logo
科言猫学术研究的AI总结
language
手机端手机端
  • Phone Feature微信小程序
简体中文简体中文
notice消息通知
博客博客
delete
arrow
返回

Process Adaptive Learning for Visual-Language Navigation

delete2026-01-01
delete0
PRE
AI
G
Gao, Chaoqi
B
Boyuan Zhang
Y
Yahong Han *
DOI：10.1007/978-3-032-04555-3_14delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
视觉语言导航（VLN）要求智能体理解语言指令并在未见环境中导航。智能体需要将语言指令与实时和历史特征对齐以实现目标定位。现有方法难以将指令与环境对齐，且依赖刚性的导航过程，限制了在未见环境中的性能。这源于指令与导航过程之间的脱节，以及终点与指令之间的弱相关性，干扰了导航。因此，我们提出了一种过程自适应跨模态Transformer（PART），它根据指令动态调整导航历史，并将实时动作预测与记忆推理相联系。该方法增强了指令与环境的对齐，同时减轻了重叠轨迹的负面影响。此外，PART采用距离自适应损失函数，以减少对特定轨迹的依赖并强化目标导向学习，提升了在未见环境中的泛化能力。在目标导向的VLN基准REVERIE和逐步VLN基准R2R上，PART超越了以往的最优方法。
Keyword:
Vision and language
Embodied AI
Agent
Navigation

期刊

A
ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING-ICANN 2025, PT IV
IF:
0
论文数:
30
被引数:
0

机构

T
tianjin university
学者数:
8.0W
论文数: 5.8W
被引数: 88
引用论文

引用论文

Multi-Target Embodied Question Answering
err2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
IF0
err2019-06-01
err0
errOAAI
errLicheng Yu; Xinlei Chen; Georgia Gkioxari; Mohit Bansal; Tamara L. Berg; Dhruv Batra
err分享
err收藏
ADAPT: Vision-Language Navigation with Modality-Aligned Action Prompts
err2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
IF0
err2022-06-01
err0
errOAAI
errBingqian Lin; Yi Zhu; Zicong Chen; Xiwen Liang; Jianzhuang Liu; Xiaodan Liang
err分享
err收藏
Bird’s-Eye-View Scene Graph for Vision-Language Navigation
err2023 IEEE/CVF International Conference on Computer Vision (ICCV)
IF0
err2023-10-01
err0
errOAAI
errRui Liu; Xiaohan Wang; Wenguan Wang; Yi Yang
err分享
err收藏
Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigation
err2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
IF0
err2019-06-01
err0
errOAAI
errXin Wang; Qiuyuan Huang; Asli Celikyilmaz; Jianfeng Gao; Dinghan Shen; Yuan-Fang Wang; William Yang Wang; Lei Zhang
err分享
err收藏
GridMM: Grid Memory Map for Vision-and-Language Navigation
err2023 IEEE/CVF International Conference on Computer Vision (ICCV)
IF0
err2023-10-01
err0
errOAAI
errZihan Wang; Xiangyang Li; Jiahao Yang; Yeqi Liu; Shuqiang Jiang
err分享
err收藏
LXMERT: Learning Cross-Modality Encoder Representations from Transformers
errProceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
IF0
err2019-01-01
err0
errOAAI
errHao Tan; Mohit Bansal
err分享
err收藏
Topological Planning with Transformers for Vision-and-Language Navigation
err2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
IF0
err2021-06-01
err0
errOAAI
errKevin Chen; Junshen K. Chen; Jo Chuang; Marynel Vazquez; Silvio Savarese
err分享
err收藏
REVERIE: Remote Embodied Visual Referring Expression in Real Indoor Environments
err2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
IF0
err2020-06-01
err0
errOAAI
errYuankai Qi; Qi Wu; Peter Anderson; Xin Wang; William Yang Wang; Chunhua Shen; Anton van den Hengel
err分享
err收藏
Think Global, Act Local: Dual-scale Graph Transformer for Vision-and-Language Navigation
err2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
IF0
err2022-06-01
err0
errOAAI
errShizhe Chen; Pierre-Louis Guhur; Makarand Tapaswi; Cordelia Schmid; Ivan Laptev
err分享
err收藏
Matterport3D: Learning from RGB-D Data in Indoor Environments
err2017 International Conference on 3D Vision (3DV)
IF0
err2017-10-01
err0
errOAAI
errAngel Chang; Angela Dai; Thomas Funkhouser; Maciej Halber; Matthias Niebner; Manolis Savva; Shuran Song; Andy Zeng; Yinda Zhang
err分享
err收藏
学者 查看更多内容