BriefGPT.xyz
May, 2015
代表性关键帧视觉化呈现自我中心照片流
Visual Summary of Egocentric Photostreams by Representative Keyframes
HTML
PDF
Ricard Mestre, Marc Bolaños, Estefanía Talavera, Petia Radeva, Xavier Giró-i-Nieto
TL;DR
提出了一种基于关键帧选择的摘要方法，该方法利用卷积神经网络提取的视觉特征对由佩戴式摄像头拍摄的自我记录图像流进行视觉摘要，通过无监督聚类将图像流划分为事件，并从每个事件中提取最相关的关键帧。经过盲品测试验证结果的质量。
Abstract
Building a
visual summary
from an
egocentric photostream
captured by a lifelogging
wearable camera
is of high interest for different appli
→