A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/1704.06767v3.pdf">the original URL</a>. The file type is <code>application/pdf</code>.
Filters
Convex Formulation of Multiple Instance Learning from Positive and Unlabeled Bags
[article]
<span title="2018-05-01">2018</span>
<i >
arXiv
</i>
<span class="release-stage" >pre-print</span>
Preserved Fulltext
Other Versions
<span title="2017-04-22">2017</span>
<span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1704.06767v1">arXiv:1704.06767v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/2nxcomhuozdprntv4hrrwds7ri">fatcat:2nxcomhuozdprntv4hrrwds7ri</a> </span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1704.06767v1">arXiv:1704.06767v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/2nxcomhuozdprntv4hrrwds7ri">fatcat:2nxcomhuozdprntv4hrrwds7ri</a> </span>
<span title="2018-02-16">2018</span>
<span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1704.06767v2">arXiv:1704.06767v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/zxxk4glinngxxjvifytgjwhfcu">fatcat:zxxk4glinngxxjvifytgjwhfcu</a> </span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1704.06767v2">arXiv:1704.06767v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/zxxk4glinngxxjvifytgjwhfcu">fatcat:zxxk4glinngxxjvifytgjwhfcu</a> </span>
Multiple instance learning (MIL) is a variation of traditional supervised learning problems where data (referred to as bags) are composed of sub-elements (referred to as instances) and only bag labels ...
A learning framework called PU learning (positive and unlabeled learning) can address this problem. In this paper, we propose a convex PU learning method to solve an MIL problem. ...
Multiple Instance Learning from Positive and Unlabeled Bags We formulate the problem of multiple instance learning from positive and unlabeled bags (PU-MIL). ...
<span class="external-identifiers">
<a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1704.06767v3">arXiv:1704.06767v3</a>
<a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/q6lmjvhuj5e35dio64ivpiqtli">fatcat:q6lmjvhuj5e35dio64ivpiqtli</a>
</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201019220817/https://arxiv.org/pdf/1704.06767v3.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext">
<button class="ui simple right pointing dropdown compact black labeled icon button serp-button">
<i class="icon ia-icon"></i>
Web Archive
[PDF]
<div class="menu fulltext-thumbnail">
<img src="https://blobs.fatcat.wiki/thumbnail/pdf/7c/fd/7cfde771805fddc38010e242d22c0d4e9652f802.180px.jpg" alt="fulltext thumbnail" loading="lazy">
</div>
</button>
</a>
<a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1704.06767v3" title="arxiv.org access">
<button class="ui compact blue labeled icon button serp-button">
<i class="file alternate outline icon"></i>
arxiv.org
</button>
</a>
Multiple instance learning for sparse positive bags
<span title="">2007</span>
<i title="ACM Press">
<a target="_blank" rel="noopener" href="https://fatcat.wiki/container/v54jrmjbpzgodi4buoyaj7vrzm" style="color: black;">Proceedings of the 24th international conference on Machine learning - ICML '07</a>
</i>
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit <a rel="external noopener" href="http://www.cs.utexas.edu/~ml/papers/bunescu-icml07.pdf">the original URL</a>. The file type is <code>application/pdf</code>.
We present a new approach to multiple instance learning (MIL) that is particularly effective when the positive bags are sparse (i.e. contain few positive instances). ...
Unlike other SVM-based MIL methods, our approach more directly enforces the desired constraint that at least one of the instances in a positive bag is positive. ...
This work was supported by grant IIS-0325116 from the NSF, and a gift from Google Inc. The experiments were run on the Mastodon cluster, provided by NSF grant EIA-0303609. ...
