Filters








38,924 Hits in 6.2 sec

Dynamical Pose Filtering for Mixtures of Gaussian Processes

Martin Fergie, Aphrodite Galata
<span title="">2012</span> <i title="British Machine Vision Association"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/6bfo5625nvdfvbgyf7ldi5wmfe" style="color: black;">Procedings of the British Machine Vision Conference 2012</a> </i> &nbsp;
In this paper we propose a novel method for discriminative monocular human pose tracking using a mixture of Gaussian processes and a dynamic programming algorithm for selecting the optimal expert at each  ...  We introduce a mixture of Gaussian processes model which optimises the size and location of each expert ensuring that each expert models a coherent region of the dataset resulting in an accurate predictive  ...  [24] adapt the Bayesian mixture of experts by replacing the linear experts with relevance vector machines allowing each expert to model a non-linear function by mapping the inputs through a kernel.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5244/c.26.7">doi:10.5244/c.26.7</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/bmvc/FergieG12.html">dblp:conf/bmvc/FergieG12</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/btdvc7fndjb4tpc5iykzgw56ua">fatcat:btdvc7fndjb4tpc5iykzgw56ua</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20180721030108/http://www.bmva.org/bmvc/2012/BMVC/paper007/paper007.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/e9/d0/e9d077cfc5f5483881321561aee3048af8e42a13.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5244/c.26.7"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

On linear mixture of expert approaches to information retrieval

Weiguo Fan, Michael Gordon, Praveen Pathak
<span title="">2006</span> <i title="Elsevier BV"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/md2ierut4nak5ociupgnvel2oa" style="color: black;">Decision Support Systems</a> </i> &nbsp;
We employ Genetic Algorithms to do such combinations and test our method using a large well known document dataset.  ...  Matching functions match the information in documents with that required by users in terms of queries to produce a set of documents to be presented to the users.  ...  There have been some efforts in using linear mixture of expert approaches, which is similar in philosophy to our approach. Bartell et al.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.dss.2004.11.014">doi:10.1016/j.dss.2004.11.014</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/c3ppcwzjf5hp7c6fae3up6n54a">fatcat:c3ppcwzjf5hp7c6fae3up6n54a</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20050408112855/http://filebox.vt.edu:80/users/wfan/paper/ARRANGER/dss_mixture.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/3f/c5/3fc543f351270a516424968d5a5786a74261ef12.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.dss.2004.11.014"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> elsevier.com </button> </a>

Generalizable Person Re-identification with Relevance-aware Mixture of Experts [article]

Yongxing Dai, Xiaotong Li, Jun Liu, Zekun Tong, Ling-Yu Duan
<span title="2021-05-19">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
To handle the above two issues, we propose a novel method called the relevance-aware mixture of experts (RaMoE), using an effective voting-based mixture mechanism to dynamically leverage source domains  ...  Almost all the existing DG ReID methods follow the same pipeline where they use a hybrid dataset from multiple source domains for training, and then directly apply the trained model to the unseen target  ...  To the best of our knowledge, this is the first work that treats DG ReID as a novel mixture-of-experts paradigm via an effective voting-based mixture mechanism.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2105.09156v1">arXiv:2105.09156v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/cf3w2h22s5bcpnpgaaxah3eyqi">fatcat:cf3w2h22s5bcpnpgaaxah3eyqi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210521092658/https://arxiv.org/pdf/2105.09156v1.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/7f/fb/7ffbc531bbb0f1cf38b47e1d728a0e297f8b4dec.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2105.09156v1" 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>

Mixture of Regression Experts in fMRI Encoding [article]

Subba Reddy Oota, Adithya Avvaru, Naresh Manwani, Raju S. Bapi
<span title="2018-12-01">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this paper, we present a mixture of experts-based model where a group of experts captures brain activity patterns related to particular regions of interest (ROI) and also show the discrimination across  ...  Classical encoding models use linear multi-variate methods to predict the brain activation (all voxels) given the stimulus.  ...  We present an experimental evidence showing that the best encoding model is achieved with the mixture of regression experts rather than using a simple linear/non-linear model alone.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1811.10740v2">arXiv:1811.10740v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/s6ebjoixkvd35pwxfudwcuzf5u">fatcat:s6ebjoixkvd35pwxfudwcuzf5u</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200904204423/https://arxiv.org/pdf/1811.10740v2.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/68/de/68de07c978ad06b7f2ad43eefa758a294339e2e0.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1811.10740v2" 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>

