Innovations in Science and Technologies Volume 2 Issue 7 (2025) · pp. 415-422
SKELETON-BASED HUMAN ACTION RECOGNITION USING TRANSFORMER MODEL WITH SOFTMAX WITH MULTIDIMENSIONAL CONNECTED WEIGHTS
Marakhimov, Avazjon, Khudaybergenov, Kabul
Abstract
Skeleton-based human action recognition (HAR), particularly from CCTV surveillance footage, has garnered significant interest within the artificial intelligence community. The skeletal modality provides a robust, high-level representation of human motion. Prevailing methods in this domain predominantly rely on a joint-centric approach, modeling the human body as a set of coordinate points. However, this representation often fails to fully capture the rich structural and kinematic relationships essential for accurate motion classification. To address this limitation, we propose a novel method termed SoftMax with Multi-Dimensional Connected Weights. This approach enhances classification by explicitly modeling the informative connections between body joints, represented as skeletal edges. We develop an end-to-end deep learning framework that learns discriminative spatio-temporal representations directly from sequences of skeleton point vectors using Convolutional Neural Networks (CNNs). Results demonstrate that our approach achieves stateof-the-art performance, underscoring the effectiveness of leveraging skeletal edge information and advanced classification techniques for human action recognition.
SoftMax, machine learning, action classification, skeleton motion, human action recognition, convolution, deep learning.
Metadata source: the journal's OAI-PMH archive · Sindex does not store the full text; it links to the source.