Generating vision-language navigation instructions incorporated fine-grained alignment annotations

doi:10.1016/j.inffus.2025.104107

2025-12-30

PRE

DOI：10.1016/j.inffus.2025.104107

原文链接

原文求助

摘要

En 中文

• 生成具有精细跨模态对齐的VLN指令的框架。 • FCA-R2R，首个带有精细对齐标注的大规模VLN数据集。 • FCA-R2R显著提升了VLN智能体的性能。

期刊

Information Fusion

IF:

15.5

论文数:

4.2K

被引数:

2.7W

机构

Chinese Academy of Military Science

学者数:

论文数: 14

被引数: 0

Tianjin Artificial Intelligence Innovation Center

学者数:

论文数: 2

被引数: 0

引用论文

Learning to Follow and Generate Instructions for Language-Capable Navigation

IEEE Transactions on Pattern Analysis and Machine Intelligence

IF0

2024-05-01

PREAI

Xiaohan Wang; Wenguan Wang; Jiayi Shao; Yi Yang

Core Challenges in Embodied Vision-Language Planning 体现视觉语言规划的核心挑战

Journal of Artificial Intelligence Research

IF0

2022-05-28

OAAI

Jonathan Francis; Nariaki Kitamura; Felix Labelle; Xiaopeng Lu; Ingrid Navarro; Jean Oh

PASTS: Progress-aware spatio-temporal transformer speaker for vision-and-language navigation PASTS：一种基于进度感知时空Transformer的视听导航说话人模型

Engineering Applications of Artificial Intelligence

IF0

2024-02-01

OAAI

Liuyi Wang; Chengju Liu; Zongtao He; Shu Li; Qingqing Yan; Huiyi Chen; Qijun Chen

IF0

OAAI

Vision for mobile robot navigation: a survey

IEEE Transactions on Pattern Analysis and Machine Intelligence

IF0

2002-01-01

OAAI

G.N. Desouza; A.C. Kak