A Survey on Recent Advances of Computer Vision Algorithms for Egocentric Video

Recent technological advances have made lightweight, head mounted cameras both practical and affordable and products like Google Glass show first approaches to in-troduce the idea of egocentric (first-person) video to the mainstream. Interestingly, the computer vision commu-nity has only recently started to explore this new domain of egocentric vision, where research can roughly be cate-gorized into three areas: Object recognition, activity de-tection/recognition, video summarization. In this paper, we try to give a broad overview about the different prob-lems that have been addressed and collect and compare evaluation results. Moreover, along with the emergence of this new domain came the introduction of numerous new and versatile benchmark datasets, which we summarize and compare as well.