Robust Point Matching Using Mixture of Asymmetric Gaussians for Nonrigid Transformation View Full Text


Ontology type: schema:Chapter     


Chapter Info

DATE

2015

AUTHORS

Gang Wang , Zhicheng Wang , Weidong Zhao , Qiangqiang Zhou

ABSTRACT

In this paper, we present a novel robust method for point matching under noise, deformation, occlusion and outliers. We introduce a new probability model to represent point sets, namely asymmetric Gaussian (AG), which can capture spatially asymmetric distributions. Firstly, we use a mixture of AGs to represent the point set. Secondly, we use \(L_2\)-minimizing estimate (\(L_2E\)), a robust estimator to estimate densities between two point sets, to estimate the transformation function in reproducing kernel Hilbert space (RKHS) with regularization theory. Thirdly, we use low-rank kernel matrix approximation to reduce the computational complexity. Experimental results show that our method outperforms the comparative state-of-the-art methods on most scenarios, and it is quite robust to noise, deformation, occlusion and outliers. More... »

PAGES

433-444

References to SciGraph publications

  • 2004-11. Distinctive Image Features from Scale-Invariant Keypoints in INTERNATIONAL JOURNAL OF COMPUTER VISION
  • 2012. Low Rank Approximation, Algorithms, Implementation, Applications in NONE
  • 2002. Asymmetric Gaussian and Its Application to Pattern Recognition in STRUCTURAL, SYNTACTIC, AND STATISTICAL PATTERN RECOGNITION
  • 2002. Multi-scale EM-ICP: A Fast and Robust Approach for Surface Registration in COMPUTER VISION — ECCV 2002
  • 2004. A Correlation-Based Approach to Robust Point Set Registration in COMPUTER VISION - ECCV 2004
  • 2010. Vector Field Learning via Spectral Filtering in MACHINE LEARNING AND KNOWLEDGE DISCOVERY IN DATABASES
  • Book

    TITLE

    Computer Vision -- ACCV 2014

    ISBN

    978-3-319-16816-6
    978-3-319-16817-3

    Author Affiliations

    From Grant

    Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1007/978-3-319-16817-3_28

    DOI

    http://dx.doi.org/10.1007/978-3-319-16817-3_28

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1021020199


    Indexing Status Check whether this publication has been indexed by Scopus and Web Of Science using the SN Indexing Status Tool
    Incoming Citations Browse incoming citations for this publication using opencitations.net

    JSON-LD is the canonical representation for SciGraph data.

    TIP: You can open this SciGraph record using an external JSON-LD service: JSON-LD Playground Google SDTT

