Filters








56,141 Hits in 2.9 sec

Correlation-based construction of neighborhood and edge features [article]

Balázs Kégl
<span title="2014-02-16">2014</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Next, we connect neighborhood features that correlate, and construct edge features by subtracting the correlated neighborhood features of each other.  ...  Motivated by an abstract notion of low-level edge detector filters, we propose a simple method of unsupervised feature construction based on pairwise statistics of features.  ...  Next, we connect neighborhood features that correlate, and construct edge features by subtracting the correlated neighborhood features of each other.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1312.7335v2">arXiv:1312.7335v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/zlzfiskwfrgbrbsk6rmcmkmgt4">fatcat:zlzfiskwfrgbrbsk6rmcmkmgt4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191015230600/https://arxiv.org/pdf/1312.7335v2.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/20/d5/20d579bb39920514b7a5c33ee340f95b98af3326.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1312.7335v2" 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>

Neo-GNNs: Neighborhood Overlap-aware Graph Neural Networks for Link Prediction [article]

Seongjun Yun, Seoyoon Kim, Junhyun Lee, Jaewoo Kang, Hyunwoo J. Kim
<span title="2022-06-09">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Our Neo-GNNs generalize neighborhood overlap-based heuristic methods and handle overlapped multi-hop neighborhoods.  ...  To address this limitation, we propose Neighborhood Overlap-aware Graph Neural Networks (Neo-GNNs) that learn useful structural features from an adjacency matrix and estimate overlapped neighborhoods for  ...  Then to consider only features of overlapped neighbors between nodes, (b) Neo-GNNs construct a diagonal matrix X struct ∈ R N ×N and (c) aggregate the features of multi-hop neighborhoods by multiplying  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2206.04216v1">arXiv:2206.04216v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/nyouqbvw3zb6rabjjwupvht454">fatcat:nyouqbvw3zb6rabjjwupvht454</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220704155301/https://arxiv.org/pdf/2206.04216v1.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/00/11/00114dd4b39b36a46e91e568bb0277102efc8450.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2206.04216v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Multiple Ocular Diseases Classification with Graph Regularized Probabilistic Multi-label Learning [chapter]

Xiangyu Chen, Yanwu Xu, Lixin Duan, Shuicheng Yan, Zhuo Zhang, Damon Wing Kee Wong, Jiang Liu
<span title="">2015</span> <i title="Springer International Publishing"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/2w3awgokqne6te4nvlofavy5a4" style="color: black;">Lecture Notes in Computer Science</a> </i> &nbsp;
In addition, to capture the characteristics of these three leading ocular diseases, we explore the extractions of various effective lowlevel features, including Global Features, Grid-based Features, and  ...  The proposed EGPM exploits the correlations among these three diseases, and simultaneously classifying them for a given fundus image.  ...  The graph construction can thus be decomposed into two sub-problems: 1) Neighborhood Selection; and 2) Edge Weight Computation.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-319-16817-3_9">doi:10.1007/978-3-319-16817-3_9</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ajz3kbvsazcphou366tk5guaxq">fatcat:ajz3kbvsazcphou366tk5guaxq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170829040018/http://vigir.missouri.edu/~gdesouza/Research/Conference_CDs/ACCV_2014/pages/PDF/835.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/a5/8a/a58ae7af2765330d191066be45d37ce18f4ace99.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-319-16817-3_9"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

Super-resolution of images based on local correlations

F.M. Candocia, J.C. Principe
<span title="">1999</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/22mhkeaq5zdqlmtti5oidj26fi" style="color: black;">IEEE Transactions on Neural Networks</a> </i> &nbsp;
First, an unsupervised feature extraction is performed on local neighborhood information from a training image.  ...  These features are then used to cluster the neighborhoods into disjoint sets for which an optimal mapping relating homologous neighborhoods across scales can be learned in a supervised manner.  ...  Superresolution architecture based on local correlations. This paradigm performs the equivalent operation of convolution with a family of kernels.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/72.750566">doi:10.1109/72.750566</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/18252533">pmid:18252533</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/rctlrsgd5rekpmqx75layyk65y">fatcat:rctlrsgd5rekpmqx75layyk65y</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20060902004653/http://iul.eng.fiu.edu/candocia/Publications/candocia_IEEE_TNN.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/b8/25/b825568a40ff8df35e16e4b2a75627b1fddce4ea.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/72.750566"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Feature vector field and feature matching

