Filters








10,459 Hits in 4.4 sec

Multiscale Particle Filter through Contour Detection Framework

<span title="2016-06-05">2016</span> <i title="International Journal of Science and Research"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/odv46yibm5gf7evzoopmrrqr3q" style="color: black;">International Journal of Science and Research (IJSR)</a> </i> &nbsp;
One can see the following features online like integrate color and gradient information via local, textural, oriented, and profile gradient-based features for understanding and comparing.The underlying  ...  model is estimated using a sequential Monte Carlo approach, and the final soft contour detection map is retrieved from the approximated trajectory distribution.  ...  For the observation model, we compute the textural gradient using a histogram of R ¼ 5 _ 5 _ 5 ¼ 125 bins. For this feature, the image is defined on the CIE Lab colorspace.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.21275/v5i6.nov164462">doi:10.21275/v5i6.nov164462</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/eve7ygqj5zgx5oyphntb2nix7q">fatcat:eve7ygqj5zgx5oyphntb2nix7q</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220227110613/https://www.ijsr.net/archive/v5i6/NOV164462.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/98/d6/98d60a74a0f8e4d3ef894786cff47e4b9aa63990.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.21275/v5i6.nov164462"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Evaluation of vocabulary trees for localization in robot applications

Soonmin Hwang, Chaehoon Park, Yukyung Choi, Donggeun Yoo, In So Kweon
<span title="">2013</span> <i title="IEEE"> 2013 13th International Conference on Control, Automation and Systems (ICCAS 2013) </i> &nbsp;
This analysis provides guidance for choosing appropriate vocabulary in robot applications.  ...  To solve this problem, an adaptive vocabulary tree has been proposed, but there has been no comparison considering the adaptive properties of the conven tional vocabulary tree.  ...  In this model, some representative features are defined by clus tering whole features in the training images. These are called visual words.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/iccas.2013.6704138">doi:10.1109/iccas.2013.6704138</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/xbjfci3oinhhhmaaaso5kcugiu">fatcat:xbjfci3oinhhhmaaaso5kcugiu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170921213406/http://koasas.kaist.ac.kr/bitstream/10203/182625/1/76866.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/6b/73/6b7381b0fc529f1e6e03db8322471eedbdecea6e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/iccas.2013.6704138"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Automatic Localization and Extraction Of Optic Disc Using Darwinian PSO and Morphological Operations

<span title="2019-09-30">2019</span> <i title="Blue Eyes Intelligence Engineering and Sciences Engineering and Sciences Publication - BEIESP"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/3sfifsouvjgadp4gfj54u3z2ku" style="color: black;">International journal of recent technology and engineering</a> </i> &nbsp;
In this paper, we propose an efficient automated system for OD detection and extraction so that exudates are extracted more effectively which will improve overall accuracy in diagnosis of Diabetic Retinopathy  ...  A novel multilevel thresholding optimized by Darwinian Particle swarm Optimization is adopted to detect optic disc in the fundus image.  ...  LITERATURE SURVEY OD detection techniques covered in this literature utilizes various OD specific image features such as brightest region, highest image deviation, anatomical structure and distance between  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.35940/ijrte.c6703.098319">doi:10.35940/ijrte.c6703.098319</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/azobkjvnbvb2rll2ecxfft7ms4">fatcat:azobkjvnbvb2rll2ecxfft7ms4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200212172636/https://www.ijrte.org/wp-content/uploads/papers/v8i3/C6703098319.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/bb/70/bb70e986b05c96613ada7066bccc2b1f27b0ef2a.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.35940/ijrte.c6703.098319"> <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>

