Filters








260 Hits in 7.0 sec

Reversion Correction and Regularized Random Walk Ranking for Saliency Detection

Yuchen Yuan, Changyang Li, Jinman Kim, Weidong Cai, David Dagan Feng
<span title="">2018</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/dhlhr4jqkbcmdbua2ca45o7kru" style="color: black;">IEEE Transactions on Image Processing</a> </i> &nbsp;
In recent saliency detection research, many graph-based algorithms have applied boundary priors as background queries, which may generate completely "reversed" saliency maps if the salient objects are  ...  Second, we propose regularized random walk ranking (RRWR) model, which introduces prior saliency estimation to every pixel in the image by taking both region and pixel image features into account, thus  ...  In this paper, in order to overcome the two issues above, we propose the reversion correction and regularized random walk ranking (RCRR) for saliency detection, a novel graph-based bottom-up saliency detection  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tip.2017.2762422">doi:10.1109/tip.2017.2762422</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/29028192">pmid:29028192</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/nuomzw6fcnedregoo2yqqoqxhq">fatcat:nuomzw6fcnedregoo2yqqoqxhq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200506145354/https://ses.library.usyd.edu.au/bitstream/handle/2123/20604/2017-j-cai-TIP2762422-YuchenYuan-10.1109:TIP.2017.2762422.pdf;jsessionid=54BF12CF946DC1E7F23A0855213167AE?sequence=2" 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/2c/32/2c3256c5560fdaaa8973dbd995e877ab1fd02a4d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tip.2017.2762422"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

A Unified RGB-T Saliency Detection Benchmark: Dataset, Baselines, Analysis and A Novel Approach [article]

Chenglong Li, Guizhao Wang, Yunpeng Ma, Aihua Zheng, Bin Luo, Jin Tang
<span title="2017-01-11">2017</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
for different saliency detection algorithms.  ...  With this benchmark, we propose a novel approach, multi-task manifold ranking with cross-modality consistency, for RGB-T saliency detection.  ...  In this work, we regard the query labels as initial superpixel saliency value, and s is thus an initial superpixel saliency vector.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1701.02829v1">arXiv:1701.02829v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/nzaqsedq7bfr3mkp6ngx7kwhce">fatcat:nzaqsedq7bfr3mkp6ngx7kwhce</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200908075136/https://arxiv.org/pdf/1701.02829v1.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/13/42/134269cac21547cf73ab05f7522e8e51971c2322.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1701.02829v1" 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 Dense sub-graph based approach for Automatic detection of Optic Disc [article]

Subrata Jana, Tribeni Prasad Banerjee, Gour Sundar Mitra Thakur, Pabitra Mitra
<span title="2022-06-28">2022</span> <i title="Cold Spring Harbor Laboratory"> medRxiv </i> &nbsp; <span class="release-stage" >pre-print</span>
The graph base is used in this paper for automatic localization of the optic disc.  ...  This paper proposed and modified a new dense sub - graph approach to locate the affected optic disc by using DRIVE, STAIR, and Drishti -GS1 databases.  ...  I ACCURACY RESULT Model Name Graph Manifold Model Spectral Saliency ROI Model Dense Saliency Model Proposed Model Accuracy(%) 83 84 85 87 93  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1101/2022.06.27.22276966">doi:10.1101/2022.06.27.22276966</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/3jsxjf2obvcndpb3vwvxql5q4a">fatcat:3jsxjf2obvcndpb3vwvxql5q4a</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220703130432/https://www.medrxiv.org/content/medrxiv/early/2022/06/28/2022.06.27.22276966.full.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/1a/75/1a75633aa50b92e3c3e05d2adf776672b9774cf6.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1101/2022.06.27.22276966"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> medrxiv.org </button> </a>

Automatic Image Co-Segmentation: A Survey [article]

