2015/01/12 by Sven Bambach, Bambach, Sven · 1 citation
Computer Science · #Advanced Image and Video Retrieval Techniques #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Human Pose and Action Recognition #Video Analysis and Summarization #Video Surveillance and Tracking Methods
paper · pdf · doi:10.48550/arxiv.1501.02825
openalex publication_date 2015/01/12 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Recent technological advances have made lightweight, head mounted cameras\nboth practical and affordable and products like Google Glass show first\napproaches to introduce the idea of egocentric (first-person) video to the\nmainstream. Interestingly, the computer vision community has only recently\nstarted to explore this new domain of egocentric vision, where research can\nroughly be categorized into three areas: Object recognition, activity\ndetection/recognition, video summarization. In this paper, we try to give a\nbroad overview about the different problems that have been addressed and\ncollect and compare evaluation results. Moreover, along with the emergence of\nthis new domain came the introduction of numerous new and versatile benchmark\ndatasets, which we summarize and compare as well.\n