Filters








6,053 Hits in 6.0 sec

Bilinear Supervised Hashing Based on 2D Image Features [article]

Yujuan Ding, Wai Kueng Wong, Zhihui Lai, Zheng Zhang
<span title="2019-01-05">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Most of the existing hashing methods focus on learning the low-dimensional vectorized binary features based on the high-dimensional raw vectorized features.  ...  However, studies on how to obtain preferable binary codes from the original 2D image features for retrieval is very limited.  ...  More importantly, the SDH method is based on vectorized features instead of 2D features.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1901.01474v1">arXiv:1901.01474v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/nkwqkqev3nh5hoyorqnejeor44">fatcat:nkwqkqev3nh5hoyorqnejeor44</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200928110434/https://arxiv.org/pdf/1901.01474v1.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/0a/3e/0a3e9b00aa5373414958bc4b4a743d4aeecb882f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1901.01474v1" 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>

Deep Sketch-Shape Hashing With Segmented 3D Stochastic Viewing

Jiaxin Chen, Jie Qin, Li Liu, Fan Zhu, Fumin Shen, Jin Xie, Ling Shao
<span title="">2019</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ilwxppn4d5hizekyd3ndvy2mii" style="color: black;">2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)</a> </i> &nbsp;
Sketch-based 3D shape retrieval has been extensively studied in recent works, most of which focus on improving the retrieval accuracy, whilst neglecting the efficiency.  ...  In this paper, we propose a novel framework for efficient sketch-based 3D shape retrieval, i.e., Deep Sketch-Shape Hashing (DSSH), which tackles the challenging problem from two perspectives.  ...  This indicates that DSSH can learn discriminative features based on L D . 2) L C .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cvpr.2019.00088">doi:10.1109/cvpr.2019.00088</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/cvpr/ChenQ00S0019.html">dblp:conf/cvpr/ChenQ00S0019</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/uwgxwcbfafdjrg4uxzw27euc3m">fatcat:uwgxwcbfafdjrg4uxzw27euc3m</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200318210919/http://openaccess.thecvf.com/content_CVPR_2019/papers/Chen_Deep_Sketch-Shape_Hashing_With_Segmented_3D_Stochastic_Viewing_CVPR_2019_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/4e/c5/4ec5fc8daf92dec2b086a98e34429f99ec716c94.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cvpr.2019.00088"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

A novel facial image recognition method based on perceptual hash using quintet triple binary pattern

Turker Tuncer, Sengul Dogan, Moloud Abdar, Paweł Pławiak
<span title="2020-08-12">2020</span> <i title="Springer Science and Business Media LLC"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/7inqmh346zfjjizjyieh7ijtma" style="color: black;">Multimedia tools and applications</a> </i> &nbsp;
In this study, a novel face recognition method based on perceptual hash is presented. The proposed perceptual hash is utilized for preprocessing and feature extraction phases.  ...  Discrete Wavelet Transform (DWT) and a novel graph based binary pattern, called quintet triple binary pattern (QTBP), are used.  ...  [51] suggested a method based on LBP and ensemble learning for face recognition.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/s11042-020-09439-8">doi:10.1007/s11042-020-09439-8</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/mwfxktgefvgndofq7lou3flgom">fatcat:mwfxktgefvgndofq7lou3flgom</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201108145714/https://link.springer.com/content/pdf/10.1007/s11042-020-09439-8.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/38/82/388245fc02554c215805a77a1d0c7e553995d9a2.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/s11042-020-09439-8"> <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>

Metric-Learning based Deep Hashing Network for Content Based Retrieval of Remote Sensing Images [article]

Subhankar Roy and Enver Sangineto and Begüm Demir and Nicu Sebe
<span title="2019-04-02">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
To overcome this problem, in this paper we introduce a metric-learning based hashing network, which learns: 1) a semantic-based metric space for effective feature representation; and 2) compact binary  ...  The traditional hashing methods in RS usually exploit hand-crafted features to learn hash functions to obtain binary codes, which can be insufficient to optimally represent the information content of RS  ...  We also report the ablation studies conducted on the AID archive.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1904.01258v1">arXiv:1904.01258v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/maqszcawmzfppmv74vohhe5eiu">fatcat:maqszcawmzfppmv74vohhe5eiu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200823001908/https://arxiv.org/pdf/1904.01258v1.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/7f/47/7f474b3c900cfbba649e30dd158b5a5e4f458392.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1904.01258v1" 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>