Xiabi Liu, Xin Duan
<span title="2019-11-18">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We firstly analyze visual/semantic cues for guiding image co-segmentation, including object cues and correlation cues.  ...  Hopefully, this comprehensive investigation will be helpful for the development of image co-segmentation technique.  ...  Sun and Ponce [26] trained a part detector based on SVM with group sparsity regularization for detecting the common object appearing in the images, from a lot of initial detectors.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1911.07685v1">arXiv:1911.07685v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/xstyqatlffdhjilkl7yo3nxldi">fatcat:xstyqatlffdhjilkl7yo3nxldi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200914204159/https://arxiv.org/pdf/1911.07685v1.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/19/7a/197a2f7b7fb8c1c985b20840f53c2ff4c28bc7ad.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1911.07685v1" 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>

Coarse-to-Fine Salient Object Detection with Low-Rank Matrix Recovery [article]

Qi Zheng, Shujian Yu, Xinge You, Qinmu Peng
<span title="2019-09-09">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Low-Rank Matrix Recovery (LRMR) has recently been applied to saliency detection by decomposing image features into a low-rank component associated with background and a sparse component associated with  ...  Given samples from the coarse saliency map, we then learn a projection that maps image features to refined saliency values, to significantly sharpen the object boundaries and to preserve the object entirety  ...  However, a fully-connected graph suffers from high computational cost. LRMR-based Saliency Detection Methods The usage of LRMR theory on saliency detection was initiated by Yan et al.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1805.07936v4">arXiv:1805.07936v4</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/yp5v4vfn5zh7zp2myay44tke6e">fatcat:yp5v4vfn5zh7zp2myay44tke6e</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200930081053/https://arxiv.org/pdf/1805.07936v4.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/bf/d5/bfd5c9f846388e6ed7fd6c5fc02ce73cfed97d3e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1805.07936v4" 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>

OBJECT MANIFOLD ALIGNMENT FOR MULTI-TEMPORAL HIGH RESOLUTION REMOTE SENSING IMAGES CLASSIFICATION

G. Gao, M. Zhang, Y. Gu
<span title="2017-05-31">2017</span> <i title="Copernicus GmbH"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/i74shj7anreaxjo327fokng66m" style="color: black;">The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences</a> </i> &nbsp;
For classifying the multi-temporal high resolution images with limited labelled samples, spectral drift and "pepper and salt" problem, an object-based manifold alignment method is proposed.  ...  Traditional approaches in this field mainly face to limited labelled samples and spectral drift of image information.  ...  ACKNOWLEDGEMENTS This work was supported by the National Science Fund for Excellent Young Scholars under the Grant 61522107 and the Natural Science Foundation of China under the Grant 61371180 and 60972144  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5194/isprs-archives-xlii-1-w1-325-2017">doi:10.5194/isprs-archives-xlii-1-w1-325-2017</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/nnvpyeptfjbsjpe76usmhwqwci">fatcat:nnvpyeptfjbsjpe76usmhwqwci</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20171202222839/https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLII-1-W1/325/2017/isprs-archives-XLII-1-W1-325-2017.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/32/cc/32cc16ae73cb61bcd98ebc294d23b4c738cd941d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5194/isprs-archives-xlii-1-w1-325-2017"> <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>

An Adaptive Semisupervised Feature Analysis for Video Semantic Recognition

Minnan Luo, Xiaojun Chang, Liqiang Nie, Yi Yang, Alexander G. Hauptmann, Qinghua Zheng
<span title="">2018</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;
Additionally, the predetermined graph separates itself from the procedure of feature selection, which might lead to downgraded performance for video semantic recognition.  ...  for its efficiency and comprehensibility.  ...  exploiting the data geometry by the manifold regularization.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tcyb.2017.2647904">doi:10.1109/tcyb.2017.2647904</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/28237940">pmid:28237940</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/luc3o3xlcbav3e47upkev3ituy">fatcat:luc3o3xlcbav3e47upkev3ituy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170315225625/http://www.cs.cmu.edu:80/~uqxchan1/papers/CYB17_OGE_SFS.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/31/e6/31e68bd643e264d7971fc99ba6c344842bbf9641.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tcyb.2017.2647904"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Image Matching via Saliency Region Correspondences

