Learning Hierarchical Feature Representation in Depth Image View Full Text


Ontology type: schema:Chapter     


Chapter Info

DATE

2015

AUTHORS

Yazhou Liu , Pongsak Lasang , Quansen Sun , Mel Siegel

ABSTRACT

This paper presents a novel descriptor, geodesic invariant feature (GIF), for representing objects in depth images. Especially in the context of parts classification of articulated objects, it is capable of encoding the invariance of local structures effectively and efficiently. The contributions of this paper lie in our multi-level feature extraction hierarchy. (1) Low-level feature encodes the invariance to articulation. Geodesic gradient is introduced, which is covariant with the non-rigid deformation of objects and is utilized to rectify the feature extraction process. (2) Mid-level feature reduces the noise and improves the efficiency. With unsupervised clustering, the primitives of objects are changed from pixels to superpixels. The benefit is two-fold: firstly, superpixel reduces the effect of the noise introduced by depth sensors; secondly, the processing speed can be improved by a big margin. (3) High-level feature captures nonlinear dependencies between the dimensions. Deep network is utilized to discover the high-level feature representation. As the feature propagates towards the deeper layers of the network, the ability of the feature capturing the data’s underlying regularities is improved. Comparisons with the state-of-the-art methods reveal the superiority of the proposed method. More... »

PAGES

593-608

References to SciGraph publications

  • 2004-11. Distinctive Image Features from Scale-Invariant Keypoints in INTERNATIONAL JOURNAL OF COMPUTER VISION
  • 2010. BRIEF: Binary Robust Independent Elementary Features in COMPUTER VISION – ECCV 2010
  • 2013. Real-Time Human Pose Recognition in Parts from Single Depth Images in MACHINE LEARNING FOR COMPUTER VISION
  • Book