<span class="external-identifiers">
<a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/1273496.1273510">doi:10.1145/1273496.1273510</a>
<a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/icml/BunescuM07.html">dblp:conf/icml/BunescuM07</a>
<a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/nz3v427aabdxllyahud4zdwu7a">fatcat:nz3v427aabdxllyahud4zdwu7a</a>
</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170814015239/http://www.cs.utexas.edu/~ml/papers/bunescu-icml07.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext">
<button class="ui simple right pointing dropdown compact black labeled icon button serp-button">
<i class="icon ia-icon"></i>
Web Archive
[PDF]
<div class="menu fulltext-thumbnail">
<img src="https://blobs.fatcat.wiki/thumbnail/pdf/fc/87/fc8753f057d8ad10b5d1e97240d1964d55892e54.180px.jpg" alt="fulltext thumbnail" loading="lazy">
</div>
</button>
</a>
<a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/1273496.1273510">
<button class="ui left aligned compact blue labeled icon button serp-button">
<i class="external alternate icon"></i>
acm.org
</button>
</a>
On-line semi-supervised multiple-instance boosting
<span title="">2010</span>
<i title="IEEE">
<a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ilwxppn4d5hizekyd3ndvy2mii" style="color: black;">2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition</a>
</i>
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit <a rel="external noopener" href="http://www.ymer.org/papers/files/2010-MILSERBoost.pdf">the original URL</a>. The file type is <code>application/pdf</code>.
Semi-supervised learning allows for incorporating priors and is more robust in case of occlusions while multiple-instance learning resolves the uncertainties where to take positive updates during tracking ...
Recent approaches tackled this problem by formulating tracking-by-detection as either one-shot semi-supervised learning or multiple instance learning. ...
In this work, we propose to combine the ideas from semi-supervised learning and multiple-instance learning (see Fig. 1 ). ...
<span class="external-identifiers">
<a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cvpr.2010.5539860">doi:10.1109/cvpr.2010.5539860</a>
<a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/cvpr/ZeislLSB10.html">dblp:conf/cvpr/ZeislLSB10</a>
<a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/svav6aprsrgmtgwsrm5nxdeiey">fatcat:svav6aprsrgmtgwsrm5nxdeiey</a>
</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170730125937/http://www.ymer.org/papers/files/2010-MILSERBoost.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext">
<button class="ui simple right pointing dropdown compact black labeled icon button serp-button">
<i class="icon ia-icon"></i>
Web Archive
[PDF]
<div class="menu fulltext-thumbnail">
<img src="https://blobs.fatcat.wiki/thumbnail/pdf/2f/32/2f326e2e5cdfdf53b6a8155163865fbd14255e6f.180px.jpg" alt="fulltext thumbnail" loading="lazy">
</div>
</button>
</a>
<a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cvpr.2010.5539860">
<button class="ui left aligned compact blue labeled icon button serp-button">
<i class="external alternate icon"></i>
ieee.com
</button>
</a>
A Generic Framework for Video Annotation via Semi-Supervised Learning
<span title="">2012</span>
<i title="Institute of Electrical and Electronics Engineers (IEEE)">
<a target="_blank" rel="noopener" href="https://fatcat.wiki/container/sbzicoknnzc3tjljn7ifvwpooi" style="color: black;">IEEE transactions on multimedia</a>
</i>
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit <a rel="external noopener" href="http://nlpr-web.ia.ac.cn:80/mmc/homepage/tzzhang/tianzhu%20zhang_files/Journal%20Articles/TMM12_zhang_A%20Generic%20Framework%20for%20Video%20Annotation.pdf">the original URL</a>. The file type is <code>application/pdf</code>.
To address this issue, Concave-Convex Procedure (CCCP) and nonnegative multiplicative updating rule are adopted. ...
To tackle this problem, we propose a novel Multiple Instance Learning Induced Similarity (MILIS) measure by learning instance sensitive classifiers; 2) how to solve the algorithm efficiently for large-scale ...
(as introduced in Section III) together to learn event model, and adopts multiple instance learning to detect the positive event instances from the event bags, where we consider the event with precise ...
