Internet Archive Scholar
Filters
























89 Hits in 6.6 sec

HDD-Net: Hybrid Detector Descriptor with Mutual Interactive Learning [article]

Axel Barroso-Laguna, Yannick Verdie, Benjamin Busam, Krystian Mikolajczyk
<span title="2020-11-26">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (5.1 MB)
https://web.archive.org/web/20200528080033/https://arxiv.org/pdf/2005.05777v1.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/2005.05777v1.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:

<span title="2020-05-12">2020</span> <span class="release-stage" >pre-print</span> <span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2005.05777v1">arXiv:2005.05777v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/zzkvuzn23jbb3pn3cj7ee6cpye">fatcat:zzkvuzn23jbb3pn3cj7ee6cpye</a> </span>
We formulate the classical hard-mining triplet loss as a new detector optimisation term to refine candidate positions based on the descriptor map.  ...  We evaluate our method extensively on different benchmarks and show improvements over the state of the art in terms of image matching on HPatches and 3D reconstruction quality while keeping on par on camera  ...  Detector Learning with Triplet Loss. Hard-negative triplet learning maximises the Euclidean distance between a positive pair and their closest negative sample.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2005.05777v2">arXiv:2005.05777v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/caujmxtkl5hnlglucli354v3ua">fatcat:caujmxtkl5hnlglucli354v3ua</a> </span>
<span class="ui label basic blue small">Multiple Versions</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200528080033/https://arxiv.org/pdf/2005.05777v1.pdf" title="fulltext PDF download [not primary version]" 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] <span style="color: #f43e3e;">&#10033;</span> <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/8e/85/8e85ffb9d03f9b42cdb294f8fff2f44f753e3b5d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2005.05777v2" 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>
Citation

Axel Barroso-Laguna, Yannick Verdie, Benjamin Busam, Krystian Mikolajczyk. "HDD-Net: Hybrid Detector Descriptor with Mutual Interactive Learning." arXiv (2020)

Learning Deformable Point Set Registration with Regularized Dynamic Graph CNNs for Large Lung Motion in COPD Patients [article]

Lasse Hansen, Doris Dittmer, Mattias P. Heinrich
<span title="2019-09-17">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

Web Archive Capture PDF (2.1 MB)
https://web.archive.org/web/20200726130103/https://arxiv.org/pdf/1909.07818v1.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/1909.07818v1.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

In this work, we present a new method that enables the learning of regularized feature descriptors with dynamic graph CNNs.  ...  Deformable registration continues to be one of the key challenges in medical image analysis.  ...  Therefore, a triplet loss is employed forcing feature similarity between corresponding keypoint regions in point set pairs.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1909.07818v1">arXiv:1909.07818v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/kp56bj2exrfvbig4ctmnmutjpe">fatcat:kp56bj2exrfvbig4ctmnmutjpe</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200726130103/https://arxiv.org/pdf/1909.07818v1.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] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1909.07818v1" 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>
Citation

Lasse Hansen, Doris Dittmer, Mattias P. Heinrich. "Learning Deformable Point Set Registration with Regularized Dynamic Graph CNNs for Large Lung Motion in COPD Patients." arXiv (2019)

SuperPoint features in endoscopy [article]

O. L. Barbed, F. Chadebecq, J. Morlana, J.M. Martínez-Montiel, A. C. Murillo
<span title="2022-03-08">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (16.4 MB)
https://web.archive.org/web/20220312190358/https://arxiv.org/pdf/2203.04302v1.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/2203.04302v1.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

