PyCAT4: A Hierarchical Vision Transformer-based Framework for 3D Human Pose Estimation 文章

ArXiv CS.CV2026-05-27NEWSen作者: Zongyou Yang, Jonathan Loo, Yinghan Hou
计算机视觉
查看原文 →
关系图谱

PyCAT4: A Hierarchical Vision Transformer-based Framework for 3D Human Pose Estimation · 相关技术

相关技术

ORMTTEPLAneural networkself-attention mechanismsself-attentiondivide-and-conquer partitioningconvolutioncomputer visionattentionalignmentUCTStanSPAReferring expression comprehension (REC)Parts-of-Speech (POS) tagsMECHISForDiTconvolutional neural networkCNNsANN