Filters








440 Hits in 9.5 sec

Learning a common dictionary for subject-transfer decoding with resting calibration

Hiroshi Morioka, Atsunori Kanemura, Jun-ichiro Hirayama, Manabu Shikauchi, Takeshi Ogawa, Shigeyuki Ikeda, Motoaki Kawanabe, Shin Ishii
<span title="">2015</span> <i title="Elsevier BV"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/sa477uo7lveh7hchpikpixop5u" style="color: black;">NeuroImage</a> </i> &nbsp;
Decoding spatial attention by using cortical currents estimated from electroencephalography with near-infrared spectroscopy prior information. NeuroImage, Vol. 90, pp. 128-139, 2014.  ...  Enhancing Recognition of Visual Concepts with Primitive Color Histograms via Non-sparse Multiple Kernel Learning. In Multilingual Information Access Evaluation II.  ...  Multi-task Learning via Non-sparse Multiple Kernel Learning. In Computer Analysis of Images and Patterns -CAIP 2011 Proceedings, Part I, pp.335-342, Seville, Spain, 2011.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.neuroimage.2015.02.015">doi:10.1016/j.neuroimage.2015.02.015</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/25682943">pmid:25682943</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/nzeblluhmbe5dlmzyy22fbldzm">fatcat:nzeblluhmbe5dlmzyy22fbldzm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170830045218/http://www.cns.atr.jp/~kawanabe/Kawanabe_Pub_2015May.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/d4/00/d400ff6bdee8256e7d3146de7f6b0dcfa2085b23.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.neuroimage.2015.02.015"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> elsevier.com </button> </a>

Sparse Camera Network for Visual Surveillance -- A Comprehensive Survey [article]

Mingli Song, Dachent Tao, Stephen J. Maybank
<span title="2013-02-03">2013</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
A sparse camera network undertakes large area surveillance using as few cameras as possible, and most cameras have non-overlapping fields of view with one another.  ...  While dense camera networks - in which most cameras have large overlapping fields of view - are well studied, we are mainly concerned with sparse camera networks.  ...  The recognition model is learned from a set of still images annotated with the action label.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1302.0446v1">arXiv:1302.0446v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/j3opbzuaw5eb3c74c2ind5pmua">fatcat:j3opbzuaw5eb3c74c2ind5pmua</a> </span>
<a target="_blank" rel="noopener" href="https://archive.org/download/arxiv-1302.0446/1302.0446.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/1302.0446v1" 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>

Author Index

<span title="">2010</span> <i title="IEEE"> 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition </i> &nbsp;
Fast Matting Using Large Kernel Matting Laplacian Matrices Face Recognition with Learning-based Descriptor Tao, Litian Efficient Histogram-Based Sliding Window Tappen, Marshall F.  ...  Workshop: Local Concept-Based Medical Image Retrieval with Correlation-Enhanced Similarity Matching Based on Global Analysis Thompson, Paul Compression of Surface Registrations using Beltrami Coefficients  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cvpr.2010.5539913">doi:10.1109/cvpr.2010.5539913</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/y6m5knstrzfyfin6jzusc42p54">fatcat:y6m5knstrzfyfin6jzusc42p54</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170830173919/https://www.computer.org/csdl/proceedings/cvpr/2010/6984/00/05539913.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/16/39/16397bed32be5db37cd286d6d3a7fc5493c92c65.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cvpr.2010.5539913"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Classification of Histology Sections via Multispectral Convolutional Sparse Coding

Yin Zhou, Hang Chang, Kenneth Barner, Paul Spellman, Bahram Parvin
<span title="">2014</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ilwxppn4d5hizekyd3ndvy2mii" style="color: black;">2014 IEEE Conference on Computer Vision and Pattern Recognition</a> </i> &nbsp;
Experimental results show that the proposed model 1) outperforms systems utilizing sparse coding for unsupervised feature learning (e.g., ); 2) is competitive with systems built upon features with biological  ...  In the field of biomedical imaging, for the purposes of visualization and/or quantification, different stains are typically used for different targets of interest (e.g., cellular/subcellular events), which  ...  The views and opinions of authors expressed herein do not necessarily state or reflect those of the United States Government or any agency thereof or the Regents of the University of California.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cvpr.2014.394">doi:10.1109/cvpr.2014.394</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/25554749">pmid:25554749</a> <a target="_blank" rel="external noopener" href="https://pubmed.ncbi.nlm.nih.gov/PMC4279924/">pmcid:PMC4279924</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/cvpr/ZhouCBSP14.html">dblp:conf/cvpr/ZhouCBSP14</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ogotmnfd2fbw5lg5ma6mtd37su">fatcat:ogotmnfd2fbw5lg5ma6mtd37su</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170829190032/https://www.eecis.udel.edu/~zhou/publications/TissueClassification_MCSCSPM_final.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/c4/45/c445bf4fe0494fc5b33c8280d3c367379293ece9.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cvpr.2014.394"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4279924" title="pubmed link"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> pubmed.gov </button> </a>