In the medical domain, handcrafted local features such as SIFT, with public pipelines such as COLMAP, are still a predominant tool for this kind of tasks.  ...  Our adapted model avoids features within specularity regions, a frequent and problematic artifact in endoscopic images, with consequent benefits for matching and reconstruction results.  ...  Advanced training loss and strategies significantly improved feature descriptor performances, e.g., by relying on triplet loss which aims at maximizing descriptor discrepancy between close but negative  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2203.04302v1">arXiv:2203.04302v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/yfe7ypdp55durhgknbzp43wtgq">fatcat:yfe7ypdp55durhgknbzp43wtgq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220312190358/https://arxiv.org/pdf/2203.04302v1.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/eb/92/eb92eeae90b9d389cb54403904df20f1a231c563.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2203.04302v1" 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>
Citation

O. L. Barbed, F. Chadebecq, J. Morlana, J.M. Martínez-Montiel, A. C. Murillo. "SuperPoint features in endoscopy." arXiv (2022)

SEKD: Self-Evolving Keypoint Detection and Description [article]

Yafei Song, Ling Cai, Jia Li, Yonghong Tian, Mingyang Li
<span title="2020-06-09">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (3.9 MB)
https://web.archive.org/web/20200702140103/https://arxiv.org/pdf/2006.05077v1.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/2006.05077v1.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

Guided by these properties, a self-supervised framework, namely self-evolving keypoint detection and description (SEKD), is proposed to learn an advanced local feature model from unlabeled natural images  ...  Ablation studies also verify the effectiveness of each critical training strategy. We will release our code along with the trained model publicly.  ...  Inspired by HardNet [22] , we use triplet loss along with hard example mining strategy to train the descriptor.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.05077v1">arXiv:2006.05077v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/g3ktwm73jbhc7exx42kt5mflwu">fatcat:g3ktwm73jbhc7exx42kt5mflwu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200702140103/https://arxiv.org/pdf/2006.05077v1.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/be/e3/bee3bfc5333a5bd9f0dbba9904b7ec256c20ee35.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.05077v1" 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>
Citation

Yafei Song, Ling Cai, Jia Li, Yonghong Tian, Mingyang Li. "SEKD: Self-Evolving Keypoint Detection and Description." arXiv (2020)

Learning to Align Images using Weak Geometric Supervision [article]

Jing Dong, Byron Boots, Frank Dellaert, Ranveer Chandra, Sudipta N. Sinha
<span title="2018-08-04">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (7.0 MB)
https://web.archive.org/web/20191014204106/https://arxiv.org/pdf/1808.01424v1.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/1808.01424v1.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

Such descriptors are often derived using supervised learning on existing datasets with ground truth correspondences. However, the cost of creating such datasets is usually prohibitive.  ...  In this paper, we propose a new approach to align two images related by an unknown 2D homography where the local descriptor is learned from scratch from the images and the homography is estimated simultaneously  ...  Part of the work was done while author Jing Dong was an intern at Microsoft Research. This work was also supported in part by National Institute of Food and Agriculture, USDA, under 2014-67021-22556.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1808.01424v1">arXiv:1808.01424v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/brkoe2ah3ncmpjxdiomzapcg3q">fatcat:brkoe2ah3ncmpjxdiomzapcg3q</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191014204106/https://arxiv.org/pdf/1808.01424v1.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/c0/91/c091c31c7f1450961e130301ddc8251d9e7fddb2.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1808.01424v1" 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>
Citation

Jing Dong, Byron Boots, Frank Dellaert, Ranveer Chandra, Sudipta N. Sinha. "Learning to Align Images using Weak Geometric Supervision." arXiv (2018)

Image Matching from Handcrafted to Deep Features: A Survey

Jiayi Ma, Xingyu Jiang, Aoxiang Fan, Junjun Jiang, Junchi Yan
<span title="2020-08-04">2020</span> <i title="Springer Science and Business Media LLC"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/hfdglwo5wbbmta6wop52fam7a4" style="color: black;">International Journal of Computer Vision</a> </i> &nbsp;

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (7.2 MB)
https://web.archive.org/web/20201108024942/https://link.springer.com/content/pdf/10.1007/s11263-020-01359-2.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit <a rel="external noopener" href="https://link.springer.com/content/pdf/10.1007/s11263-020-01359-2.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

