当前位置: X-MOL 学术Pattern Recogn. Lett. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Temporally sorting images from real-world events
Pattern Recognition Letters ( IF 5.1 ) Pub Date : 2021-05-04 , DOI: 10.1016/j.patrec.2021.04.027
Rafael Padilha , Fernanda A. Andaló , Bahram Lavi , Luís A.M. Pereira , Anderson Rocha

As smartphones become ubiquitous in modern life, every major event — from musical concerts to terrorist attempts — is massively captured by multiple devices and instantly uploaded to the Internet. Once shared through social media, the chronological order between available media pieces cannot be reliably recovered, hindering the understanding and reconstruction of that event. In this work, we propose data-driven methods for temporally sorting images originated from heterogeneous sources and captured from distinct angles, viewpoints, and moments. We model the chronological sorting task as an ensemble of binary classifiers whose answers are combined hierarchically to estimate an image’s temporal position within the duration of the event. We evaluate our method on images from the Notre-Dame Catedral fire and the Grenfell Tower fire events and discuss research challenges for analyzing data from real-world forensic events. Finally, we employ visualization techniques to understand what our models have learned, offering additional insights to the problem.



中文翻译:

临时排序来自真实事件的图像

随着智能手机在现代生活中无处不在,从音乐会到恐怖袭击的每一个重大事件都被多个设备大量捕获,并立即上传到Internet。一旦通过社交媒体共享,可用媒体之间的时间顺序就无法可靠地恢复,从而阻碍了对该事件的理解和重建。在这项工作中,我们提出了数据驱动的方法,用于对来自异类源并从不同角度,视点和瞬间捕获的图像进行时间排序。我们将按时间顺序排序的任务建模为二进制分类器的集合,其答案按层次结构组合在一起以估计事件持续时间内的图像时间位置。我们根据巴黎圣母院大火和格林菲尔大厦大火的图像评估我们的方法,并讨论分析实际法医事件数据的研究挑战。最后,我们采用可视化技术来了解我们的模型学到了什么,从而提供了对该问题的更多见解。

更新日期:2021-05-19
down
wechat
bug