Faryal Shamsi

Faryal Shamsi

Auto-generated profile, based on publicly available information

Faryal Shamsi

Department of Computer Science, Sukkur IBA University, Sukkur, Sindh, Pakistan

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
3 January 2025 in IEEE Access
Verified
Journal Article
Open access
FSFaryal Shamsi
Faryal Shamsi
ISIrum Sindhu
Irum Sindhu
With the rapid growth of social media platforms, the volume of video content on the internet has increased exponentially. YouTube, the most popular social networking platform, manages over 500 hours of video uploads every minute. Indexing, retrieving, navigating, and searching this vast collection of video data pose significant challenges. Existing video indexing techniques largely depend on user-provided textual annotations such as titles, descriptions, and hashtags. However, this information is often inaccurate or irrelevant to the actual video content. In this context, automation is essential for accurately understanding video content and effectively managing video files. Over the years, various video summarization methods have been proposed, accompanied by several review papers. However, the literature on video summarization remains somewhat fragmented. Many review studies reference outdated methodologies that have since been superseded by advancements in fields like deep learning. In this paper, we systematically reviewed over 300 research papers and shortlisted 44 studies based on strict quality criteria. Our detailed search strategy and review methodology are thoroughly discussed in the paper. This review specifically focuses on summarizing video summarization techniques that utilize deep learning. Additionally, it highlights the practical applications of each model and discusses relevant datasets. The systematic literature review presented here is valuable for new researchers exploring the intersection of deep learning and multimedia content, particularly video data. The insights provided can help address challenges related to video indexing and retrieval for social networking platforms.