利用语义相似度预测图像中物体的角度和距离

Creativity & cognition : proceedings of the ... Creativity & Cognition Conference. Creativity & Cognition Conference Pub Date : 2011-11-03 DOI:10.1145/2069618.2069655

Sterling Somers, J. Gagné, C. Astudillo, J. Davies

{"title":"利用语义相似度预测图像中物体的角度和距离","authors":"Sterling Somers, J. Gagné, C. Astudillo, J. Davies","doi":"10.1145/2069618.2069655","DOIUrl":null,"url":null,"abstract":"A presentation of an Artificial Intelligence (AI) called Visuo that stores and guesses quantitative visual-spatial magnitudes (e.g., sizes of objects). In this analysis, Visuo is used to store polar (angle and distance) relationships between objects in images. It uses a database of tagged images as its memory and approximates unexperienced magnitudes by analogy with semantically related concepts. This shows the transferring of information from high semantically related concepts yielding significantly higher accuracy in angle and distance estimations over using medium or low semantically similar items.","PeriodicalId":90479,"journal":{"name":"Creativity & cognition : proceedings of the ... Creativity & Cognition Conference. Creativity & Cognition Conference","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2011-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"Using semantic similarity to predict angle and distance of objects in images\",\"authors\":\"Sterling Somers, J. Gagné, C. Astudillo, J. Davies\",\"doi\":\"10.1145/2069618.2069655\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"A presentation of an Artificial Intelligence (AI) called Visuo that stores and guesses quantitative visual-spatial magnitudes (e.g., sizes of objects). In this analysis, Visuo is used to store polar (angle and distance) relationships between objects in images. It uses a database of tagged images as its memory and approximates unexperienced magnitudes by analogy with semantically related concepts. This shows the transferring of information from high semantically related concepts yielding significantly higher accuracy in angle and distance estimations over using medium or low semantically similar items.\",\"PeriodicalId\":90479,\"journal\":{\"name\":\"Creativity & cognition : proceedings of the ... Creativity & Cognition Conference. Creativity & Cognition Conference\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2011-11-03\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Creativity & cognition : proceedings of the ... Creativity & Cognition Conference. Creativity & Cognition Conference\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1145/2069618.2069655\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Creativity & cognition : proceedings of the ... Creativity & Cognition Conference. Creativity & Cognition Conference","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/2069618.2069655","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 1

摘要

一种名为Visuo的人工智能(AI)的演示，它可以存储和猜测定量的视觉空间大小(例如物体的大小)。在此分析中，Visuo用于存储图像中物体之间的极性(角度和距离)关系。它使用标记图像的数据库作为记忆，并通过与语义相关的概念类比来近似没有经验的大小。这表明，与使用中等或低语义相似的项目相比，从高语义相关概念传递的信息在角度和距离估计方面产生了显著更高的准确性。

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

Using semantic similarity to predict angle and distance of objects in images

A presentation of an Artificial Intelligence (AI) called Visuo that stores and guesses quantitative visual-spatial magnitudes (e.g., sizes of objects). In this analysis, Visuo is used to store polar (angle and distance) relationships between objects in images. It uses a database of tagged images as its memory and approximates unexperienced magnitudes by analogy with semantically related concepts. This shows the transferring of information from high semantically related concepts yielding significantly higher accuracy in angle and distance estimations over using medium or low semantically similar items.

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

Creativity & cognition : proceedings of the ... Creativity & Cognition Conference. Creativity & Cognition Conference

自引率

0.00%

发文量