Grounding semantics in robots for Visual Question Answering

In this thesis I describe an operational implementation of an object detection and description system that incorporates in an end-to-end Visual Question Answering system and evaluated it on two visual question answering datasets for compositional language and elementary visual reasoning.

Detalles Bibliográficos
Autor: Wahle, Björn
Tipo de recurso: tesis de maestría
Fecha de publicación:2019
País:España
Institución:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2117/167445
Acceso en línea:https://hdl.handle.net/2117/167445
Access Level:acceso abierto
Palabra clave:Semantics
Natural language processing (Computer science)
Machine learning
object description
object classification
visual question answering
grounding semantics
image segmentation
Semàntica
Tractament del llenguatge natural (Informàtica)
Aprenentatge automàtic
Àrees temàtiques de la UPC::Informàtica
Descripción
Sumario:In this thesis I describe an operational implementation of an object detection and description system that incorporates in an end-to-end Visual Question Answering system and evaluated it on two visual question answering datasets for compositional language and elementary visual reasoning.