The Scalable Distributed Two-layer Content Based Image Retrieval Data Store

Stanisław Deniziak, Tomasz Michno, Adam Krechowicz
<span title="2015-10-11">2015</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/zbznsfsymfchdlmdsmo2bglth4" style="color: black;">Proceedings of the 2015 Federated Conference on Computer Science and Information Systems</a> </i> &nbsp;
More advanced techniques, incorporating image content features, should be used.  ...  In this paper we propose new multimedia database structure with ability of Content Based Image Retrieval which is based on our previous work: Query by Shape method (QS).  ...  As a continuation of the previous research [1] , we would like to propose the Content Based Image Retrieval Database incorporating Query by Shape Method.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.15439/2015f272">doi:10.15439/2015f272</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/fedcsis/DeniziakMK15.html">dblp:conf/fedcsis/DeniziakMK15</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ddutcficnzcj3iey66aotlrhre">fatcat:ddutcficnzcj3iey66aotlrhre</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170808022807/https://annals-csis.org/proceedings/2015/pliks/272.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/1d/46/1d46a8dcc1fc696dcca8b60fb5c67e6e60f00674.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.15439/2015f272"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

NODIS: Neural Ordinary Differential Scene Understanding [article]

Cong Yuren, Hanno Ackermann, Wentong Liao, Michael Ying Yang, Bodo Rosenhahn
<span title="2020-07-18">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this work, we interpret that formulation as Ordinary Differential Equation (ODE).  ...  Semantic image understanding is a challenging topic in computer vision. It requires to detect all objects in an image, but also to identify all the relations between them.  ...  Scene Graph Generation: Scene graphs are proposed in [15] for the task of image retrieval and also potential for many applications [17, 32, 18] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2001.04735v3">arXiv:2001.04735v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/cry67soiangltptjk324ctyali">fatcat:cry67soiangltptjk324ctyali</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200723111015/https://arxiv.org/pdf/2001.04735v3.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/c6/c8/c6c81f794fc00409a09cc80f9490c0ce36c5c129.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2001.04735v3" 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>

Location recognition over large time lags

Basura Fernando, Tatiana Tommasi, Tinne Tuytelaars
<span title="">2015</span> <i title="Elsevier BV"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/dsarpzh6wfgadnyijwv5l6gh2i" style="color: black;">Computer Vision and Image Understanding</a> </i> &nbsp;
We present an extensive analysis on different features, looking for the most discriminative and most robust to the image variability induced by large time lags.  ...  Moreover, we show that the described task benefits from domain adaptation.  ...  U S C R I P T ods and we show promising results in both location recognition and interactive location retrieval.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.cviu.2015.05.016">doi:10.1016/j.cviu.2015.05.016</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/yf2beaioxrcifixyovwqxgsmfi">fatcat:yf2beaioxrcifixyovwqxgsmfi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190429005222/https://iris.uniroma1.it/retrieve/handle/11573/900396/291969/Fernando_Preprint-Location-recognition_2015.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/01/12/01127a814b93cfaeb546ff8d575e2405cec0bbb5.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.cviu.2015.05.016"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> elsevier.com </button> </a>

Omnidirectional CNN for Visual Place Recognition and Navigation [article]

Tsun-Hsuan Wang, Hung-Jui Huang, Juan-Ting Lin, Chan-Wei Hu, Kuo-Hao Zeng, Min Sun
<span title="2018-03-12">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
To train a powerful O-CNN, we build a virtual world for training on a large scale. We also propose a continuous lifted structured feature embedding loss to learn the concept of distance efficiently.  ...  Given a visual input, the task of the O-CNN is not to retrieve the matched place exemplar, but to retrieve the closest place exemplar and estimate the relative distance between the input and the closest  ...  We thank Institute of Information Science at the Academia Sinica, MOST-107-2634-F-007-007 for their supports. We thank Tsu-Ching Hsiao for the construction of virtual environments.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1803.04228v1">arXiv:1803.04228v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/evyhdpwt5vbr3oquqyaixpnpnq">fatcat:evyhdpwt5vbr3oquqyaixpnpnq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191013061539/https://arxiv.org/pdf/1803.04228v1.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/4a/6f4a8b7f88f88f74e3330539073916bf9fb6dffd.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1803.04228v1" 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>

