HumanPoseNet: An all-transformer architecture for pose estimation with efficient patch expansion and attentional feature refinement

Varun Gupta, Ankit Yadav, Dinesh Kumar Vishwakarma. HumanPoseNet: An all-transformer architecture for pose estimation with efficient patch expansion and attentional feature refinement. Expert Syst. Appl., 244:122894, 2024. [doi]

Abstract

Abstract is missing.