4 papers
SignVerse-2M: A Two-Million-Clip Pose-Native Universe of 55+ Sign Languages
Sen Fang, Hongbin Zhong, Yanxin Zhang +1
Existing large-scale sign language resources typically provide supervision only at the level of raw video-text alignment and are often produced in laboratory settings. While such r…
Stable Signer: Hierarchical Sign Language Generative Model
Sen Fang, Yalin Feng, Hongbin Zhong +2
Sign Language Production (SLP) is the process of converting the complex input text into a real video. Most previous works focused on the Text2Gloss, Gloss2Pose, Pose2Vid stages, an…
StreamFlow: Theory, Algorithm, and Implementation for High-Efficiency Rectified Flow Generation
Sen Fang, Hongbin Zhong, Yalin Feng +2
New technologies such as Rectified Flow and Flow Matching have significantly improved the performance of generative models in the past two years, especially in terms of control acc…
SignDiff: Diffusion Model for American Sign Language Production
Sen Fang, Chunyu Sui, Yanghao Zhou +4
In this paper, we propose a dual-condition diffusion pre-training model named SignDiff that can generate human sign language speakers from a skeleton pose. SignDiff has a novel Fra…