Dr. Md Meftahul Ferdaus

In an era where AI systems require vast amounts of labeled data, few-shot learning emerges as a game-changing paradigm that enables models to learn from just a handful of examples. Our comprehensive survey, accepted for publication in ACM Computing Surveys (IF: 28.0, #1 in Computer Science Theory & Methods), explores how few-shot learning is revolutionizing video analysis and 3D object detection—two critical domains where data annotation is particularly expensive and time-consuming. From autonomous vehicles recognizing rare objects to surveillance systems adapting to new scenarios, we examine cutting-edge techniques that make AI more practical and accessible. This work provides researchers and practitioners with a systematic understanding of few-shot learning methods, their applications, and future directions in visual computing.