ConvFormer: parameter reduction in transformer models for 3D human pose estimation by leveraging dynamic multi-headed convolutional attention

• Published in: The Visual computer Vol. 40; no. 4; pp. 2555 - 2569
• Main Authors: Diaz-Arias, Alec, Shin, Dmitriy
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.04.2024; Springer Nature B.V
• Subjects: Accuracy; Artificial Intelligence; Computer Graphics; Computer Science; Connectivity; Datasets; Hypotheses; Image Processing and Computer Vision; Mathematical models; Original Article; Parameter identification; Pose estimation; Reduction; Sparsity; Three dimensional models; Transformers; Dynamic convolutions; Monocular motion capture; 3D human pose estimation

Recently, fully-transformer architectures have replaced the defacto convolutional architecture for the 3D human pose estimation task. In this paper, we propose ConvFormer , a novel convolutional transformer that leverages a new dynamic multi-headed convolutional self-attention mechanism for monocula...