Filters








137,905 Hits in 6.8 sec

Multiple-Instance Active Learning for Image Categorization [chapter]

Dong Liu, Xian-Sheng Hua, Linjun Yang, Hong-Jiang Zhang
<span title="">2009</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> &nbsp;
Both multiple-instance learning and active learning are widely employed in image categorization, but generally they are applied separately. This paper studies the integration of these two methods.  ...  Different from typical active learning approaches, the sample selection strategy in multiple-instance active learning needs to handle samples in different granularities, that is, instance/region and bag  ...  In this paper, we study the integration of multiple-instance learning and active learning in image categorization application.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-540-92892-8_27">doi:10.1007/978-3-540-92892-8_27</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/vzzt3ldmlfd7bpka6xjfmwalk4">fatcat:vzzt3ldmlfd7bpka6xjfmwalk4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170809042837/http://www.ee.columbia.edu/~dongliu/Papers/ActiveLearning_MMM09.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/da/c4/dac482743ba7aada875110c77ccdb7a0dcdb816e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-540-92892-8_27"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

A Survey on Multi-label Classification for Images

Radhika Devkar, Sankirti Shiravale
<span title="2017-03-15">2017</span> <i title="Foundation of Computer Science"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/b637noqf3vhmhjevdfk3h5pdsu" style="color: black;">International Journal of Computer Applications</a> </i> &nbsp;
In multi-label classification, each instance is assigned to multiple classes; it is a common problem in data analysis.  ...  Finally, paper is concluded towards challenges in multi-label classification for images for future research.  ...  [27] , represented categorization technique for object to categorize into multiple and nested categories and it uses joint SVM to learn visual categories. Xiaoyu Zhang et al.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5120/ijca2017913398">doi:10.5120/ijca2017913398</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ogsxomnv2fet3pmio5tbxym3fe">fatcat:ogsxomnv2fet3pmio5tbxym3fe</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20180603012854/https://www.ijcaonline.org/archives/volume162/number8/devkar-2017-ijca-913398.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/40/30/40304366505520da5c6ec3b633cef1aaa717d553.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5120/ijca2017913398"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

DEMIAL: an active learning framework for multiple instance image classification using dictionary ensembles

Gökhan KOÇYİĞİT, Yusuf YASLAN
<span title="">2018</span> <i title="The Scientific and Technological Research Council of Turkey"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ewkcv4t6w5f2pc7j2w426gox7a" style="color: black;">Turkish Journal of Electrical Engineering and Computer Sciences</a> </i> &nbsp;
Due to the structure of images, different regions can be interpreted as instances. Thus, multiple instances can be obtained for each image, which makes image categorization a MIL problem.  ...  In this work, we develop DEMIAL (dictionary ensembles multiple instance active learning), a multiple instance active learning method that utilizes sparse feature representation and classifier ensemble  ...  Acknowledgment We express our thanks to Prof Dr Zehra Ç ataltepe for her valuable comments.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3906/elk-1703-319">doi:10.3906/elk-1703-319</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/oibqddzzbzbclgdfhlxy3ai3ym">fatcat:oibqddzzbzbclgdfhlxy3ai3ym</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200209075231/http://journals.tubitak.gov.tr/elektrik/issues/elk-18-26-1/elk-26-1-49-1703-319.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/49/97/499724a22f4230a9ee7550da059d0841aa9f966a.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3906/elk-1703-319"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> Publisher / doi.org </button> </a>

Convolutional Cobweb: A Model of Incremental Learning from 2D Images [article]

Christopher J. MacLellan, Harshil Thakur
<span title="2022-01-18">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
This paper presents a new concept formation approach that supports the ability to incrementally learn and predict labels for visual images.  ...  This work integrates the idea of convolutional image processing, from computer vision research, with a concept formation approach that is based on psychological studies of how humans incrementally form  ...  We also thank the Drexel University STAR program for providing support for Harshil Thakur to work on this project over the summer term.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2201.06740v1">arXiv:2201.06740v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/zozjd7gzangapivljhv32gumku">fatcat:zozjd7gzangapivljhv32gumku</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220121203124/https://arxiv.org/pdf/2201.06740v1.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/ea/7d/ea7d9b7908498fbb498acb6e248a043311496fa6.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2201.06740v1" 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>

Revisiting Multiple Instance Neural Networks [article]