Learning query-class dependent weights in automatic video retrieval

Rong Yan, Jun Yang, Alexander G. Hauptmann
<span title="">2004</span> <i title="ACM Press"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/lahlxihmo5fhzpexw7rundu24u" style="color: black;">Proceedings of the 12th annual ACM international conference on Multimedia - MULTIMEDIA &#39;04</a> </i> &nbsp;
In this work, we propose using query-class dependent weights within a hierarchial mixture-of-expert framework to combine multiple retrieval results.  ...  efficiently and generalized to the unseen queries easily.  ...  Basically we will check if the mean of expert outputs for the relevant training data is smaller than that of the irrelevant training data.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/1027527.1027661">doi:10.1145/1027527.1027661</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/mm/YanYH04.html">dblp:conf/mm/YanYH04</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ygmufz7oifgu3cl3uq7f5ocixe">fatcat:ygmufz7oifgu3cl3uq7f5ocixe</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170922211102/http://cgit.nutn.edu.tw:8080/cgit/PaperDL/CMS_090207132138.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/04/28/04288fe31c2e3839202761e72cd1b87d4f52672f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/1027527.1027661"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> acm.org </button> </a>

SF-HME system

Petros Belsis, Kostas Fragos, Stefanos Gritzalis, Christos Skourlas
<span title="">2006</span> <i title="ACM Press"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/uo6yx5jpgnf2zl7mkrumytd4ti" style="color: black;">Proceedings of the 2006 ACM symposium on Applied computing - SAC &#39;06</a> </i> &nbsp;
In this paper, we propose the SF-HME, a Hierarchical Mixture-of-Experts system, attempting to overcome limitations common to other machinelearning based approaches when applied to spam mail classification  ...  Despite their popularity -due both to their simplicity and relative ease of interpretationthe non-linearity assumption of data samples is inappropriate in practice, due to its inability to capture the  ...  It is commonly used to train Gaussian mixtures and other mixture models. The principle of maximum likelihood is a standard way to motivate error functions.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/1141277.1141360">doi:10.1145/1141277.1141360</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/sac/BelsisFGS06.html">dblp:conf/sac/BelsisFGS06</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/4dpk3ggbsfc4pita2qlhqsyuyi">fatcat:4dpk3ggbsfc4pita2qlhqsyuyi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20120803070410/http://glotta.ntua.gr:80/nlp_lab/Fraggos/files/SAC2006submitted.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/6f/4d/6f4dca9519b41d7698f6367ecc5a289b1c0b01f9.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/1141277.1141360"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> acm.org </button> </a>

Regression tracking with data relevance determination

Ioannis Patras, Edwin R. Hancock
<span title="">2007</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ilwxppn4d5hizekyd3ndvy2mii" style="color: black;">2007 IEEE Conference on Computer Vision and Pattern Recognition</a> </i> &nbsp;
To this end, a Bayesian Mixture of Experts (BME) is trained on a dataset of image patches that are generated by applying artificial transformations to the template at the first frame.  ...  To do so, we couple the BME with a probabilistic kernel-based classifier which, when trained, can determine the probability that a new/unseen observation can accurately predict the state of the target  ...  [11] train Bayesian Mixture of Experts in order to learn a multimodal posterior p(x|y).  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cvpr.2007.383239">doi:10.1109/cvpr.2007.383239</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/cvpr/PatrasH07.html">dblp:conf/cvpr/PatrasH07</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/lpqss4dmkzfkhktu6rz3rh4by4">fatcat:lpqss4dmkzfkhktu6rz3rh4by4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20120417142911/http://www.eecs.qmul.ac.uk:80/~ioannisp/pubs/ecopies/CVPR2007RegressionTracking.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/44/fb/44fbf234bafb9d667bf71a6bb93939020a7420c1.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cvpr.2007.383239"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Solving Regression Problems Using Competitive Ensemble Models [chapter]