<span class="external-identifiers">
<a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tmm.2012.2191944">doi:10.1109/tmm.2012.2191944</a>
<a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/7uaujwzq4nfrto5jaim7bf4ify">fatcat:7uaujwzq4nfrto5jaim7bf4ify</a>
</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20180107074945/http://nlpr-web.ia.ac.cn:80/mmc/homepage/tzzhang/tianzhu%20zhang_files/Journal%20Articles/TMM12_zhang_A%20Generic%20Framework%20for%20Video%20Annotation.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext">
<button class="ui simple right pointing dropdown compact black labeled icon button serp-button">
<i class="icon ia-icon"></i>
Web Archive
[PDF]
<div class="menu fulltext-thumbnail">
<img src="https://blobs.fatcat.wiki/thumbnail/pdf/7d/f7/7df7bd36179ba1851497307b733dd7b3316d1dd8.180px.jpg" alt="fulltext thumbnail" loading="lazy">
</div>
</button>
</a>
<a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tmm.2012.2191944">
<button class="ui left aligned compact blue labeled icon button serp-button">
<i class="external alternate icon"></i>
ieee.com
</button>
</a>
A generic framework for event detection in various video domains
<span title="">2010</span>
<i title="ACM Press">
<a target="_blank" rel="noopener" href="https://fatcat.wiki/container/lahlxihmo5fhzpexw7rundu24u" style="color: black;">Proceedings of the international conference on Multimedia - MM '10</a>
</i>
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit <a rel="external noopener" href="http://www.nlpr.ia.ac.cn/2010papers/gjhy/gh89.pdf">the original URL</a>. The file type is <code>application/pdf</code>.
Concretely, a Graph-based Semi-Supervised Multiple Instance Learning (GSSMIL) algorithm is proposed to jointly explore small-scale expert labeled videos and large-scale unlabeled videos to train the event ...
To tackle this problem, we propose a novel Multiple Instance Learning Induced Similarity (MILIS) measure by learning instance sensitive classifiers. ...
in Sec. 4.2) and adopts multiple instance learning to detect the positive event instances from the event bags, where we consider event with precise localization in a video clip as positive event instance ...
<span class="external-identifiers">
<a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/1873951.1873967">doi:10.1145/1873951.1873967</a>
<a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/mm/ZhangXZLL10.html">dblp:conf/mm/ZhangXZLL10</a>
<a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/aznsm4tedzak3nn4ifq22x2p3y">fatcat:aznsm4tedzak3nn4ifq22x2p3y</a>
</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170809222235/http://www.nlpr.ia.ac.cn/2010papers/gjhy/gh89.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext">
<button class="ui simple right pointing dropdown compact black labeled icon button serp-button">
<i class="icon ia-icon"></i>
Web Archive
[PDF]
<div class="menu fulltext-thumbnail">
<img src="https://blobs.fatcat.wiki/thumbnail/pdf/26/c9/26c94f5286b677cf0e3fecdedc0f58f725a5264d.180px.jpg" alt="fulltext thumbnail" loading="lazy">
</div>
</button>
</a>
<a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/1873951.1873967">
<button class="ui left aligned compact blue labeled icon button serp-button">
<i class="external alternate icon"></i>
acm.org
</button>
</a>
A Convex Relaxation for Weakly Supervised Classifiers
[article]
<span title="2012-06-27">2012</span>
<i >
arXiv
</i>
<span class="release-stage" >pre-print</span>
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit <a rel="external noopener" href="https://arxiv.org/ftp/arxiv/papers/1206/1206.6413.pdf">the original URL</a>. The file type is <code>application/pdf</code>.
Empirically, our method compares favorably to standard ones on different datasets for multiple instance learning and semi-supervised learning as well as on clustering tasks. ...
To avoid this problem, we propose a cost function based on a convex relaxation of the soft-max loss. ...
This paper was partially supported by the European Research Council (SIERRA and VIDEOWORLD projects). ...
