iggroup:弱监督图像和视频分组

Andrew Gilbert, R. Bowden
{"title":"iggroup:弱监督图像和视频分组","authors":"Andrew Gilbert, R. Bowden","doi":"10.1109/ICCV.2011.6126493","DOIUrl":null,"url":null,"abstract":"We present a generic, efficient and iterative algorithm for interactively clustering classes of images and videos. The approach moves away from the use of large hand labelled training datasets, instead allowing the user to find natural groups of similar content based upon a handful of “seed” examples. Two efficient data mining tools originally developed for text analysis; min-Hash and APriori are used and extended to achieve both speed and scalability on large image and video datasets. Inspired by the Bag-of-Words (BoW) architecture, the idea of an image signature is introduced as a simple descriptor on which nearest neighbour classification can be performed. The image signature is then dynamically expanded to identify common features amongst samples of the same class. The iterative approach uses APriori to identify common and distinctive elements of a small set of labelled true and false positive signatures. These elements are then accentuated in the signature to increase similarity between examples and “pull” positive classes together. By repeating this process, the accuracy of similarity increases dramatically despite only a few training examples, only 10% of the labelled groundtruth is needed, compared to other approaches. It is tested on two image datasets including the caltech101 [9] dataset and on three state-of-the-art action recognition datasets. On the YouTube [18] video dataset the accuracy increases from 72% to 97% using only 44 labelled examples from a dataset of over 1200 videos. The approach is both scalable and efficient, with an iteration on the full YouTube dataset taking around 1 minute on a standard desktop machine.","PeriodicalId":6391,"journal":{"name":"2011 International Conference on Computer Vision","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2011-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"10","resultStr":"{\"title\":\"iGroup: Weakly supervised image and video grouping\",\"authors\":\"Andrew Gilbert, R. Bowden\",\"doi\":\"10.1109/ICCV.2011.6126493\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We present a generic, efficient and iterative algorithm for interactively clustering classes of images and videos. The approach moves away from the use of large hand labelled training datasets, instead allowing the user to find natural groups of similar content based upon a handful of “seed” examples. Two efficient data mining tools originally developed for text analysis; min-Hash and APriori are used and extended to achieve both speed and scalability on large image and video datasets. Inspired by the Bag-of-Words (BoW) architecture, the idea of an image signature is introduced as a simple descriptor on which nearest neighbour classification can be performed. The image signature is then dynamically expanded to identify common features amongst samples of the same class. The iterative approach uses APriori to identify common and distinctive elements of a small set of labelled true and false positive signatures. These elements are then accentuated in the signature to increase similarity between examples and “pull” positive classes together. By repeating this process, the accuracy of similarity increases dramatically despite only a few training examples, only 10% of the labelled groundtruth is needed, compared to other approaches. It is tested on two image datasets including the caltech101 [9] dataset and on three state-of-the-art action recognition datasets. On the YouTube [18] video dataset the accuracy increases from 72% to 97% using only 44 labelled examples from a dataset of over 1200 videos. The approach is both scalable and efficient, with an iteration on the full YouTube dataset taking around 1 minute on a standard desktop machine.\",\"PeriodicalId\":6391,\"journal\":{\"name\":\"2011 International Conference on Computer Vision\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2011-11-06\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"10\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2011 International Conference on Computer Vision\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICCV.2011.6126493\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2011 International Conference on Computer Vision","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICCV.2011.6126493","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 10

摘要

提出了一种通用、高效、迭代的图像和视频类交互聚类算法。该方法不再使用大型手工标记的训练数据集,而是允许用户基于少数“种子”示例找到相似内容的自然组。最初为文本分析开发的两种高效数据挖掘工具;使用和扩展min-Hash和APriori来实现大型图像和视频数据集的速度和可扩展性。受词袋(BoW)体系结构的启发,引入了图像签名的思想,作为一个简单的描述符,可以在其上执行最近邻分类。然后动态扩展图像签名以识别同一类样本之间的共同特征。迭代方法使用APriori来识别一小组标记的真阳性和假阳性签名的共同和独特元素。然后在签名中强调这些元素,以增加示例之间的相似性,并将正类“拉”在一起。通过重复这一过程,尽管只有少数训练样本,但相似性的准确性显著提高,与其他方法相比,只需要标记的基础事实的10%。它在两个图像数据集(包括caltech101[9]数据集)和三个最先进的动作识别数据集上进行了测试。在YouTube[18]视频数据集上,仅使用来自1200多个视频数据集的44个标记示例,准确率从72%提高到97%。该方法既可扩展又高效,在标准桌面机器上对整个YouTube数据集进行迭代大约需要1分钟。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
iGroup: Weakly supervised image and video grouping
We present a generic, efficient and iterative algorithm for interactively clustering classes of images and videos. The approach moves away from the use of large hand labelled training datasets, instead allowing the user to find natural groups of similar content based upon a handful of “seed” examples. Two efficient data mining tools originally developed for text analysis; min-Hash and APriori are used and extended to achieve both speed and scalability on large image and video datasets. Inspired by the Bag-of-Words (BoW) architecture, the idea of an image signature is introduced as a simple descriptor on which nearest neighbour classification can be performed. The image signature is then dynamically expanded to identify common features amongst samples of the same class. The iterative approach uses APriori to identify common and distinctive elements of a small set of labelled true and false positive signatures. These elements are then accentuated in the signature to increase similarity between examples and “pull” positive classes together. By repeating this process, the accuracy of similarity increases dramatically despite only a few training examples, only 10% of the labelled groundtruth is needed, compared to other approaches. It is tested on two image datasets including the caltech101 [9] dataset and on three state-of-the-art action recognition datasets. On the YouTube [18] video dataset the accuracy increases from 72% to 97% using only 44 labelled examples from a dataset of over 1200 videos. The approach is both scalable and efficient, with an iteration on the full YouTube dataset taking around 1 minute on a standard desktop machine.
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
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信