Intelligent visual surveillance — A survey

In Su Kim, Hong Seok Choi, Kwang Moo Yi, Jin Young Choi, Seong G. Kong
<span title="">2010</span> <i title="Springer Nature"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/oeafm75vpzfbtmpxwsotjqu3hy" style="color: black;">International Journal of Control, Automation and Systems</a> </i> &nbsp;
the visual events of the scene.  ...  The second part reviews widearea surveillance techniques based on the fusion of multiple visual sensors, camera calibration and cooperative camera systems.  ...  The mean-shift tracker is a popular kernel tracking method, which uses a weighted color histogram to represent the object.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/s12555-010-0501-4">doi:10.1007/s12555-010-0501-4</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/pdv6jpfqfnfiraqe4ngxzvywvu">fatcat:pdv6jpfqfnfiraqe4ngxzvywvu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20140503221230/http://astro.temple.edu/~skong/publications/2010-IJCAS.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/ec/fcec976816f3fdaf02217d1c1825dd0786e83732.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/s12555-010-0501-4"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

High-level event recognition in unconstrained videos

Yu-Gang Jiang, Subhabrata Bhattacharya, Shih-Fu Chang, Mubarak Shah
<span title="2012-11-13">2012</span> <i title="Springer Nature"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/prsrkwgmmjas7elf5ki2xrsyvm" style="color: black;">International Journal of Multimedia Information Retrieval</a> </i> &nbsp;
The goal of high-level event recognition is to automatically detect complex high-level events in a given video sequence.  ...  While the existing solutions vary, we identify common key modules and provide detailed descriptions along with some insights for each of them, including extraction and representation of low-level features  ...  Acknowledgments This work was supported in part by the Intelligence Advanced Research Projects Activity (IARPA) via Department of Interior National Business Center contract numbers D11PC20066, D11PC20070  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/s13735-012-0024-2">doi:10.1007/s13735-012-0024-2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/mfzttic3svb4tho2xb6aczgp4y">fatcat:mfzttic3svb4tho2xb6aczgp4y</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170808122243/http://www.yugangjiang.info/publication/IJMIR-EventSurvey.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/6a/72/6a720e2bf71cbb3c037919e84f78734349020622.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/s13735-012-0024-2"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

Tracking Moving Objects in Video

G. Jemilda
<span title="">2017</span> <i title="International Academy Publishing (IAP)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/3uo3zcmrgvgspdzqe6w6sjoezq" style="color: black;">Journal of Computers</a> </i> &nbsp;
Although there has been some success with building trackers for specific object classes such as human, face, mice etc.  ...  Especially in the videos which are not clear in its original form i.e. the video which requires enhancement and its quality has to be improved.  ...  Feature extraction enables to derive a set of feature vectors, also called descriptors, from a set of detected features. Here Gabor filter is used as the feature extractors.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.17706/jcp.12.3.221-229">doi:10.17706/jcp.12.3.221-229</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/wsjcaogh3zcf5cnrxofv43d2pu">fatcat:wsjcaogh3zcf5cnrxofv43d2pu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200307045111/http://www.jcomputers.us/vol12/jcp1203-03.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/f0/b7/f0b7c23d193a5c8a5833fb00050c61a975b3f8c5.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.17706/jcp.12.3.221-229"> <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>

Semantics Extraction from Images [chapter]

