학술논문
Target Region Prediction from Navigation Instructions in Urban Areas / 市街地での移動指示文に基づく目標領域予測
Document Type
Journal Article
Author
Source
Proceedings of the Annual Conference of JSAI. 2023, :2
Subject
Language
Japanese
ISSN
2758-7347
Abstract
In this work, we propose a Trimodal Navigable Region Segmentation Model (TNRSM), which can handle three modalities: image, navigation instruction, and semantic segmentation masks. We validated our model on the Talk2Car-Regseg dataset. The results demonstrated that our method outperformed the baseline method in all evaluation metrics in the Referring Navigable Regions task.