    [
      {
        "@context": "https://springernature.github.io/scigraph/jsonld/sgcontext.json", 
        "about": [
          {
            "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/0104", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Statistics", 
            "type": "DefinedTerm"
          }, 
          {
            "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/01", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Mathematical Sciences", 
            "type": "DefinedTerm"
          }
        ], 
        "author": [
          {
            "affiliation": {
              "alternateName": "Tongji University", 
              "id": "https://www.grid.ac/institutes/grid.24516.34", 
              "name": [
                "CAD Research Center, Tongji University, Shanghai, 201804, China"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Wang", 
            "givenName": "Gang", 
            "id": "sg:person.015455120421.44", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015455120421.44"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Tongji University", 
              "id": "https://www.grid.ac/institutes/grid.24516.34", 
              "name": [
                "CAD Research Center, Tongji University, Shanghai, 201804, China"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Wang", 
            "givenName": "Zhicheng", 
            "id": "sg:person.011142370621.54", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011142370621.54"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Tongji University", 
              "id": "https://www.grid.ac/institutes/grid.24516.34", 
              "name": [
                "CAD Research Center, Tongji University, Shanghai, 201804, China"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Zhao", 
            "givenName": "Weidong", 
            "id": "sg:person.016241577225.48", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016241577225.48"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Tongji University", 
              "id": "https://www.grid.ac/institutes/grid.24516.34", 
              "name": [
                "CAD Research Center, Tongji University, Shanghai, 201804, China"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Zhou", 
            "givenName": "Qiangqiang", 
            "id": "sg:person.07455410767.14", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.07455410767.14"
            ], 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "sg:pub.10.1007/978-3-540-24672-5_44", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1001446604", 
              "https://doi.org/10.1007/978-3-540-24672-5_44"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-540-24672-5_44", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1001446604", 
              "https://doi.org/10.1007/978-3-540-24672-5_44"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1162/0899766052530802", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1003321337"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/3-540-70659-3_42", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1007416422", 
              "https://doi.org/10.1007/3-540-70659-3_42"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/3-540-47979-1_28", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1014022108", 
              "https://doi.org/10.1007/3-540-47979-1_28"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-642-15880-3_10", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1026896536", 
              "https://doi.org/10.1007/978-3-642-15880-3_10"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-642-15880-3_10", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1026896536", 
              "https://doi.org/10.1007/978-3-642-15880-3_10"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-1-4471-2227-2", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1028124903", 
              "https://doi.org/10.1007/978-1-4471-2227-2"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-1-4471-2227-2", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1028124903", 
              "https://doi.org/10.1007/978-1-4471-2227-2"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/s1077-3142(03)00009-2", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1050999329"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/s1077-3142(03)00009-2", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1050999329"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1023/b:visi.0000029664.99615.94", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1052687286", 
              "https://doi.org/10.1023/b:visi.0000029664.99615.94"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/34.121791", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061155634"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/34.993558", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061157405"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tpami.2005.87", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061742941"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tpami.2006.171", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061743011"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tpami.2006.81", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061743123"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tpami.2010.223", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061743935"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tpami.2010.46", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061743964"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1198/004017001316975880", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1064197387"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2013.279", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1094577312"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2013.279", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1094577312"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2015", 
        "datePublishedReg": "2015-01-01", 
        "description": "In this paper, we present a novel robust method for point matching under noise, deformation, occlusion and outliers. We introduce a new probability model to represent point sets, namely asymmetric Gaussian (AG), which can capture spatially asymmetric distributions. Firstly, we use a mixture of AGs to represent the point set. Secondly, we use \\(L_2\\)-minimizing estimate (\\(L_2E\\)), a robust estimator to estimate densities between two point sets, to estimate the transformation function in reproducing kernel Hilbert space (RKHS) with regularization theory. Thirdly, we use low-rank kernel matrix approximation to reduce the computational complexity. Experimental results show that our method outperforms the comparative state-of-the-art methods on most scenarios, and it is quite robust to noise, deformation, occlusion and outliers.", 
        "editor": [
          {
            "familyName": "Cremers", 
            "givenName": "Daniel", 
            "type": "Person"
          }, 
          {
            "familyName": "Reid", 
            "givenName": "Ian", 
            "type": "Person"
          }, 
          {
            "familyName": "Saito", 
            "givenName": "Hideo", 
            "type": "Person"
          }, 
          {
            "familyName": "Yang", 
            "givenName": "Ming-Hsuan", 
            "type": "Person"
          }
        ], 
        "genre": "chapter", 
        "id": "sg:pub.10.1007/978-3-319-16817-3_28", 
        "inLanguage": [
          "en"
        ], 
        "isAccessibleForFree": false, 
        "isFundedItemOf": [
          {
            "id": "sg:grant.7008316", 
            "type": "MonetaryGrant"
          }
        ], 
        "isPartOf": {
          "isbn": [
            "978-3-319-16816-6", 
            "978-3-319-16817-3"
          ], 
          "name": "Computer Vision -- ACCV 2014", 
          "type": "Book"
        }, 
        "name": "Robust Point Matching Using Mixture of Asymmetric Gaussians for Nonrigid Transformation", 
        "pagination": "433-444", 
        "productId": [
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1007/978-3-319-16817-3_28"
            ]
          }, 
          {
            "name": "readcube_id", 
            "type": "PropertyValue", 
            "value": [
              "6426edc7b61d1c2e02d83eddeb205d0679556a3aec67d3dbd767dc28d6fbad0e"
            ]
          }, 
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1021020199"
            ]
          }
        ], 
        "publisher": {
          "location": "Cham", 
          "name": "Springer International Publishing", 
          "type": "Organisation"
        }, 
        "sameAs": [
          "https://doi.org/10.1007/978-3-319-16817-3_28", 
          "https://app.dimensions.ai/details/publication/pub.1021020199"
        ], 
        "sdDataset": "chapters", 
        "sdDatePublished": "2019-04-15T18:10", 
        "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
        "sdPublisher": {
          "name": "Springer Nature - SN SciGraph project", 
          "type": "Organization"
        }, 
        "sdSource": "s3://com-uberresearch-data-dimensions-target-20181106-alternative/cleanup/v134/2549eaecd7973599484d7c17b260dba0a4ecb94b/merge/v9/a6c9fde33151104705d4d7ff012ea9563521a3ce/jats-lookup/v90/0000000001_0000000264/records_8681_00000256.jsonl", 
        "type": "Chapter", 
        "url": "http://link.springer.com/10.1007/978-3-319-16817-3_28"
      }
    ]
     

