Filters








5,325 Hits in 6.4 sec

Generalized Deformable Models, Statistical Physics, and Matching Problems

Alan L. Yuille
<span title="">1990</span> <i title="MIT Press - Journals"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/rckx6fqoszfvva5c53bqivu5am" style="color: black;">Neural Computation</a> </i> &nbsp;
prob- lems in vision and neural networks theory in terms of elastic network and deformable templates with binary matching fields.  ...  Minimizing E.la] with respect to a corresponds to deforming the template in parameter space to find the best match.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1162/neco.1990.2.1.1">doi:10.1162/neco.1990.2.1.1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/v34qoilpnfakhhqfdk2mipj55y">fatcat:v34qoilpnfakhhqfdk2mipj55y</a> </span>
<a target="_blank" rel="noopener" href="https://archive.org/details/sim_neural-computation_spring-1990_2_1/page/1" title="read fulltext microfilm" 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> Archive [Microfilm] <div class="menu fulltext-thumbnail"> <img src="https://archive.org/serve/sim_neural-computation_spring-1990_2_1/__ia_thumb.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1162/neco.1990.2.1.1"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> mitpressjournals.org </button> </a>

Real-time tracking of multiple objects in space-variant vision based on magnocellular visual pathway

Seonghoon Kang, Seong-Whan Lee
<span title="">2002</span> <i title="Elsevier BV"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/jm6w2xclfzguxnhmnmq5omebpi" style="color: black;">Pattern Recognition</a> </i> &nbsp;
Therefore, we propose a deformation formula in order to solve the matching problem in space-variant vision.  ...  In particular, the matching process plays an important role in multiple objects tracking. In traditional vision, the matching process is simple when the target objects are rigid.  ...  Considering deformation in the space-variant coordinate system, caused by the movement of the target region, matching in space-variant vision becomes very e cient and simple.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/s0031-3203(01)00200-x">doi:10.1016/s0031-3203(01)00200-x</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ew4uarmp3fbbnjpjcnauuukeia">fatcat:ew4uarmp3fbbnjpjcnauuukeia</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170706014836/http://cavr.korea.ac.kr/publication/journal/02_02.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/dc/47/dc47b75949787fe2282540d773309542eaf3a396.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/s0031-3203(01)00200-x"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> elsevier.com </button> </a>

Industrial Printing Image Defect Detection Using Multi-Edge Feature Fusion Algorithm

Bangchao Liu, Youping Chen, Jingming Xie, Bing Chen, Padmapriya Praveenkumar
<span title="2021-10-04">2021</span> <i title="Hindawi Limited"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/y3fh56bfunh5fgneywwba6d4ke" style="color: black;">Complexity</a> </i> &nbsp;
Firstly, according to the characteristics of sheet-fed printing system, a new printing image database is established; compared with the existing databases, it has larger translation, deformation, and uneven  ...  In order to reduce the number of false detections which are caused by the position, deformation, and brightness deviation between the detected image and reference image, multi-edge feature fusion algorithm  ...  eoretically, the more the features are fused, the better the robustness of the template will be, and subsequent experiments will test the proposed template detection performance with different fusion  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1155/2021/2036466">doi:10.1155/2021/2036466</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/2ioj72kt65hgjeqt5tm2uvspfa">fatcat:2ioj72kt65hgjeqt5tm2uvspfa</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211006200756/https://downloads.hindawi.com/journals/complexity/2021/2036466.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/45/82/45821f78b38a16156e8d8f0abeabf9eb1953c2f3.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1155/2021/2036466"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> hindawi.com </button> </a>

Invariant Multi-scale Object Categorisation and Recognition [chapter]

João Rodrigues, J. M. Hans du Buf
<span title="">2007</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;
Object recognition requires that templates with canonical views are stored in memory. Such templates must somehow be normalised.  ...  Dynamic routing in neighbouring neural layers allows feature maps of input objects and stored templates to converge.  ...  Extensive experiments with many more object views are required to determine the minimum number of templates, both in human and in computer vision. Acknowledgements.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-540-72847-4_59">doi:10.1007/978-3-540-72847-4_59</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/grfayttgivcb5csp445r5mwkbe">fatcat:grfayttgivcb5csp445r5mwkbe</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20100622050443/http://sapientia.ualg.pt/bitstream/10400.1/169/1/RODInv.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/d6/73/d673b2af269e7692515dd43ac501f02d759fc435.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-540-72847-4_59"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

