Filters








28,043 Hits in 6.5 sec

Evaluating Color Representations for On-Line Road Detection

Jose M. Alvarez, Theo Gevers, Antonio M. Lopez
<span title="">2013</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/6s36fqp6q5hgpdq2scjq3sfu6a" style="color: black;">2013 IEEE International Conference on Computer Vision Workshops</a> </i> &nbsp;
The evaluation is done on a set of 7000 road images acquired using an on-board camera in different real-driving situations.  ...  Most existing algorithms use color to classify pixels as road or background.  ...  ICT Centre of Excellence Program.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/iccvw.2013.82">doi:10.1109/iccvw.2013.82</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/iccvw/AlvarezGL13.html">dblp:conf/iccvw/AlvarezGL13</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/jxlfztj4ijel3kmzkmrnql7aiq">fatcat:jxlfztj4ijel3kmzkmrnql7aiq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170809091131/http://www.cv-foundation.org/openaccess/content_iccv_workshops_2013/W20/papers/Alvarez_Evaluating_Color_Representations_2013_ICCV_paper.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/cb/a8/cba87ed981836c459e92a4d19c6bd9dccdd0dc56.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/iccvw.2013.82"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Background-Invariant Robust Hand Detection based on Probabilistic One-Class Color Segmentation and Skeleton Matching

Andrey Kopylov, Oleg Seredin, Olesia Kushnir, Inessa Gracheva, Aleksandr Larin
<span title="">2018</span> <i title="SCITEPRESS - Science and Technology Publications"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/liyq3gs4rneptl2m3dmjrh4qf4" style="color: black;">Proceedings of the 7th International Conference on Pattern Recognition Applications and Methods</a> </i> &nbsp;
At first, skin segmentation is performed by one-class color pixel classifier which is trained using just a face image fragment without any background training sample.  ...  To adjust output of the one-class classifier the structure-transferring filter built on probabilistic gamma-normal model is applied.  ...  PARAMETRIC REPRESENTATION OF SKIN IN COLOR SPACE USING ONE-CLASS CLASSIFIER The approach to segmentation based on skin color representation requires a pixel distribution model in the proper color space  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5220/0006649805030510">doi:10.5220/0006649805030510</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/icpram/KopylovSKGL18.html">dblp:conf/icpram/KopylovSKGL18</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/tgc6iwzwnbenbhbyuchdbvgfh4">fatcat:tgc6iwzwnbenbhbyuchdbvgfh4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190226175852/http://pdfs.semanticscholar.org/8228/10d58e6c4241a18a8ab4f764fd164d8f3b10.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/82/28/822810d58e6c4241a18a8ab4f764fd164d8f3b10.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5220/0006649805030510"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Deep Cosine Metric Learning for Person Re-identification

Nicolai Wojke, Alex Bewley
<span title="">2018</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/wsjivbkuezdvxdnrhihbwjrxlu" style="color: black;">2018 IEEE Winter Conference on Applications of Computer Vision (WACV)</a> </i> &nbsp;
This paper presents a method for learning such a feature space where the cosine similarity is effectively optimized through a simple re-parametrization of the conventional softmax classification regime  ...  In particular, we achieve better generalization on the test set compared to a network trained with triplet loss.  ...  Conclusion We have presented a re-parametrization of the conventional softmax classifier that enforces a cosine similarity on the representation space when trained to identify the individuals in the training  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/wacv.2018.00087">doi:10.1109/wacv.2018.00087</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/wacv/WojkeB18.html">dblp:conf/wacv/WojkeB18</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/jgv6akn5ofespf3p2y7gx4t4ky">fatcat:jgv6akn5ofespf3p2y7gx4t4ky</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190501002131/https://elib.dlr.de/116408/1/WACV2018.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/06/80/0680ec4651e8f4d7ee5a2ea742a859fa2a9d11bd.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/wacv.2018.00087"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Improving Generalization via Scalable Neighborhood Component Analysis [article]