    Download the RDF metadata as:  json-ld nt turtle xml License info

    HOW TO GET THIS DATA PROGRAMMATICALLY:

    JSON-LD is a popular format for linked data which is fully compatible with JSON.

    curl -H 'Accept: application/ld+json' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-16817-3_28'

    N-Triples is a line-based linked data format ideal for batch operations.

    curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-16817-3_28'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-16817-3_28'

    RDF/XML is a standard XML format for linked data.

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-16817-3_28'


     

    This table displays all metadata directly associated to this object as RDF triples.

    160 TRIPLES      23 PREDICATES      44 URIs      20 LITERALS      8 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1007/978-3-319-16817-3_28 schema:about anzsrc-for:01
    2 anzsrc-for:0104
    3 schema:author N4e8d7f53f69745c4bd8dcc694aedfff1
    4 schema:citation sg:pub.10.1007/3-540-47979-1_28
    5 sg:pub.10.1007/3-540-70659-3_42
    6 sg:pub.10.1007/978-1-4471-2227-2
    7 sg:pub.10.1007/978-3-540-24672-5_44
    8 sg:pub.10.1007/978-3-642-15880-3_10
    9 sg:pub.10.1023/b:visi.0000029664.99615.94
    10 https://doi.org/10.1016/s1077-3142(03)00009-2
    11 https://doi.org/10.1109/34.121791
    12 https://doi.org/10.1109/34.993558
    13 https://doi.org/10.1109/cvpr.2013.279
    14 https://doi.org/10.1109/tpami.2005.87
    15 https://doi.org/10.1109/tpami.2006.171
    16 https://doi.org/10.1109/tpami.2006.81
    17 https://doi.org/10.1109/tpami.2010.223
    18 https://doi.org/10.1109/tpami.2010.46
    19 https://doi.org/10.1162/0899766052530802
    20 https://doi.org/10.1198/004017001316975880
    21 schema:datePublished 2015
    22 schema:datePublishedReg 2015-01-01
    23 schema:description In this paper, we present a novel robust method for point matching under noise, deformation, occlusion and outliers. We introduce a new probability model to represent point sets, namely asymmetric Gaussian (AG), which can capture spatially asymmetric distributions. Firstly, we use a mixture of AGs to represent the point set. Secondly, we use \(L_2\)-minimizing estimate (\(L_2E\)), a robust estimator to estimate densities between two point sets, to estimate the transformation function in reproducing kernel Hilbert space (RKHS) with regularization theory. Thirdly, we use low-rank kernel matrix approximation to reduce the computational complexity. Experimental results show that our method outperforms the comparative state-of-the-art methods on most scenarios, and it is quite robust to noise, deformation, occlusion and outliers.
    24 schema:editor N4771d348428041389daf53be258e275f
    25 schema:genre chapter
    26 schema:inLanguage en
    27 schema:isAccessibleForFree false
    28 schema:isPartOf N701ea30961f74f619773dcbb7a219cd0
    29 schema:name Robust Point Matching Using Mixture of Asymmetric Gaussians for Nonrigid Transformation
    30 schema:pagination 433-444
    31 schema:productId N27dcabe9935c4042af9a85595a2359df
    32 Nb52e46eeea7b41ca8c5640eb807e9070
    33 Ndba41404374a4e2c9c45d221ccbc5ea6
    34 schema:publisher N3b8dd0542c334c478c0f3fa928984e56
    35 schema:sameAs https://app.dimensions.ai/details/publication/pub.1021020199
    36 https://doi.org/10.1007/978-3-319-16817-3_28
    37 schema:sdDatePublished 2019-04-15T18:10
    38 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    39 schema:sdPublisher N46ee38379e01443a83b42e6d92795a33
    40 schema:url http://link.springer.com/10.1007/978-3-319-16817-3_28