A Deformable Object Tracking Algorithm Based on the Boundary Element Method that is Robust to Occlusions and Spurious Edges

Michael A. Greminger, Bradley J. Nelson
<span title="2007-08-09">2007</span> <i title="Springer Nature"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/hfdglwo5wbbmta6wop52fam7a4" style="color: black;">International Journal of Computer Vision</a> </i> &nbsp;
This article introduces a template based deformable object tracking algorithm, based on the boundary element method, that is able to track a wide range of deformable objects.  ...  Computer vision is a logical sensing choice for tracking deformable objects because the large amount of data that is collected by a vision system allows many points within the deformable object to be tracked  ...  Yuille et al. (1992) used a deformable template matching algorithm to track facial features.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/s11263-007-0076-6">doi:10.1007/s11263-007-0076-6</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/awhfo4ccvrfsziyc32rcsfzdtm">fatcat:awhfo4ccvrfsziyc32rcsfzdtm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20160428220601/http://www.d.umn.edu/~mgreming/papers/ijcv.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/28/e7/28e7dedac1d9d0eca37bdbf7aca5b28e407ec857.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/s11263-007-0076-6"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

3D-CODED : 3D Correspondences by Deep Deformation [article]

Thibault Groueix, Matthew Fisher, Vladimir G. Kim, Bryan C. Russell, Mathieu Aubry
<span title="2018-07-27">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We present a new deep learning approach for matching deformable shapes by introducing Shape Deformation Networks which jointly encode 3D shapes and correspondences.  ...  We demonstrate that our simple approach improves on state-of-the-art results on the difficult FAUST-inter challenge, with an average correspondence error of 2.88cm.  ...  Learning 3D shape reconstruction by template deformation To put an input shape S in correspondence with a template A, our first goal is to design a neural network that will take S as input and predict  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1806.05228v2">arXiv:1806.05228v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/u77ad5tzijb4lbhhw4lui4hphe">fatcat:u77ad5tzijb4lbhhw4lui4hphe</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200929175650/https://arxiv.org/pdf/1806.05228v2.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/39/e6/39e6c02d87e3f4f96ce0060a848719d8bc03cdd2.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1806.05228v2" 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>

Survey on Face Recognition using Neural Network

Sindhu V M
<span title="2020-09-30">2020</span> <i title="International Journal for Research in Applied Science and Engineering Technology (IJRASET)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/hsp44774azcezeyiq4kuzpfh5a" style="color: black;">International Journal for Research in Applied Science and Engineering Technology</a> </i> &nbsp;
This method can be show the deformable templates for detecting the eyes and mouths in real image [4] .  ...  This approach mainly uses when the multi-pose face recognition using the fuzzy ant algorithm for correct matching with the database given [5] .  ...  Feature extraction from Alan L, Deformable The templates give the each This paper gives better  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.22214/ijraset.2020.31522">doi:10.22214/ijraset.2020.31522</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/zziy7q37xnglxdelui6hl3ko3q">fatcat:zziy7q37xnglxdelui6hl3ko3q</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200928195554/http://ijraset.com/fileserve.php?FID=31522" 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/36/12/3612efd08c1dc1233b1774ad286c6000bfdb50e3.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.22214/ijraset.2020.31522"> <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>

ShapeFlow: Learnable Deformations Among 3D Shapes [article]

Chiyu "Max" Jiang, Jingwei Huang, Andrea Tagliasacchi, Leonidas Guibas
<span title="2021-06-23">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We present ShapeFlow, a flow-based model for learning a deformation space for entire classes of 3D shapes with large intra-class variations.  ...  ShapeFlow allows learning a multi-template deformation space that is agnostic to shape topology, yet preserves fine geometric details.  ...  Broader impact The work has broad potential impact within the computer vision and graphics community, as it describes a novel methodology that enables a range of new applications, from animation to novel  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.07982v2">arXiv:2006.07982v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/aouuxvjhc5hb7furw36dpwqhya">fatcat:aouuxvjhc5hb7furw36dpwqhya</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210628203032/https://arxiv.org/pdf/2006.07982v2.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/3f/b1/3fb122561ab9af1cc54a742a519480a20a667457.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.07982v2" 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>