Zhirong Wu, Alexei A. Efros, Stella X. Yu
<span title="2018-08-14">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We use a deep neural network to learn the visual feature that preserves the neighborhood structure in the semantic space, based on the Neighborhood Component Analysis (NCA) criterion.  ...  Current major approaches to visual recognition follow an end-to-end formulation that classifies an input image into one of the pre-determined set of semantic categories.  ...  Acknowledgements This work was supported in part by Berkeley DeepDrive. ZW would like to thank Yuanjun Xiong for helpful discussions.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1808.04699v1">arXiv:1808.04699v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/auyj2rlrzfedli4f4w7aubf5zu">fatcat:auyj2rlrzfedli4f4w7aubf5zu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200829192527/https://arxiv.org/pdf/1808.04699v1.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/82/91/8291340882dcf0671b8c7e19c019e7a763c08301.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1808.04699v1" 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>

Road Detection by One-Class Color Classification: Dataset and Experiments [article]

Jose M. Alvarez and Theo Gevers and Antonio M. Lopez
<span title="2014-12-18">2014</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Then, we devise a simple online algorithm and conduct an exhaustive evaluation of different classifiers and the effect of using different color representation to characterize pixels.  ...  In this paper, we first introduce a dataset of road images taken at different times and in different scenarios using an onboard camera.  ...  From the results, we conclude that combining multiple color representations using a parametric classifier outperforms the accuracy of single color representations.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1412.3506v2">arXiv:1412.3506v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/urxdepq2obe73hzevd2cmpwmvy">fatcat:urxdepq2obe73hzevd2cmpwmvy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191016043624/https://arxiv.org/pdf/1412.3506v2.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/63/9e/639e21b345c2905d08d880567babb43ae84ab2b9.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1412.3506v2" 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 Feature Learning via Non-parametric Instance Discrimination

Zhirong Wu, Yuanjun Xiong, Stella X. Yu, Dahua Lin
<span title="">2018</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ilwxppn4d5hizekyd3ndvy2mii" style="color: black;">2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition</a> </i> &nbsp;
Neural net classifiers trained on data with annotated class labels can also capture apparent visual similarity among categories without being directed to do so.  ...  of classes, by merely asking the feature to be discriminative of individual instances?  ...  Non-Parametric Softmax Classifier Parametric Classifier. We formulate the instance-level classification objective using the softmax criterion.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cvpr.2018.00393">doi:10.1109/cvpr.2018.00393</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/cvpr/WuXYL18.html">dblp:conf/cvpr/WuXYL18</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/gz7a6t6yxbhktavshli6o32br4">fatcat:gz7a6t6yxbhktavshli6o32br4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190623133743/http://openaccess.thecvf.com/content_cvpr_2018/papers/Wu_Unsupervised_Feature_Learning_CVPR_2018_paper.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/92/f1/92f1903520d817e247d056a69ec91b602a921165.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cvpr.2018.00393"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination [article]

Zhirong Wu, Yuanjun Xiong, Stella Yu, Dahua Lin
<span title="2018-05-05">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Neural net classifiers trained on data with annotated class labels can also capture apparent visual similarity among categories without being directed to do so.  ...  We formulate this intuition as a non-parametric classification problem at the instance-level, and use noise-contrastive estimation to tackle the computational challenges imposed by the large number of  ...  Non-Parametric Softmax Classifier Parametric Classifier. We formulate the instance-level classification objective using the softmax criterion.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1805.01978v1">arXiv:1805.01978v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/3ilhvltoinfo5ckxynd5fhjtdq">fatcat:3ilhvltoinfo5ckxynd5fhjtdq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200828134745/https://arxiv.org/pdf/1805.01978v1.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/41/b0/41b03c500922893906d04403cff16a5d08f26ea7.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1805.01978v1" 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>

Skin segmentation using color pixel classification: analysis and comparison

S.L. Phung, A. Bouzerdoum, D. Chai
<span title="">2005</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;
Our analysis of several representative color spaces using the Bayesian classifier with the histogram technique shows that skin segmentation based on color pixel classification is largely unaffected by  ...  the choice of the color space.  ...  This research is supported in part by the Australian Research Council.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tpami.2005.17">doi:10.1109/tpami.2005.17</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/15628277">pmid:15628277</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/wa7nibk63jhfpkv6pdznh3w3r4">fatcat:wa7nibk63jhfpkv6pdznh3w3r4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190430205151/https://ro.uow.edu.au/cgi/viewcontent.cgi?article=1254&amp;context=infopapers" 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/48/e0/48e04d7ab5e414a20ae2702c387c3322f88bd32b.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tpami.2005.17"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Fragment-based Visual Tracking with Multiple Representations