<span class="external-identifiers">
<a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1206.6413v1">arXiv:1206.6413v1</a>
<a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/jroc2kovr5e7zdueu6ayvjitfa">fatcat:jroc2kovr5e7zdueu6ayvjitfa</a>
</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200911055936/https://arxiv.org/ftp/arxiv/papers/1206/1206.6413.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext">
<button class="ui simple right pointing dropdown compact black labeled icon button serp-button">
<i class="icon ia-icon"></i>
Web Archive
[PDF]
<div class="menu fulltext-thumbnail">
<img src="https://blobs.fatcat.wiki/thumbnail/pdf/1e/f4/1ef4d73e6e489006c93966ff20af6525f0b46221.180px.jpg" alt="fulltext thumbnail" loading="lazy">
</div>
</button>
</a>
<a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1206.6413v1" title="arxiv.org access">
<button class="ui compact blue labeled icon button serp-button">
<i class="file alternate outline icon"></i>
arxiv.org
</button>
</a>
Semi-supervised multi-instance multi-label learning for video annotation task
<span title="">2012</span>
<i title="ACM Press">
<a target="_blank" rel="noopener" href="https://fatcat.wiki/container/lahlxihmo5fhzpexw7rundu24u" style="color: black;">Proceedings of the 20th ACM international conference on Multimedia - MM '12</a>
</i>
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit <a rel="external noopener" href="https://cs.nju.edu.cn/_upload/tpl/01/0b/267/template267/zhouzh.files/publication/mm12.pdf">the original URL</a>. The file type is <code>application/pdf</code>.
It is also noteworthy that a video clip is often relevant to multiple concepts. Indeed, the video annotation task is inherently a Multi-Instance Multi-Label learning (MIML) problem. ...
This approach takes label correlations into account, and enforces similar instances to share similar multi-labels. ...
instances of all bags, and W is the similarity matrix for instances. ...
<span class="external-identifiers">
<a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/2393347.2396300">doi:10.1145/2393347.2396300</a>
<a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/mm/XuJXZ12.html">dblp:conf/mm/XuJXZ12</a>
<a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/sjrz2obs2fbcte6uafxovtdlmi">fatcat:sjrz2obs2fbcte6uafxovtdlmi</a>
</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170809134536/https://cs.nju.edu.cn/_upload/tpl/01/0b/267/template267/zhouzh.files/publication/mm12.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext">
<button class="ui simple right pointing dropdown compact black labeled icon button serp-button">
<i class="icon ia-icon"></i>
Web Archive
[PDF]
<div class="menu fulltext-thumbnail">
<img src="https://blobs.fatcat.wiki/thumbnail/pdf/54/39/5439850c7461806ad38313a9f47de3c7b9705cb0.180px.jpg" alt="fulltext thumbnail" loading="lazy">
</div>
</button>
</a>
<a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/2393347.2396300">
<button class="ui left aligned compact blue labeled icon button serp-button">
<i class="external alternate icon"></i>
acm.org
</button>
</a>
Audio Event and Scene Recognition: A Unified Approach using Strongly and Weakly Labeled Data
[article]
<span title="2017-02-18">2017</span>
<i >
arXiv
</i>
<span class="release-stage" >pre-print</span>
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/1611.04871v3.pdf">the original URL</a>. The file type is <code>application/pdf</code>.
Other Versions
<span title="2016-11-23">2016</span>
<span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1611.04871v2">arXiv:1611.04871v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/xzhxjmg3ungm3oj3vngowwcpu4">fatcat:xzhxjmg3ungm3oj3vngowwcpu4</a> </span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1611.04871v2">arXiv:1611.04871v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/xzhxjmg3ungm3oj3vngowwcpu4">fatcat:xzhxjmg3ungm3oj3vngowwcpu4</a> </span>
<span title="2016-11-12">2016</span>
<span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1611.04871v1">arXiv:1611.04871v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/bghnu5kg4vb2nk3sjg37hksuf4">fatcat:bghnu5kg4vb2nk3sjg37hksuf4</a> </span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1611.04871v1">arXiv:1611.04871v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/bghnu5kg4vb2nk3sjg37hksuf4">fatcat:bghnu5kg4vb2nk3sjg37hksuf4</a> </span>
In this paper we propose a novel learning framework called Supervised and Weakly Supervised Learning where the goal is to learn simultaneously from weakly and strongly labeled data. ...
