Fig. 2
Swin Transformer-based YOLOv10 architecture (YOLOv10-ST) for Indian Sign Language recognition. For layer-wise specifications such as attention head count and embedding sizes is described in subsection “YOLOv10-ST”.
Fig. 2 | Scientific Reports
Swin Transformer-based YOLOv10 architecture (YOLOv10-ST) for Indian Sign Language recognition. For layer-wise specifications such as attention head count and embedding sizes is described in subsection “YOLOv10-ST”.