Diabetic Maculopathy Detection using Image Processing

<span title="2019-12-30">2019</span> <i title="Blue Eyes Intelligence Engineering and Sciences Engineering and Sciences Publication - BEIESP"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/h673cvfolnhl3mnbjxkhtxdtg4" style="color: black;">International Journal of Engineering and Advanced Technology</a> </i> &nbsp;
For diabetic retinopathy, it needs a continuous monitoring process.  ...  In image processing techniques, we use image pre processing to reduce the noise and use segmentation process to extract the features of the macula.  ...  [5] proposed another adaptive method for automatic segmentation of OD from color fundus images.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.35940/ijeat.a1102.1291s419">doi:10.35940/ijeat.a1102.1291s419</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/uhvpnqqmbzcahlwhnxwr5fxxzy">fatcat:uhvpnqqmbzcahlwhnxwr5fxxzy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200210022204/https://www.ijeat.org/wp-content/uploads/papers/v9i1s4/A11021291S419.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/fc/98/fc983f7c26a355860285d4a3a509c0a4f28ad8d6.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.35940/ijeat.a1102.1291s419"> <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>

Location Recognition Over Large Time Lags [article]

Basura Fernando, Tatiana Tommasi, Tinne Tuytelaars
<span title="2015-05-26">2015</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We present an extensive analysis on different features, looking for the most discriminative and most robust to the image variability induced by large time lags.  ...  Moreover, we show that the described task benefits from domain adaptation.  ...  We use existing domain adaptation meth-ods and we show promising results in both location recognition and interactive location retrieval. The rest of the paper is organized as follows.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1409.7556v3">arXiv:1409.7556v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ymvdzu5bcvhtbnl3peyxontqd4">fatcat:ymvdzu5bcvhtbnl3peyxontqd4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191018145835/https://arxiv.org/pdf/1409.7556v3.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/d5/cc/d5cc33597f5f4e6e867d4e3122bcea358109d755.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1409.7556v3" 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>

Similarity Based Retrieval In Case Based Reasoning For Analysis Of Medical Images

M. Das Gupta, S. Banerjee
<span title="2015-03-01">2015</span> <i title="Zenodo"> Zenodo </i> &nbsp;
Content Based Image Retrieval (CBIR) coupled with Case Based Reasoning (CBR) is a paradigm that is becoming increasingly popular in the diagnosis and therapy planning of medical ailments utilizing the  ...  digital content of medical images.  ...  BT/PR4256/BID/7/393/2012 dated 02.08.2012) for supporting this research.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5281/zenodo.1100021">doi:10.5281/zenodo.1100021</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/4ivotln7afgsbir3v7n5dtkz5u">fatcat:4ivotln7afgsbir3v7n5dtkz5u</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200112141345/https://zenodo.org/record/1100022/files/10000893.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/8b/79/8b79a8c64cffaf4b4756c57755ebc353737e1049.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5281/zenodo.1100021"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> zenodo.org </button> </a>

Optic Disk Segmentation through Edge Density Filter in Retinal Images

<span title="2020-01-10">2020</span> <i title="Blue Eyes Intelligence Engineering and Sciences Engineering and Sciences Publication - BEIESP"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/cj3bm7tgcffurfop7xzswxuks4" style="color: black;">VOLUME-8 ISSUE-10, AUGUST 2019, REGULAR ISSUE</a> </i> &nbsp;
Accurate and Efficient Detection of Optic Disk (OD) is an important task for the diagnosis of various eye related diseases such as Diabetic Retinopathy, Glaucoma, and papilledema in automatic retinal image  ...  Next, based on the ODP, a sub-image extraction is accomplished and it is processed for blood vessel removal through morphological technique.  ...  Figure.1 features of retinal image For an efficient and early detection of DR, an accurate segmentation of OD is the preliminary step.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.35940/ijitee.c8989.019320">doi:10.35940/ijitee.c8989.019320</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/xtsaqnk7vzatnarhit52lndpyq">fatcat:xtsaqnk7vzatnarhit52lndpyq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220225100909/https://www.ijitee.org/wp-content/uploads/papers/v9i3/C8989019320.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/73/40/7340e977a6cb3585095ec3423f5ef0e92c2e3c39.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.35940/ijitee.c8989.019320"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

A Video Representation Method Based on Multi-view Structure Preserving Embedding for Action Retrieval

