Filters








7,958 Hits in 4.5 sec

Efficient geometric algorithms for parsing in two dimensions

P. Liang, M. Narasimhan, M. Shilman, P. Viola
<span title="">2005</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/bytixui4szbgzkqzgwf65jphty" style="color: black;">Eighth International Conference on Document Analysis and Recognition (ICDAR&#39;05)</a> </i> &nbsp;
For documents, where the terminals are arranged in two dimensions and the grammar is ambiguous, parsing time can be exponential in the number of terminals.  ...  Assuming a clean design for the parsing software, the same parsing framework can be tested with various geometric constraints to determine the most effective combination.  ...  Geometric Parsing Is Exponential In this paper we will study algorithms for parsing terminals arranged on a two dimensional page.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/icdar.2005.98">doi:10.1109/icdar.2005.98</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/icdar/LiangNSV05.html">dblp:conf/icdar/LiangNSV05</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/kzy2kmfsebhehlobzc6z37zko4">fatcat:kzy2kmfsebhehlobzc6z37zko4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170810173156/http://shilman.net/papers/liang_geometric_icdar2005.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/27/43/2743562c1faa2c4c1f88b727158a68ca2c2fa45b.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/icdar.2005.98"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

User-reconfigurable CAD Feature Recognition in 1- and 2-topologies with Reduction of Search Space via Geometry Filters

Juan Camilo Pareja Corcho, Oscar Mauricio Betancur Acosta, Oscar E. Ruiz, Carlos Cadavid
<span title="">2019</span> <i title="The Eurographics Association"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/3b2gfcxv55cp3ci45zegttwu6i" style="color: black;">Spanish Computer Graphics Conference</a> </i> &nbsp;
Unlike the existing methods which are FACE-based, the present one permits combinations of topologies whose dimensions are 2, 1 or 0. This system has been implemented in an industrial environment.  ...  In the context of Computer-Aided Design and Manufacturing, the problem of feature recognition plays a key role in the integration of systems.  ...  An important part of research in CAD-CAPP systems is focused on the development and implementation of new and more efficient feature recognition algorithms.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.2312/ceig.20191205">doi:10.2312/ceig.20191205</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/ceig/CorchoARC19.html">dblp:conf/ceig/CorchoARC19</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/xmpwdweqzbeu5azcd5nyp5kp74">fatcat:xmpwdweqzbeu5azcd5nyp5kp74</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201102230224/https://diglib.eg.org/xmlui/bitstream/handle/10.2312/ceig20191205/069-072.pdf;jsessionid=B470E1BCA2012C0046356B106038530A?sequence=1" 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/c8/7e/c87ec1a42aa4d04c4b29709572e6b23221146686.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.2312/ceig.20191205"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Creating consistent scene graphs using a probabilistic grammar

Tianqiang Liu, Siddhartha Chaudhuri, Vladimir G. Kim, Qixing Huang, Niloy J. Mitra, Thomas Funkhouser
<span title="2014-11-19">2014</span> <i title="Association for Computing Machinery (ACM)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/cqrugwalkvcezgalqorn4fwnuu" style="color: black;">ACM Transactions on Graphics</a> </i> &nbsp;
In this paper, we develop algorithms that infer such information via parsing with a probabilistic grammar learned from examples.  ...  Abstract Growing numbers of 3D scenes in online repositories provide new opportunities for data-driven scene understanding, editing, and synthesis.  ...  The where x.box is the bounding box of the object x on the ground plane, Dist is the distance between two points or two bounding boxes.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/2661229.2661243">doi:10.1145/2661229.2661243</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/vhe7gkr5zvcspjar4neshl2uzm">fatcat:vhe7gkr5zvcspjar4neshl2uzm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20160331234212/http://shape.cs.princeton.edu/vkcorrs//papers_small/14_SIGGRAPHAsia_SceneHierarchy.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/61/c4/61c4bd261fce844414314ae921416ad147c8f66e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/2661229.2661243"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> acm.org </button> </a>

Implicit geometric constraint detection in freehand sketches using relative shape histogram