    TITLE

    Computer Vision -- ACCV 2014

    ISBN

    978-3-319-16810-4
    978-3-319-16811-1

    Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1007/978-3-319-16811-1_39

    DOI

    http://dx.doi.org/10.1007/978-3-319-16811-1_39

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1015449875


    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/2008/0801", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Artificial Intelligence and Image Processing", 
            "type": "DefinedTerm"
          }, 
          {
            "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/08", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Information and Computing Sciences", 
            "type": "DefinedTerm"
          }
        ], 
        "author": [
          {
            "affiliation": {
              "alternateName": "Nanjing University of Science and Technology", 
              "id": "https://www.grid.ac/institutes/grid.410579.e", 
              "name": [
                "Nanjing University of Science and Technology, Nanjing, China"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Liu", 
            "givenName": "Yazhou", 
            "id": "sg:person.011547566102.59", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011547566102.59"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "name": [
                "Panasonic R&D Center Singapore, Singapore, Singapore"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Lasang", 
            "givenName": "Pongsak", 
            "id": "sg:person.01324226204.06", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01324226204.06"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Nanjing University of Science and Technology", 
              "id": "https://www.grid.ac/institutes/grid.410579.e", 
              "name": [
                "Nanjing University of Science and Technology, Nanjing, China"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Sun", 
            "givenName": "Quansen", 
            "id": "sg:person.0665262737.23", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0665262737.23"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Carnegie Mellon University", 
              "id": "https://www.grid.ac/institutes/grid.147455.6", 
              "name": [
                "Carnegie Mellon University, Pittsburgh, USA"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Siegel", 
            "givenName": "Mel", 
            "id": "sg:person.01372341404.93", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01372341404.93"
            ], 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "https://doi.org/10.1109/tpami.2012.231", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1003742061"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-642-28661-2_5", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1018988958", 
              "https://doi.org/10.1007/978-3-642-28661-2_5"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1145/1390156.1390294", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1034603392"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-642-15561-1_56", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1034663897", 
              "https://doi.org/10.1007/978-3-642-15561-1_56"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-642-15561-1_56", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1034663897", 
              "https://doi.org/10.1007/978-3-642-15561-1_56"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.cviu.2007.09.014", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1040969278"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.sigpro.2011.12.005", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1041719350"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tpami.2009.155", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1048054623"
            ], 
            "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/10.1145/2047196.2047270", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1053252950"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/mci.2010.938364", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061392393"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tip.2012.2210234", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061643301"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tpami.2002.1017623", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061742396"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tpami.2005.188", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061742845"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tpami.2006.244", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061743071"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tpami.2008.112", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061743474"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tpami.2009.167", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061743745"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tpami.2011.222", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061744104"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tpami.2012.120", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061744236"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tpami.2012.241", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061744335"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tpami.2013.50", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061744581"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1561/2200000006", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1068001401"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/robot.2010.5509559", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1093342429"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/iccv.2005.147", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1093369149"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2004.1315241", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1094870330"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2013.444", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095468539"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2013.444", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095468539"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/3dv.2013.43", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095532495"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/3dv.2013.44", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095765165"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2015", 
        "datePublishedReg": "2015-01-01", 
        "description": "This paper presents a novel descriptor, geodesic invariant feature (GIF), for representing objects in depth images. Especially in the context of parts classification of articulated objects, it is capable of encoding the invariance of local structures effectively and efficiently. The contributions of this paper lie in our multi-level feature extraction hierarchy. (1) Low-level feature encodes the invariance to articulation. Geodesic gradient is introduced, which is covariant with the non-rigid deformation of objects and is utilized to rectify the feature extraction process. (2) Mid-level feature reduces the noise and improves the efficiency. With unsupervised clustering, the primitives of objects are changed from pixels to superpixels. The benefit is two-fold: firstly, superpixel reduces the effect of the noise introduced by depth sensors; secondly, the processing speed can be improved by a big margin. (3) High-level feature captures nonlinear dependencies between the dimensions. Deep network is utilized to discover the high-level feature representation. As the feature propagates towards the deeper layers of the network, the ability of the feature capturing the data\u2019s underlying regularities is improved. Comparisons with the state-of-the-art methods reveal the superiority of the proposed method.", 
        "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.10.1007/978-3-319-16811-1_39", 
        "inLanguage": [
          "en"
        ], 
        "isAccessibleForFree": false, 
        "isFundedItemOf": [
          {
            "id": "sg:grant.7177986", 
            "type": "MonetaryGrant"
          }, 
          {
            "id": "sg:grant.7185337", 
            "type": "MonetaryGrant"
          }
        ], 
        "isPartOf": {
          "isbn": [
            "978-3-319-16810-4", 
            "978-3-319-16811-1"
          ], 
          "name": "Computer Vision -- ACCV 2014", 
          "type": "Book"
        }, 
        "name": "Learning Hierarchical Feature Representation in Depth Image", 
        "pagination": "593-608", 
        "productId": [
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1007/978-3-319-16811-1_39"
            ]
          }, 
          {
            "name": "readcube_id", 
            "type": "PropertyValue", 
            "value": [
              "499cb7e775970d6d9626957c94c3d987b10a50d2603b2f045157c885d7ce9175"
            ]
          }, 
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1015449875"
            ]
          }
        ], 
        "publisher": {
          "location": "Cham", 
          "name": "Springer International Publishing", 
          "type": "Organisation"
        }, 
        "sameAs": [
          "https://doi.org/10.1007/978-3-319-16811-1_39", 
          "https://app.dimensions.ai/details/publication/pub.1015449875"
        ], 
        "sdDataset": "chapters", 
        "sdDatePublished": "2019-04-15T16:15", 
        "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_8675_00000252.jsonl", 
        "type": "Chapter", 
        "url": "http://link.springer.com/10.1007/978-3-319-16811-1_39"
      }
    ]
     

    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.10.1007/978-3-319-16811-1_39'

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

    curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-16811-1_39'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-16811-1_39'

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

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-16811-1_39'


     

