Customized Summarizations of Visual Data Collections,Computer Graphics Forum

当前位置： X-MOL 学术 › Comput. Graph. Forum › 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.)

Customized Summarizations of Visual Data Collections
Computer Graphics Forum ( IF 2.7 ) Pub Date : 2021-07-12 , DOI: 10.1111/cgf.14336
Mengke Yuan _{1,

2} , Bernard Ghanem ₃ , Dong‐Ming Yan _{1,

2} , Baoyuan Wu _{4,

5,

6} , Xiaopeng Zhang _{1,

2} , Peter Wonka ₃

Affiliation

We propose a framework to generate customized summarizations of visual data collections, such as collections of images, materials, 3D shapes, and 3D scenes. We assume that the elements in the visual data collections can be mapped to a set of vectors in a feature space, in which a fitness score for each element can be defined, and we pose the problem of customized summarizations as selecting a subset of these elements. We first describe the design choices a user should be able to specify for modeling customized summarizations and propose a corresponding user interface. We then formulate the problem as a constrained optimization problem with binary variables and propose a practical and fast algorithm based on the alternating direction method of multipliers (ADMM). Our results show that our problem formulation enables a wide variety of customized summarizations, and that our solver is both significantly faster than state-of-the-art commercial integer programming solvers and produces better solutions than fast relaxation-based solvers.

中文翻译：

可视化数据集合的定制摘要

我们提出了一个框架来生成视觉数据集合的定制摘要，例如图像、材料、3D 形状和 3D 场景的集合。我们假设视觉数据集合中的元素可以映射到特征空间中的一组向量，其中可以定义每个元素的适应度分数，并且我们提出了自定义摘要的问题作为选择这些元素的子集. 我们首先描述用户应该能够为自定义摘要建模而指定的设计选择，并提出相应的用户界面。然后，我们将该问题表述为具有二元变量的约束优化问题，并提出了一种基于乘法器交替方向法 (ADMM) 的实用且快速的算法。

更新日期：2021-07-12

点击分享查看原文

点击收藏

阅读更多本刊最新论文本刊介绍/投稿指南11