Filters








17,391 Hits in 3.6 sec

Learning Statistical Texture for Semantic Segmentation [article]

Lanyun Zhu, Deyi Ji, Shiping Zhu, Weihao Gan, Wei Wu, Junjie Yan
<span title="2021-03-06">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this paper, we fully take advantages of the low-level texture features and propose a novel Statistical Texture Learning Network (STLNet) for semantic segmentation.  ...  Existing semantic segmentation works mainly focus on learning the contextual information in high-level semantic features with CNNs.  ...  Conclusion In this paper, we propose a novel STLNet for semantic segmentation. The key innovation lies in learning texture features from the statistical perspective.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2103.04133v1">arXiv:2103.04133v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/75vtx6zblvghdjywbl3b7kshmm">fatcat:75vtx6zblvghdjywbl3b7kshmm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210315122732/https://arxiv.org/pdf/2103.04133v1.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/c7/19c79ca9898266404623312dfbdad9b4331ee051.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2103.04133v1" 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>

Analysis of segment statistics for semantic classification of natural images

Dejan Depalov, Thrasyvoulos N. Pappas, Bernice E. Rogowitz, Thrasyvoulos N. Pappas, Scott J. Daly
<span title="2007-02-15">2007</span> <i title="SPIE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/65pgs7wxtvg7npmapw4eoo6dzy" style="color: black;">Human Vision and Electronic Imaging XII</a> </i> &nbsp;
We have proposed a new approach for semantic image classification that utilizes the adaptive perceptual color-texture segmentation algorithm by Chen et al., which segments natural scenes into perceptually  ...  For this, we compare the statistics of the segment features obtained using the Chen et al. algorithm to those that correspond to human segmentations, and show that they are remarkably similar.  ...  The resulting segments were manually labeled to be used as the ground truth for collecting statistics and supervised learning. Each segment was assigned exactly one label.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1117/12.716237">doi:10.1117/12.716237</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/hvei/DepalovP07.html">dblp:conf/hvei/DepalovP07</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/vhu4qsqb4fgz5el3q7fcaavtpe">fatcat:vhu4qsqb4fgz5el3q7fcaavtpe</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20100615115236/http://www.eecs.northwestern.edu/~pappas/papers/depalov_hvei07.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/6f/c6/6fc649b842eebf66b91543951b8ca7907a9bdde6.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1117/12.716237"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Semantic Scene Segmentation using Random Multinomial Logit

Ananth Ranganathan
<span title="">2009</span> <i title="British Machine Vision Association"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/6bfo5625nvdfvbgyf7ldi5wmfe" style="color: black;">Procedings of the British Machine Vision Conference 2009</a> </i> &nbsp;
Semantic segmentation or scene analysis involves labeling all the components in an image, usually at the pixel level.  ...  segmentation.  ...  Semantic segmentation or scene analysis involves labeling all the components in an image, usually at the pixel level.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5244/c.23.59">doi:10.5244/c.23.59</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/bmvc/Ranganathan09.html">dblp:conf/bmvc/Ranganathan09</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/cvj6fk2ii5bsdluxltc2ioaove">fatcat:cvj6fk2ii5bsdluxltc2ioaove</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20140715140614/http://www.bmva.org/bmvc/2009/Papers/Paper153/Abstract153.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/9e/f1/9ef1c235305a4235a2fa3aa66d7295900ccf0c89.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5244/c.23.59"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

CNN based texture synthesize with Semantic segment [article]

Xianye Liang, Bocheng Zhuo, Peijie Li, Liangju He
<span title="2016-05-16">2016</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
The state-of-art CNN can not capture the spatial location of texture in image, lead to significant distortion after texture synthesize, we propose a new way to generating-image by adding the semantic segment  ...  areas such as photo editing, image design, computer animation, real-time rendering for large scale of scenes and for visual effects in movies.  ...  .), attribute to the development of deep learning in image semantic segmentation, which has been one of the most active topics in the field of image understanding and computer vision for a long time. we  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1605.04731v1">arXiv:1605.04731v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/gkou4yzxk5bwvon6wvphc6asui">fatcat:gkou4yzxk5bwvon6wvphc6asui</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200930144431/https://arxiv.org/ftp/arxiv/papers/1605/1605.04731.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/b4/c9/b4c97a351b59ad674fac28e24b587dce47173965.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1605.04731v1" 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>

