SignDino: Self-Supervised Sign Language Representation Learning via Temporal-Axis Self-Distillation
SignDino, a self-supervised sign-video encoder that moves the DINOv3 student--teacher recipe from the spatial domain of image crops to the temporal domain of tracked sign streams, provides a strong public self-supervised representation and shows competitive or state-of-the-art performance under matched downstream evalu...
Jun-Yi Hu, Zhe-Wen He, Hao Huang et al.
· 0 citations