Junqiu Wang, Yasushi Yagi
<span title="2016-02-01">2016</span> <i title="Science Publications"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/56jvtobdgzeibi4xy2nmkyuoya" style="color: black;">American Journal of Engineering and Applied Sciences</a> </i> &nbsp;
Our experimental results demonstrate that the integration of appearance and spatial information by combining parametric and non-parametric representation is effective for tracking targets in difficult  ...  We segment an input object into several fragments based on the appearance similarity and spatial distribution.  ...  The corresponding author confirms that all of the other authors have read and approved the manuscript and no ethical issues involved.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3844/ajeassp.2016.187.194">doi:10.3844/ajeassp.2016.187.194</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/hxed43kjqfdo5ldk2epeniql2e">fatcat:hxed43kjqfdo5ldk2epeniql2e</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20180719211651/http://thescipub.com/pdf/10.3844/ajeassp.2016.187.194" 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/ef/6e/ef6e9ac506b164b765a153cb6ffcc8beff3ae695.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3844/ajeassp.2016.187.194"> <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>

Automatic detection of melanoma progression by histological analysis of secondary sites

Nikita V. Orlov, Ashani T. Weeraratna, Stephen M. Hewitt, Christopher E. Coletta, John D. Delaney, D. Mark Eckley, Lior Shamir, Ilya G. Goldberg
<span title="2012-03-29">2012</span> <i title="Wiley"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/vlghmc36xnhadgvjbpyrvcjllq" style="color: black;">Cytometry Part A</a> </i> &nbsp;
We found that the HE color space consistently outperformed other color spaces with all three classifiers, while the different classifiers did not have as large of an effect on accuracy.  ...  We also obtained a classification accuracy of 100% when testing entire cores that were not previously used in training (four random trials with one test core for each of 7 classes, 28 tests total).  ...  Acknowledgments This research was supported by the Intramural Research Program of the NIH, National Institute on Aging (Z01: AG000685-02). Literature Cited  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1002/cyto.a.22044">doi:10.1002/cyto.a.22044</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/22467531">pmid:22467531</a> <a target="_blank" rel="external noopener" href="https://pubmed.ncbi.nlm.nih.gov/PMC3331954/">pmcid:PMC3331954</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/443mj6zu7nfylgnw4jivk3eefe">fatcat:443mj6zu7nfylgnw4jivk3eefe</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191209013712/http://europepmc.org/backend/ptpmcrender.fcgi?accid=PMC3331954&amp;blobtype=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/aa/70/aa70617c716f39459fec962f1c70ddb0fe6e9835.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1002/cyto.a.22044"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> wiley.com </button> </a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3331954" title="pubmed link"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> pubmed.gov </button> </a>

Image processing in plant diseases detection

K Santhasheela, Deepan Chakravarthi AV
<span title="2019-07-01">2019</span> <i title="Comprehensive Publications"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/tl5urhlm3zdupfoestvdzpqnoq" style="color: black;">International Journal of Engineering in Computer Science</a> </i> &nbsp;
Hence use of image processing techniques to detect and classify diseases in agricultural applications is helpful.  ...  Overdose of pesticides causes harmful chronic diseases on human beings as not washed properly. Excess use also damages plants nutrient quality. It results in huge loss of production to farmer.  ...  ~ 15 ~ Version of S. Annadurai [7] can be found in Alasdair McAndrew [6] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.33545/26633582.2019.v1.i2a.13">doi:10.33545/26633582.2019.v1.i2a.13</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/raupgepa6vdubcfahqrwibvjem">fatcat:raupgepa6vdubcfahqrwibvjem</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220227154606/https://www.computersciencejournals.com/ijecs/article/view/13/1-2-1" 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/5e/0f/5e0fbef0a0fdee7cc8a3dd5afcec8674e767d99d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.33545/26633582.2019.v1.i2a.13"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Synthesis of supervised classification algorithm using intelligent and statistical tools [article]