Ioannis Pratikakis, Anastasia Bolovinou, Bassilios Gatos, Stavros Perantonis
<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> &nbsp;
An overview of the state-of-the-art on semantics extraction from images is presented.  ...  In this survey, we present the relevant approaches in terms of content representation as well as in terms of knowledge representation.  ...  To take into account the spatial structure of semantic concepts, the proposed framework supports spatial relation representation via the visual concept ontology.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-642-20795-2_3">doi:10.1007/978-3-642-20795-2_3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/h3xh2fmryfgj5hwn5k5fjsximy">fatcat:h3xh2fmryfgj5hwn5k5fjsximy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190304215444/http://pdfs.semanticscholar.org/c1bd/75dd43ad483e93a0c915d754b15e42eeec04.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/c1/bd/c1bd75dd43ad483e93a0c915d754b15e42eeec04.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-642-20795-2_3"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

Modèle de graphe et modèle de langue pour la reconnaissance de scènes visuelles

Trong-Ton Pham, Loïc Maisonnasse, Philippe Muhlen, Eric Gaussier
<span title="2010-04-30">2010</span> <i title="Lavoisier"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/irkvakmpo5cllcy5z6tarfe66m" style="color: black;">Document Numérique</a> </i> &nbsp;
First, extracted image regions that are visually similar will be grouped into clusters using an unsupervised learning algorithm. Each cluster is then associated with a visual concept.  ...  Two instances of the visual graph model have been applied to the problem of scene recognition and robot localization.  ...  In [Swain & Ballard 1991] , an image is represented by its color histogram. Similar images are identified by matching theirs color histograms with the color histogram of the sample image.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3166/dn.13.1.211-227">doi:10.3166/dn.13.1.211-227</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/v4vexsghgjgqdhcdiondnsy62q">fatcat:v4vexsghgjgqdhcdiondnsy62q</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200318073534/https://tel.archives-ouvertes.fr/file/index/docid/703372/filename/thesis_pham.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/d8/7fd8d608109d292cd8a13c6bcd04f6ebaa69c7e9.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3166/dn.13.1.211-227"> <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>

Extracting Semantics from Multimedia Content: Challenges and Solutions [chapter]

Lexing Xie, Rong Yan
<span title="">2008</span> <i title="Springer US"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/mrw623ncpvfbva6mtaat6yb7li" style="color: black;">Signals and Communication Technology</a> </i> &nbsp;
We then present challenges for each of the five components along with their existing solutions: designing multimedia lexicons and using them for concept detection, handling multiple media sources and resolving  ...  We start with an system overview with the five major components that extracts and uses semantic metadata: data annotation, multimedia ontology, feature representation, model learning and retrieval systems  ...  For example, when color histograms are used to learn the video concept "airplane" of two video frames that have the same color histogram (e.g. white/gray on blue backgroun), one can contain an airplane  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-0-387-76569-3_2">doi:10.1007/978-0-387-76569-3_2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/jul6fw7esfaurct6erjnvpcq6q">fatcat:jul6fw7esfaurct6erjnvpcq6q</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20100623015026/http://www.ee.columbia.edu/~xlx/research/papers/springer_content_semantics.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/15/05/15058a4523b8b584da387a920bbde92d7146841f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-0-387-76569-3_2"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

Visual Object Recognition

Kristen Grauman, Bastian Leibe
<span title="2011-04-19">2011</span> <i title="Morgan &amp; Claypool Publishers LLC"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/nfywethoofedfg7fm5jcmwhmve" style="color: black;">Synthesis Lectures on Artificial Intelligence and Machine Learning</a> </i> &nbsp;
The visual recognition problem is central to computer vision research.  ...  Hough transform; window-based descriptors, histograms of oriented gradients and rectangular features; part-based models, star graph models and fully connected constellations; pyramid match kernels; detection  ...  Bastian Leibe's work on the project was supported in part by the UMIC cluster of excellence (DFG EXC 89).  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.2200/s00332ed1v01y201103aim011">doi:10.2200/s00332ed1v01y201103aim011</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/fhz7aokkfjav7fuauuorfstq4y">fatcat:fhz7aokkfjav7fuauuorfstq4y</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20111111035345/http://www.morganclaypool.com.ezproxy.lib.utah.edu/doi/pdfplus/10.2200/S00332ED1V01Y201103AIM011" 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/05/0a/050abd09669aea2276bf91dc3dab18c7ff8c13dc.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.2200/s00332ed1v01y201103aim011"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