F.C. Wu, Z.H. Wang, X.G. Wang
<span title="">2010</span> <i title="Elsevier BV"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/jm6w2xclfzguxnhmnmq5omebpi" style="color: black;">Pattern Recognition</a> </i> &nbsp;
The feature vector field effectively represents image edges and feature points including corners and edge points with big curvature.  ...  Using the feature vector field, some novel descriptors are constructed for point matching and curve matching.  ...  Also, we gratefully acknowledge the support from the National Natural Science Foundation of China (60835003) and the National High-Tech Research and Development Program of China (2006AA01Z116).  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.patcog.2010.05.001">doi:10.1016/j.patcog.2010.05.001</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ug2h7c6l65czbhn5pombbbf45y">fatcat:ug2h7c6l65czbhn5pombbbf45y</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170809021521/http://www.nlpr.ia.ac.cn/2010papers/gjkw/gk3.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/c5/58/c5584a0d6f16dbf98160af58a0e84f42bddf179f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.patcog.2010.05.001"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> elsevier.com </button> </a>

Robust Smooth Feature Extraction from Point Clouds

Joel II Daniels, Linh K. Ha, Tilo Ochotta, Claudio T. Silva
<span title="">2007</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/fpn4z6hccjecjncyhtp26e4api" style="color: black;">IEEE International Conference on Shape Modeling and Applications 2007 (SMI &#39;07)</a> </i> &nbsp;
We demonstrate the benefits of our method with two applications: surface meshing and point-based geometry compression.  ...  We present a robust method that identifies sharp features in a point cloud by returning a set of smooth curves aligned along the edges.  ...  Award, the Army Research Office, and the DFG Graduiertenkolleg 1042 "Explorative Analysis and Visualization of Large Information Spaces".  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/smi.2007.32">doi:10.1109/smi.2007.32</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/smi/DanielsHOS07.html">dblp:conf/smi/DanielsHOS07</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/rzycbmyderaw7flyclwkwfljce">fatcat:rzycbmyderaw7flyclwkwfljce</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20100728023254/http://www.sci.utah.edu/~csilva/papers/smi2007.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/37/b1/37b100eaad54c7937409437f9aca84a381e8e48a.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/smi.2007.32"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Feature Point Selection using Structural Graph Matching for MLS based Image Registration

Hema PMenon, K A Narayanankutty, Indulekha T S
<span title="2014-08-20">2014</span> <i title="Foundation of Computer Science"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/b637noqf3vhmhjevdfk3h5pdsu" style="color: black;">International Journal of Computer Applications</a> </i> &nbsp;
This paper focuses on the use of the structural information of an image, for selecting control points, as it remains the same even when it undergoes most of the transformation and illumination changes.  ...  The process of registration depends on the homologous control points that are selected from the source and the target images.  ...  Structure based image registration overcomes most of the disadvantage of intensity and feature based methods.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5120/17513-8067">doi:10.5120/17513-8067</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/72ng2ajwvvdctknu5fnkkdpjre">fatcat:72ng2ajwvvdctknu5fnkkdpjre</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170809212612/http://research.ijcaonline.org/volume100/number4/pxc3898067.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/cc/4e/cc4e80caa20b93e9449a7088f617c874b9cb3206.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5120/17513-8067"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Single-Subject Structural Networks with Closed-Form Rotation Invariant Matching Improve Power in Developmental Studies of the Cortex [chapter]

Benjamin M. Kandel, Danny JJ Wang, James C. Gee, Brian B. Avants
<span title="">2014</span> <i title="Springer International Publishing"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/2w3awgokqne6te4nvlofavy5a4" style="color: black;">Lecture Notes in Computer Science</a> </i> &nbsp;
Previous methods for constructing singlesubject cortical networks have used patch-based correlations and distance metrics based on curvature and thickness.  ...  We present here a method for constructing similarity-based cortical structural networks that utilizes a rotation-invariant representation of structure.  ...  In the first camp, [10] used a combination of cortical thickness and curvature-based metrics to construct networks.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-319-10443-0_18">doi:10.1007/978-3-319-10443-0_18</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/wtenhwlycbd5bptshulh7xqbiq">fatcat:wtenhwlycbd5bptshulh7xqbiq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170808181326/http://picsl.upenn.edu/wp-content/uploads/2014/02/StructuralNetworks.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/38/08/3808b0a0ab8e77ea6a5e2c651d36d2d22e43b4d2.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-319-10443-0_18"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

Prediction of lncRNA–Disease Associations via Closest Node Weight Graphs of the Spatial Neighborhood Based on the Edge Attention Graph Convolutional Network

