Face recognition has become a major research area due to the rapid growth of intelligent software applications. However, reliable face identification remains challenging because human facial features vary significantly under different conditions. Originating from pattern recognition, image processing, and computer vision, modern face recognition continues to advance through new algorithms and learning-based approaches. This paper describes and analyzes the existing literature regarding facial recognition and surveillance systems. It describes and explains the principles underlying facial recognition and surveillance in a general sense and analyzes the most significant application domains. Furthermore, it describes and analyzes the most relevant and widely used benchmark datasets that can be used to measure the recognition and surveillance performance of such systems. We also discuss and analyze the most relevant and significant issues related to existing systems and datasets. Two primary feature extraction categories are discussed in detail, followed by a comparison of appearance-based, model-based, and hybrid methods. Important components such as feature selection, distance measures, classification techniques, and evaluation protocols are also reviewed. Finally, the review summarizes current challenges and emerging research trends, offering insights into future directions for developing more accurate, robust, and practical face recognition systems.
The increasing demand for the deployment of deep neural networks (DNNs) in edge devices has led to the development of lightweight deep learning (LDL) models designed to operate efficiently under resource constraints. Although DNNs have achieved remarkable success in various applications, their high computational requirements often limit their deployment on devices with restricted memory and processing power. This challenge has motivated researchers to develop optimized LDL models that balance accuracy, speed, and efficiency while maintaining competitive performance. Despite existing surveys covering specific aspects of LDL models, a comprehensive review encompassing image classification, object detection, and segmentation remains limited. This proposed survey systematically explores recent advancements in LDL models, highlighting their architectures, optimization techniques, and real-world applications. This survey conducts an empirical evaluation by testing latest state-of-the-art LDL models on the Jetson Orin edge device using benchmark datasets: Caltech-256 for classification, VisDrone for object detection, and COCO for segmentation. The experimental analysis focuses on key performance metrics, including inference speed, model accuracy, and computational efficiency, while comparing LDL models with their conventional counterparts. This study provides a holistic understanding of the role of LDL models in edge computing, providing insight into emerging trends, challenges, and future research directions in the field.
Video summarization seeks to produce concise yet informative representations of long videos by selecting segments aligned with human preferences. However, this task remains challenging due to annotation subjectivity and the discrepancy between continuous score regression during training and discrete selection at inference. Existing approaches often rely on dense attention mechanisms for long-range dependency modeling or employ generative frameworks to capture subjectivity, both of which introduce significant computational overhead and limited robustness under scarce supervision. To address this, we propose FSGM-Sum, a lightweight Factorized Spatio-Temporal Gating Mixer for single-pass frame importance prediction. Specifically, our method decomposes importance estimation into complementary temporal and channel saliency signals, where temporal dynamics are modeled via multi-dilation depthwise mixing and channel relevance is captured through global pooling with a compact gating network. These signals are fused through an additive factorization to form a structured gating mechanism, coupled with a temperature-calibrated scoring head for stable optimization and reliable score distributions. This design enables efficient modeling of spatio-temporal dependencies without constructing dense attention maps. We evaluate our approach on standard benchmarks, including SumMe and TVSum under rank-based evaluation protocols. Our method achieves competitive or superior alignment with human annotations while maintaining a significantly simpler and faster inference pipeline. Overall, FSGM-Sum demonstrates that factorized spatio-temporal gating provides an effective and practical alternative to attention-heavy and generative video summarization models. Code is available at: \url{https://github.com/SMRaza1009/FSGM-Sum.git}