Product
Help
Pricing
About
Jobs
Log in
Get started
Work
Add to collection
Learning from Unlabeled 3D Environments for Vision-and-Language Navigation
HTML
PDF
Details
Locations
Year:
2022
Type:
conference-paper
Source:
Lecture notes in computer science
Parent work:
Computer Vision – ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part XXXIX
DOI:
10.1007/978-3-031-19842-7_37
Authors:
Shizhe Chen,
Pierre-Louis Guhur,
Makarand Tapaswi,
Cordelia Schmid,
Ivan Laptev
Institutions:
Centre National de la Recherche Scientifique,
Institut national de recherche en sciences et technologies du numérique,
Université Paris Sciences et Lettres,
École Normale Supérieure - PSL,
International Institute of Information Technology, Hyderabad
Language:
English
Topic:
Multimodal Machine Learning Applications
Subfield:
Computer Vision and Pattern Recognition
Field:
Computer Science
Domain:
Physical Sciences
Keywords:
vision-and-language navigation,
HM3D,
pseudo-labeling,
cross-view consistency,
navigation graph,
instruction generation,
language model fine-tuning,
dataset construction,
generalization to unseen environments
show all 9
Open Access status:
green
Funders:
Agence Nationale de la Recherche,
Grand Équipement National De Calcul Intensif
Award:
PaRis Artificial Intelligence Research InstitutE
OpenAlex ID:
W4293329554
FWCI:
3.717
Cites:
56
Cited by:
80
Related to:
10