RT Journal Article
T1 OG-SGG: Ontology-guided Scene Graph Generation—A case Study in Transfer Learning for Telepresence Robotics
A1 Amodeo Zurbano, Fernando
A1 Caballero, Fernando
A1 Díaz Rodríguez, Natalia
A1 Merino, Luis
K1 Robots
K1 Ontologies
K1 Task analysis
K1 Telepresence
K1 Semantics
K1 Generators
K1 Cognition
AB Scene graph generation from images is a task of great interest to applications such as robotics, because graphs are the main way to represent knowledge about the world and regulate human-robot interactions in tasks such as Visual Question Answering (VQA). Unfortunately, its corresponding area of machine learning is still relatively in its infancy, and the solutions currently offered do not specialize well in concrete usage scenarios. Specifically, they do not take existing “expert” knowledge about the domain world into account; and that might indeed be necessary in order to provide the level of reliability demanded by the use case scenarios. In this paper, we propose an initial approximation to a framework called Ontology-Guided Scene Graph Generation (OG-SGG), that can improve the performance of an existing machine learning based scene graph generator using prior knowledge supplied in the form of an ontology (specifically, using the axioms defined within); and we present results evaluated on a specific scenario founded in telepresence robotics. These results show quantitative and qualitative improvements in the generated scene graphs.
PB IEEE
YR 2022
FD 2022-12-19
LK https://hdl.handle.net/10433/23445
UL https://hdl.handle.net/10433/23445
LA en
NO IEEE Access, vol. 10, pp. 132564-132583, 2022
NO This work was supported in part by Programa Operativo FEDER Andalucia 2014-2020; in part by Consejeria de Economía y Conocimiento (TELEPORTA, UPO-1264631; and DeepBot, PY20_00817); and in part by the project PLEC2021-007868, funded by MCIN/AEI/10.13039/501100011033 and the European Union NextGenerationEU/PRTR. The work of Natalia Díaz-Rodríguez was supported in part by the Spanish Government Juan de la Cierva Incorporación under Contract IJC2019-039152-I, and in part by the Google Research Scholar Programme.
NO Proyectos de investigación: UPO-1264631PY20_00817PLEC2021-007868MCIN/AEI/10.13039/501100011033IJC2019-039152-I
NO Universidad Pablo de Olavide
DS RIO
RD May 9, 2026