Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{190704,
        author = {Gagana Jain A and Teerthalakshmi  A M and Akshatha Kiran Bole and Anusha Kaveramma B D and Vijayalakshmi R},
        title = {Human Action Recognition Using Deep Learning},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {8},
        pages = {2015-2017},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=190704},
        abstract = {an outline of, generally eight lines:
HAR has continued to enjoy a considerable number of research interests with broad applications in surveillance, healthcare, human–computer interaction, and sports analytics using deep learning. Deep learning models automatically learn discriminative spatial and temporal features from raw videos or sensor data, reducing the necessity of handcrafted features. CNNs typically extract information of a spatial nature from video frames, while temporal dynamics are modeled with RNNs or LSTM networks. Large benchmark datasets and data augmentation techniques improve the robustness and generalization capability of the models. Recent methods also leverage 3D CNNs and attention mechanisms in order to capture the pattern of motion effectively. In general, deep learning-based HAR systems show promising performance for real-world applications.},
        keywords = {Human Action Recognition, Deep Learning, CNN, LSTM. Video Analysis; Spatio-temporal Features.},
        month = {January},
        }