Název:	Balanced Feature Fusion for Grouped 3D Pose Estimation
Autoři:	Peng, Jihua Zhou, Yanghong Mok, P.Y.
Citace zdrojového dokumentu:	WSCG 2022: full papers proceedings: 30. International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision, p. 103-108.
Datum vydání:	2022
Nakladatel:	Václav Skala - UNION Agency
Typ dokumentu:	conferenceObject
URI:	http://hdl.handle.net/11025/49583
ISBN:	978-80-86943-33-6
ISSN:	2464-4617
Klíčová slova:	3D odhad lidské pozice;seskupení funkce fúze;anatomické vztahy
Klíčová slova v dalším jazyce:	3D human pose estimation;grouping feature fusion;anatomical relationships
Abstrakt v dalším jazyce:	3D human pose estimation by grouping human body joints according to anatomical relationship is currently a popular and effective method. For grouped pose estimation, fusing features of different groups together effectively is the key step to ensure the integrity of whole body pose prediction. However, the existing methods for feature fusion between groups require a large number of network parameters, and thus are often computational expensive. In this paper, we propose a simple yet efficient feature fusion method that can improve the accuracy of pose esti- mation while require fewer parameters and less calculations. Experiments have shown that our proposed network outperforms previous state-of-the-art results on Human3.6M dataset.
Práva:	© Václav Skala - UNION Agency
Vyskytuje se v kolekcích:	WSCG 2022: Full Papers Proceedings

Všechny záznamy v DSpace jsou chráněny autorskými právy, všechna práva vyhrazena.