    41 sgo:license sg:explorer/license/
    42 sgo:sdDataset chapters
    43 rdf:type schema:Chapter
    44 N07a418b4861f415fa49930a4d94102e1 rdf:first N7624e34f1ec54e109270401a6b992ff5
    45 rdf:rest N5e76a26ef72848428bd0dc83bb4bb048
    46 N1c1716b6ec2841eb80feb6a34d5132bd rdf:first sg:person.07455410767.14
    47 rdf:rest rdf:nil
    48 N27dcabe9935c4042af9a85595a2359df schema:name readcube_id
    49 schema:value 6426edc7b61d1c2e02d83eddeb205d0679556a3aec67d3dbd767dc28d6fbad0e
    50 rdf:type schema:PropertyValue
    51 N35ad7dc966164409a527f607804e6d07 rdf:first sg:person.016241577225.48
    52 rdf:rest N1c1716b6ec2841eb80feb6a34d5132bd
    53 N3b8dd0542c334c478c0f3fa928984e56 schema:location Cham
    54 schema:name Springer International Publishing
    55 rdf:type schema:Organisation
    56 N46ee38379e01443a83b42e6d92795a33 schema:name Springer Nature - SN SciGraph project
    57 rdf:type schema:Organization
    58 N4771d348428041389daf53be258e275f rdf:first N4e684d26a6934bdcbbb783d352951726
    59 rdf:rest N745e111782c042fc9381a74443b9e534
    60 N4c7b65d76aaf4daea2ebcbce831d2379 rdf:first sg:person.011142370621.54
    61 rdf:rest N35ad7dc966164409a527f607804e6d07
    62 N4e684d26a6934bdcbbb783d352951726 schema:familyName Cremers
    63 schema:givenName Daniel
    64 rdf:type schema:Person
    65 N4e8d7f53f69745c4bd8dcc694aedfff1 rdf:first sg:person.015455120421.44
    66 rdf:rest N4c7b65d76aaf4daea2ebcbce831d2379
    67 N5e76a26ef72848428bd0dc83bb4bb048 rdf:first Ndb080fb485574713aa495467e17ce575
    68 rdf:rest rdf:nil
    69 N701ea30961f74f619773dcbb7a219cd0 schema:isbn 978-3-319-16816-6
    70 978-3-319-16817-3
    71 schema:name Computer Vision -- ACCV 2014
    72 rdf:type schema:Book
    73 N745e111782c042fc9381a74443b9e534 rdf:first N7519e63a3fbb40058878e152954100af
    74 rdf:rest N07a418b4861f415fa49930a4d94102e1
    75 N7519e63a3fbb40058878e152954100af schema:familyName Reid
    76 schema:givenName Ian
    77 rdf:type schema:Person
    78 N7624e34f1ec54e109270401a6b992ff5 schema:familyName Saito
    79 schema:givenName Hideo
    80 rdf:type schema:Person
    81 Nb52e46eeea7b41ca8c5640eb807e9070 schema:name dimensions_id
    82 schema:value pub.1021020199
    83 rdf:type schema:PropertyValue
    84 Ndb080fb485574713aa495467e17ce575 schema:familyName Yang
    85 schema:givenName Ming-Hsuan
    86 rdf:type schema:Person
    87 Ndba41404374a4e2c9c45d221ccbc5ea6 schema:name doi
    88 schema:value 10.1007/978-3-319-16817-3_28
    89 rdf:type schema:PropertyValue
    90 anzsrc-for:01 schema:inDefinedTermSet anzsrc-for:
    91 schema:name Mathematical Sciences
    92 rdf:type schema:DefinedTerm
    93 anzsrc-for:0104 schema:inDefinedTermSet anzsrc-for:
    94 schema:name Statistics
    95 rdf:type schema:DefinedTerm
    96 sg:grant.7008316 http://pending.schema.org/fundedItem sg:pub.10.1007/978-3-319-16817-3_28
    97 rdf:type schema:MonetaryGrant
    98 sg:person.011142370621.54 schema:affiliation https://www.grid.ac/institutes/grid.24516.34
    99 schema:familyName Wang
    100 schema:givenName Zhicheng
    101 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011142370621.54
    102 rdf:type schema:Person
    103 sg:person.015455120421.44 schema:affiliation https://www.grid.ac/institutes/grid.24516.34
    104 schema:familyName Wang
    105 schema:givenName Gang
    106 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015455120421.44
    107 rdf:type schema:Person
    108 sg:person.016241577225.48 schema:affiliation https://www.grid.ac/institutes/grid.24516.34
    109 schema:familyName Zhao