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

    194 TRIPLES      23 PREDICATES      54 URIs      20 LITERALS      8 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1007/978-3-319-16811-1_39 schema:about anzsrc-for:08
    2 anzsrc-for:0801
    3 schema:author N4038dedc35954824819283aae6394896
    4 schema:citation sg:pub.10.1007/978-3-642-15561-1_56
    5 sg:pub.10.1007/978-3-642-28661-2_5
    6 sg:pub.10.1023/b:visi.0000029664.99615.94
    7 https://doi.org/10.1016/j.cviu.2007.09.014
    8 https://doi.org/10.1016/j.sigpro.2011.12.005
    9 https://doi.org/10.1109/3dv.2013.43
    10 https://doi.org/10.1109/3dv.2013.44
    11 https://doi.org/10.1109/cvpr.2004.1315241
    12 https://doi.org/10.1109/cvpr.2013.444
    13 https://doi.org/10.1109/iccv.2005.147
    14 https://doi.org/10.1109/mci.2010.938364
    15 https://doi.org/10.1109/robot.2010.5509559
    16 https://doi.org/10.1109/tip.2012.2210234
    17 https://doi.org/10.1109/tpami.2002.1017623
    18 https://doi.org/10.1109/tpami.2005.188
    19 https://doi.org/10.1109/tpami.2006.244
    20 https://doi.org/10.1109/tpami.2008.112
    21 https://doi.org/10.1109/tpami.2009.155
    22 https://doi.org/10.1109/tpami.2009.167
    23 https://doi.org/10.1109/tpami.2011.222
    24 https://doi.org/10.1109/tpami.2012.120
    25 https://doi.org/10.1109/tpami.2012.231
    26 https://doi.org/10.1109/tpami.2012.241
    27 https://doi.org/10.1109/tpami.2013.50
    28 https://doi.org/10.1145/1390156.1390294
    29 https://doi.org/10.1145/2047196.2047270
    30 https://doi.org/10.1561/2200000006
    31 schema:datePublished 2015
    32 schema:datePublishedReg 2015-01-01
    33 schema:description This paper presents a novel descriptor, geodesic invariant feature (GIF), for representing objects in depth images. Especially in the context of parts classification of articulated objects, it is capable of encoding the invariance of local structures effectively and efficiently. The contributions of this paper lie in our multi-level feature extraction hierarchy. (1) Low-level feature encodes the invariance to articulation. Geodesic gradient is introduced, which is covariant with the non-rigid deformation of objects and is utilized to rectify the feature extraction process. (2) Mid-level feature reduces the noise and improves the efficiency. With unsupervised clustering, the primitives of objects are changed from pixels to superpixels. The benefit is two-fold: firstly, superpixel reduces the effect of the noise introduced by depth sensors; secondly, the processing speed can be improved by a big margin. (3) High-level feature captures nonlinear dependencies between the dimensions. Deep network is utilized to discover the high-level feature representation. As the feature propagates towards the deeper layers of the network, the ability of the feature capturing the data’s underlying regularities is improved. Comparisons with the state-of-the-art methods reveal the superiority of the proposed method.
    34 schema:editor Ne89bfec824614a4d91084083bec15b09
    35 schema:genre chapter
    36 schema:inLanguage en
    37 schema:isAccessibleForFree false
    38 schema:isPartOf N5d1982b26ae646f6a304a0432a302e39
    39 schema:name Learning Hierarchical Feature Representation in Depth Image
    40 schema:pagination 593-608
    41 schema:productId N01094d72202c408b8cd95b2fb5e1a901
    42 N23a33992bb5a4c74b8f54d5868cb1611
    43 Nf90f9703ea894d3a8b8f1edb0cc3d17a
    44 schema:publisher N20ea22b31c17444684127df96ea5af2a
    45 schema:sameAs https://app.dimensions.ai/details/publication/pub.1015449875
    46 https://doi.org/10.1007/978-3-319-16811-1_39
    47 schema:sdDatePublished 2019-04-15T16:15
    48 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    49 schema:sdPublisher Ne3dbb34961f9411bbc6faa025de10ab1
    50 schema:url http://link.springer.com/10.1007/978-3-319-16811-1_39
    51 sgo:license sg:explorer/license/
    52 sgo:sdDataset chapters
    53 rdf:type schema:Chapter
    54 N01094d72202c408b8cd95b2fb5e1a901 schema:name readcube_id
    55 schema:value 499cb7e775970d6d9626957c94c3d987b10a50d2603b2f045157c885d7ce9175
    56 rdf:type schema:PropertyValue
    57 N09afbbf370c248ecba2fec9018ade52a schema:familyName Saito
    58 schema:givenName Hideo
    59 rdf:type schema:Person