Perceptually based techniques for semantic image classification and retrieval

Dejan Depalov, Thrasyvoulos Pappas, Dongge Li, Bhavan Gandhi, Bernice E. Rogowitz, Thrasyvoulos N. Pappas, Scott J. Daly
<span title="2006-02-02">2006</span> <i title="SPIE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/65pgs7wxtvg7npmapw4eoo6dzy" style="color: black;">Human Vision and Electronic Imaging XI</a> </i> &nbsp;
We present a new approach for semantic classification that utilizes a recently proposed color-texture segmentation algorithm (by Chen et al.), which combines knowledge of human perception and signal characteristics  ...  The color and texture features of these regions are used as medium level descriptors, based on which we extract semantic labels, first at the segment and then at the scene level.  ...  (b) Selected segment. (c) Its color composition. (d) Its texture composition. Figure 3 . 3 Statistics of dominant colors.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1117/12.660612">doi:10.1117/12.660612</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/hvei/DepalovPLG06.html">dblp:conf/hvei/DepalovPLG06</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/w5oe3m4f3nc6hmot3xfpacdjou">fatcat:w5oe3m4f3nc6hmot3xfpacdjou</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20070325201258/http://www.ece.northwestern.edu:80/~pappas/papers/depalov_hvei06.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/52/96/52963850a0b887cbac51e29db6a6a0999291bcd0.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1117/12.660612"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Understanding Rooftop PV Panel Semantic Segmentation of Satellite and Aerial Images for Better Using Machine Learning