Ke Zhang, Hui Sun, Weili Shi, Yuwen Feng, Zhengang Jiang, Zhengang Jiang
<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;
Applied to the content-based retrieval task, the proposed method can be combined with Euclidean distance for the comparison of low-dimensional features.  ...  This paper proposes a novel and effective video representation module for content-based action retrieval framework, in which feature learning can be conducted with complementary information and intrinsic  ...  MULTI-VIEW VISUAL FEATURE Color, shape and texture are the essential visual features [39] which are proven beneficial for content-based image retrieval [40] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2019.2905641">doi:10.1109/access.2019.2905641</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/eqnhun66qjemfb4sru7jo6oj5y">fatcat:eqnhun66qjemfb4sru7jo6oj5y</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210429155521/https://ieeexplore.ieee.org/ielx7/6287639/8600701/08668507.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/ac/69/ac6941186f0a2750732d387e9f855512826b30f3.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2019.2905641"> <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>

Polyrigid and Polyaffine Transformations: A New Class of Diffeomorphisms for Locally Rigid or Affine Registration [chapter]

Vincent Arsigny, Xavier Pennec, Nicholas Ayache
<span title="">2003</span> <i title="Springer Berlin Heidelberg"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/2w3awgokqne6te4nvlofavy5a4" style="color: black;">Lecture Notes in Computer Science</a> </i> &nbsp;
We introduce a novel family of geometrical transformations for the non-rigid registration of medical images, called polyrigid and polyaffine.  ...  Preliminary experiments on synthetic and real images already illustrate the potentialities and good properties of this approach.  ...  Pitiot for providing us with the histological slices through an associated teams collaboration between Epidaure at INRIA and LONI at UCLA.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-540-39903-2_101">doi:10.1007/978-3-540-39903-2_101</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/dfknjn2e6bgaxns67hb5vjrgsu">fatcat:dfknjn2e6bgaxns67hb5vjrgsu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20150519201856/http://www-sop.inria.fr/asclepios/Publications/Xavier.Pennec/Arsigny_MICCAI03.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/2b/2c/2b2c5343f404af119d5f5770b6e16d608b424aee.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-540-39903-2_101"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

K-LITE: Learning Transferable Visual Models with External Knowledge [article]

Sheng Shen, Chunyuan Li, Xiaowei Hu, Yujia Xie, Jianwei Yang, Pengchuan Zhang, Anna Rohrbach, Zhe Gan, Lijuan Wang, Lu Yuan, Ce Liu, Kurt Keutzer (+2 others)
<span title="2022-04-20">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Alternatively, learning with external knowledge about images is a promising way which leverages a much more structured source of supervision.  ...  We study the performance of K-LITE on two important computer vision problems, image classification and object detection, benchmarking on 20 and 13 different existing datasets, respectively.  ...  Acknowledgments The authors gratefully acknowledge Chenguang Zhu, Wenhao Yu, Yuwei Fang for the early insightful discussions on the use of dictionary for rare concepts in NLP task, Hao Cheng for the inspirations  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2204.09222v1">arXiv:2204.09222v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/kwgric4mybdizmo5fxfxg6raxe">fatcat:kwgric4mybdizmo5fxfxg6raxe</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220613033814/https://arxiv.org/pdf/2204.09222v1.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/56/70/567060b12e048b3d14e66ccc3b6683628d0e8b3d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2204.09222v1" 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 Hybrid Machine-Crowd Approach to Photo Retrieval Result Diversification [chapter]

Anca-Livia Radu, Bogdan Ionescu, María Menéndez, Julian Stöttinger, Fausto Giunchiglia, Antonella De Angeli
<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 to tackle this issue by combining two approaches previously considered nonoverlapping: machine image analysis for a pre-filtering of the initial query results followed by crowd-sourcing for  ...  In this paper we address the issue of optimizing the actual social photo retrieval technology in terms of users' requirements.  ...  Then, we determine using the features of all images a Synthetic Representative Image Feature (SRI) by taking the average of the Euclidean distances between all image features; Step 2: for each image, I  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-319-04114-8_3">doi:10.1007/978-3-319-04114-8_3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/xktlwp2qfjbhrknakyevgkxidq">fatcat:xktlwp2qfjbhrknakyevgkxidq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170809015804/http://eprints.biblio.unitn.it/4244/1/techRep039.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/77/2a/772afeb9aece4fd580d62d5b029adfe1a9cc9678.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-319-04114-8_3"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 10,459 results