TransHash: Transformer-based Hamming Hashing for Efficient Image Retrieval [article]

Yongbiao Chen
<span title="2021-05-05">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
To learn fine-grained features, we innovate a dual-stream feature learning on top of the transformer to learn discriminative global and local features. (2) Besides, we adopt a Bayesian learning scheme  ...  We perform comprehensive experiments on three widely-studied datasets: CIFAR-10, NUSWIDE and IMAGENET.  ...  Based on the way they extract features, existing hashing-based works can be divided into two categories, namely, shallow methods and deep learning-based methods.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2105.01823v1">arXiv:2105.01823v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/h7fzcwnit5bc7e23mrssf6dp5e">fatcat:h7fzcwnit5bc7e23mrssf6dp5e</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210507024550/https://arxiv.org/pdf/2105.01823v1.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/03/10/0310f2e82ccb474580512cfd17dfc0fb102d1f06.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2105.01823v1" 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>

Learning to Rank 3D Features [chapter]

Oncel Tuzel, Ming-Yu Liu, Yuichi Taguchi, Arvind Raghunathan
<span title="">2014</span> <i title="Springer International Publishing"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/2w3awgokqne6te4nvlofavy5a4" style="color: black;">Lecture Notes in Computer Science</a> </i> &nbsp;
We propose a max-margin learning framework to identify discriminative features on the surface of three dimensional objects.  ...  We propose a max-margin learning framework to identify discriminative features on the surface of three dimensional objects.  ...  The weighting scheme based on hash table bins has connection to well-known bag-of-words model, where hash keys can be considered the codewords mapping features to a histogram.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-319-10590-1_34">doi:10.1007/978-3-319-10590-1_34</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/lhneyqh27fhjzcd6vmtvllldjq">fatcat:lhneyqh27fhjzcd6vmtvllldjq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20160812133555/http://www.merl.com/publications/docs/TR2014-078.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/b3/1c/b31cc80e33625a320e1f249f2aebc3a72dfadf1b.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-319-10590-1_34"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

Online Learning of Binary Feature Indexing for Real-Time SLAM Relocalization [chapter]

Youji Feng, Yihong Wu, Lixin Fan
<span title="">2015</span> <i title="Springer International Publishing"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/2w3awgokqne6te4nvlofavy5a4" style="color: black;">Lecture Notes in Computer Science</a> </i> &nbsp;
In the learning process, the hash keys are constructed with the aim of obtaining uniform hash buckets and high collision rates, which makes the method more efficient on approximate nearest neighbor search  ...  Being different from the popular Locality Sensitive Hashing (LSH), the proposed method construct the hash keys by an online learning process instead of pure randomness.  ...  [10] have designed a relocalization module based on binary features [11] [12] [13] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-319-16628-5_15">doi:10.1007/978-3-319-16628-5_15</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/fajumdby6vemtn64vpnymiddne">fatcat:fajumdby6vemtn64vpnymiddne</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170812170750/http://vigir.missouri.edu/~gdesouza/Research/Conference_CDs/ACCV_2014/pages/workshop2/pdffiles/workshop2-paper5-Online%20Learning%20of%20Binary%20Feature%20Indexing%20for%20Real-time%20SLAM%20Relocalization.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/20/2a/202ab9e474ce9eda453b6fd728ce1ecde5b16bea.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-319-16628-5_15"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

Deep Hash Remote Sensing Image Retrieval with Hard Probability Sampling

Xue Shan, Pingping Liu, Guixia Gou, Qiuzhan Zhou, Zhen Wang
<span title="2020-08-27">2020</span> <i title="MDPI AG"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/kay2tsbijbawliu45dnhvyvgsq" style="color: black;">Remote Sensing</a> </i> &nbsp;
Therefore, a growing number of studies are focusing on remote sensing image retrieval.  ...  Given the above considerations, we propose a deep hash remote sensing image retrieval method, called the hard probability sampling hash retrieval method (HPSH), which combines hash code learning with hard  ...  X.S. conducted experimental verification of the deep hard probability sampling hash retrieval method, finished the paper and corrected it for final publication.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/rs12172789">doi:10.3390/rs12172789</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/gspneonmbjbcriomrbqpbvdp7q">fatcat:gspneonmbjbcriomrbqpbvdp7q</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200829113807/https://res.mdpi.com/d_attachment/remotesensing/remotesensing-12-02789/article_deploy/remotesensing-12-02789-v2.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/d3/02d35eb081a66475f80da2eb82ed0efd4f5f8e19.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/rs12172789"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> mdpi.com </button> </a>