Xinggang Wang, Yongluan Yan, Peng Tang, Xiang Bai, Wenyu Liu
<span title="2016-10-08">2016</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this paper, we revisit the problem of solving multiple instance learning problems using neural networks. Neural networks are appealing for solving multiple instance learning problem.  ...  Deep neural networks have achieved great success in supervised learning problems, and multiple instance learning as a typical weakly-supervised learning method is effective for many applications in computer  ...  INTRODUCTION Multiple instance learning (MIL) was originally proposed for drug activity prediction [1] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1610.02501v1">arXiv:1610.02501v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/qmaxn4ms3rfvpp7ch2z2pxj3ju">fatcat:qmaxn4ms3rfvpp7ch2z2pxj3ju</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191022035024/https://arxiv.org/pdf/1610.02501v1.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/08/20/0820ccfdba775c304bedb9c3d82ee8758e0a416b.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1610.02501v1" 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>

Category-orthogonal object features guide information processing in recurrent neural networks trained for object categorization [article]

Sushrut Thorat, Giacomo Aldegheri, Tim C. Kietzmann
<span title="2022-05-10">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Here we test RNNs trained for object categorization on the hypothesis that recurrence iteratively aids object categorization via the communication of category-orthogonal auxiliary variables (the location  ...  Recurrent neural networks (RNNs) have been shown to perform better than feedforward architectures in visual object categorization tasks, especially in challenging conditions such as cluttered images.  ...  successfully learned to classify the images in the dataset.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2111.07898v2">arXiv:2111.07898v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ky2ogo342vfzledtqsk65shvwe">fatcat:ky2ogo342vfzledtqsk65shvwe</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220512230441/https://arxiv.org/pdf/2111.07898v2.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/b9/f1/b9f1f3411233b5b5f115d29d8ae5e5d7b5291547.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2111.07898v2" 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>

Minimizing Supervision in Multi-label Categorization [article]

Rajat, Munender Varshney, Pravendra Singh, Vinay P. Namboodi
<span title="2020-05-26">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
The approach we adopt is one of active learning, i.e., incrementally selecting a set of samples that need supervision based on the current model, obtaining supervision for these samples, retraining the  ...  Multiple categories of objects are present in most images. Treating this as a multi-class classification is not justified. We treat this as a multi-label classification problem.  ...  images from which we pool images in small increment for multiple iterations using active learning metrics.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2005.12892v1">arXiv:2005.12892v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/sd653cguurg2ldcqa2a2dvy45m">fatcat:sd653cguurg2ldcqa2a2dvy45m</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200529093520/https://arxiv.org/pdf/2005.12892v1.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] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2005.12892v1" 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>

Unsupervised Object Class Discovery via Saliency-Guided Multiple Class Learning

Jun-Yan Zhu, Jiajun Wu, Yan Xu, Eric Chang, Zhuowen Tu
<span title="2015-04-01">2015</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/3px634ph3vhrtmtuip6xznraqi" style="color: black;">IEEE Transactions on Pattern Analysis and Machine Intelligence</a> </i> &nbsp;
detection is adopted to convert unsupervised learning into multiple instance learning, formulated as bottom-up multiple class learning (bMCL); (2) we utilize the Discriminative EM (DiscEM) to solve our  ...  We develop an algorithm for simultaneously localizing objects and discovering object classes via bottom-up (saliency-guided) multiple class learning (bMCL), and make the following contributions: (1) saliency  ...  Review of Multiple Instance Learning Multiple instance learning (MIL) is a popular approach in weakly supervised learning.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tpami.2014.2353617">doi:10.1109/tpami.2014.2353617</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/26353299">pmid:26353299</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/cg3y3ayekvdapd74ijzwpaxruy">fatcat:cg3y3ayekvdapd74ijzwpaxruy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170808210758/http://pages.ucsd.edu/~ztu/publication/cvpr12_bmcl.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/33/8e/338e74b41371fc2b25064c2f3fa4ebcfe509fb2c.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tpami.2014.2353617"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Unsupervised object class discovery via saliency-guided multiple class learning

Jun-Yan Zhu, Jiajun Wu, Yichen Wei, Eric Chang, Zhuowen Tu
<span title="">2012</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ilwxppn4d5hizekyd3ndvy2mii" style="color: black;">2012 IEEE Conference on Computer Vision and Pattern Recognition</a> </i> &nbsp;
detection is adopted to convert unsupervised learning into multiple instance learning, formulated as bottom-up multiple class learning (bMCL); (2) we utilize the Discriminative EM (DiscEM) to solve our  ...  We develop an algorithm for simultaneously localizing objects and discovering object classes via bottom-up (saliency-guided) multiple class learning (bMCL), and make the following contributions: (1) saliency  ...  Review of Multiple Instance Learning Multiple instance learning (MIL) is a popular approach in weakly supervised learning.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cvpr.2012.6248057">doi:10.1109/cvpr.2012.6248057</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/cvpr/ZhuWWCT12.html">dblp:conf/cvpr/ZhuWWCT12</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/f62oxwaev5f5bjkcascvnvwhhm">fatcat:f62oxwaev5f5bjkcascvnvwhhm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170808210758/http://pages.ucsd.edu/~ztu/publication/cvpr12_bmcl.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/33/8e/338e74b41371fc2b25064c2f3fa4ebcfe509fb2c.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cvpr.2012.6248057"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

