返回全部动态
TransSLR：用于手语识别的轻量级 Transformer
原标题：TransSLR: A Lightweight Transformer for Sign Language Recognition
AI 摘要
arXiv 论文提出 TransSLR，一种轻量级时间 Transformer 编码器，用于手语识别，针对中非手语（CASL）等低资源语言。TransSLR 在 CASL-W60 基准上达到 80.39% 的准确率，比之前最好成绩提升 10.46%，且计算开销低，适合资源受限环境。
以上摘要由 AI 生成，可能存在误差。事实请以原文为准。
正文节选
Computer Science > Computer Vision and Pattern Recognition Title:TransSLR: A Lightweight Transformer for Sign Language Recognition View PDF HTML (experimental) Abstract:Automated Sign Language Recognition for under-represented languages remains a largely unsolved problem. Central African Sign Language (CASL) exemplifies this gap: the only available bench-mark, CASL-W60, has a best reported accuracy of 69.93%, and we show that the common heuristic of fine-tuning high-resource models f
发布时间：2026-08-10 12:00
抓取时间：2026-08-10 12:26
来源机构：arXiv