Understanding Social Relationships with Person-Pair Relations
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 reality. However, existing methods infer the social relationship of each person pair in isolation, without considering...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Tsinghua University Press
2022-06-01
|
Series: | Big Data Mining and Analytics |
Subjects: | |
Online Access: | https://www.sciopen.com/article/10.26599/BDMA.2021.9020022 |
_version_ | 1811344591496937472 |
---|---|
author | Hang Zhao Haicheng Chen Leilai Li Hai Wan |
author_facet | Hang Zhao Haicheng Chen Leilai Li Hai Wan |
author_sort | Hang Zhao |
collection | DOAJ |
description | 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 reality. However, existing methods infer the social relationship of each person pair in isolation, without considering the context-aware information for person pairs in the same scenario. The 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 other. For 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 "friends" or other similar coarse-level relationships, such as "intimate" . This context-aware information should thus be considered in social relationship understanding. Therefore, 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 information. Unlike 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. |
first_indexed | 2024-04-13T19:50:27Z |
format | Article |
id | doaj.art-ce011be531b64f31b76435d5179918f7 |
institution | Directory Open Access Journal |
issn | 2096-0654 |
language | English |
last_indexed | 2024-04-13T19:50:27Z |
publishDate | 2022-06-01 |
publisher | Tsinghua University Press |
record_format | Article |
series | Big Data Mining and Analytics |
spelling | doaj.art-ce011be531b64f31b76435d5179918f72022-12-22T02:32:34ZengTsinghua University PressBig Data Mining and Analytics2096-06542022-06-015212012910.26599/BDMA.2021.9020022Understanding Social Relationships with Person-Pair RelationsHang Zhao0Haicheng Chen1Leilai Li2Hai Wan3Guizhou Post and Telecommunications Planning and Design Institute Co., Ltd., Guiyang 550003, ChinaSchool of Computer Science and Engineering, Sun Yat-sen University, Guangzhou 510006, ChinaPing An Technology (Shenzhen) Co., Ltd., Shenzhen 518049, ChinaSchool of Computer Science and Engineering, Sun Yat-sen University, Guangzhou 510006, ChinaSocial 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 reality. However, existing methods infer the social relationship of each person pair in isolation, without considering the context-aware information for person pairs in the same scenario. The 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 other. For 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 "friends" or other similar coarse-level relationships, such as "intimate" . This context-aware information should thus be considered in social relationship understanding. Therefore, 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 information. Unlike 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.https://www.sciopen.com/article/10.26599/BDMA.2021.9020022social relationship understandingperson-pair relationsperson-pair relation network (pprn) |
spellingShingle | Hang Zhao Haicheng Chen Leilai Li Hai Wan Understanding Social Relationships with Person-Pair Relations Big Data Mining and Analytics social relationship understanding person-pair relations person-pair relation network (pprn) |
title | Understanding Social Relationships with Person-Pair Relations |
title_full | Understanding Social Relationships with Person-Pair Relations |
title_fullStr | Understanding Social Relationships with Person-Pair Relations |
title_full_unstemmed | Understanding Social Relationships with Person-Pair Relations |
title_short | Understanding Social Relationships with Person-Pair Relations |
title_sort | understanding social relationships with person pair relations |
topic | social relationship understanding person-pair relations person-pair relation network (pprn) |
url | https://www.sciopen.com/article/10.26599/BDMA.2021.9020022 |
work_keys_str_mv | AT hangzhao understandingsocialrelationshipswithpersonpairrelations AT haichengchen understandingsocialrelationshipswithpersonpairrelations AT leilaili understandingsocialrelationshipswithpersonpairrelations AT haiwan understandingsocialrelationshipswithpersonpairrelations |