A brief introduction to weakly supervised learning

Zhi-Hua Zhou
<span title="2017-08-25">2017</span> <i title="Oxford University Press (OUP)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/u4bdhpukkbe3ncikyibr6q4x7e" style="color: black;">National Science Review</a> </i> &nbsp;
Thus, it is desirable for machine-learning techniques to work with weak supervision.  ...  Supervised learning techniques construct predictive models by learning from a large number of training examples, where each training example has a label indicating its ground-truth output.  ...  Multi-instance learning has been successfully applied to various tasks, such as image categorization/retrieval/annotation [48] [49] [50] , text categorization [51, 52] , spam detection [53] , medical  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1093/nsr/nwx106">doi:10.1093/nsr/nwx106</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/k4kkqubjabck5kk72fl5ahmq7u">fatcat:k4kkqubjabck5kk72fl5ahmq7u</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190503135633/https://watermark.silverchair.com/nwx106.pdf?token=AQECAHi208BE49Ooan9kkhW_Ercy7Dm3ZL_9Cf3qfKAc485ysgAAAjQwggIwBgkqhkiG9w0BBwagggIhMIICHQIBADCCAhYGCSqGSIb3DQEHATAeBglghkgBZQMEAS4wEQQMA7SZQ4KSgWHD3DwqAgEQgIIB5yCzEbMpW8U2MlTKe-LSQK9Fmry1rGmeKedFetrbh8dgw1LMxz_3_6e2jB7jzEAgVbHFTUXFFAJI3IX3efuS58UKuN4L00B7VG31cPwmcPG6-VAZI-_qVtADub11do5gQofM7pkljY_HUcq8vrF7O1XIrTS5A0DvQOQVZ2PXGTHqX0FWkadSbTXtk18sKs_iwhk8Qx3I7gO_f5NkKD1P2nH4IGIZZir4R-bqm9xiYa0VKM1p0a2u2R8R3-isTSTXb5aAry26_UUciy6mYgZVVdXCUVxyja3C1ipyFdxhkFqCtcrhkI6WqvrN8BB3hkZyrKf0kI3A-2T59Q8RFMzUOepg0ztNOcUbE2uE-rWZVug1na3D5jDIcpdnW6eNnOzV2034PV2vfaVCG5e7XyF8wygs_xTET9HhtuxTObe2xn2KJ74cfkTYErvzQXx9iSEmpILSwXANQLpk_M209ZDJ67HhBrP304RHdhrr0QV9pttn4u-xv3gC6WMxPf5pSzgcnVoAYG7faLHanJGH-Q7trg-NvUXZYfwRl5ai0ECwUzdDD62NQawBXlNkrycbpeQNpoCdbhadsuOcTAg7hUK03Ks6-hHwemctMjCRVuI2aJc83j1sd8xSRZ42fNfjZ-s-frkRRmD0tkY" 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/61/82/6182413ba608fc60926a878470ee0e1324fdee26.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1093/nsr/nwx106"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> oup.com </button> </a>

Twin Support Vector Machine for Multiple Instance Learning Based on Bag Dissimilarities

Divya Tomar, Sonal Agarwal
<span title="">2016</span> <i title="Hindawi Limited"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/gdgab5ivavcfro52kek2ipdpfi" style="color: black;">Advances in Artificial Intelligence</a> </i> &nbsp;
In multiple instance learning (MIL) framework, an object is represented by a set of instances referred to as bag.  ...  In this study, we represent each bag by a vector of its dissimilarities to the other existing bags in the training dataset and propose a multiple instance learning based Twin Support Vector Machine (MIL-TWSVM  ...  Wu et al. extended deep learning to multiple instance learning framework for image annotation [51] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1155/2016/1269708">doi:10.1155/2016/1269708</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/52ze5ehtvbadjlkiaynixtvary">fatcat:52ze5ehtvbadjlkiaynixtvary</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200209193453/http://downloads.hindawi.com/archive/2016/1269708.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/24/cd/24cd7633dcb5aade201be9cf57598274c0fe5f69.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1155/2016/1269708"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> hindawi.com </button> </a>