Alexander Toshev, Jianbo Shi, Kostas Daniilidis
<span title="">2007</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ilwxppn4d5hizekyd3ndvy2mii" style="color: black;">2007 IEEE Conference on Computer Vision and Pattern Recognition</a> </i> &nbsp;
The co-saliency score function, which characterizes these spectral components, can be directly used as a similarity metric as well as a positive feedback for updating and establishing new point correspondences  ...  The co-saliency score function, which characterizes these spectral components, can be directly used as a similarity metric as well as a positive feedback for updating and establishing new point correspondences  ...  Spectral approaches for weighted graph matching have been extensively studied, some of the notable works being [11, 8] . Such approaches characterize the graphs by their dominant eigenvectors.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cvpr.2007.382973">doi:10.1109/cvpr.2007.382973</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/cvpr/ToshevSD07.html">dblp:conf/cvpr/ToshevSD07</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/wmeldoj6krfgpnx5zwxvhtqdti">fatcat:wmeldoj6krfgpnx5zwxvhtqdti</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170921214548/http://repository.upenn.edu/cgi/viewcontent.cgi?article=1562&amp;context=cis_papers" 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/e4/e8/e4e87d6c689745357a4866d3a7c68aad48eaf8d0.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cvpr.2007.382973"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Affinity Learning via Self-Supervised Diffusion for Spectral Clustering

Jianfeng Ye, Qilin Li, Jinlong Yu, Xincheng Wang, Huaming Wang
<span title="">2020</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/q7qi7j4ckfac7ehf3mjbso4hne" style="color: black;">IEEE Access</a> </i> &nbsp;
INDEX TERMS Affinity learning, diffusion process, spectral clustering.  ...  Commonly used affinity matrices are constructed by either the Gaussian kernel or the self-expressive model with sparse or low-rank constraints.  ...  It starts with (a) input data and generates (b) initial affinity graph using the Gaussian kernel or sparse representation model, and then (c) it updates the affinity graph using the diffusion process which  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2020.3044696">doi:10.1109/access.2020.3044696</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/scycrm2d7navjayvdccwytc3qy">fatcat:scycrm2d7navjayvdccwytc3qy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210428191803/https://ieeexplore.ieee.org/ielx7/6287639/9312710/09293293.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/b7/c1/b7c19085363bef0de0c8e41daea0f80c3697f384.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2020.3044696"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> ieee.com </button> </a>

Graphs as Tools to Improve Deep Learning Methods [article]

Carlos Lassance and Myriam Bontonou and Mounia Hamidouche and Bastien Pasdeloup and Lucas Drumetz and Vincent Gripon
<span title="2021-10-08">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
This chapter is composed of four main parts: tools for visualizing intermediate layers in a DNN, denoising data representations, optimizing graph objective functions and regularizing the learning process  ...  However, although they are state-of-the-art in many machine learning challenges, they still suffer from several limitations.  ...  Their values are initialized at random and updated during a training phase.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2110.03999v1">arXiv:2110.03999v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/k7yny2xcfze2xhuklh5u7ba2hy">fatcat:k7yny2xcfze2xhuklh5u7ba2hy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211012190440/https://arxiv.org/pdf/2110.03999v1.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/34/4c/344cbd847a0f5853246b431b3b80d6646fe59fa9.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2110.03999v1" 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>

Video Co-segmentation [chapter]

Jose C. Rubio, Joan Serrat, Antonio López
<span title="">2013</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;
Image co-segmentation trades the need for such knowledge for something much easier to obtain, namely, additional images showing the object from other viewpoints.  ...  In addition, the method works in an unsupervised manner, by learning to segment at testing time.  ...  Sundaram and Keutzer [3] apply spectral clustering to all the video sequence pixels with an affinity matrix given by the gPb 2D contour detection algorithm [4] which combines intensity, color and texture  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-642-37444-9_2">doi:10.1007/978-3-642-37444-9_2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/3qmbsl57fbcvziakumgaiiipvm">fatcat:3qmbsl57fbcvziakumgaiiipvm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170829165604/http://www.cvc.uab.es/~joans/conferences/12%20ACCV%20Video%20co-segmentation.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/db/d0/dbd0b2c71e25e13b967e9bf171af6747f1388531.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-642-37444-9_2"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

Structure Learning with Similarity Preserving [article]

