关键词：计算机视觉系统;OM抽样理论;认知科学;人类行为
摘 要：I present my work towards learning a better computer vision system that learns and generalizes object categories better, and behaves in ways closer to what human behave. Speci cally, I focus on two key components of such a system: learning better features, and revisiting existing problem statements. For the rst component, I propose and analyze novel receptive eld learning and dictionary learning methods, mathematically justi ed by the Nystrom sampling theory, that learn more compact and e ective features for object recognition tasks. For the second component, I propose to combine otherwise independently developed computer vision and cognitive science studies, and present the rst large-scale system that allows computers to learn and generalize closer to what a human learner will do. I also provide a large-scale human behavior database, which will hopefully enable further research along this research direction.