Yakov Frayman, Bernard F. Rolfe, Geoffrey I. Webb
<span title="">2002</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;
A comparison is made between a competitive ensemble model and that of MARS with bagging, mixture of experts, hierarchical mixture of experts and a neural network ensemble over several public domain regression  ...  However, it is also possible to combine the ensemble members in a competitive fashion where the best prediction of a relevant ensemble member is selected for a particular input.  ...  In Tables 2-6 , HME (ensemble learning) is a Hierarchical mixture of experts trained using Bayesian methods, HME (early stopping) is a Hierarchical mixtures of experts trained using early stopping, HME  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/3-540-36187-1_45">doi:10.1007/3-540-36187-1_45</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/rzs6gbolbrcspeqgpkbyk5gznq">fatcat:rzs6gbolbrcspeqgpkbyk5gznq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20050528154100/http://www.csse.monash.edu:80/~webb/Files/FraymanRolfeWebb02.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/24/25/2425391d19a3658dbdd7307774bba8774429e330.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/3-540-36187-1_45"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

Deformable model fitting with a mixture of local experts

Jason M Saragih, Simon Lucey, Jeffrey F Cohn
<span title="">2009</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/753trptklbb4nj6jquqadzwwdu" style="color: black;">2009 IEEE 12th International Conference on Computer Vision</a> </i> &nbsp;
In particular, the use of a mixture of linear classifiers is proposed, the computational complexity of which scales linearly with the number of mixture components.  ...  Local experts have been used to great effect for fitting deformable models to images.  ...  In all methods the linear SVM was used for the local experts, where the training data consisted of (11 × 11)-patches.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/iccv.2009.5459461">doi:10.1109/iccv.2009.5459461</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/iccv/SaragihLC09a.html">dblp:conf/iccv/SaragihLC09a</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/3bxiph4jijfvhibkvz7yct5cqm">fatcat:3bxiph4jijfvhibkvz7yct5cqm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170813042215/http://vigir.missouri.edu/~gdesouza/Research/Conference_CDs/IEEE_ICCV_2009/contents/pdf/iccv2009_290.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/bb/6a/bb6a056f91b23745971e9da029baeef24c780bf9.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/iccv.2009.5459461"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Adaptive Mixtures of Local Experts

Robert A. Jacobs, Michael I. Jordan, Steven J. Nowlan, Geoffrey E. Hinton
<span title="">1991</span> <i title="MIT Press - Journals"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/rckx6fqoszfvva5c53bqivu5am" style="color: black;">Neural Computation</a> </i> &nbsp;
We present a new supervised learning procedure for systems composed of many separate networks, each of which learns to handle a subset of the complete set of training cases.  ...  We demonstrate that the learning procedure divides up a vowel discrimination task into appropriate subtasks, each of which can be solved by a very simple expert network.  ...  Hinton is a fellow of the Canadian Institute for Advanced Research.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1162/neco.1991.3.1.79">doi:10.1162/neco.1991.3.1.79</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/4p7qojbaujbrbmwv2iv74mfimi">fatcat:4p7qojbaujbrbmwv2iv74mfimi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20140811051022/http://courses.cs.tamu.edu/rgutier/cpsc636_s10/jacobs1991moe.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/c8/d9/c8d90974c3f3b40fa05e322df2905fc16204aa56.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1162/neco.1991.3.1.79"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> mitpressjournals.org </button> </a>

Efficient bifurcation and parameterization of multi-dimensional combustion manifolds using deep mixture of experts: an a priori study [article]

Opeoluwa Owoyele, Prithwish Kundu, Pinaki Pal
<span title="2019-11-08">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
This approach relies on the mixture of experts (MoE) framework, where each neural network is trained to be specialized in a given portion of the input space.  ...  The assignment of different input regions to the experts is determined by a gating network, which is a neural network classifier.  ...  Acknowledgements The submitted manuscript has been created by UChicago Argonne, LLC, Operator of Argonne National  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1910.10765v2">arXiv:1910.10765v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/uqrk5yo3jncyvhryzhiazfsshy">fatcat:uqrk5yo3jncyvhryzhiazfsshy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200901152158/https://arxiv.org/ftp/arxiv/papers/1910/1910.10765.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/83/ea836b383b4687bc209fd516384825252ce8d69e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1910.10765v2" 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>

Using knowledge partitioning to investigate the psychological plausibility of mixtures of experts

