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.
| Mualliflar | Marakhimov, Avazjon, Khudaybergenov, Kabul |
|---|---|
| Jurnal | Innovations in Science and Technologies |
| Nashr sanasi | 2025-08-27 |
| Jild | 2 |
| Son | 7 |
| Betlar | 415-422 |
| Til | Ingliz |
SoftMax, machine learning, action classification, skeleton motion, human action recognition, convolution, deep learning.
This article is devoted to current issues and future development opportunities in the field of small business in the Republic. During our research, we examined the work of the world's leading experts and researchers…
Ushbu maqolada O‘zbekiston Respublikasi Davlat aktivlarini boshqarishagentligida bajariladigan baholash xizmatlari ish hajmiga ta’sir etuvchi omillar ko‘p omilliekonometrik model yordamida tahlil qilindi. Tadqiqotda…
Mazkur tadqiqotda pivo ishlab chiqarishning dastlabki bosqichlari bo‘lgan zator tayyorlash va qaynatish jarayonlari uchun bashoratli boshqaruv tizim modellarini ishlab chiqish va ularning algoritmik yechimlarini…
Мазкур мақолада асосий фондлар қийматини баҳолаш жараёнининг шаклланиши ва эволюцияси таҳлил қилинган. Тадқиқотда бозор ислоҳотлари иштирокчилари томонидан асосий фондлар ҳамда уларга нисбатан мулкий ҳуқуқларни…
Ushbu maqolada innovatsion boshqaruv konsepsiyasi va uning asosida rahbar xodimlarda yetakchilik salohiyatini shakllantirish masalalari tahlil qilinadi. Bugungi global raqobat sharoitida tashkilotlarning muvaffaqiyati…
Ушбу мақолада тижорат банкларининг қимматли қоғозлар бозорида эмиссион операцияларининг мазмунига доир назарий ёндашувлар, иқтисодчи олимларнинг қарашлари ва амалдаги муаммолар таҳлил қилинган. Шунингдек, мазкур бозорда…
Мақолада ижтимоий инфратузилманинг (транспорт, алоқа, соғлиқни сақлаш, коммунал хизматлар, ижтимоий сервислар) ривожланиши билан таълим тизими натижалари ўртасидаги икки томонлама боғлиқлик ёритилади. Инфратузилма…
В статье рассмотрены дискуссионные вопросы методов практического измерения уровня теневой экономики в новых условиях трансформации государственных мер по борьбе с теневой экономикой, изучены влияющие факторы…
В данной статье исследуется свойство сходимости онлайн- градиентного обучения для алгоритма обратного распространения ошибки для нейронных сетей прямого распространения с двумя скрытыми слоями с множественными весовыми…
Ushbu maqolada tijorat banklarining qimmatli investitsion jozibadorligini oshirishda banklarning fond bozoridagi faoliyatini takomillashtirish tamoyillariga asoslangan ijtimoiy yo‘naltirilgan bozor sharoitida uning…