    60 N20ea22b31c17444684127df96ea5af2a schema:location Cham
    61 schema:name Springer International Publishing
    62 rdf:type schema:Organisation
    63 N23a33992bb5a4c74b8f54d5868cb1611 schema:name doi
    64 schema:value 10.1007/978-3-319-16811-1_39
    65 rdf:type schema:PropertyValue
    66 N2e2e415230f3449a909ace8626db7230 rdf:first sg:person.0665262737.23
    67 rdf:rest Ndb710b74914743a08268f87a4a65340f
    68 N4038dedc35954824819283aae6394896 rdf:first sg:person.011547566102.59
    69 rdf:rest Na04b605807a547e6b27ced7ce65c82c4
    70 N5d1982b26ae646f6a304a0432a302e39 schema:isbn 978-3-319-16810-4
    71 978-3-319-16811-1
    72 schema:name Computer Vision -- ACCV 2014
    73 rdf:type schema:Book
    74 N848ebe97ab174967aee8aa6e4186964f rdf:first Nabffe7dea65545d583393f6e23e6765d
    75 rdf:rest rdf:nil
    76 Na04b605807a547e6b27ced7ce65c82c4 rdf:first sg:person.01324226204.06
    77 rdf:rest N2e2e415230f3449a909ace8626db7230
    78 Naa1a8b392b5b4c868b007e9a69e14f5e schema:familyName Reid
    79 schema:givenName Ian
    80 rdf:type schema:Person
    81 Nabffe7dea65545d583393f6e23e6765d schema:familyName Yang
    82 schema:givenName Ming-Hsuan
    83 rdf:type schema:Person
    84 Nae4c16e1c0b94944a734c8e5b791925d rdf:first Naa1a8b392b5b4c868b007e9a69e14f5e
    85 rdf:rest Nd2f7398f0a074ae2b455df0b483e755e
    86 Nb2815bc8e41c4429b54d1cb3544d17f2 schema:name Panasonic R&D Center Singapore, Singapore, Singapore
    87 rdf:type schema:Organization
    88 Nb8ede5958cae463fb51855edbd850077 schema:familyName Cremers
    89 schema:givenName Daniel
    90 rdf:type schema:Person
    91 Nd2f7398f0a074ae2b455df0b483e755e rdf:first N09afbbf370c248ecba2fec9018ade52a
    92 rdf:rest N848ebe97ab174967aee8aa6e4186964f
    93 Ndb710b74914743a08268f87a4a65340f rdf:first sg:person.01372341404.93
    94 rdf:rest rdf:nil
    95 Ne3dbb34961f9411bbc6faa025de10ab1 schema:name Springer Nature - SN SciGraph project
    96 rdf:type schema:Organization
    97 Ne89bfec824614a4d91084083bec15b09 rdf:first Nb8ede5958cae463fb51855edbd850077
    98 rdf:rest Nae4c16e1c0b94944a734c8e5b791925d
    99 Nf90f9703ea894d3a8b8f1edb0cc3d17a schema:name dimensions_id
    100 schema:value pub.1015449875
    101 rdf:type schema:PropertyValue
    102 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
    103 schema:name Information and Computing Sciences
    104 rdf:type schema:DefinedTerm
    105 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
    106 schema:name Artificial Intelligence and Image Processing
    107 rdf:type schema:DefinedTerm
    108 sg:grant.7177986 http://pending.schema.org/fundedItem sg:pub.10.1007/978-3-319-16811-1_39
    109 rdf:type schema:MonetaryGrant
    110 sg:grant.7185337 http://pending.schema.org/fundedItem sg:pub.10.1007/978-3-319-16811-1_39
    111 rdf:type schema:MonetaryGrant
    112 sg:person.011547566102.59 schema:affiliation https://www.grid.ac/institutes/grid.410579.e
    113 schema:familyName Liu
    114 schema:givenName Yazhou
    115 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011547566102.59
    116 rdf:type schema:Person
    117 sg:person.01324226204.06 schema:affiliation Nb2815bc8e41c4429b54d1cb3544d17f2
    118 schema:familyName Lasang
    119 schema:givenName Pongsak
    120 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01324226204.06
    121 rdf:type schema:Person
    122 sg:person.01372341404.93 schema:affiliation https://www.grid.ac/institutes/grid.147455.6
    123 schema:familyName Siegel
    124 schema:givenName Mel
    125 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01372341404.93
    126 rdf:type schema:Person
    127 sg:person.0665262737.23 schema:affiliation https://www.grid.ac/institutes/grid.410579.e
    128 schema:familyName Sun
    129 schema:givenName Quansen
    130 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0665262737.23
    131 rdf:type schema:Person
    132 sg:pub.10.1007/978-3-642-15561-1_56 schema:sameAs https://app.dimensions.ai/details/publication/pub.1034663897
    133 https://doi.org/10.1007/978-3-642-15561-1_56
    134 rdf:type schema:CreativeWork
    135 sg:pub.10.1007/978-3-642-28661-2_5 schema:sameAs https://app.dimensions.ai/details/publication/pub.1018988958
    136 https://doi.org/10.1007/978-3-642-28661-2_5
    137 rdf:type schema:CreativeWork
