图像排名与密度树为谷歌地图

Special Interest Group on Computer Graphics and Interactive Techniques Conference Talks Pub Date : 2020-08-17 DOI:10.1145/3388767.3407353

Jared Johnson, Sema Berkiten

{"title":"图像排名与密度树为谷歌地图","authors":"Jared Johnson, Sema Berkiten","doi":"10.1145/3388767.3407353","DOIUrl":null,"url":null,"abstract":"We propose an unsupervised learning technique for image ranking of photos contributed by Google Maps users. A density tree is built for each point-of-interest (POI), such as The National Mall or the Louvre. This tree is used to construct clusters, which are then ranked based on size and quality. We choose a representative image for each cluster, resulting in a ranked set of high-quality, diverse, and relevant images for each POI. We validated our algorithm in a side-by-side preference study.","PeriodicalId":368810,"journal":{"name":"Special Interest Group on Computer Graphics and Interactive Techniques Conference Talks","volume":"97 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2020-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Image Ranking with Density Trees for Google Maps\",\"authors\":\"Jared Johnson, Sema Berkiten\",\"doi\":\"10.1145/3388767.3407353\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We propose an unsupervised learning technique for image ranking of photos contributed by Google Maps users. A density tree is built for each point-of-interest (POI), such as The National Mall or the Louvre. This tree is used to construct clusters, which are then ranked based on size and quality. We choose a representative image for each cluster, resulting in a ranked set of high-quality, diverse, and relevant images for each POI. We validated our algorithm in a side-by-side preference study.\",\"PeriodicalId\":368810,\"journal\":{\"name\":\"Special Interest Group on Computer Graphics and Interactive Techniques Conference Talks\",\"volume\":\"97 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2020-08-17\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Special Interest Group on Computer Graphics and Interactive Techniques Conference Talks\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1145/3388767.3407353\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Special Interest Group on Computer Graphics and Interactive Techniques Conference Talks","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3388767.3407353","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 0

摘要

我们提出了一种无监督学习技术，用于对谷歌地图用户提供的照片进行图像排序。为每个兴趣点(POI)构建密度树，例如国家广场或卢浮宫。该树用于构建集群，然后根据大小和质量对集群进行排名。我们为每个集群选择一个代表性图像，从而为每个POI生成一组高质量、多样化和相关的图像。我们在并排偏好研究中验证了我们的算法。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Image Ranking with Density Trees for Google Maps

We propose an unsupervised learning technique for image ranking of photos contributed by Google Maps users. A density tree is built for each point-of-interest (POI), such as The National Mall or the Louvre. This tree is used to construct clusters, which are then ranked based on size and quality. We choose a representative image for each cluster, resulting in a ranked set of high-quality, diverse, and relevant images for each POI. We validated our algorithm in a side-by-side preference study.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

Special Interest Group on Computer Graphics and Interactive Techniques Conference Talks

自引率

0.00%

发文量