arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2104.00805cs.CVcs.HCcs.MM
收藏

可计算性:信息效用的图像可计算度量

Memorability: An image-computable measure of information utility

Adobe Research(Adobe研究院);Brown University(布朗大学);Stanford University(斯坦福大学);Massachusetts Institute of Technology(麻省理工学院)

Zoya Bylinskii, Lore Goetschalckx, Anelise Newman, Aude Oliva

摘要:

图像中的像素,以及它们组成的对象,场景和动作,决定了图像是令人难忘还是令人难忘。虽然记忆力因图像而异,但它在很大程度上独立于个人观察者。观察者独立性使记忆性成为图像可计算的信息度量,并有资格进行自动预测。在本章中,我们将用计算镜头放大记忆力,详细介绍最先进的算法,这些算法可以准确预测图像相对于人类行为数据的记忆力,使用从原始像素到语义标签的不同尺度的图像特征。我们讨论了面部,对象和场景记忆性的算法和可视化的设计,以及超越静态场景推广到动作和视频的算法。我们涵盖了最先进的深度学习方法,这些方法是当前记忆预测领域的领跑者。除了预测,我们还展示了最近的人工智能。方法可以用于创建和修改视觉可记忆性。最后,我们预览了可记忆性所支持的计算应用程序,从过滤视觉流到增强增强现实界面。

英文摘要:

The pixels in an image, and the objects, scenes, and actions that they compose, determine whether an image will be memorable or forgettable. While memorability varies by image, it is largely independent of an individual observer. Observer independence is what makes memorability an image-computable measure of information, and eligible for automatic prediction. In this chapter, we zoom into memorability with a computational lens, detailing the state-of-the-art algorithms that accurately predict image memorability relative to human behavioral data, using image features at different scales from raw pixels to semantic labels. We discuss the design of algorithms and visualizations for face, object, and scene memorability, as well as algorithms that generalize beyond static scenes to actions and videos. We cover the state-of-the-art deep learning approaches that are the current front runners in the memorability prediction space. Beyond prediction, we show how recent A.I. approaches can be used to create and modify visual memorability. Finally, we preview the computational applications that memorability can power, from filtering visual streams to enhancing augmented reality interfaces.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