Peiran Li, Haoran Zhang, Zhiling Guo, Suxing Lyu, Jinyu Chen, Wenjing Li, Xuan Song, Ryosuke Shibasaki, Jinyue Yan
<span title="">2021</span> <i title="Elsevier BV"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ipbmagcy2fffnkr477wpmdydsi" style="color: black;">Advances in Applied Energy</a> </i> &nbsp;
the notable resolution threshold for effective semantic-segmentation.  ...  .  Finding the notable resolution threshold for effective PV panel semantic-segmentation.  Exploring homogeneous texture feature and heterogenous color feature of PV panel image data.  Providing recommendations  ...  Most of the "fashionable" semantic segmentation machine learning methods were developed based on these concentrated datasets.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.adapen.2021.100057">doi:10.1016/j.adapen.2021.100057</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/jusj2wwc3nfopmfw7hgijkx34i">fatcat:jusj2wwc3nfopmfw7hgijkx34i</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210721140315/https://pdf.sciencedirectassets.com/777797/AIP/1-s2.0-S2666792421000494/main.pdf?X-Amz-Security-Token=IQoJb3JpZ2luX2VjEMX%2F%2F%2F%2F%2F%2F%2F%2F%2F%2FwEaCXVzLWVhc3QtMSJIMEYCIQDyTSf9KyGh9D2CaW%2F5y%2BS%2B900mDQuTgVQxGmxkq4164gIhAI2su27QwjQAWQ6o4zDyK4Ev%2FHLW3jeXj7I2243CaeMjKoMECL7%2F%2F%2F%2F%2F%2F%2F%2F%2F%2FwEQBBoMMDU5MDAzNTQ2ODY1IgxwndgSXSgepzSBo1cq1wPVXezIqxLWRcrd%2F2iOFbGvBLNj9lAdp8yyOqPpuikG%2F5JYExf8LAjgKIn8b5CkE%2BtOVvkCqcmyO0uZ0GRT4fC8RBKC1RB%2B7tUwlixgrpocibXKn47j7u%2BZ43OGYobsu2V1cCQy61FWPQGpreHz1cICnYb5uC9KkploAsHPUsg2uTkuS6OXQdtm%2B6eI7OcquJB0JcWQb6CpcU3hhPHIEr7IoBubuPrHDfgS1WGS4HS8iL9VHm5z2U%2BR%2FHmR%2B4cPXz66GnX7Prfh%2Fsq8y0nZbKaWS7w0p3XX7AeuN6HqRH2E2JGgG3XQcU5c8w5Nz9VfZLtbdV51mNLtXlvBtzzjWjyTS7c7PI4873YBu3I0Jg6ijFCo2uWFLcKvnPiW3aDMfAlxLGr7KLDpG1tu6tFbldO7Rq%2BCffHzICAs56VQhTzoIdQHdoxiv2OnoEiut1F9j3A30fY6IERxOTbAU3e%2Fu7EWzsxlJaneNR7yzdPpnUdWc7yWjOGFvFyV6CnkYl6SeS4tmc5l5ER1mSKYmvVNkB5iVqB%2BDTYz%2BSkhZ2BvPUF4xOILVy9HvsWG7kZTjoYM2NFvB4HwpMMkl3TMvK5q0UJHrxoyIB8j%2B%2F18cooEkPQKDlnGxa3yDxgwrbDghwY6pAGIr%2F9Fp3WAbC%2Fx7hc7FJhn7Zw99UzAu1gm4VOHsNB%2B%2F0HgcTOUMlWfU5sh7fMZwS573jthUYqy4%2F%2Bz2Vqjvwto2GUVLc%2FyHmYnJxjFDGvVKtMCDkiSk2N55UhDsmtEQtO%2FqjBAG2JS4RRWyHtlm%2BvlT8J9Dsj1g5jfdtd3yYTi%2B%2BWfVz5YU0AujCUpHqCPThTMxqh9WlYGVsM4FxZxs0AvJvHcXA%3D%3D&amp;X-Amz-Algorithm=AWS4-HMAC-SHA256&amp;X-Amz-Date=20210721T140310Z&amp;X-Amz-SignedHeaders=host&amp;X-Amz-Expires=300&amp;X-Amz-Credential=ASIAQ3PHCVTY4YUCLJ4O%2F20210721%2Fus-east-1%2Fs3%2Faws4_request&amp;X-Amz-Signature=b29365508c8634a907def9a3a480b3081e0eaa128d7b6524370def4b14422b0a&amp;hash=8c991b909c71ee9803c317967f9093008e3fac31171bc097c62b7867e0b89b0f&amp;host=68042c943591013ac2b2430a89b270f6af2c76d8dfd086a07176afe7c76c2c61&amp;pii=S2666792421000494&amp;tid=spdf-c3d9960a-3793-496a-a8be-cb189dd3cef0&amp;sid=3f949a6b7534254cf5184821ed345c663f5dgxrqa&amp;type=client" 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/43/16/431674f1312b049b42b736d9b213f6249a95a764.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.adapen.2021.100057"> <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>

Content Based Video Retrieval Systems

B V Patel
<span title="2012-04-30">2012</span> <i title="Academy and Industry Research Collaboration Center (AIRCC)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/7g2a2uxhlfg2hiongaqdzvmdna" style="color: black;">International Journal of UbiComp</a> </i> &nbsp;
These features are intended for selecting, indexing and ranking according to their potential interest to the user.  ...  This survey reviews the interesting features that can be extracted from video data for indexing and retrieval along with similarity measurement methods.  ...  Texture Segmentation used as a description for regions into segments its two types are region based and boundary based.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5121/iju.2012.3202">doi:10.5121/iju.2012.3202</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/rrtofvbjfbakhacn565qre5enq">fatcat:rrtofvbjfbakhacn565qre5enq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20180604145921/http://www.airccse.org/journal/iju/papers/3212iju02.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/02/83/0283327014955760380ca1a4dde466867cc0d6ae.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5121/iju.2012.3202"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

The Unreasonable Effectiveness of Texture Transfer for Single Image Super-Resolution [chapter]