Jianwei Li, Mengfan Kong, Duanyang Wang, Zhenwu Yang, Xiaoke Hao
<span title="2022-01-04">2022</span> <i title="Frontiers Media SA"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/r7trx2kj6je5jhtaoy3rztibgy" style="color: black;">Frontiers in Genetics</a> </i> &nbsp;
In this study, a model based on closest node weight graph of the spatial neighborhood (CNWGSN) and edge attention graph convolutional network (EAGCN), LDA-EAGCN, was developed to uncover potential lncRNA–disease  ...  The CNWGSN features of lncRNA–disease associations combined with known lncRNA–disease associations were introduced to train EAGCN, and correlation scores of input data were predicted with EAGCN for judging  ...  Then the closest node weight graph of L i and D i and the spatial neighborhood features are integrated into the CNWGSN features of lncRNA i and disease i.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3389/fgene.2021.808962">doi:10.3389/fgene.2021.808962</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/35058974">pmid:35058974</a> <a target="_blank" rel="external noopener" href="https://pubmed.ncbi.nlm.nih.gov/PMC8763691/">pmcid:PMC8763691</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/i2fpaadovjfldprr5pual5t5yi">fatcat:i2fpaadovjfldprr5pual5t5yi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220426050644/https://fjfsdata01prod.blob.core.windows.net/articles/files/808962/pubmed-zip/.versions/1/.package-entries/fgene-12-808962/fgene-12-808962.pdf?sv=2018-03-28&amp;sr=b&amp;sig=pZZxgNOwHHJFo%2BFji213Cz8vdE%2F3PGZLj%2Ft5BoaLLHA%3D&amp;se=2022-04-26T05%3A06%3A53Z&amp;sp=r&amp;rscd=attachment%3B%20filename%2A%3DUTF-8%27%27fgene-12-808962.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/7e/5e/7e5e3f6262fe2145d5534c5b7f8df8e11ce1720d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3389/fgene.2021.808962"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> frontiersin.org </button> </a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8763691" title="pubmed link"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> pubmed.gov </button> </a>

Geometric graphs from data to aid classification tasks with Graph Convolutional Networks

Yifan Qian, Paul Expert, Pietro Panzarasa, Mauricio Barahona
<span title="2021-04-09">2021</span> <i title="Elsevier BV"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/5cekcl3stvfxxfsctgk6zwoqwe" style="color: black;">Patterns</a> </i> &nbsp;
Here, we show that, even if additional relational information is not available in the dataset, one can improve classification by constructing geometric graphs from the features themselves, and using them  ...  Traditional classification tasks learn to assign samples to given classes based solely on sample features.  ...  The 0-1 adjacency matrix of the MST is denoted by A MST . We then add edges to the MST based on two types of criteria: (1) local neighborhoods or (2) balancing local and global distances.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.patter.2021.100237">doi:10.1016/j.patter.2021.100237</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/33982027">pmid:33982027</a> <a target="_blank" rel="external noopener" href="https://pubmed.ncbi.nlm.nih.gov/PMC8085612/">pmcid:PMC8085612</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/fnnuusmrljh7rc64ksjnhfaqry">fatcat:fnnuusmrljh7rc64ksjnhfaqry</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210528160221/http://europepmc.org/backend/ptpmcrender.fcgi?accid=PMC8085612&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/62/f8/62f8098ee49d366d1a734fbc2b2c689cbdc0eda2.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.patter.2021.100237"> <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> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8085612" title="pubmed link"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> pubmed.gov </button> </a>

Identification and Classification of Surface Cracks on Concrete Members Based on Image Processing

Xiaoping Cao, Tao Li, Jiawei Bai, Zhikai Wei
<span title="2020-06-30">2020</span> <i title="International Information and Engineering Technology Association"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/wsuaubw4tnbbhjln4ji2em2dmi" style="color: black;">Traitement du signal</a> </i> &nbsp;
Specifically, each sample image was preprocessed through cropping and neighborhood operation, subject to gray adaptive thresholding, and further processed based on morphological gradient and local gray  ...  The crack identification and classification are essential to the discovery and maintenance of early defects in concrete members.  ...  Based on the preset length a and width b, the fitted line was translated to construct a rectangular template M of the size a×b.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18280/ts.370320">doi:10.18280/ts.370320</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/torb4kobdnda3pnlut5sgikdwi">fatcat:torb4kobdnda3pnlut5sgikdwi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201104151453/http://www.iieta.org/download/file/fid/36058" 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/55/9c/559cf265589c0a1efe2699214db45e632a4449d8.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18280/ts.370320"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Image objects and multi-scale features for annotation detection

