SignVerse-2M：覆盖 55+ 种手语的 200 万段姿态原生数据集
SignVerse-2M: A Two-Million-Clip Pose-Native Universe of 55+ Sign Languages
AI 导读
研究者发布 SignVerse-2M 多语言手语数据集，包含约 200 万段来自 55+ 种手语的姿态片段，全部用统一的 DWPose 管线将身体、手部和面部运动转为关键点表示。数据集同时开源处理管线、任务定义及 SignDW Transformer 基线，实验表明其支持多语言文本到姿态建模，生成的姿态可直接驱动多种姿态条件渲染系统。
正文 · 原文
Abstract:Large-scale sign language resources usually pair RGB videos with text and support recognition, translation, and generation. However, RGB frames contain backgrounds, clothing, and other appearance information unrelated to signing motion. Representing the videos as whole-body keypoints such as DWPose removes much of this variation, produces a compact description of body, hand, and facial movement, and matches the input used by recent pose-guided video models. Existing datasets do not provide this representation at scale for in-the-wild sign language videos. We present SignVerse-2M, a multilingual dataset containing approximately two million pose clips from more than 55 sign languages. We process publicly available sign language videos with a shared DWPose pipeline, representing body, hand, and facial motion in the same keypoint format across all clips. The source videos include diverse signers, viewpoints, and recording environments. We also release the processing pipeline, task definitions, and SignDW Transformer baselines. Experiments show that the data supports multilingual text-to-pose modeling and that the generated poses can directly drive several recent pose-conditioned rendering systems.
| Comments: | 13 pages. Project Page at: this https URL |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Computation and Language (cs.CL) |
| Cite as: | arXiv:2605.01720 [cs.CV] |
| (or arXiv:2605.01720v4 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2605.01720 arXiv-issued DOI via DataCite |
Submission history
From: Sen Fang [view email]
[v1]
Sun, 3 May 2026 05:26:26 UTC (25,638 KB)
[v2]
Wed, 6 May 2026 16:29:09 UTC (25,638 KB)
[v3]
Fri, 7 Aug 2026 01:18:00 UTC (25,465 KB)
[v4]
Sat, 24 Oct 2026 00:29:29 UTC (19,161 KB)
来源：arXiv cs.AI · arxiv.org