J. Pu, K. Ramani
<span title="">2007</span> <i title="ACM Press"> Proceedings of the 4th Eurographics workshop on Sketch-based interfaces and modeling - SBIM &#39;07 </i> &nbsp;
To evaluate the performance of the proposed algorithm, a userbased experiment is conducted and the results are presented in this paper.  ...  The basic idea arises from such a discovery that the same geometric constraints between two geometric primitives have similar relative shape histograms.  ...  Acknowledgements We acknowledge the early support of 21st Century Research and Technology funds in Shape Search.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/1384429.1384453">doi:10.1145/1384429.1384453</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/rftnkq4it5hubi72h4cajisvhe">fatcat:rftnkq4it5hubi72h4cajisvhe</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170813133246/https://engineering.purdue.edu/PRECISE/Publications/ImplicitGeometricConstraintDetectioninFreehandSketc/p107-pu.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/6d/e6/6de6a44d74d8e57826abe8aa756ce005d195bd47.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/1384429.1384453"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> acm.org </button> </a>

Reconfigurable 3D CAD Feature Recognition Supporting Confluent n-Dimensional Topologies and Geometric Filters for Prismatic and Curved Models

Juan Pareja-Corcho, Oscar Betancur-Acosta, Jorge Posada, Antonio Tammaro, Oscar Ruiz-Salguero, Carlos Cadavid
<span title="2020-08-13">2020</span> <i title="MDPI AG"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ye33srllvnanjouxn4tmrfgjsq" style="color: black;">Mathematics</a> </i> &nbsp;
Feature Recognition (FR) in Computer-aided Design (CAD) models is central for Design and Manufacturing.  ...  Unlike the existing methods that are FACE-based, the present one permits combinations of topologies whose dimensions are two (SHELL or FACE), one (LOOP or EDGE), or 0 (VERTEX).  ...  An essential part in the efforts in CAD-CAPP systems research is the development of efficient and effective automated feature recognition algorithms.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/math8081356">doi:10.3390/math8081356</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/slktp7donrdk5movhc6pok7dqy">fatcat:slktp7donrdk5movhc6pok7dqy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201127020935/https://res.mdpi.com/d_attachment/mathematics/mathematics-08-01356/article_deploy/mathematics-08-01356-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/1e/67/1e67af42d381f3c1264fd1a8f1e05a2884409103.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/math8081356"> <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>

Implicit Geometric Constraint Detection in Freehand Sketches Using Relative Shape Histogram [article]

J. Pu, K. Ramani
<span title="">2007</span> <i title="The Eurographics Association"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/jr7zmaowq5a3djlbdocjvzag3i" style="color: black;">Sketch-Based Interfaces and Modeling</a> </i> &nbsp;
To evaluate the performance of the proposed algorithm, a userbased experiment is conducted and the results are presented in this paper.  ...  The basic idea arises from such a discovery that the same geometric constraints between two geometric primitives have similar relative shape histograms.  ...  Acknowledgements We acknowledge the early support of 21st Century Research and Technology funds in Shape Search.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.2312/sbm/sbm07/107-114">doi:10.2312/sbm/sbm07/107-114</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/cz5k3jz6urb65a2bopxvojmruu">fatcat:cz5k3jz6urb65a2bopxvojmruu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220115212549/https://diglib.eg.org/xmlui/bitstream/handle/10.2312/SBM.SBM07.107-114/107-114.pdf;jsessionid=56D43A17E38022EEB4C9FC0A61840C8A?sequence=1" 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/36/35/363543135cd22fb69837ff0c8e149bd48cb0930a.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.2312/sbm/sbm07/107-114"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Learning deep representations for semantic image parsing: a comprehensive overview

Lili Huang, Jiefeng Peng, Ruimao Zhang, Guanbin Li, Liang Lin
<span title="2018-08-30">2018</span> <i title="Springer Nature America, Inc"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/mea4bx5mifbxdbgjmmfhl6qbhq" style="color: black;">Frontiers of Computer Science</a> </i> &nbsp;
Semantic image parsing, which refers to the process of decomposing images into semantic regions and constructing the structure representation of the input, has recently aroused widespread interest in the  ...  In this paper, we summarize three aspects of the progress of research on semantic image parsing, i.e., category-level semantic segmentation, instance-level semantic segmentation, and beyond segmentation  ...  The work in [30] transformed existing datasets (i.e., SIFT Flow, LM+SUN, and Geometric Context dataset) for use in geometric parsing.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/s11704-018-7195-8">doi:10.1007/s11704-018-7195-8</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/p5hvfwhl5rbork5vf4rpnx3h6u">fatcat:p5hvfwhl5rbork5vf4rpnx3h6u</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200826163744/https://arxiv.org/pdf/1810.04377v1.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/d3/e4/d3e4d66398871b8a2a72e9bc4ad589648aef1c17.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/s11704-018-7195-8"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

