首页> Neural networks : the official journal of the International Neural Network Society> PanoGen++: Domain-adapted text-guided panoramic environment generation for vision-and-language navigation.

PanoGen++: Domain-adapted text-guided panoramic environment generation for vision-and-language navigation.

导出 LinkOut

翻译打印收藏纠错

第一作者： Sen,Wang

第一单位： College of Intelligence and Computing, Tianjin University, Tianjin, 300354, China; Tianjin Artificial Intelligence Innovation Center, Tianjin, 300450, China.

作者： Sen,Wang ^[1] ; Dongliang,Zhou ^[2] ; Liang,Xie ^[3] ; Chao,Xu ^[4] ; Ye,Yan ^[3] ; Erwei,Yin ^[5]

作者单位： College of Intelligence and Computing, Tianjin University, Tianjin, 300354, China; Tianjin Artificial Intelligence Innovation Center, Tianjin, 300450, China. ^[1] Harbin Institute of Technology, Shenzhen, 518055, China. Electronic address: zhoudongliang@hit.edu.cn. ^[2] Defense Innovation Institute, Academy of Military Sciences, Beijing, 100871, China; Tianjin Artificial Intelligence Innovation Center, Tianjin, 300450, China. ^[3] College of Intelligence and Computing, Tianjin University, Tianjin, 300354, China. ^[4] Defense Innovation Institute, Academy of Military Sciences, Beijing, 100871, China; Tianjin Artificial Intelligence Innovation Center, Tianjin, 300450, China. Electronic address: yinerwei1985@gmail.com. ^[5]

关键词 Cross-modal learning Multimedia computing Text-to-image generation Vision-and-language navigation

医学主题词人类(Humans);语言(Language)

DOI 10.1016/j.neunet.2025.107320

PMID 40081273

发布时间 2025-04-28

翻译满意度评价：

准确一般字义偏差语意偏离译文作用小提交