Mixed bi-subject kinship verification via multi-view multi-task learning.pdfVIP

下载本文档

7
0
约4.95万字
约 8页
2017-03-16 发布于天津
举报
版权申诉

Mixed bi-subject kinship verification via multi-view multi-task learning.pdf

1、本文档共8页，可阅读全部内容。
2、原创力文档（book118）网站文档一经付费（服务费），不意味着购买了该文档的版权，仅供个人/单位学习、研究之用，不得用于商业用途，未经授权，严禁复制、发行、汇编、翻译或者网络传播等，侵权必究。
3、本站所有内容均由合作方或网友上传，本站不对文档的完整性、权威性及其观点立场正确性做任何保证或承诺！文档内容仅供研究参考，付费前请自行鉴别。如您付费，意味着您自己接受本站规则且自行承担风险，本站不退款、不进行额外附加服务；查看《如何避免下载的几个坑》。如果您已付费下载过本站文档，您可以点击这里二次下载。
4、如文档侵犯商业秘密、侵犯著作权、侵犯人身权等，请点击“版权申诉”（推荐），也可以打举报电话：400-050-0827(电话支持时间：9:00-18:30)。
5、该文档为VIP文档，如果想要下载，成为VIP会员后，下载免费。
6、成为VIP后，下载本文档将扣除1次下载权益。下载后，不支持退款、换文档。如有疑问请联系我们。
7、成为VIP后，您将拥有八大权益，权益包括：VIP文档下载权益、阅读免打扰、文档格式转换、高级专利检索、专属身份标志、高级客服、多端互通、版权登记。
8、VIP文档为合作方或网友上传，每下载1次，网站将根据用户上传文档的质量评分、类型等，对文档贡献者给予高额补贴、流量扶持。如果你也想贡献VIP文档。上传文档

Mixed bi-subject kinship verification via multi-view multi-task learning.pdf

Neurocomputing 214 (2016) 350–357 Contents lists available at ScienceDirect Neurocomputing journal homepage: /locate/neucom Mixed bi-subject kinship veri?cation via multi-view multi-task learning Xiaoqian Qin a,b,c, Xiaoyang Tan a,b,n, Songcan Chen a,b a College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China b Collaborative Innovation Center of Novel Software Technology and Industrialization, Nanjing 210016, China c Huaiyin Normal University, Huaian 223300, China article info Article history: Received 1 December 2015 Received in revised form 7 June 2016 Accepted 9 June 2016 Communicated by Dr Jiwen Lu Available online 16 June 2016 Keywords: Mixed-kinship veri?cation Multi-task learning Multi-view learning abstract Bi-subject kinship veri?cation addresses the problem of verifying whether there exists some kind of kin relationship (i.e., father–son, father-daughter, mother–son and mother–daughter) between a pair of parent–child subjects based purely on their visual appearance. The task is challenging due to the involvement of two different subjects possibly with different genders and ages. In addition, collecting suf?cient training samples for each type of kinship is dif?cult. In this work, we present a novel method to address these issues by considering each type of kin relation veri?cation as one task and learning them at one time in the framework of multi-task learning, by sharing feature sets and useful structures among the tasks. Particularly our contributions are three folds: ?rst, we introduce a new type of learning problem, called mixed bi-subject kinship veri?cation, to the topic of bi-subject kinship veri?cation: instead of simply verifying whether some ?xed kinship relationship (e.g., mother–son) can be established for a given pair of parent–child images, we try to ?gure out whether any type of the four kinship relations can be established according to the visual features of the image pair, with