Generating 3D Building Models from Architectural Drawings: A Survey

Xuetao Yin, Peter Wonka, Anshuman Razdan
<span title="">2009</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/mst7benysjfpbf6tk2lttvwoaq" style="color: black;">IEEE Computer Graphics and Applications</a> </i> &nbsp;
Although existing solutions share a common pipeline, they often choose different algorithms for various process steps.  ...  This survey of model generation from paper and CAD-based architectural drawings covers the common pipeline and compares various algorithms for each step of the process.  ...  To that end, we now introduce the existing systems' algorithms for the two main pipeline phases-image parsing and 3D model extrusion-and briefly explore other choices.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/mcg.2009.9">doi:10.1109/mcg.2009.9</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/19363955">pmid:19363955</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/kneygfeubvbo5e4tie4wrqrggu">fatcat:kneygfeubvbo5e4tie4wrqrggu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20101011041708/http://www.public.asu.edu:80/~pwonka/Publications/2009.CGA.Yin.FloorplanExtrusionSurvey.IEEEDigitalLibrary.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/6e/ac/6eac61658c8394081ef5e3645ff2c7e6bb342c8c.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/mcg.2009.9"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

4D Association Graph for Realtime Multi-person Motion Capture Using Multiple Video Cameras [article]

Yuxiang Zhang, Liang An, Tao Yu, Xiu Li, Kun Li, Yebin Liu
<span title="2020-02-28">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
To this end, for the first time, we unify per-view parsing, cross-view matching, and temporal tracking into a single optimization framework, i.e., a 4D association graph that each dimension (image space  ...  algorithm.  ...  With ground truth 3D skeletons, our dataset enables more effective quantitative evaluations for both 2D parsing and 3D tracking algorithms.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2002.12625v1">arXiv:2002.12625v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/n53pvzavgnendg4x54qn3d65oq">fatcat:n53pvzavgnendg4x54qn3d65oq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200321203655/https://arxiv.org/pdf/2002.12625v1.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/2002.12625v1" 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 new approach for recognizing handwritten mathematics using relational grammars and fuzzy sets

Scott MacLean, George Labahn
<span title="2012-03-20">2012</span> <i title="Springer Nature"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/qlbwpi6y5ratlbyijgcz2zwany" style="color: black;">International Journal on Document Analysis and Recognition</a> </i> &nbsp;
A fast, incremental parsing algorithm is developed, motivated by the two-dimensional structure of written mathematics. The approach reports all identifiable parses of the input.  ...  We present a new approach for parsing twodimensional input using relational grammars and fuzzy sets.  ...  In the first step, terminal symbols and potential subexpression structures are identified efficiently using a fuzzy r-CFG and associated parsing algorithms.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/s10032-012-0184-x">doi:10.1007/s10032-012-0184-x</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ttdtzjbhavbfvlmvylruogqdpi">fatcat:ttdtzjbhavbfvlmvylruogqdpi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20130108035245/https://cs.uwaterloo.ca/~glabahn/Papers/fuzzy.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/42/14/4214da002218342474c7cd58362e3652d2a307bd.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/s10032-012-0184-x"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

AlgoSketch: Algorithm Sketching and Interactive Computation [article]

Chuanjun Li, Timothy S. Miller, Robert C. Zeleznik, Joseph J. LaViola Jr.
<span title="">2008</span> <i title="The Eurographics Association"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/jr7zmaowq5a3djlbdocjvzag3i" style="color: black;">Sketch-Based Interfaces and Modeling</a> </i> &nbsp;
In this paper, we present the details behind AlgoSketch including the design of our 2D algorithmic description language, support for iteration and flow of control constructs and a simple debugging trace  ...  Based on preliminary user feedback, we believe AlgoSketch has the potential to be used to design and test new algorithms before more efficient code is implemented.  ...  Acknowledgements This work is supported, in part, with grants from Microsoft Research and IARPA.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.2312/sbm/sbm08/175-182">doi:10.2312/sbm/sbm08/175-182</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/7r4vgnuvqvbb5p4bj5jvpdf6pm">fatcat:7r4vgnuvqvbb5p4bj5jvpdf6pm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170811204656/http://www.eecs.ucf.edu/~jjl/pubs/AlgoSketch-sbim08-final.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/24/62/24625d6cbc924cf805563c23b35b06b310215531.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.2312/sbm/sbm08/175-182"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