Over the past decades, growing amount and diversity of methods have been proposed for image matching, particularly with the development of deep learning techniques over the recent years.  ...  Finally, we conclude with the current status of image matching technologies and deliver insightful discussions and prospects for future works.  ...  Zhou et al. (2018) proposed to learn from the images of multiple views for the description of 3D keypoints.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/s11263-020-01359-2">doi:10.1007/s11263-020-01359-2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/a2epfaolwjfm5mcrsmn7g6sd7m">fatcat:a2epfaolwjfm5mcrsmn7g6sd7m</a> </span>
<span class="ui label basic orange small" title="Open Access">Open Access</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201108024942/https://link.springer.com/content/pdf/10.1007/s11263-020-01359-2.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/77/a9/77a956512e22e37223ac6a00dcf191a086951505.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/s11263-020-01359-2"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> springer.com </button> </a>
Citation

Jiayi Ma, Xingyu Jiang, Aoxiang Fan, Junjun Jiang, Junchi Yan. "Image Matching from Handcrafted to Deep Features: A Survey." International Journal of Computer Vision 129.1 (2020)

Object Detection Using Keygraphs [article]

Marcelo Hashimoto, Roberto Marcondes Cesar Junior
<span title="2013-10-01">2013</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (4.3 MB)
https://web.archive.org/web/20191026061327/https://arxiv.org/pdf/1310.0171v1.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/1310.0171v1.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

The accuracy of the implementation is shown by results of over 800 experiments with a well-known database of images.  ...  The speed is illustrated by real-time tracking with two different cameras in ordinary hardware.  ...  The latter extended those contributions using triplet vector descriptors and normalized triangular region vectors.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1310.0171v1">arXiv:1310.0171v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/4sfnmklqsjcgxlwa2evd4sqdey">fatcat:4sfnmklqsjcgxlwa2evd4sqdey</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191026061327/https://arxiv.org/pdf/1310.0171v1.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/80/87/8087ef0018fe63f5250d7860a476d9c0f1a68b47.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1310.0171v1" 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>
Citation

Marcelo Hashimoto, Roberto Marcondes Cesar Junior. "Object Detection Using Keygraphs." arXiv (2013)

Improving the HardNet Descriptor [article]

Milan Pultar
<span title="2020-11-23">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

Web Archive Capture PDF (9.6 MB)
https://web.archive.org/web/20200729044641/https://arxiv.org/pdf/2007.09699v1.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/2007.09699v1.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:

<span title="2020-07-19">2020</span> <span class="release-stage" >pre-print</span> <span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2007.09699v1">arXiv:2007.09699v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ggqxozxsozh67gc47hqqgfovma">fatcat:ggqxozxsozh67gc47hqqgfovma</a> </span>
In the thesis we consider the problem of local feature descriptor learning for wide baseline stereo focusing on the HardNet descriptor, which is close to state-of-the-art.  ...  It is based on registered images from selected cameras from the AMOS dataset.  ...  We focus on improving the descriptor part, namely using the HardNet architecture [39] with the triplet margin loss function.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2007.09699v2">arXiv:2007.09699v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/qenrgkzqqvbtrhvsqtpvcibnd4">fatcat:qenrgkzqqvbtrhvsqtpvcibnd4</a> </span>
<span class="ui label basic blue small">Multiple Versions</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200729044641/https://arxiv.org/pdf/2007.09699v1.pdf" title="fulltext PDF download [not primary version]" 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] <span style="color: #f43e3e;">&#10033;</span> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2007.09699v2" 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>
Citation

Milan Pultar. "Improving the HardNet Descriptor." arXiv (2020)

Deep Learning for Instance Retrieval: A Survey [article]