The primary problem domain focus of this paper is acoustic event and scene detection in audio recordings. We first propose a naive formulation for leveraging labeled data in both forms. ...
The constraint on this unlabeled data is that they are grouped into bags and within each bag of instances at least one instance is positive. ...
<span class="external-identifiers">
<a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1611.04871v3">arXiv:1611.04871v3</a>
<a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/jclmmvkhzrhyfgjygjpxxafw6a">fatcat:jclmmvkhzrhyfgjygjpxxafw6a</a>
</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200826134331/https://arxiv.org/pdf/1611.04871v3.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext">
<button class="ui simple right pointing dropdown compact black labeled icon button serp-button">
<i class="icon ia-icon"></i>
Web Archive
[PDF]
<div class="menu fulltext-thumbnail">
<img src="https://blobs.fatcat.wiki/thumbnail/pdf/8e/24/8e249e0ca1f1e9b50236e453ae8755e240c0bf72.180px.jpg" alt="fulltext thumbnail" loading="lazy">
</div>
</button>
</a>
<a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1611.04871v3" title="arxiv.org access">
<button class="ui compact blue labeled icon button serp-button">
<i class="file alternate outline icon"></i>
arxiv.org
</button>
</a>
Collective Semi-Supervised Learning for User Profiling in Social Media
[article]
<span title="2016-06-24">2016</span>
<i >
arXiv
</i>
<span class="release-stage" >pre-print</span>
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/1606.07707v1.pdf">the original URL</a>. The file type is <code>application/pdf</code>.
The joint learning from multiple relationships and unlabeled data yields a computationally sound and accurate approach to model user attributes in social media. ...
In this paper, we present a novel solution termed Collective Semi-Supervised Learning (CSL), which provides a principled means to integrate different types of social relationship and unlabeled data under ...
ACKNOWLEDGMENTS This work is supported by the Singapore National Research Foundation under its International Research Centre @ Singapore Funding Initiative and administered by the IDM Programme Office, ...
<span class="external-identifiers">
<a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1606.07707v1">arXiv:1606.07707v1</a>
<a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/2dpz6hiruzh5logx3oh3qpvt7q">fatcat:2dpz6hiruzh5logx3oh3qpvt7q</a>
</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200823040239/https://arxiv.org/pdf/1606.07707v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext">
<button class="ui simple right pointing dropdown compact black labeled icon button serp-button">
<i class="icon ia-icon"></i>
Web Archive
[PDF]
<div class="menu fulltext-thumbnail">
<img src="https://blobs.fatcat.wiki/thumbnail/pdf/60/0f/600fd48db3621714d272f4f23a64c0d0ae37c8d1.180px.jpg" alt="fulltext thumbnail" loading="lazy">
</div>
</button>
</a>
<a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1606.07707v1" title="arxiv.org access">
<button class="ui compact blue labeled icon button serp-button">
<i class="file alternate outline icon"></i>
arxiv.org
</button>
</a>
Convex and Scalable Weakly Labeled SVMs
[article]
<span title="2013-08-22">2013</span>
<i >
arXiv
</i>
<span class="release-stage" >pre-print</span>
Preserved Fulltext
The Internet Archive has a preservation copy of this work in our general collections. The file type is <code>application/pdf</code>.