Muhammad Waleed Gondal, Bernhard Schölkopf, Michael Hirsch
<span title="">2019</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;
We provide a better understanding of texture constraining mechanism and develop a novel semantically guided texture constraining method for further improvement.  ...  We show that texture loss [1] alone allows the generation of perceptually high quality images.  ...  Instead of matching the global level statistics of an image we divide the image into r segments semantically.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-030-11021-5_6">doi:10.1007/978-3-030-11021-5_6</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/3kdewbcq6varto3sbdkxqvusly">fatcat:3kdewbcq6varto3sbdkxqvusly</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190807111817/http://openaccess.thecvf.com/content_ECCVW_2018/papers/11133/Gondal_The_Unreasonable_Effectiveness_of_Texture_Transfer_for_Single_Image_Super-resolution_ECCVW_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/b6/75/b675d6406c299403a883d298c0a9e3b526158fbe.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-030-11021-5_6"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

Level generation and style enhancement – deep learning for game development overview [article]

Piotr Migdał, Bartłomiej Olechno, Błażej Podgórski
<span title="2021-07-15">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
. - Unsupervised semantic segmentation for extracting semantic features (e.g. Tile2Vec). - Texture synthesis - creating large patterns based on a smaller sample (e.g. InGAN).  ...  . - Neural style transfer for changing visual themes. - Image translation - turning semantic maps into images (e.g. GauGAN). - Semantic segmentation for turning images into semantic masks (e.g.  ...  We are grateful to Olle Bergman, Anna Olchowik and Jan Marucha for their comments and to Rafał Jakubanis for his extensive editorial feedback on the draft.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2107.07397v1">arXiv:2107.07397v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/usno4wbir5gsjdv44cy5kikzka">fatcat:usno4wbir5gsjdv44cy5kikzka</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210718170840/https://arxiv.org/pdf/2107.07397v1.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/4f/b1/4fb1483a96ecafff9d463274b142753b3f3b2696.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2107.07397v1" 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>

Grid Saliency for Context Explanations of Semantic Segmentation [article]

Lukas Hoyer, Mauricio Munoz, Prateek Katiyar, Anna Khoreva, Volker Fischer
<span title="2019-11-07">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
As the proposed grid saliency allows to spatially disentangle the object and its context, we specifically explore its potential to produce context explanations for semantic segmentation networks, discovering  ...  investigate the effectiveness of grid saliency on a synthetic dataset with an artificially induced bias between objects and their context as well as on the real-world Cityscapes dataset using state-of-the-art segmentation  ...  Semantic segmentation. CNNs have become a default technique for semantic segmentation [30, 31, 32] . [33] first showcased the use of CNNs for segmentation.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1907.13054v2">arXiv:1907.13054v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ik7vn7rqwrbi3irkfmm6gnnkhu">fatcat:ik7vn7rqwrbi3irkfmm6gnnkhu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200930071834/https://arxiv.org/pdf/1907.13054v2.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/11/7d/117d0bae3ccc24d81a1abac4c93ec1dd86b738e8.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1907.13054v2" 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>

Benefiting from Multitask Learning to Improve Single Image Super-Resolution [article]

Mohammad Saeed Rad, Behzad Bozorgtabar, Claudiu Musat, Urs-Viktor Marti, Max Basler, Hazim Kemal Ekenel, Jean-Philippe Thiran
<span title="2019-07-29">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
given image by using multitask learning, simultaneously for image super-resolution and semantic segmentation.  ...  At run-time only layers resulting HR image are used and no segmentation label is required.  ...  to learn semantic information.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1907.12488v1">arXiv:1907.12488v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/knhdqe6to5eujmii4p6xflupx4">fatcat:knhdqe6to5eujmii4p6xflupx4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200823174514/https://arxiv.org/pdf/1907.12488v1.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/ba/aa/baaa190cebdfdefe4915efe6d01dd7bb476dc883.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1907.12488v1" 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 automatic image annotation techniques

Dengsheng Zhang, Md. Monirul Islam, Guojun Lu
<span title="">2012</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 typical method of bridging the semantic gap is through the automatic image annotation (AIA) which extracts semantic features using machine learning techniques.  ...  We analyse key aspects of the various AIA methods, including both feature extraction and semantic learning methods. Major methods are discussed and illustrated in details.  ...  Acknowledgement The authors are grateful for the constructive and valuable comments made by the many expert reviewers.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.patcog.2011.05.013">doi:10.1016/j.patcog.2011.05.013</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/tse6w7ltwnactpra3kgplc3yqi">fatcat:tse6w7ltwnactpra3kgplc3yqi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170810084132/http://is.hust.edu.vn/~oanhnt/recycle_bin/ThongtinKT-BTL/refs/PR-2011-%20A%20review%20on%20automatic%20image%20annotation%20techniques.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/32/0b/320b9a7a00cecf02fbcae5deac34a7a6a58e6fc5.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.patcog.2011.05.013"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> elsevier.com </button> </a>