    138 sg:pub.10.1023/b:visi.0000029664.99615.94 schema:sameAs https://app.dimensions.ai/details/publication/pub.1052687286
    139 https://doi.org/10.1023/b:visi.0000029664.99615.94
    140 rdf:type schema:CreativeWork
    141 https://doi.org/10.1016/j.cviu.2007.09.014 schema:sameAs https://app.dimensions.ai/details/publication/pub.1040969278
    142 rdf:type schema:CreativeWork
    143 https://doi.org/10.1016/j.sigpro.2011.12.005 schema:sameAs https://app.dimensions.ai/details/publication/pub.1041719350
    144 rdf:type schema:CreativeWork
    145 https://doi.org/10.1109/3dv.2013.43 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095532495
    146 rdf:type schema:CreativeWork
    147 https://doi.org/10.1109/3dv.2013.44 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095765165
    148 rdf:type schema:CreativeWork
    149 https://doi.org/10.1109/cvpr.2004.1315241 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094870330
    150 rdf:type schema:CreativeWork
    151 https://doi.org/10.1109/cvpr.2013.444 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095468539
    152 rdf:type schema:CreativeWork
    153 https://doi.org/10.1109/iccv.2005.147 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093369149
    154 rdf:type schema:CreativeWork
    155 https://doi.org/10.1109/mci.2010.938364 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061392393
    156 rdf:type schema:CreativeWork
    157 https://doi.org/10.1109/robot.2010.5509559 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093342429
    158 rdf:type schema:CreativeWork
    159 https://doi.org/10.1109/tip.2012.2210234 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061643301
    160 rdf:type schema:CreativeWork
    161 https://doi.org/10.1109/tpami.2002.1017623 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061742396
    162 rdf:type schema:CreativeWork
    163 https://doi.org/10.1109/tpami.2005.188 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061742845
    164 rdf:type schema:CreativeWork
    165 https://doi.org/10.1109/tpami.2006.244 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061743071
    166 rdf:type schema:CreativeWork
    167 https://doi.org/10.1109/tpami.2008.112 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061743474
    168 rdf:type schema:CreativeWork
    169 https://doi.org/10.1109/tpami.2009.155 schema:sameAs https://app.dimensions.ai/details/publication/pub.1048054623
    170 rdf:type schema:CreativeWork
    171 https://doi.org/10.1109/tpami.2009.167 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061743745
    172 rdf:type schema:CreativeWork
    173 https://doi.org/10.1109/tpami.2011.222 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061744104
    174 rdf:type schema:CreativeWork
    175 https://doi.org/10.1109/tpami.2012.120 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061744236
    176 rdf:type schema:CreativeWork
    177 https://doi.org/10.1109/tpami.2012.231 schema:sameAs https://app.dimensions.ai/details/publication/pub.1003742061
    178 rdf:type schema:CreativeWork
    179 https://doi.org/10.1109/tpami.2012.241 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061744335
    180 rdf:type schema:CreativeWork
    181 https://doi.org/10.1109/tpami.2013.50 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061744581
    182 rdf:type schema:CreativeWork
    183 https://doi.org/10.1145/1390156.1390294 schema:sameAs https://app.dimensions.ai/details/publication/pub.1034603392
    184 rdf:type schema:CreativeWork
    185 https://doi.org/10.1145/2047196.2047270 schema:sameAs https://app.dimensions.ai/details/publication/pub.1053252950
    186 rdf:type schema:CreativeWork
    187 https://doi.org/10.1561/2200000006 schema:sameAs https://app.dimensions.ai/details/publication/pub.1068001401
    188 rdf:type schema:CreativeWork
    189 https://www.grid.ac/institutes/grid.147455.6 schema:alternateName Carnegie Mellon University
    190 schema:name Carnegie Mellon University, Pittsburgh, USA
    191 rdf:type schema:Organization
    192 https://www.grid.ac/institutes/grid.410579.e schema:alternateName Nanjing University of Science and Technology
    193 schema:name Nanjing University of Science and Technology, Nanjing, China
    194 rdf:type schema:Organization
     




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


    ...