Ali Douik, Mourad Moussa Jlassi
<span title="2009-12-11">2009</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
A fundamental task in detecting foreground objects in both static and dynamic scenes is to take the best choice of color system representation and the efficient technique for background modeling.  ...  We propose in this paper a non-parametric algorithm dedicated to segment and to detect objects in color images issued from a football sports meeting.  ...  Each one of them is expressed in adapted color system representation that will contribute to an optimal classification. A.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/0912.2302v1">arXiv:0912.2302v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/k6sx7esfirbuvhq7io72gsr3qe">fatcat:k6sx7esfirbuvhq7io72gsr3qe</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200824003645/https://arxiv.org/ftp/arxiv/papers/0912/0912.2302.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/1c/ad/1cad6073fda18391846f09e8d6b257941b744b45.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/0912.2302v1" 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>

Combining Color and Shape Information for Appearance-Based Object Recognition Using Ultrametric Spin Glass-Markov Random Fields [chapter]

B. Caputo, Gy. Dorkó, H. Niemann
<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;
Shape and color information are important cues for object recognition. An ideal system should give the option to use both forms of information, as well as the option to use just one of the two.  ...  Experimental results on a database of 100 objects confirm the effectiveness of the proposed approach.  ...  Acknowledgments This work has been supported by the "Graduate Research Center of the University of Erlangen-Nuremberg for 3D Image Analysis and Synthesis", and by the Foundation BLANCEFLOR Boncompagni-Ludovisi  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/3-540-45665-1_8">doi:10.1007/3-540-45665-1_8</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/pjqkvuxi4vfpzoj26fdv2tudae">fatcat:pjqkvuxi4vfpzoj26fdv2tudae</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190303072647/http://pdfs.semanticscholar.org/c502/8a255e94a8772ba79e97e4ce850bdbc1f819.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/c5/02/c5028a255e94a8772ba79e97e4ce850bdbc1f819.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/3-540-45665-1_8"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

On Nonparametric Guidance for Learning Autoencoder Representations [article]

Jasper Snoek and Ryan Prescott Adams and Hugo Larochelle
<span title="2011-10-26">2011</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
The most common way of introducing such problem-specific guidance in autoencoders has been through the incorporation of a parametric component that ties the latent representation to the label information  ...  Unsupervised discovery of latent representations, in addition to being useful for density modeling, visualisation and exploratory data analysis, is also increasingly important for learning features relevant  ...  investigated the use of a linear logistic regression classifier for the parametric mapping.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1102.1492v4">arXiv:1102.1492v4</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/i3vjqxbdrrbpdecb5fon4zg5r4">fatcat:i3vjqxbdrrbpdecb5fon4zg5r4</a> </span>
<a target="_blank" rel="noopener" href="https://archive.org/download/arxiv-1102.1492/1102.1492.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/1102.1492v4" 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>

A Review on Classification Techniques for Human Activity Recognition

Sonali, Ashok Kumar Bathla
<span title="2015-02-28">2015</span> <i title="Green Publication"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/4rsmbu2ye5hadkdlomzixtcunu" style="color: black;">Journal of advance research in business, management and accounting</a> </i> &nbsp;
This paper provides a detailed overview of various state-of-the-art research papers on human activity recognition using different types of classifiers.  ...  From this survey, we can make conclusion of various advantageous and disadvantageous facts about different classifiers used in the detection and classification task.  ...  Color feature extraction and geometric feature extraction are also used for the same [10] . The drawback of this approach was that, it could track only one object in a video sequence.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.53555/nnbma.v1i2.131">doi:10.53555/nnbma.v1i2.131</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ci3d5tgrwfew7c6ixcc2jqyo7m">fatcat:ci3d5tgrwfew7c6ixcc2jqyo7m</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220422065500/https://nnpub.org/index.php/BMA/article/download/131/107" 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/29/18/2918ef2ab2d4004fbaf685360cfa35e51692bc90.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.53555/nnbma.v1i2.131"> <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>
&laquo; Previous Showing results 1 &mdash; 15 out of 28,043 results