publicado: 2021
Materias:
Ciencias Informáticas
First Person Vision
Human Computer Interaction
Action Recognition
Attention module
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/141291
http://50jaiio.sadio.org.ar/pdfs/saiv/SAIV-08.pdf
Aporte de:
SEDICI (UNLP) de Universidad Nacional de La Plata
id I19-R120-10915-141291
record_format dspace
institution Universidad Nacional de La Plata
institution_str I-19
repository_str R-120
collection SEDICI (UNLP)
language Inglés
topic Ciencias Informáticas
First Person Vision
Human Computer Interaction
Action Recognition
Attention module
spellingShingle Ciencias Informáticas
First Person Vision
Human Computer Interaction
Action Recognition
Attention module
Straminsky, Axel
Jacobo, Julio
Buemi, María Elena
An efficient action detection from first person vision with attention model
topic_facet Ciencias Informáticas
First Person Vision
Human Computer Interaction
Action Recognition
Attention module
description 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.
format Objeto de conferencia
Objeto de conferencia
author Straminsky, Axel
Jacobo, Julio
Buemi, María Elena
author_facet Straminsky, Axel
Jacobo, Julio
Buemi, María Elena
author_sort Straminsky, Axel
title An efficient action detection from first person vision with attention model
title_short An efficient action detection from first person vision with attention model
title_full An efficient action detection from first person vision with attention model
title_fullStr An efficient action detection from first person vision with attention model
title_full_unstemmed An efficient action detection from first person vision with attention model
title_sort efficient action detection from first person vision with attention model
publishDate 2021
url http://sedici.unlp.edu.ar/handle/10915/141291
http://50jaiio.sadio.org.ar/pdfs/saiv/SAIV-08.pdf
work_keys_str_mv AT straminskyaxel anefficientactiondetectionfromfirstpersonvisionwithattentionmodel
AT jacobojulio anefficientactiondetectionfromfirstpersonvisionwithattentionmodel
AT buemimariaelena anefficientactiondetectionfromfirstpersonvisionwithattentionmodel
AT straminskyaxel efficientactiondetectionfromfirstpersonvisionwithattentionmodel
AT jacobojulio efficientactiondetectionfromfirstpersonvisionwithattentionmodel
AT buemimariaelena efficientactiondetectionfromfirstpersonvisionwithattentionmodel
bdutipo_str Repositorios
_version_ 1764820458712072193

Ejemplares similares