Template Matching Advances and Applications in Image Analysis [article]

Nazanin Sadat Hashemi, Roya Babaie Aghdam, Atieh Sadat Bayat Ghiasi, Parastoo Fatemi
<span title="2016-10-23">2016</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Additionally, deformable models and templates originating from classic template matching were discussed.  ...  In general, although template matching methods have restrictions which limit their application, they are recommended for use with other object recognition methods as pre- or post-processing steps.  ...  The concept of deformable templates was simultaneously introduced in computer vision by Widrow [17] with rubber masks, and by Fischler and Elschlager [5] with spring-loaded templates.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1610.07231v1">arXiv:1610.07231v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/rcnwppm5gfdjlp6mt74wj6msoe">fatcat:rcnwppm5gfdjlp6mt74wj6msoe</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200906103741/https://arxiv.org/pdf/1610.07231v1.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/9d/06/9d0620bc650adba1af40a29724a67664aa78f5e3.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1610.07231v1" 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>

Self-organizing neural networks based on spatial isomorphism for active contour modeling

Y.V Venkatesh, N Rishikesh
<span title="">2000</span> <i title="Elsevier BV"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/jm6w2xclfzguxnhmnmq5omebpi" style="color: black;">Pattern Recognition</a> </i> &nbsp;
To start with this deformation process, the model requires a rough boundary as the initial contour.  ...  To this end, we present a new active contour model, which is a neural network, based on self-organization.  ...  Acknowledgements This is a part of the collaborative research project, between the Indian Institute of Science and the National University of Singapore, on pattern recognition using neural networks.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/s0031-3203(99)00046-1">doi:10.1016/s0031-3203(99)00046-1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/fowa5nynnbefhi6d2m5k7ein5q">fatcat:fowa5nynnbefhi6d2m5k7ein5q</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20120130204107/http://mbu.iisc.ernet.in/~rngrp/pdfs/pr_ActiveContours.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/2d/f0/2df0265f738dc3fa000583113c98bb162c8f891e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/s0031-3203(99)00046-1"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> elsevier.com </button> </a>

Matching an Elastic Model of Chromosomal Shape to Features on a Self-Organising Map

M. Turner, J. Austin, N. M. Allinson, P. Thompson
<span title="">1993</span> <i title="British Machine Vision Association"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/6bfo5625nvdfvbgyf7ldi5wmfe" style="color: black;">Procedings of the British Machine Vision Conference 1993</a> </i> &nbsp;
Our model has a hierarchical organisation, with increasingly coarse shape descriptions at higher levels.  ...  We propose using this information to train a neural network to recognise structurally damaged chromosomes.  ...  The relative importance of matching the image points compared with minimising deformations in controlled by the parameters a and y.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5244/c.7.50">doi:10.5244/c.7.50</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/bmvc/TurnerAAT93.html">dblp:conf/bmvc/TurnerAAT93</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/n6c6vxcrejfr3bi7oknc4mbvry">fatcat:n6c6vxcrejfr3bi7oknc4mbvry</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20130528063000/http://www.bmva.org/bmvc/1993/bmvc-93-050.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/84/0c/840c33b22ec76b8a2379be73f9ece9baee34b0f8.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5244/c.7.50"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Webcam-Based 2D Eye Gaze Estimation System By Means of Binary Deformable Eyeball Templates

