Face detection in videos is a fundamental task with significant practical applications in various domains, including security, surveillance, and human-computer interaction. However, it becomes increasingly challenging when dealing with videos that contain various adverse conditions, such as low lighting, occlusions, pose variations, and scale changes. Traditional face detection methods often struggle to provide accurate and reliable results under these challenging conditions. This research explores the application of deep learning algorithms to enhance the performance of face detection in videos under challenging conditions. To validate the effectivenessof our approach, we conduct extensive experiments on benchmark datasets with various challenging conditions. The experimental results demonstrate that our proposed method outperforms state-of-the-art techniques in terms of accuracy, robustness, and computational efficiency. Additionally, we provide an in-depth analysis of the model’s performance under different challenging scenarios, highlighting its ability to handle occlusions, pose variations, and low- resolution frames effectively. Keywords: Face Detection , Deep Learning , Video Analysis, Challenging Conditions , Low lighting , Occlusion .