SRBIR: Semantic Region Based Image Retrieval by Extracting the Dominant Region and Semantic Learning

Rajam
<span title="2011-03-01">2011</span> <i title="Science Publications"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/wake4w3hqzd4ndiy2zowpciv64" style="color: black;">Journal of Computer Science</a> </i> &nbsp;
The Support Vector Machine-Binary Decision Tree (SVM-BDT) is used for semantic learning and it finds the semantic category of an image.  ...  , roses and does the semantic learning, is proposed.  ...  The color, texture and color-texture semantic templates are found for each semantic category. These semantic templates are used in constructing the SVM-BDT.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3844/jcssp.2011.400.408">doi:10.3844/jcssp.2011.400.408</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/m2txfsnzwvbrjg6h7lbf3chs2y">fatcat:m2txfsnzwvbrjg6h7lbf3chs2y</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170829220101/http://thescipub.com/PDF/jcssp.2011.400.408.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/0f/99/0f993f81d4d2539262270e13275eaacc7888a9b4.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3844/jcssp.2011.400.408"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Image region annotation based on segmentation and semantic correlation analysis

Jing Zhang, Yakun Mu, Shengwei Feng, Kehuang Li, Yubo Yuan, Chin-Hui Lee
<span title="2018-08-01">2018</span> <i title="Institution of Engineering and Technology (IET)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/dscocsarvbb5boe7eixzypaetu" style="color: black;">IET Image Processing</a> </i> &nbsp;
A texture-enhanced image segmentation JSEG algorithm is first used to improve the pixel consistency in a segmented image region.  ...  The authors propose an image region annotation framework by exploring syntactic and semantic correlations among segmented regions in an image.  ...  Statistical analysis In general, statistical hypothesis test provides an important basis for evaluating the effectiveness and generalisation capabilities of machine learning methods, especially in the  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1049/iet-ipr.2017.0917">doi:10.1049/iet-ipr.2017.0917</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/uitqykfenbbtlpbcj6j4ue3fly">fatcat:uitqykfenbbtlpbcj6j4ue3fly</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210716183904/https://ietresearch.onlinelibrary.wiley.com/doi/pdfdirect/10.1049/iet-ipr.2017.0917" 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/a5/42/a542e1fd24e6ceaef50989757624b70fd4a96c9f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1049/iet-ipr.2017.0917"> <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>

Crohn's disease tissue segmentation from abdominal MRI using semantic information and graph cuts

Dwarikanath Mahapatra, Peter J. Schuffler, Jeroen A.W. Tielbeek, Franciscus M. Vos, Joachim M. Buhmann
<span title="">2013</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/qcepwfkflvg5toaa6fh2alj3b4" style="color: black;">2013 IEEE 10th International Symposium on Biomedical Imaging</a> </i> &nbsp;
Intensity, texture, curvature and context information are used with random forest (RF) classifiers to calculate probability maps for graph cut segmentation.  ...  Inclusion of semantic information significantly improves segmentation accuracy and its importance is reflected in quantitative measures and visual results.  ...  [5] use decision forests for semantic segmentation of multiple organs from CT images. A machine learning approach for detecting colorectal cancer is taken in [6] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/isbi.2013.6556486">doi:10.1109/isbi.2013.6556486</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/isbi/MahapatraSTVB13.html">dblp:conf/isbi/MahapatraSTVB13</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/yrtx7uhga5c3bgnoadxkwukive">fatcat:yrtx7uhga5c3bgnoadxkwukive</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200321062916/http://homepage.tudelft.nl/h5u3d/papers/CrohnsDisseaseTissue.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/6d/d4/6dd4fd19de65489eb2f4aa642cbb9da9721a0426.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/isbi.2013.6556486"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 17,391 results