Wei Chen, Yu Liu, Weiping Wang, Erwin Bakker, Theodoros Georgiou, Paul Fieguth, Li Liu, Michael S. Lew
<span title="2022-01-08">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (3.5 MB)
https://web.archive.org/web/20220112005623/https://arxiv.org/pdf/2101.11282v3.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/2101.11282v3.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

Other Versions

<span title="2021-02-03">2021</span> <span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2101.11282v2">arXiv:2101.11282v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/niwgmr5pdvgkfnek3esxgnb7ei">fatcat:niwgmr5pdvgkfnek3esxgnb7ei</a> </span>
<span title="2021-01-27">2021</span> <span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2101.11282v1">arXiv:2101.11282v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/e64s3d4ap5e7xomu7khaelqcm4">fatcat:e64s3d4ap5e7xomu7khaelqcm4</a> </span>
In this survey we review recent instance retrieval works that are developed based on deep learning algorithms and techniques, with the survey organized by deep network architecture types, deep features  ...  In recent years a vast amount of visual content has been generated and shared from many fields, such as social media platforms, medical imaging, and robotics.  ...  ACKNOWLEDGMENT The authors would like to thank the pioneer researchers in instance retrieval and other related fields.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2101.11282v3">arXiv:2101.11282v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/qvodunmw4bdltcneadyt7d7h5m">fatcat:qvodunmw4bdltcneadyt7d7h5m</a> </span>
<span class="ui label basic orange small" title="Open Access">Open Access</span> <span class="ui label basic blue small">Multiple Versions</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220112005623/https://arxiv.org/pdf/2101.11282v3.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/d7/73/d7736352067f37fc4d9e8bc7ae68b5239b44b78d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2101.11282v3" 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>
Citation

Wei Chen, Yu Liu, Weiping Wang, Erwin Bakker, Theodoros Georgiou, Paul Fieguth, Li Liu, Michael S. Lew. "Deep Learning for Instance Retrieval: A Survey." arXiv (2022)

Anomaly Detection of Defect using Energy of Point Pattern Features within Random Finite Set Framework [article]

Ammar Mansoor Kamoona, Amirali Khodadadian Gostar, Alireza Bab-Hadiashar, Reza Hoseinnezhad
<span title="2021-08-27">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (5.9 MB)
https://web.archive.org/web/20210901084212/https://arxiv.org/pdf/2108.12159v1.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/2108.12159v1.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

To the best of our knowledge, we are the first to propose using transfer learning of local/point pattern features to overcome these limitations and capture geometrical information of the image regions.  ...  Experimental results show the outstanding performance of our proposed approach compared to the state-of-the-art methods, and the proposed RFS energy outperforms the state-of-the-art in the few shot learning  ...  ACKNOWLEDGMENT This work was supported by the Australian Research Council (the ARC) via the Project Linkage grant LP160101081.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2108.12159v1">arXiv:2108.12159v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ztswpxqwpbekbooefanyaoiem4">fatcat:ztswpxqwpbekbooefanyaoiem4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210901084212/https://arxiv.org/pdf/2108.12159v1.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/8f/ec/8fec178e2a9b8b626ad89d34cd7b5a4a2db9ef1d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2108.12159v1" 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>
Citation

Ammar Mansoor Kamoona, Amirali Khodadadian Gostar, Alireza Bab-Hadiashar, Reza Hoseinnezhad. "Anomaly Detection of Defect using Energy of Point Pattern Features within Random Finite Set Framework." arXiv (2021)

3D Point Cloud Descriptors in Hand-crafted and Deep Learning Age: State-of-the-Art [article]

Xian-Feng Han, Shi-Jie Sun, Xiang-Yu Song, Guo-Qiang Xiao
<span title="2020-07-27">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

Web Archive Capture PDF (1.5 MB)
https://web.archive.org/web/20200806132633/https://arxiv.org/pdf/1802.02297v2.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/1802.02297v2.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