Other Versions
<span title="2013-08-12">2013</span>
<span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1303.1271v4">arXiv:1303.1271v4</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/veetfsoolfcidm3pqythz2iiwy">fatcat:veetfsoolfcidm3pqythz2iiwy</a> </span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1303.1271v4">arXiv:1303.1271v4</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/veetfsoolfcidm3pqythz2iiwy">fatcat:veetfsoolfcidm3pqythz2iiwy</a> </span>
<span title="2013-07-07">2013</span>
<span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1303.1271v3">arXiv:1303.1271v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/yzmkgug77rcmxbp6rlrdhaxbke">fatcat:yzmkgug77rcmxbp6rlrdhaxbke</a> </span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1303.1271v3">arXiv:1303.1271v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/yzmkgug77rcmxbp6rlrdhaxbke">fatcat:yzmkgug77rcmxbp6rlrdhaxbke</a> </span>
<span title="2013-05-01">2013</span>
<span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1303.1271v2">arXiv:1303.1271v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/nkg6w6gdlnc6bblij6v6mh2x6a">fatcat:nkg6w6gdlnc6bblij6v6mh2x6a</a> </span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1303.1271v2">arXiv:1303.1271v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/nkg6w6gdlnc6bblij6v6mh2x6a">fatcat:nkg6w6gdlnc6bblij6v6mh2x6a</a> </span>
<span title="2013-03-06">2013</span>
<span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1303.1271v1">arXiv:1303.1271v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/rsckc72vorfzpakiqnn57uabty">fatcat:rsckc72vorfzpakiqnn57uabty</a> </span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1303.1271v1">arXiv:1303.1271v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/rsckc72vorfzpakiqnn57uabty">fatcat:rsckc72vorfzpakiqnn57uabty</a> </span>
In this paper, we study the problem of learning from weakly labeled data, where labels of the training examples are incomplete. ...
Experiments on three weakly labeled learning tasks, namely, (i) semi-supervised learning; (ii) multi-instance learning for locating regions of interest in content-based information retrieval; and (iii) ...
It is worth noting that identification of the key (or positive) instances from the positive bags can be very useful in many real-world applications. ...
<span class="external-identifiers">
<a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1303.1271v5">arXiv:1303.1271v5</a>
<a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/3xqbttwx5rffjmifidls5tapfi">fatcat:3xqbttwx5rffjmifidls5tapfi</a>
</span>
<a target="_blank" rel="noopener" href="https://archive.org/download/arxiv-1303.1271/1303.1271.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext">
<button class="ui simple right pointing dropdown compact black labeled icon button serp-button">
<i class="icon ia-icon"></i>
File Archive
[PDF]
</button>
</a>
<a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1303.1271v5" title="arxiv.org access">
<button class="ui compact blue labeled icon button serp-button">
<i class="file alternate outline icon"></i>
arxiv.org
</button>
</a>
On multiple-instance learning of halfspaces
<span title="">2012</span>
<i title="Elsevier BV">
<a target="_blank" rel="noopener" href="https://fatcat.wiki/container/5xfy4fcdxvcvdiybp6iqbffqc4" style="color: black;">Information Processing Letters</a>
</i>
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit <a rel="external noopener" href="http://indigo.uic.edu/bitstream/handle/10027/9674/MILHalfspacesIPL-June1-final%20%281%29.pdf?sequence=2">the original URL</a>. The file type is <code>application/pdf</code>.
In multiple-instance learning the learner receives bags, i.e., sets of instances. A bag is labeled positive if it contains a positive example of the target. ...
We also show that the hypothesis finding problem is NP-complete and formulate several open problems. ...
Acknowledgement: We would like to thank Robert Langlois, Hans Ulrich Simon, and Balázs Szörényi for several interesting discussions. ...