SuperParsing: Scalable Nonparametric Image Parsing with Superpixels [chapter]

Joseph Tighe, Svetlana Lazebnik
<span title="">2010</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;
To our knowledge, this is the first complete evaluation of image parsing on a dataset of this size, and it establishes a new benchmark for the problem.  ...  It works by scene-level matching with global image descriptors, followed by superpixel-level matching with local features and efficient Markov random field (MRF) optimization for incorporating neighborhood  ...  Acknowledgments This research was supported in part by NSF CAREER award IIS-0845629, Microsoft Research Faculty Fellowship, and Xerox.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-642-15555-0_26">doi:10.1007/978-3-642-15555-0_26</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/rmjiivztmbfm5bzvlra7vppria">fatcat:rmjiivztmbfm5bzvlra7vppria</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20110523053440/http://www.cs.unc.edu/~lazebnik/publications/eccv10-jtighe.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/91/4f/914f6db28db0de5f439e891dac38f09bbdc5a452.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-642-15555-0_26"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

Holistic 3D Scene Parsing and Reconstruction from a Single RGB Image [chapter]

Siyuan Huang, Siyuan Qi, Yixin Zhu, Yinxue Xiao, Yuanlu Xu, Song-Chun Zhu
<span title="">2018</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;
The proposed HSG captures three essential and often latent dimensions of the indoor scenes: i) latent human context, describing the affordance and the functionality of a room arrangement, ii) geometric  ...  The optimal configuration, represented by a parse graph, is inferred using Markov chain Monte Carlo (MCMC), which efficiently traverses through the non-differentiable solution space, jointly optimizing  ...  larger Algorithm 1 Joint inference algorithm 1: Given Image I, initialized parse graph pg init 2: procedure Step1(V o g , V l g ) ⊲ Inference without hidden human context 3: for different temperatures  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-030-01234-2_12">doi:10.1007/978-3-030-01234-2_12</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/n2lyd2g6sve6lartrjexgdal3q">fatcat:n2lyd2g6sve6lartrjexgdal3q</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190728160421/http://openaccess.thecvf.com:80/content_ECCV_2018/papers/Siyuan_Huang_Monocular_Scene_Parsing_ECCV_2018_paper.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/f5/fa/f5fa658645885128a6260863cae2d563d090d951.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-030-01234-2_12"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

Cross-view Semantic Segmentation for Sensing Surroundings [article]

Bowen Pan, Jiankai Sun, Ho Yin Tiga Leung, Alex Andonian, Bolei Zhou
<span title="2020-06-18">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In the cross-view semantic segmentation task, the agent is trained to parse the first-view observations into a top-down-view semantic map indicating the spatial location of all the objects at pixel-level  ...  To facilitate the robot perception with such a surrounding sensing capability, we introduce a novel visual task called Cross-view Semantic Segmentation as well as a framework named View Parsing Network  ...  Two methods are included as the comparison baselines: (1) 3D geometric method.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1906.03560v3">arXiv:1906.03560v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/vu4bx7xw4ze6jj3yztlcgbm43i">fatcat:vu4bx7xw4ze6jj3yztlcgbm43i</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200623202538/https://arxiv.org/pdf/1906.03560v3.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/1906.03560v3" 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 self-organizing geometric algorithm for autonomous data partitioning [article]

Christopher A. Tucker
<span title="2014-12-25">2014</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
A model of a geometric algorithm is introduced and methodology of its operation is presented for the dynamic partitioning of data spaces.  ...  7 The author proposes the geometric algorithm illustrated in this paper is suitable as a governing algorithm, similar in form and function of DNA cores and RNA assemblers in organic systems, a set of procedural  ...  primitives for artificial life constructs in a machine.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1412.7860v1">arXiv:1412.7860v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ebat3ep7njbk7luugn7opc5zky">fatcat:ebat3ep7njbk7luugn7opc5zky</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200910090619/https://arxiv.org/ftp/arxiv/papers/1412/1412.7860.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/e6/f6/e6f6db1de57b5e494252f0c698958c5a86ed2269.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1412.7860v1" 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>
&laquo; Previous Showing results 1 &mdash; 15 out of 7,958 results