Other Versions

<span title="2018-02-07">2018</span> <span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1802.02297v1">arXiv:1802.02297v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/eabr7dn6mvd5plhgdmbbefu25y">fatcat:eabr7dn6mvd5plhgdmbbefu25y</a> </span>
Finally, we present the future research direction of the extraction of 3D point cloud descriptors.  ...  of novel 3D point cloud descriptors for accuracy of the efficiency of 3D computer vision tasks in recent years.  ...  many applications in real scenarios, such as robot localization and navigation [126] , autonomous driving, augmented reality [145] and 3D medical imaging.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1802.02297v2">arXiv:1802.02297v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/jslhwu3jefb2pispewdrzyicgu">fatcat:jslhwu3jefb2pispewdrzyicgu</a> </span>
<span class="ui label basic blue small">Multiple Versions</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200806132633/https://arxiv.org/pdf/1802.02297v2.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] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1802.02297v2" 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>
Citation

Xian-Feng Han, Shi-Jie Sun, Xiang-Yu Song, Guo-Qiang Xiao. "3D Point Cloud Descriptors in Hand-crafted and Deep Learning Age: State-of-the-Art." arXiv (2020)

Image Registration for Placenta Reconstruction

Floris Gaisser, Pieter P. Jonker, Toshio Chiba
<span title="">2016</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ilwxppn4d5hizekyd3ndvy2mii" style="color: black;">2016 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)</a> </i> &nbsp;

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (1.0 MB)
https://web.archive.org/web/20160806010354/http://www.cv-foundation.org:80/openaccess/content_cvpr_2016_workshops/w15/papers/Gaisser_Image_Registration_for_CVPR_2016_paper.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2016; you can also visit <a rel="external noopener" href="http://www.cv-foundation.org:80/openaccess/content_cvpr_2016_workshops/w15/papers/Gaisser_Image_Registration_for_CVPR_2016_paper.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

By using similarity learning in training a Convolutional Neural Network we created a novel feature extraction method, allowing robust matching of keypoints for image registration and therefore taking the  ...  The matching performance of our method is up to three times better while the mean projection error is reduced with 64% for the registered images.  ...  In contrast to state-of-the-art keypoint descriptors, our novel matching learning method increases the difference between different areas on top of the invariant feature extraction.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cvprw.2016.66">doi:10.1109/cvprw.2016.66</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/cvpr/GaisserJC16.html">dblp:conf/cvpr/GaisserJC16</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/jwlyg3ccezbdddyxlg7xds6mve">fatcat:jwlyg3ccezbdddyxlg7xds6mve</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20160806010354/http://www.cv-foundation.org:80/openaccess/content_cvpr_2016_workshops/w15/papers/Gaisser_Image_Registration_for_CVPR_2016_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/82/c0/82c0fd6da77fc2f1577acec23edcb0d0bde302b2.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cvprw.2016.66"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>
Citation

Floris Gaisser, Pieter P. Jonker, Toshio Chiba. "Image Registration for Placenta Reconstruction." 2016 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (2016) 473-480

A Decade Survey of Content Based Image Retrieval using Deep Learning [article]

Shiv Ram Dubey
<span title="2020-11-23">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (2.6 MB)
https://web.archive.org/web/20201207041132/https://arxiv.org/pdf/2012.00641v1.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/2012.00641v1.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

Other Versions

<span title="2021-05-20">2021</span> <span class="release-stage">accepted</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2012.00641v2">arXiv:2012.00641v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/zwq3emomovbf7fxiq5sxhggnma">fatcat:zwq3emomovbf7fxiq5sxhggnma</a> </span>
In early days, various hand designed feature descriptors have been investigated based on the visual cues such as color, texture, shape, etc. that represent the images.  ...  The survey presented in this paper will help in further research progress in image retrieval using deep learning.  ...  The real-valued descriptors generated using CNNs are used for medical image retrieval as well [190] , [191] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2012.00641v1">arXiv:2012.00641v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/2zcho2szpzcc3cs6uou3jpcley">fatcat:2zcho2szpzcc3cs6uou3jpcley</a> </span>
<span class="ui label basic orange small" title="Open Access">Open Access</span> <span class="ui label basic blue small">Multiple Versions</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201207041132/https://arxiv.org/pdf/2012.00641v1.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/36/46/36461c8627c3d54d9009fd83dab10c6e1950b401.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2012.00641v1" 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>
Citation