<span class="external-identifiers">
<a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.ipl.2012.08.017">doi:10.1016/j.ipl.2012.08.017</a>
<a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/b2qodm6j2vazblmzmd53arwk64">fatcat:b2qodm6j2vazblmzmd53arwk64</a>
</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170809122749/http://indigo.uic.edu/bitstream/handle/10027/9674/MILHalfspacesIPL-June1-final%20%281%29.pdf?sequence=2" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext">
<button class="ui simple right pointing dropdown compact black labeled icon button serp-button">
<i class="icon ia-icon"></i>
Web Archive
[PDF]
<div class="menu fulltext-thumbnail">
<img src="https://blobs.fatcat.wiki/thumbnail/pdf/3a/b8/3ab83fdc1275779504cb95ced61afce579b8910c.180px.jpg" alt="fulltext thumbnail" loading="lazy">
</div>
</button>
</a>
<a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.ipl.2012.08.017">
<button class="ui left aligned compact blue labeled icon button serp-button">
<i class="external alternate icon"></i>
elsevier.com
</button>
</a>
Improving Image Categorization by Using Multiple Instance Learning with Spatial Relation
[chapter]
<span title="">2011</span>
<i title="Springer Berlin Heidelberg">
<a target="_blank" rel="noopener" href="https://fatcat.wiki/container/2w3awgokqne6te4nvlofavy5a4" style="color: black;">Lecture Notes in Computer Science</a>
</i>
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit <a rel="external noopener" href="https://link.springer.com/content/pdf/10.1007%2F978-3-642-24085-0_12.pdf">the original URL</a>. The file type is <code>application/pdf</code>.
Discriminative Multiple Instance Learning (MIL) can be used for this task by regarding each image as a bag and sub-windows in the image as instances. ...
We select a subset of sub-windows per positive bag to avoid those limitations. Spatial relations between sub-windows are used as clues for selection. ...
Given training bags and instances that satisfy MIL labeling constraints, MIL approaches can learn to classify unlabeled bags as well as unlabeled instances in the bags. ...
<span class="external-identifiers">
<a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-642-24085-0_12">doi:10.1007/978-3-642-24085-0_12</a>
<a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/wckxnasmarcw5maf5nklxwfica">fatcat:wckxnasmarcw5maf5nklxwfica</a>
</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190503040523/https://link.springer.com/content/pdf/10.1007%2F978-3-642-24085-0_12.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext">
<button class="ui simple right pointing dropdown compact black labeled icon button serp-button">
<i class="icon ia-icon"></i>
Web Archive
[PDF]
<div class="menu fulltext-thumbnail">
<img src="https://blobs.fatcat.wiki/thumbnail/pdf/74/23/74237ae8f2ab9af57b63cef9b943c552e9371037.180px.jpg" alt="fulltext thumbnail" loading="lazy">
</div>
</button>
</a>
<a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-642-24085-0_12">
<button class="ui left aligned compact blue labeled icon button serp-button">
<i class="external alternate icon"></i>
springer.com
</button>
</a>
Ballpark Learning: Estimating Labels from Rough Group Comparisons
[article]
<span title="2016-06-30">2016</span>
<i >
arXiv
</i>
<span class="release-stage" >pre-print</span>
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/1607.00034v1.pdf">the original URL</a>. The file type is <code>application/pdf</code>.
In our setting, we receive sets ("bags") of unlabeled instances with constraints on label proportions. ...
We relax the unrealistic assumption of known label proportions, made in previous work; instead, we assume only to have upper and lower bounds, and constraints on bag differences. ...
The authors thank the anonymous reviewers and Ami Wiesel for their helpful comments. Dafna Shahaf is a Harry&Abe Sherman assistant professor, and is supported by ISF grant 1764/15 and Alon grant. ...
<span class="external-identifiers">
<a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1607.00034v1">arXiv:1607.00034v1</a>
<a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/tmao36pf4zaihkhkdplrocpopy">fatcat:tmao36pf4zaihkhkdplrocpopy</a>
</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191016133552/https://arxiv.org/pdf/1607.00034v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext">
<button class="ui simple right pointing dropdown compact black labeled icon button serp-button">
<i class="icon ia-icon"></i>
Web Archive
[PDF]
<div class="menu fulltext-thumbnail">
<img src="https://blobs.fatcat.wiki/thumbnail/pdf/cd/e2/cde27648c4c64acb01b192bdc52c133321536e33.180px.jpg" alt="fulltext thumbnail" loading="lazy">
</div>
</button>
</a>
<a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1607.00034v1" title="arxiv.org access">
<button class="ui compact blue labeled icon button serp-button">
<i class="file alternate outline icon"></i>
arxiv.org
</button>
</a>
MI2LS
<span title="">2013</span>
<i title="ACM Press">
<a target="_blank" rel="noopener" href="https://fatcat.wiki/container/fqqihtxlu5bvfaqxjyvqcob35a" style="color: black;">Proceedings of the 19th ACM SIGKDD international conference on Knowledge discovery and data mining - KDD '13</a>
</i>
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit <a rel="external noopener" href="http://faculty.engineering.asu.edu/jingruihe/wp-content/uploads/2015/06/fp0627-Dans-Laptops-conflicted-copy-2013-06-25.pdf">the original URL</a>. The file type is <code>application/pdf</code>.