Zhao Kang and Xiao Lu and Yiwei Lu and Chong Peng and Zenglin Xu
<span title="2019-12-03">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
To reveal more underlying effective manifold structure, in this paper, we explicitly model the data relation.  ...  Consequently, this technique is particularly suitable for the class of learning problems that are sensitive to sample similarity, e.g., clustering and semisupervised classification.  ...  Acknowledgment This paper was in part supported by Grants from the Natural Science Foundation of China (Nos. 61806045 and 61572111) and a Fundamental Research Fund for the Central Universities of China  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1912.01197v1">arXiv:1912.01197v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/rrgraoj4hfdbboa66qx5rbfcgu">fatcat:rrgraoj4hfdbboa66qx5rbfcgu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200910041232/https://arxiv.org/pdf/1912.01197v1.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/48/fa/48fa9380e9e568d1c586fcd87bc6cde47c9eb8e0.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1912.01197v1" 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>

Sparsity Regularized Deep Subspace Clustering for Multicriterion-Based Hyperspectral Band Selection

Samiran Das, Sawon Pratiher, Chirag Kyal, Pedram Ghamisi
<span title="">2022</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/b2n2tpw5ang73osulebz6bm4ju" style="color: black;">IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing</a> </i> &nbsp;
The work subsequently selects the representative bands from each cluster by combining structural information of the band images with the statistical similarity measure.  ...  Hyperspectral images provide rich spectral information corresponding to visible and near-infrared imaging regions, facilitating accurate classification, object identification, and target detection.  ...  For more information, see https://creativecommons.org/licenses/by/4.0/ manifold information.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/jstars.2022.3172112">doi:10.1109/jstars.2022.3172112</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/sdrvf2r5ind23p2iruylfmgccy">fatcat:sdrvf2r5ind23p2iruylfmgccy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220611122855/https://ieeexplore.ieee.org/ielx7/4609443/9656571/09767632.pdf?tp=&amp;arnumber=9767632&amp;isnumber=9656571&amp;ref=" 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/ec/a2/eca20c5f306a03a118e6d838a6e8cd60b3ac9a68.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/jstars.2022.3172112"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> ieee.com </button> </a>

Graph Learning-Convolutional Networks [article]

Bo Jiang, Ziyan Zhang, Doudou Lin, Jin Tang
<span title="2018-11-25">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
also to facilitate the graph convolution operation in GLCN for unknown label estimation.  ...  The aim of GLCN is to learn an optimal graph structure that best serves graph CNNs for semi-supervised learning by integrating both graph learning and graph convolution together in a unified network architecture  ...  For spectral methods, they generally define graph convolution operation based on spectral representation of graphs. For example, Bruna et al.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1811.09971v1">arXiv:1811.09971v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/llqo62kdzbeitpqm6dzbgnfkyu">fatcat:llqo62kdzbeitpqm6dzbgnfkyu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200827162330/https://arxiv.org/pdf/1811.09971v1.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/4c/ef/4ceff477009a59582e85f9179b0b07a855f3221b.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1811.09971v1" 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>

Visual Saliency Modeling for River Detection in High-Resolution SAR Imagery

Fei Gao, Fei Ma, Jun Wang, Jinping Sun, Erfu Yang, Huiyu Zhou
<span title="">2018</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/q7qi7j4ckfac7ehf3mjbso4hne" style="color: black;">IEEE Access</a> </i> &nbsp;
2017) Visual saliency modeling for river detection in highresolution SAR imagery. IEEE Access.  ...  For effective saliency detection, the original image is first over-segmented into a set of primitive superpixels.  ...  Optimization from Robust Background Detection (RBD) [45] , Saliency Detection via Graph-based Manifold Ranking (GMR) [43] , Graph-regularized Saliency Detection with Convex-hull-based Center Prior (  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2017.2777444">doi:10.1109/access.2017.2777444</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/t3qbnt2pdba43d47q55jaq7bz4">fatcat:t3qbnt2pdba43d47q55jaq7bz4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190413034348/https://core.ac.uk/download/pdf/145658180.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/ad/42/ad42d86c67316f5db1bcbf44e64c4ea0d8475fc7.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2017.2777444"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> ieee.com </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 260 results