Sébastien Hélie, Gyslain Giguère, Denis Cousineau, Robert Proulx
<span title="2007-08-22">2007</span> <i title="Springer Nature"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/srtrvzrec5a3fmhgvgc3676jlu" style="color: black;">Artificial Intelligence Review</a> </i> &nbsp;
Also, some participants used non-linear experts to partition the stimulus space. This new type of KP was further explored in a second study, which included more training sessions.  ...  Over the years, the presence of knowledge partitioning (KP) in human function learning data has been used to argue that mixture-of-experts models (MOE) constitute a psychologically plausible explanation  ...  Acknowledgements The authors would like to thank Dominic Charbonneau and Sonja Engmann for their help with the participants in the experiments, and two anonymous reviewers for their useful comments on  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/s10462-007-9024-7">doi:10.1007/s10462-007-9024-7</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/7amx7mlutvbjvn7rrml5vpx2ne">fatcat:7amx7mlutvbjvn7rrml5vpx2ne</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20100619204823/http://www.psych.ucsb.edu/%7Ehelie/papers/Helie.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/9d/c4/9dc47f39aa04c88373b3594f9e9e6b2f2bad1704.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/s10462-007-9024-7"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

Expert2Coder: Capturing Divergent Brain Regions Using Mixture of Regression Experts [article]

Subba Reddy Oota and Naresh Manwani and Raju S. Bapi
<span title="2020-05-29">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this paper, we achieve this by clustering similar regions together and for every cluster we learn a different linear regression model using a mixture of linear experts model.  ...  State-of-the-art encoding models use a single global model (linear or non-linear) to predict brain activation given the stimulus.  ...  MoRE Training Using the approach discussed in Section II and using the insights from the experiments in Section III-A, we trained a separate mixture of five-regression experts (MoRE) model for each subject  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1909.12299v2">arXiv:1909.12299v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/txsr6qjk65dmjcp6ipnap72jbu">fatcat:txsr6qjk65dmjcp6ipnap72jbu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200604135306/https://arxiv.org/pdf/1909.12299v2.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/42/4b/424b93276386aae60bf5e525fbcd83f387997de4.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1909.12299v2" 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>

BM³E : Discriminative Density Propagation for Visual Tracking

Cristian Sminchisescu, Atul Kanaujia, Dimitris N. Metaxas
<span title="">2007</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;
We introduce BM 3 E, a Conditional Bayesian Mixture of Experts Markov Model, for consistent probabilistic estimates in discriminative visual tracking.  ...  Instead of inverting a non-linear generative observation model at run-time, we learn to cooperatively predict complex state distributions directly from descriptors that encode image observations -typically  ...  The authors thank Zhiguo Li for useful comments, support with the human motion database creation, and for posing as a subject.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tpami.2007.1111">doi:10.1109/tpami.2007.1111</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/17848782">pmid:17848782</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ivpkrfiwvzewbetvvfc74xhwca">fatcat:ivpkrfiwvzewbetvvfc74xhwca</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170809045252/http://research.cs.rutgers.edu/~kanaujia/MyPapers/TPAMI2007Manuscript.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/6e/9f/6e9f0403751c60e10a582f53ac91f5d77739944f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tpami.2007.1111"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Tracking articulated objects by learning intrinsic structure of motion

Xinxiao Wu, Wei Liang, Yunde Jia
<span title="">2009</span> <i title="Elsevier BV"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/6r4znskbk5h2ngu345slqsm6eu" style="color: black;">Pattern Recognition Letters</a> </i> &nbsp;
To solve this problem, we combine Bayesian mixture of experts (BME) with Gaussian mixture model (GMM) to establish a probabilistic non-linear mapping from the embedding space to the configuration space  ...  In this paper, we propose a novel dimensionality reduction method, temporal neighbor preserving embedding (TNPE), to learn the low-dimensional intrinsic motion manifold of articulated objects.  ...  Acknowledgements This work was partially supported by the Natural Science Foundation of China (60675021), the Chinese High-Tech Program (2006AA01Z120), and Beijing key discipline program.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.patrec.2008.09.014">doi:10.1016/j.patrec.2008.09.014</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/dml53mqp3zbeficmxbnqbwb75m">fatcat:dml53mqp3zbeficmxbnqbwb75m</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20150424221050/http://iitlab.bit.edu.cn:80/mcislab/~wuxinxiao/papers/ta_2009.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/db/0d/db0ddd15f60a6e9130cfe2ad1b5e06386d8ac6cb.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.patrec.2008.09.014"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> elsevier.com </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 38,924 results