Unsupervised video anomaly detection approaches often demand complex models and substantial computational resources for effective performance. In contrast, we introduce a supervised and end-to-end trainable deep learning approach that leverages both performance and computational efficiency by harnessing frame-level annotated data. The framework begins with the utilization of an Inception encoder network in the initial stage to learn feature representations. Notably, the Inception network’s proficiency in capturing intricate and high-level features in frames seamlessly extends to the analysis of video data. By using these extracted features, the model excels in identifying deviations from learned patterns, making it highly adept at detecting anomalies in video sequences. The subsequent stage involves a sequence of fully connected layers followed by a classifier that is responsible for classifying input frames as either normal or anomalous based on the extracted features. To thoroughly validate this methodology, extensive experiments are carried out on widely used benchmark datasets. These evaluations involved comprehensive comparisons with contemporary approaches in the field. The experimental findings consistently validate the efficacy and efficiency of the proposed approach, underscoring its outstanding accuracy in identifying anomalies. Additionally, the approach operates with significantly reduced computational overhead, rendering it an appealing solution for real-world applications that demand timely and precise anomaly detection.