In Multiple Instance Learning (MIL), each entity is normally expressed as a set of instances. ...
Out of a similar motivation, to incorporate the consistencies between different information sources into MIL, we propose a novel research framework -Multi-Instance Learning from Multiple Information Sources ...
However, the proposed formulation is non-convex and contains too many constraints derived on both the bag and the instance levels. ...
<span class="external-identifiers">
<a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/2487575.2487651">doi:10.1145/2487575.2487651</a>
<a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/kdd/ZhangHL13.html">dblp:conf/kdd/ZhangHL13</a>
<a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ldesbl7thnc3ti73cp3d3qzjwa">fatcat:ldesbl7thnc3ti73cp3d3qzjwa</a>
</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170829055819/http://faculty.engineering.asu.edu/jingruihe/wp-content/uploads/2015/06/fp0627-Dans-Laptops-conflicted-copy-2013-06-25.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext">
<button class="ui simple right pointing dropdown compact black labeled icon button serp-button">
<i class="icon ia-icon"></i>
Web Archive
[PDF]
<div class="menu fulltext-thumbnail">
<img src="https://blobs.fatcat.wiki/thumbnail/pdf/70/34/703478b0b7745784b240d7814e689a51d6e5c258.180px.jpg" alt="fulltext thumbnail" loading="lazy">
</div>
</button>
</a>
<a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/2487575.2487651">
<button class="ui left aligned compact blue labeled icon button serp-button">
<i class="external alternate icon"></i>
acm.org
</button>
</a>
∝SVM for learning with label proportions
[article]
<span title="2013-06-04">2013</span>
<i >
arXiv
</i>
<span class="release-stage" >pre-print</span>
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/1306.0886v1.pdf">the original URL</a>. The file type is <code>application/pdf</code>.
We study the problem of learning with label proportions in which the training data is provided in groups and only the proportion of each class in each group is known. ...
In order to solve it efficiently, we propose two algorithms: one based on simple alternating optimization and the other based on a convex relaxation. ...
We thank Novi Quadrianto and Yu-Feng Li for their help. We thank Jun Wang, Yadong Mu and anonymous reviewers for the insightful suggestions. ...
<span class="external-identifiers">
<a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1306.0886v1">arXiv:1306.0886v1</a>
<a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/oo6kfenzu5eljgsqjvtdf5oosy">fatcat:oo6kfenzu5eljgsqjvtdf5oosy</a>
</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200911055225/https://arxiv.org/pdf/1306.0886v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext">
<button class="ui simple right pointing dropdown compact black labeled icon button serp-button">
<i class="icon ia-icon"></i>
Web Archive
[PDF]
<div class="menu fulltext-thumbnail">
<img src="https://blobs.fatcat.wiki/thumbnail/pdf/d0/1d/d01dfc8eb4ef0ded67f3096c133aa047d2bb0062.180px.jpg" alt="fulltext thumbnail" loading="lazy">
</div>
</button>
</a>
<a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1306.0886v1" title="arxiv.org access">
<button class="ui compact blue labeled icon button serp-button">
<i class="file alternate outline icon"></i>
arxiv.org
</button>
</a>
« Previous
Showing results 1 — 15 out of 982 results