Jin-Woo Kim
<span title="2010-10-30">2010</span> <i title="The Korean Institute of Information and Communication Sciences"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/q4k2tgdvnbdrlo36b5ayw32icu" style="color: black;">Journal of information and communication convergence engineering</a> </i> &nbsp;
We introduce two brand-new algorithms for fast and sub-pixel precise pupil center detection and 2D Eye Gaze estimation by means of deformable template matching methodology.  ...  Then, by using the percentage of black pixels over eyeball circle area, we convert the image into binary (Black and white color) for being used in the next part: DTBGE (Deformable Template based 2D Gaze  ...  Fig. 2 . 2 Binary image conversion for deformable template matching based 2D Gaze Estimation Algorithm.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.6109/jicce.2010.8.5.575">doi:10.6109/jicce.2010.8.5.575</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/afavmwe37rhnfjd2d2hec6kowy">fatcat:afavmwe37rhnfjd2d2hec6kowy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170820091554/http://ocean.kisti.re.kr/downfile/volume/kimics/E1ICAW/2010/v8n5/E1ICAW_2010_v8n5_575.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/e9/0f/e90fe5923e5da89cbe62f363b01d05e91f327ea2.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.6109/jicce.2010.8.5.575"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Page 48 of Neural Computation Vol. 4, Issue 1 [page]

<span title="">1992</span> <i title="MIT Press Journals"> <a target="_blank" rel="noopener" href="https://archive.org/details/pub_neural-computation" style="color: black;">Neural Computation </a> </i> &nbsp;
A very similar notion of distance has arisen in computer vision, via so-called deformable templates, for the purpose of object recognition (see Fischler and Elschlager 1973; Widrow 1973; Burr 1980; Bajcsy  ...  with Handwritten Numerals.  ... 
<span class="external-identifiers"> </span>
<a target="_blank" rel="noopener" href="https://archive.org/details/sim_neural-computation_1992-01_4_1/page/48" title="read fulltext microfilm" 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> Archive [Microfilm] <div class="menu fulltext-thumbnail"> <img src="https://archive.org/serve/sim_neural-computation_1992-01_4_1/__ia_thumb.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a>

DeformNet: Free-Form Deformation Network for 3D Shape Reconstruction from a Single Image [article]

Andrey Kurenkov, Jingwei Ji, Animesh Garg, Viraj Mehta, JunYoung Gwak, Christopher Choy, Silvio Savarese
<span title="2017-08-11">2017</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
DeformNet takes an image input, searches the nearest shape template from a database, and deforms the template to match the query image.  ...  this FFD layer combined with shape retrieval for smooth and detail-preserving 3D reconstruction of qualitatively plausible point clouds with respect to a single query image (c) compared to other state-of-the-art  ...  Since it is defined on a 3D grid, FFD fits with 3D convolutional neural network and has been used for generating 3D deformation using a neural network before [38] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1708.04672v1">arXiv:1708.04672v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/tdbjw6rn5bch3kuidapivqgsd4">fatcat:tdbjw6rn5bch3kuidapivqgsd4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200912045647/https://arxiv.org/pdf/1708.04672v1.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/17/12/17120f384e1d8fe9cec5b4f15d1d240b5fda0549.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1708.04672v1" 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>

Neural Puppet: Generative Layered Cartoon Characters

Omid Poursaeed, Vladimir G. Kim, Eli Shechtman, Jun Saito, Serge Belongie
<span title="">2020</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/wsjivbkuezdvxdnrhihbwjrxlu" style="color: black;">2020 IEEE Winter Conference on Applications of Computer Vision (WACV)</a> </i> &nbsp;
We express pose changes as a deformation of a layered 2.5D template mesh, and devise a novel architecture that learns to predict mesh deformations matching the template to a target image.  ...  We capture these subtle changes by applying an image translation network to refine the mesh rendering, providing an end-to-end model to generate new animations of a character with high visual quality.  ...  Learning to Generate with Deformable Templates. Deformable templates have been used for decades to address analysis and synthesis problems [5, 9, 3, 4, 41, 69] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/wacv45572.2020.9093346">doi:10.1109/wacv45572.2020.9093346</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/wacv/PoursaeedKSSB20.html">dblp:conf/wacv/PoursaeedKSSB20</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/t7j6l5um3fhfpbjyqix3lsfnsa">fatcat:t7j6l5um3fhfpbjyqix3lsfnsa</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200709214343/https://openaccess.thecvf.com/content_WACV_2020/papers/Poursaeed_Neural_Puppet_Generative_Layered_Cartoon_Characters_WACV_2020_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/9a/05/9a0504a72704c43fd8873db015fe292f1d9ed262.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/wacv45572.2020.9093346"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 5,325 results