Jindong Chen, Eric Saund, Yizhou Wang
<span title="">2008</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/mlkexztp5vbdfo3nlsmbuf4oia" style="color: black;">Pattern Recognition (ICPR), Proceedings of the International Conference on</a> </i> &nbsp;
A second issue is to devise image features that offer inferential power for machine learning algorithms. We report on a feature that measures edge turn statistics.  ...  A third issue is how to combine local and neighborhood evidence. We exploit the alpha shape tree in a direct inference architecture.  ...  We select the top 300 features from a set of 888 by correlation-based method [6] , and then train a Log-itBoost model [5] with 108 iterations.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/icpr.2008.4761932">doi:10.1109/icpr.2008.4761932</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/icpr/ChenSW08.html">dblp:conf/icpr/ChenSW08</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/owyboqbscrfvffjq6y3nr53z2q">fatcat:owyboqbscrfvffjq6y3nr53z2q</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20110613103705/http://www2.parc.com/isl/members/saund/papers/2008-icpr-chen-etal-annodetect-Paper_2800_abstract_1531_0.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/55/70/5570b73958b80c5e3a4bcf94fae19471c2d06c6e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/icpr.2008.4761932"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Estimating Potential Customers Anywhere and Anytime Based on Location-Based Social Networks [chapter]

Hsun-Ping Hsieh, Cheng-Te Li, Shou-De Lin
<span title="">2015</span> <i title="Springer International Publishing"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/2w3awgokqne6te4nvlofavy5a4" style="color: black;">Lecture Notes in Computer Science</a> </i> &nbsp;
geographical, mobility, and features on location-based social networks.  ...  To tackle the task based on store sensors, we develop a method called Potential Customer Estimator (PCE), which models the spatial and temporal correlation between existing stores and query locations using  ...  With the feature-based top store detection, we can derive the weight of each feature π k and use feature weight to initialize the edge weight w uv in the correlation graph (line 4-5).  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-319-23525-7_35">doi:10.1007/978-3-319-23525-7_35</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/g2uxz5sm5bhnnfq3tl6yrg7lvu">fatcat:g2uxz5sm5bhnnfq3tl6yrg7lvu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190307043753/http://pdfs.semanticscholar.org/dabd/706aae0d78b5706221563c22eff5f830e839.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/da/bd/dabd706aae0d78b5706221563c22eff5f830e839.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-319-23525-7_35"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

Image feature optimization based on nonlinear dimensionality reduction

Rong Zhu, Min Yao
<span title="">2009</span> <i title="Zhejiang University Press"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/zlforxkowngszn3m3pm4si3xha" style="color: black;">Journal of Zhejiang University: Science A</a> </i> &nbsp;
We formulate image feature optimization as the establishment of a mapping between high-and low-dimensional space via a five-tuple model.  ...  We propose a novel globular neighborhood based locally linear embedding (GNLLE) algorithm using neighborhood update and an incremental neighbor search scheme, which not only can handle sparse datasets  ...  ACKNOWLEDGEMENTS We would like to thank the anonymous reviewers for valuable comments and useful suggestions, and Piotr Dollar, and Vincent Rabaud for providing us with the LSML algorithm.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1631/jzus.a0920310">doi:10.1631/jzus.a0920310</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/gd3bjvvsa5d43lmfrpyq36cqlq">fatcat:gd3bjvvsa5d43lmfrpyq36cqlq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190308103305/http://pdfs.semanticscholar.org/e6f1/5e81b3df7f2fb86876a59a44c5f357b69f73.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/e6/f1/e6f15e81b3df7f2fb86876a59a44c5f357b69f73.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1631/jzus.a0920310"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Geometric Graphs from Data to Aid Classification Tasks with Graph Convolutional Networks

Yifan Qian, Paul Expert, Pietro Panzarasa, Mauricio Barahona
<span title="">2020</span> <i title="Elsevier BV"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/tol7woxlqjeg5bmzadeg6qrg3e" style="color: black;">Social Science Research Network</a> </i> &nbsp;
SUMMARY Traditional classification tasks learn to assign samples to given classes based solely on sample features.  ...  This allows us to leverage recent graphbased deep-learning algorithms and extend the applicability of Graph Neural Networks to feature-only datasets.  ...  The 0-1 adjacency matrix of the MST is denoted by A MST . We then add edges to the MST based on two types of criteria: (1) local neighborhoods or (2) balancing local and global distances.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.2139/ssrn.3713501">doi:10.2139/ssrn.3713501</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/hoza6ok3kfaltfizjs54h3pgkm">fatcat:hoza6ok3kfaltfizjs54h3pgkm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210716001727/https://spiral.imperial.ac.uk:8443/bitstream/10044/1/88614/9/1-s2.0-S266638992100057X-main.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/0b/15/0b153c30c367df82ac3c81d9f400310d91bb0da8.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.2139/ssrn.3713501"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ssrn.com </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 56,141 results