TransHash: Transformer-based Hamming Hashing for Efficient Image Retrieval

Yongbiao Chen, Sheng Zhang, Fangxin Liu, Zhigang Chang, Mang Ye, Zhengwei Qi
<span title="2022-06-27">2022</span> <i title="ACM"> Proceedings of the 2022 International Conference on Multimedia Retrieval </i> &nbsp;
To learn fine-grained features, we innovate a dual-stream multi-granular feature learning on top of the transformer to learn discriminative global and local features. (2) Besides, we adopt a Bayesian learning  ...  We perform comprehensive experiments on three widely-studied datasets: CIFAR-10, NUSWIDE and IMAGENET.  ...  Based on the way they extract features, existing hashing-based works can be divided into two categories, namely, shallow methods and deep learning-based methods.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/3512527.3531405">doi:10.1145/3512527.3531405</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/j7fvd7v52veb3oh3j5svge6pcq">fatcat:j7fvd7v52veb3oh3j5svge6pcq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220628044201/https://dl.acm.org/doi/pdf/10.1145/3512527.3531405" 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/4e/43/4e431e3ec36133416517cbd2c00942478704d74c.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/3512527.3531405"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> acm.org </button> </a>

Fast Neuroimaging-Based Retrieval for Alzheimer's Disease Analysis [chapter]

Xiaofeng Zhu, Kim-Han Thung, Jun Zhang, Dinggang Shen
<span title="">2016</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;
This paper proposes a framework of fast neuroimaging-based retrieval and AD analysis, by three key steps: (1) landmark detection, which efficiently extracts landmark-based neuroimaging features without  ...  landmarks; and (3) hashing, which converts high-dimensional features of subjects into binary codes, for efficiently conducting approximate nearest neighbor search and diagnosis of AD.  ...  To this end, we propose a novel landmark selection method that integrates subspace learning and 2D feature selection in a unified framework.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-319-47157-0_38">doi:10.1007/978-3-319-47157-0_38</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/28959800">pmid:28959800</a> <a target="_blank" rel="external noopener" href="https://pubmed.ncbi.nlm.nih.gov/PMC5614455/">pmcid:PMC5614455</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/frhzoivdi5dxtajqqj5tznh66m">fatcat:frhzoivdi5dxtajqqj5tznh66m</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200211144248/http://europepmc.org/backend/ptpmcrender.fcgi?accid=PMC5614455&amp;blobtype=pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/21/44/21449648ae48aa0e49daaea7a6a1fd619f8fdb73.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-319-47157-0_38"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5614455" title="pubmed link"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> pubmed.gov </button> </a>

Angular Deep Supervised Hashing for Image Retrieval

Chang Zhou, Lai Man Po, Wilson Y.F. Yuen, Kwok Wai Cheung, Xuyuan Xu, Kin Wai Lau, Yuzhi Zhao, Mengyan Liu, Peter H.W. Wong
<span title="">2019</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;
Deep learning based image hashing methods learn hash codes by using powerful feature extractors and nonlinear transformations to achieve highly efficient image retrieval.  ...  In this paper, we propose a novel semantic learning based hashing method for image retrieval to optimize the deep features structure in the hash space from a perspective of angular view.  ...  The angular based hashing approach learns the optimal hash code more directly because the learned features can be naturally converted to hash codes without quantization constraint in training process.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2019.2939650">doi:10.1109/access.2019.2939650</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/w2uszs7nzrcs3aym3dg23v6quy">fatcat:w2uszs7nzrcs3aym3dg23v6quy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210428224516/https://ieeexplore.ieee.org/ielx7/6287639/8600701/08825992.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/26/e4/26e45d5c2e4f5365a07b047737b1570708893703.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2019.2939650"> <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>

