Show simple item record

dc.contributor.authorYuan, Mengke
dc.contributor.authorGhanem, Bernard
dc.contributor.authorYan, Dongming
dc.contributor.authorWu, Baoyuan
dc.contributor.authorZhang, Xiaopeng
dc.contributor.authorWonka, Peter
dc.date.accessioned2021-07-14T06:23:18Z
dc.date.available2021-07-14T06:23:18Z
dc.date.issued2021-07-12
dc.identifier.citationYuan, M., Ghanem, B., Yan, D., Wu, B., Zhang, X., & Wonka, P. (2021). Customized Summarizations of Visual Data Collections. Computer Graphics Forum. doi:10.1111/cgf.14336
dc.identifier.issn0167-7055
dc.identifier.issn1467-8659
dc.identifier.doi10.1111/cgf.14336
dc.identifier.urihttp://hdl.handle.net/10754/670193
dc.description.abstractWe 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.
dc.description.sponsorshipThis work was partially supported by the National Natural Science Foundation of China (Nos. 62071157, 61620106003, 61772523, 61972459), the KAUST Baseline Funding, the China Postdoctoral Science Foundation (No. 2020M680754), the Open Project Program of State Key Laboratory of Virtual Reality Technology and Systems, Beihang University (No. VRLAB2020C03), and the Tencent AI Lab Rhino-Bird Focused Research Program (No. JR202023).
dc.publisherWiley
dc.relation.urlhttps://onlinelibrary.wiley.com/doi/10.1111/cgf.14336
dc.rightsArchived with thanks to Computer Graphics Forum
dc.titleCustomized Summarizations of Visual Data Collections
dc.typeArticle
dc.contributor.departmentElectrical Engineering Program
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
dc.contributor.departmentComputer Science Program
dc.contributor.departmentVisual Computing Center (VCC)
dc.identifier.journalComputer Graphics Forum
dc.rights.embargodate2022-07-12
dc.eprint.versionPost-print
dc.contributor.institutionNational Laboratory of Pattern Recognition Institute of Automation, Chinese Academy of Sciences #95 East Zhongguancun Road Beijing 100190 P. R. China
dc.contributor.institutionSchool of Artificial Intelligence University of Chinese Academy of Sciences No.19(A) Yuquan Road, Shijingshan District Beijing 100149 P. R. China
dc.contributor.institutionSchool of Data Science Chinese University of Hong Kong 2001 Longxiang Road, Longgang District Shenzhen P. R. China
dc.contributor.institutionSecure Computing Lab of Big Data Shenzhen Research Institute of Big Data 2001 Longxiang Road, Longgang District Shenzhen P. R. China
dc.contributor.institutionTencent AI Lab Shenzhen P. R. China
kaust.personGhanem, Bernard
kaust.personWonka, Peter
kaust.acknowledged.supportUnitKAUST baseline funding
dc.date.published-online2021-07-12
dc.date.published-print2021-09


This item appears in the following Collection(s)

Show simple item record