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{173788,
        author = {Dhanashree B. Shinde and Prathamesh Umesh Chalawadi and Mohammed Husain Zubair Ahmed and Dipak Rajendra Yadav and Yash Vishwanath Adawade},
        title = {Video Summarization using Attention Mechanisms},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {10},
        pages = {1972-1973},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=173788},
        abstract = {Video summarization is a critical task in multimedia analysis, aiming to generate concise and meaningful summaries of lengthy video content. Attention mechanisms, inspired by their success in natural language processing and computer vision, have emerged as powerful tools in this domain. By focusing on salient features and temporally significant frames, attention models can dynamically highlight key moments, enabling more accurate and context-aware summarizations. This paper explores the application of attention mechanisms in video summarization, leveraging temporal and spatial attention to capture essential video dynamics. Experimental results demonstrate that attention-based models outperform traditional methods, offering state of-the-art performance in creating compact, informative summaries suitable for various applications, including content browsing, video indexing, and recommendation systems.},
        keywords = {Video Summarization, Attention Mechanisms, Visual Attention, Audio-Visual Attention, Long Short-Term Memory (LSTM).},
        month = {March},
        }