Understanding Social Relationships with Person-Pair Relations

作     者：Hang Zhao Haicheng Chen Leilai Li Hai Wan Hang Zhao;Haicheng Chen;Leilai Li;Hai Wan

作者机构：the Guizhou Post and Telecommunications Planning and Design Institute Co.Ltd.Guiyang 550003China School of Computer Science and EngineeringSun Yat-sen UniversityGuangzhou 510006China Ping An Technology(Shenzhen)Co.Ltd.Shenzhen 518049China 

出 版 物：《Big Data Mining and Analytics》 (大数据挖掘与分析（英文）)

年 卷 期：2022年第5卷第2期

页      面：120-129页

核心收录：

学科分类：0303[法学-社会学] 12[管理学] 1204[管理学-公共管理] 03[法学] 030301[法学-社会学] 

基　　金：supported by the National Natural Science Foundation of China(Nos.61976232 and 51978675) Humanities and Social Science Research Project of Ministry of Education(No.18YJCZH006) and AllChina Federation of Returned Overseas Chinese Research Project(No.17BZQK216) 

主　　题：social relationship understanding person-pair relations Person-Pair Relation Network(PPRN) 

摘      要：Social relationship understanding infers existing social relationships among individuals in a given scenario,which has been demonstrated to have a wide range of practical value in ***,existing methods infer the social relationship of each person pair in isolation,without considering the context-aware information for person pairs in the same *** context-aware information for person pairs exists extensively in reality,that is,the social relationships of different person pairs in a simple scenario are always related to each *** instance,if most of the person pairs in a simple scenario have the same social relationship,“friends,then the other pairs have a high probability of being“friendsor other similar coarse-level relationships,such as“intimate.This context-aware information should thus be considered in social relationship ***,this paper proposes a novel end-to-end trainable Person-Pair Relation Network(PPRN),which is a GRU-based graph inference network,to first extract the visual and position information as the person-pair feature information,then enable it to transfer on a fully-connected social graph,and finally utilizes different aggregators to collect different kinds of person-pair *** existing methods,the method—with its message passing mechanism in the graph model—can infer the social relationship of each person-pair in a joint way(i.e.,not in isolation).Extensive experiments on People In Social Context(PISC)-and People In Photo Album(PIPA)-relation datasets show the superiority of our method compared to other methods.