Category Learning in the Brain

Carol A. Seger, Earl K. Miller
<span title="">2010</span> <i title="Annual Reviews"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/wvgbt52rybemba5u26h7rswksq" style="color: black;">Annual Review of Neuroscience</a> </i> &nbsp;
These systems interact during category learning.  ...  The basal ganglia and medial temporal lobe interact competitively or cooperatively, depending on the demands of the learning task.  ...  We thank Timothy Buschman, Jason Cromer, Jefferson Roy, Brian Spiering, and Marlene Wicherski for valuable comments, and Dan Lopez-Paniagua for preparing the figures.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1146/annurev.neuro.051508.135546">doi:10.1146/annurev.neuro.051508.135546</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/20572771">pmid:20572771</a> <a target="_blank" rel="external noopener" href="https://pubmed.ncbi.nlm.nih.gov/PMC3709834/">pmcid:PMC3709834</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/o5umscv6xfhqlfo23cmn2yimre">fatcat:o5umscv6xfhqlfo23cmn2yimre</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190224095244/http://pdfs.semanticscholar.org/6055/6238329efe7974bac7911f350021b4322ab6.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/60/55/60556238329efe7974bac7911f350021b4322ab6.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1146/annurev.neuro.051508.135546"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3709834" title="pubmed link"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> pubmed.gov </button> </a>

MILES: Multiple-Instance Learning via Embedded Instance Selection

Yixin Chen, Jinbo Bi, J.Z. Wang
<span title="">2006</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/3px634ph3vhrtmtuip6xznraqi" style="color: black;">IEEE Transactions on Pattern Analysis and Machine Intelligence</a> </i> &nbsp;
Index Terms-Multiple-instance learning, feature subset selection, 1-norm support vector machine, image categorization, object recognition, drug activity prediction.  ...  We propose a learning method, MILES (Multiple-Instance Learning via Embedded instance Selection), which converts the multiple-instance learning problem to a standard supervised learning problem that does  ...  We would also like to thank Timor Kadir for providing the salient region detector and Rob Fergus for sharing the details on the object class recognition experiments.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tpami.2006.248">doi:10.1109/tpami.2006.248</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/17108368">pmid:17108368</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/sgjls2smpvfdjas7boboxgppoy">fatcat:sgjls2smpvfdjas7boboxgppoy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170809135612/http://www.engr.uconn.edu/~jinbo/doc/mil_tpami06.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/d6/6d/d66d30d3148de6cecce2f2be9f4b99ad4549ccaa.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tpami.2006.248"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Look-ahead before you leap: end-to-end active recognition by forecasting the effect of motion [article]

Dinesh Jayaraman, Kristen Grauman
<span title="2016-08-05">2016</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Results across two challenging datasets confirm both that our end-to-end system successfully learns meaningful policies for active category recognition, and that "learning to look ahead" further boosts  ...  In this work, we first show how a recurrent neural network-based system may be trained to perform end-to-end learning of motion policies suited for this "active recognition" setting.  ...  We also thank Texas Advanced Computing Center for their generous support, and Mohsen Malmir and Jianxiong Xiao for their assistance sharing GERMS and SUN360 data respectively.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1605.00164v2">arXiv:1605.00164v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ftjjkvzu7nfzree24bnqevkf3i">fatcat:ftjjkvzu7nfzree24bnqevkf3i</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200912095105/https://arxiv.org/pdf/1605.00164v2.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/c7/aa/c7aa51818a1a5ccfc6debe105645f1cf31c6923a.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1605.00164v2" 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>

Multimodal fusion using learned text concepts for image categorization

Qiang Zhu, Mei-Chen Yeh, Kwang-Ting Cheng
<span title="">2006</span> <i title="ACM Press"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/lahlxihmo5fhzpexw7rundu24u" style="color: black;">Proceedings of the 14th annual ACM international conference on Multimedia - MULTIMEDIA &#39;06</a> </i> &nbsp;
Specific to each image category, a text concept is first learned from a set of labeled texts in images of the target category using Multiple Instance Learning [1] .  ...  For an image under classification which contains multiple detected text lines, we calculate a weighted Euclidian distance between each text line and the learned text concept of the target category.  ...  The study on Multiple Instance Learning was first motivated by the problem of predicting the drug molecule activity level.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/1180639.1180698">doi:10.1145/1180639.1180698</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/mm/ZhuYC06.html">dblp:conf/mm/ZhuYC06</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/gfnskh6brncl7fz3sva3ja2ag4">fatcat:gfnskh6brncl7fz3sva3ja2ag4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20100806202205/http://engineering.ucsb.edu/~zhuq/paper/mm06.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/e8/34/e834982537c8e2df9835a1802575145cb095b1cd.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/1180639.1180698"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> acm.org </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 137,905 results