Grounding human-object interaction to affordance behavior in multimodal datasets.
affordance detection
habitat detection
human-object interaction
multimodal datasets
multimodal grounding
neural models
transformers
Journal
Frontiers in artificial intelligence
ISSN: 2624-8212
Titre abrégé: Front Artif Intell
Pays: Switzerland
ID NLM: 101770551
Informations de publication
Date de publication:
2023
2023
Historique:
received:
30
10
2022
accepted:
03
01
2023
entrez:
16
2
2023
pubmed:
17
2
2023
medline:
17
2
2023
Statut:
epublish
Résumé
While affordance detection and Human-Object interaction (HOI) detection tasks are related, the theoretical foundation of affordances makes it clear that the two are distinct. In particular, researchers in affordances make distinctions between J. J. Gibson's traditional definition of an affordance, "the action possibilities" of the object within the environment, and the definition of a
Identifiants
pubmed: 36793938
doi: 10.3389/frai.2023.1084740
pmc: PMC9923013
doi:
Types de publication
Journal Article
Langues
eng
Pagination
1084740Informations de copyright
Copyright © 2023 Henlein, Gopinath, Krishnaswamy, Mehler and Pustejovsky.
Déclaration de conflit d'intérêts
The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.
Références
Brain Cogn. 2006 Nov;62(2):134-42
pubmed: 16730868
Neurosci Biobehav Rev. 2017 Jun;77:403-417
pubmed: 28432011
Brain Cogn. 2012 Oct;80(1):64-73
pubmed: 22634033
J Exp Psychol Hum Percept Perform. 2010 Aug;36(4):812-24
pubmed: 20695701
Proc Natl Acad Sci U S A. 2020 Oct 20;117(42):25966-25974
pubmed: 32989131
Neuroscience. 2015 Dec 3;310:512-27
pubmed: 26420170
Behav Brain Sci. 2002 Feb;25(1):73-96; discussion 96-144
pubmed: 12625088