Cargando…
Outdoor Vision-and-Language Navigation Needs Object-Level Alignment
In the field of embodied AI, vision-and-language navigation (VLN) is a crucial and challenging multi-modal task. Specifically, outdoor VLN involves an agent navigating within a graph-based environment, while simultaneously interpreting information from real-world urban environments and natural langu...
Autores principales: | Sun, Yanjun, Qiu, Yue, Aoki, Yoshimitsu, Kataoka, Hirokatsu |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10346337/ https://www.ncbi.nlm.nih.gov/pubmed/37447877 http://dx.doi.org/10.3390/s23136028 |
Ejemplares similares
-
Vital information matching in vision-and-language navigation
por: Jia, Zixi, et al.
Publicado: (2022) -
Joint Multimodal Embedding and Backtracking Search in Vision-and-Language Navigation
por: Hwang, Jisu, et al.
Publicado: (2021) -
Temporal and Fine-Grained Pedestrian Action Recognition on Driving Recorder Database
por: Kataoka, Hirokatsu, et al.
Publicado: (2018) -
A Robust Indoor/Outdoor Navigation Filter Fusing Data from Vision and Magneto-Inertial Measurement Unit
por: Caruso, David, et al.
Publicado: (2017) -
Outdoor Lighting: Physics, Vision and Perception
por: Schreuder, Duco
Publicado: (2008)