    110 schema:givenName Weidong
    111 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016241577225.48
    112 rdf:type schema:Person
    113 sg:person.07455410767.14 schema:affiliation https://www.grid.ac/institutes/grid.24516.34
    114 schema:familyName Zhou
    115 schema:givenName Qiangqiang
    116 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.07455410767.14
    117 rdf:type schema:Person
    118 sg:pub.10.1007/3-540-47979-1_28 schema:sameAs https://app.dimensions.ai/details/publication/pub.1014022108
    119 https://doi.org/10.1007/3-540-47979-1_28
    120 rdf:type schema:CreativeWork
    121 sg:pub.10.1007/3-540-70659-3_42 schema:sameAs https://app.dimensions.ai/details/publication/pub.1007416422
    122 https://doi.org/10.1007/3-540-70659-3_42
    123 rdf:type schema:CreativeWork
    124 sg:pub.10.1007/978-1-4471-2227-2 schema:sameAs https://app.dimensions.ai/details/publication/pub.1028124903
    125 https://doi.org/10.1007/978-1-4471-2227-2
    126 rdf:type schema:CreativeWork
    127 sg:pub.10.1007/978-3-540-24672-5_44 schema:sameAs https://app.dimensions.ai/details/publication/pub.1001446604
    128 https://doi.org/10.1007/978-3-540-24672-5_44
    129 rdf:type schema:CreativeWork
    130 sg:pub.10.1007/978-3-642-15880-3_10 schema:sameAs https://app.dimensions.ai/details/publication/pub.1026896536
    131 https://doi.org/10.1007/978-3-642-15880-3_10
    132 rdf:type schema:CreativeWork
    133 sg:pub.10.1023/b:visi.0000029664.99615.94 schema:sameAs https://app.dimensions.ai/details/publication/pub.1052687286
    134 https://doi.org/10.1023/b:visi.0000029664.99615.94
    135 rdf:type schema:CreativeWork
    136 https://doi.org/10.1016/s1077-3142(03)00009-2 schema:sameAs https://app.dimensions.ai/details/publication/pub.1050999329
    137 rdf:type schema:CreativeWork
    138 https://doi.org/10.1109/34.121791 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061155634
    139 rdf:type schema:CreativeWork
    140 https://doi.org/10.1109/34.993558 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061157405
    141 rdf:type schema:CreativeWork
    142 https://doi.org/10.1109/cvpr.2013.279 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094577312
    143 rdf:type schema:CreativeWork
    144 https://doi.org/10.1109/tpami.2005.87 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061742941
    145 rdf:type schema:CreativeWork
    146 https://doi.org/10.1109/tpami.2006.171 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061743011
    147 rdf:type schema:CreativeWork
    148 https://doi.org/10.1109/tpami.2006.81 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061743123
    149 rdf:type schema:CreativeWork
    150 https://doi.org/10.1109/tpami.2010.223 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061743935
    151 rdf:type schema:CreativeWork
    152 https://doi.org/10.1109/tpami.2010.46 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061743964
    153 rdf:type schema:CreativeWork
    154 https://doi.org/10.1162/0899766052530802 schema:sameAs https://app.dimensions.ai/details/publication/pub.1003321337
    155 rdf:type schema:CreativeWork
    156 https://doi.org/10.1198/004017001316975880 schema:sameAs https://app.dimensions.ai/details/publication/pub.1064197387
    157 rdf:type schema:CreativeWork
    158 https://www.grid.ac/institutes/grid.24516.34 schema:alternateName Tongji University
    159 schema:name CAD Research Center, Tongji University, Shanghai, 201804, China
    160 rdf:type schema:Organization
     




    Preview window. Press ESC to close (or click here)


    ...