Shiv Ram Dubey. "A Decade Survey of Content Based Image Retrieval using Deep Learning." arXiv (2020)

Open-Source Face Recognition Frameworks: A Review of the Landscape

David Wanyonyi, Turgay Celik
<span title="">2022</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;

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (1.5 MB)
https://web.archive.org/web/20220518230816/https://ieeexplore.ieee.org/ielx7/6287639/9668973/09762647.pdf?tp=&arnumber=9762647&isnumber=9668973&ref=

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit <a rel="external noopener" href="https://ieeexplore.ieee.org/ielx7/6287639/9668973/09762647.pdf?tp=&arnumber=9762647&isnumber=9668973&ref=">the original URL</a>. The file type is <code>application/pdf</code>.

The advancement and maturity of open-source FR frameworks have contributed to this trend, influencing many open-source research publications available in the public domain.  ...  The evolution and success of the open-source DL algorithms on FR, leveraging GPU technologies, have benefited from open datasets, resulting in many FR open-source implementations.  ...  It uses various backbones such as ResNet and DenseNet, with loss functions such as AmSoftmax, ArcFace, Softmax, Focal, and Triplet.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2022.3170037">doi:10.1109/access.2022.3170037</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/wd6vnuaqzbg2rjnwrrknhxlfya">fatcat:wd6vnuaqzbg2rjnwrrknhxlfya</a> </span>
<span class="ui label basic orange small" title="Directory of Open Access Journals">DOAJ</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220518230816/https://ieeexplore.ieee.org/ielx7/6287639/9668973/09762647.pdf?tp=&amp;arnumber=9762647&amp;isnumber=9668973&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/d6/74/d6743a45bb84425584c5d0fac942300b1996af9e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2022.3170037"> <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>
Citation

David Wanyonyi, Turgay Celik. "Open-Source Face Recognition Frameworks: A Review of the Landscape." IEEE Access (2022) 50601-50623

Registering Image Volumes using 3D SIFT and Discrete SP-Symmetry [article]

Laurent Chauvin, William Wells III, Matthew Toews
<span title="2022-05-30">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (2.5 MB)
https://web.archive.org/web/20220610052035/https://arxiv.org/pdf/2205.15456v1.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/2205.15456v1.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

A binary feature sign s ∈{-1,+1} is defined as the sign of the Laplacian operator ∇^2, and used to obtain a descriptor that is invariant to image sign inversion s → -s and 3D parity transforms (x,y,z)→  ...  Augmenting local feature properties with sign in addition to standard (location, scale, orientation) geometry leads to descriptors that are invariant to coordinate reflections and intensity contrast inversion  ...  Descriptors may be learned via triplet loss and gradient analysis [33] , [42] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2205.15456v1">arXiv:2205.15456v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/u2o4kpr5jzhjxcrnspbefnz4ka">fatcat:u2o4kpr5jzhjxcrnspbefnz4ka</a> </span>
<span class="ui label basic orange small" title="Open Access">Open Access</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220610052035/https://arxiv.org/pdf/2205.15456v1.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/35/ea/35ea3c7d136ceb3426cdc59b16fd49180ff13551.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2205.15456v1" 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>
Citation

Laurent Chauvin, William Wells III, Matthew Toews. "Registering Image Volumes using 3D SIFT and Discrete SP-Symmetry." arXiv (2022)

&laquo; Previous Showing results 1 &mdash; 15 out of 89 results