A Survey on Contemporary Computer-Aided Tumor, Polyp, and Ulcer Detection Methods in Wireless Capsule Endoscopy Imaging [article]

Tariq Rahim, Muhammad Arslan Usman, Soo Young Shin
<span title="2019-10-01">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Several studies have been included with in-depth detail of their methodologies, findings, and conclusions. Also, we have attempted to classify these methods based on their technical aspects.  ...  Various anomalies can take place in the GI tract of a human being but the most important and common ones and the aim of this survey are ulcers, polyps, and tumors.  ...  Mapping 3D color data on each image point to closest visual words and computing the amount of each visual word resulting a histogram (w, d).  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1910.00265v1">arXiv:1910.00265v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/cziq6sauuzaqpgpmca5pmgdwke">fatcat:cziq6sauuzaqpgpmca5pmgdwke</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200929160043/https://arxiv.org/pdf/1910.00265v1.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/1f/f1/1ff188e23cacbdce71bdaeab9672ab9a502ad3a0.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1910.00265v1" 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>

Enhanced Computer Vision With Microsoft Kinect Sensor: A Review

Jungong Han, Ling Shao, Dong Xu, Jamie Shotton
<span title="">2013</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/snhjqrgxbff5teva5lfasxmfr4" style="color: black;">IEEE Transactions on Cybernetics</a> </i> &nbsp;
With the invention of the low-cost Microsoft Kinect sensor, high-resolution depth and visual (RGB) sensing has become available for widespread use.  ...  The reviewed approaches are classified according to the type of vision problems that can be addressed or enhanced by means of the Kinect sensor.  ...  Acknowledgments A part of this work was done while J. Han was employed by CWI, the Netherlands. Therefore, J. Han would like to thank Dr. E.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tcyb.2013.2265378">doi:10.1109/tcyb.2013.2265378</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/23807480">pmid:23807480</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/gfwxijctnbgonnanvdklslbguq">fatcat:gfwxijctnbgonnanvdklslbguq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170922212310/http://lshao.staff.shef.ac.uk/pub/KinectReview_TC2013.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/9e/86/9e869b71aaf7550bd54f5c3e8a9994643d542b3e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tcyb.2013.2265378"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Smile detection in the wild based on transfer learning [article]

Xin Guo and Luisa F. Polanía and Kenneth E. Barner
<span title="2018-01-17">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Three different models are built as a result of fine-tuning the face recognition model with different inputs, including aligned, unaligned and grayscale images generated from the GENKI-4K dataset.  ...  To leverage the large amount of labeled data from face recognition datasets and to alleviate overfitting on smile detection, an efficient transfer learning-based smile detection approach is proposed in  ...  The concept of transfer learning, as applied to visual recognition tasks, refers to transferring image representations learned with CNNs on large datasets to other visual recognition tasks with limited  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1802.02185v1">arXiv:1802.02185v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/irnrd5237rg2vmyrdziuzqrelm">fatcat:irnrd5237rg2vmyrdziuzqrelm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200930073618/https://arxiv.org/pdf/1802.02185v1.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/cf/a8/cfa86d446005d646d55a168ab13db53271d38295.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1802.02185v1" 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>

Sparse coding of human motion trajectories with non-negative matrix factorization

Christian Vollmer, Sven Hellbach, Julian Eggert, Horst-Michael Gross
<span title="">2014</span> <i title="Elsevier BV"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/bby322qx6ndsje4ypr56c7nnly" style="color: black;">Neurocomputing</a> </i> &nbsp;
We use shift-invariant Non-negative Matrix Factorization (NMF) for decomposing continuous-valued time series into a number of characteristic primitives, i.e. the basis vectors, and their activations, which  ...  simple standard classification models with few parameters.  ...  Although very similar in concept, here we present a different method that allows the application of the efficient multiplicative learning and decomposition algorithms as gained from NMF.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.neucom.2012.12.054">doi:10.1016/j.neucom.2012.12.054</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/zjfbka7us5fk5ihhts4vivq5sy">fatcat:zjfbka7us5fk5ihhts4vivq5sy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170810145306/http://www.tu-ilmenau.de/fileadmin/media/neurob/publications/journals/Vollmer-NC-2014.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/8b/a8/8ba87fee0a896148f619dbcc3ef93ab6788d361a.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.neucom.2012.12.054"> <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 440 results