Semi-supervised based Unknown Attack Detection in EDR Environment

<span title="2020-12-31">2020</span> <i title="Korean Society for Internet Information (KSII)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/hupfbobgkvepdnt5g32qxkypsy" style="color: black;">KSII Transactions on Internet and Information Systems</a> </i> &nbsp;
The proposed technology uses a combination of AutoEncoder and 1D CNN (1-Dimention Convolutional Neural Network) based on semi-supervised learning.  ...  Endpoint Detection and Response (EDR) technology is focused on providing visibility, and strong countermeasures are lacking.  ...  hashing pseudo-code Fig. 8 . 8 Difference between 1D CNN and 2D CNN; (a) 1D CNN feature detector movement method; (b) 2D CNN feature detector movement method Fig. 9 . 9 Cumulative distribution function  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3837/tiis.2020.12.016">doi:10.3837/tiis.2020.12.016</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/no6o5drfejarng7d6slm4egixi">fatcat:no6o5drfejarng7d6slm4egixi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210105025123/http://itiis.org/digital-library/manuscript/file/24150/TIIS%20Vol%2014,%20No%2012-16.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/ca/27/ca27195a9d42a4744d77e00d83008121ff9fe2e2.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3837/tiis.2020.12.016"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Several Tunable GMM Kernels [article]

Ping Li
<span title="2018-05-08">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In 2010, (Ping Li UAI'10) developed the method of "abc-robust-logitboost" and compared it with other supervised learning methods on datasets used by the deep learning literature.  ...  In this study, we propose a series of "tunable GMM kernels" which are simple and perform largely comparably to tree methods on the same datasets.  ...  , we will provide an empirical study on kernel SVMs based on the tunable GMM kernels.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1805.02830v1">arXiv:1805.02830v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/to3uoieqvzhhlfqhfcebvjaxoq">fatcat:to3uoieqvzhhlfqhfcebvjaxoq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200917165426/https://arxiv.org/pdf/1805.02830v1.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/a9/11a9c4e56c76d202da03af57656b46868b785edd.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1805.02830v1" 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>

Stochastic Multiview Hashing for Large-Scale Near-Duplicate Video Retrieval

Yanbin Hao, Tingting Mu, Richang Hong, Meng Wang, Ning An, John Y. Goulermas
<span title="">2017</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/sbzicoknnzc3tjljn7ifvwpooi" style="color: black;">IEEE transactions on multimedia</a> </i> &nbsp;
Index Terms-Near-duplicate video retrieval, hashing, multiview learning, semi-supervised learning, divergence.  ...  Reliable mapping functions, which convert multiple types of keyframe features, enhanced by auxiliary information such as video-keyframe association and ground truth relevance to binary hash code strings  ...  ACKNOWLEDGEMENTS This work was supported by "The International Research Base for Developing Innovative Gerontechnology" sponsored by the national "111" project (No. B14025) of China.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tmm.2016.2610324">doi:10.1109/tmm.2016.2610324</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/w3k32jluljbt7lvk7rax6tq6w4">fatcat:w3k32jluljbt7lvk7rax6tq6w4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190429084645/https://www.research.manchester.ac.uk/portal/files/46115431/Manuscript_final_with_bios.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/22/9d/229d1ee54d67db59b000bfa8ad1fcc1f2281788f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tmm.2016.2610324"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

A Novel Unsupervised Convolutional Network Based on Gabor and (2D)2PCA for Feature Extraction and Recognition

Ruru Lu, Min Jiang, Jun Kong, Shengwei Tian, Yilihamu Yaermaimaiti
<span title="">2016</span> <i title="ICIC International"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/wdc7itdnm5ekhoql3paw7mmr4q" style="color: black;">ICIC Express Letters</a> </i> &nbsp;
It is based on a convolutional structure and can extract more useful multi-level features.  ...  However, features extracted by (2D) 2 PCA essentially are low-level and sensitive to distortions. To solve this problem, a new unsupervised deep learning network is proposed in this paper.  ...  Compared with PCA, (2D) 2 PCA can learn more features. Furthermore, it is more efficient in computation. The reasons depend on two aspects.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.24507/icicel.10.10.2459">doi:10.24507/icicel.10.10.2459</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/mpopugj5wven7fxpw6g4p4yyl4">fatcat:mpopugj5wven7fxpw6g4p4yyl4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220310020658/http://www.icicel.org/ell/contents/2016/10/el-10-10-24.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/73/18/73182d54dcff92daafde2542b7f4def8ae188f9d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.24507/icicel.10.10.2459"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 6,053 results