{"title":"排名框架下的个人年龄估计","authors":"Yong Ma, T. Xiong, Y. Zou, Kongqiao Wang","doi":"10.1145/1991996.1992034","DOIUrl":null,"url":null,"abstract":"Different from traditional age estimation methods under classification or regression frameworks, this paper proposes a novel person-specific age estimation method under ranking framework. The basic idea is to consider the aging process as a personal age-ranked image sequences and extract the relevant information from this sequences. The estimation of age for an unknown face image is determined by first utilizing face recognition to find the persons in template sets who looks similar to the unseen person, then estimating the ranking order of the unseen person in corresponding person-specific image sequences, lastly mapping and fusing the rank order to its real age. Under this framework, our proposed system not only can estimate the correct the age orders of pairs of faces naturally but also can estimate the real age accurately. The proposed method has shown encouraging performance in the comparative experiments either as an age ranker or as an accurate age estimator and the experiment also proved the validity of the above assumption.","PeriodicalId":390933,"journal":{"name":"Proceedings of the 1st ACM International Conference on Multimedia Retrieval","volume":"47 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2011-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"18","resultStr":"{\"title\":\"Person-specific age estimation under ranking framework\",\"authors\":\"Yong Ma, T. Xiong, Y. Zou, Kongqiao Wang\",\"doi\":\"10.1145/1991996.1992034\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Different from traditional age estimation methods under classification or regression frameworks, this paper proposes a novel person-specific age estimation method under ranking framework. The basic idea is to consider the aging process as a personal age-ranked image sequences and extract the relevant information from this sequences. The estimation of age for an unknown face image is determined by first utilizing face recognition to find the persons in template sets who looks similar to the unseen person, then estimating the ranking order of the unseen person in corresponding person-specific image sequences, lastly mapping and fusing the rank order to its real age. Under this framework, our proposed system not only can estimate the correct the age orders of pairs of faces naturally but also can estimate the real age accurately. The proposed method has shown encouraging performance in the comparative experiments either as an age ranker or as an accurate age estimator and the experiment also proved the validity of the above assumption.\",\"PeriodicalId\":390933,\"journal\":{\"name\":\"Proceedings of the 1st ACM International Conference on Multimedia Retrieval\",\"volume\":\"47 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2011-04-18\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"18\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of the 1st ACM International Conference on Multimedia Retrieval\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1145/1991996.1992034\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 1st ACM International Conference on Multimedia Retrieval","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/1991996.1992034","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Person-specific age estimation under ranking framework
Different from traditional age estimation methods under classification or regression frameworks, this paper proposes a novel person-specific age estimation method under ranking framework. The basic idea is to consider the aging process as a personal age-ranked image sequences and extract the relevant information from this sequences. The estimation of age for an unknown face image is determined by first utilizing face recognition to find the persons in template sets who looks similar to the unseen person, then estimating the ranking order of the unseen person in corresponding person-specific image sequences, lastly mapping and fusing the rank order to its real age. Under this framework, our proposed system not only can estimate the correct the age orders of pairs of faces naturally but also can estimate the real age accurately. The proposed method has shown encouraging performance in the comparative experiments either as an age ranker or as an accurate age estimator and the experiment also proved the validity of the above assumption.