October
2016
Visual Motif Discovery via First-Person Vision
Authors:
Abstract:
Visual motifs are images of visual experiences that are significant and shared across many people, such as an image of an informative sign viewed by many people and that of a familiar social situation such as when interacting with a clerk at a store. The goal of this study is to discover visual motifs from a collection of first-person videos recorded by a wearable camera. To achieve this goal, we develop a commonality clustering method that leverages three important aspects: inter-video similarity, intra-video sparseness, and people’s visual attention. The problem is posed as normalized spectral clustering, and is solved e ciently using a weighted covariance matrix. Experimental results suggest the e↵ectiveness of our method over several state-of-the-art methods in terms of both accuracy and e ciency of visual motif discovery.
copied = false, 2000);
">
@conference{Yonetani-2016-109800,
author = {Ryo Yonetani And Kris M. Kitani And Yoichi Sato},
title = {Visual Motif Discovery via First-Person Vision},
booktitle = {Proceedings of (ECCV) European Conference on Computer Vision},
year = {2016},
month = {October},
pages = {187 - 203},
}
author = {Ryo Yonetani And Kris M. Kitani And Yoichi Sato},
title = {Visual Motif Discovery via First-Person Vision},
booktitle = {Proceedings of (ECCV) European Conference on Computer Vision},
year = {2016},
month = {October},
pages = {187 - 203},
}