An Adversarial Neuro-Tensorial Approach for Learning Disentangled Representations View Full Text


Ontology type: schema:ScholarlyArticle     


Article Info

DATE

2019-02-16

AUTHORS

Mengjiao Wang, Zhixin Shu, Shiyang Cheng, Yannis Panagakis, Dimitris Samaras, Stefanos Zafeiriou

ABSTRACT

Several factors contribute to the appearance of an object in a visual scene, including pose, illumination, and deformation, among others. Each factor accounts for a source of variability in the data, while the multiplicative interactions of these factors emulate the entangled variability, giving rise to the rich structure of visual object appearance. Disentangling such unobserved factors from visual data is a challenging task, especially when the data have been captured in uncontrolled recording conditions (also referred to as “in-the-wild”) and label information is not available. In this paper, we propose a pseudo-supervised deep learning method for disentangling multiple latent factors of variation in face images captured in-the-wild. To this end, we propose a deep latent variable model, where the multiplicative interactions of multiple latent factors of variation are explicitly modelled by means of multilinear (tensor) structure. We demonstrate that the proposed approach indeed learns disentangled representations of facial expressions and pose, which can be used in various applications, including face editing, as well as 3D face reconstruction and classification of facial expression, identity and pose. More... »

PAGES

1-20

References to SciGraph publications

  • 2004-11. Active Appearance Models Revisited in INTERNATIONAL JOURNAL OF COMPUTER VISION
  • 2011. Transforming Auto-Encoders in ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING – ICANN 2011
  • 2002. Multilinear Analysis of Image Ensembles: TensorFaces in COMPUTER VISION — ECCV 2002
  • 2018-10-09. Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network in COMPUTER VISION – ECCV 2018
  • Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1007/s11263-019-01163-7

    DOI

    http://dx.doi.org/10.1007/s11263-019-01163-7

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1112215350


    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": "Imperial College London", 
              "id": "https://www.grid.ac/institutes/grid.7445.2", 
              "name": [
                "Imperial College London, London, UK"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Wang", 
            "givenName": "Mengjiao", 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Stony Brook University", 
              "id": "https://www.grid.ac/institutes/grid.36425.36", 
              "name": [
                "Stony Brook University, Stony Brook, USA"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Shu", 
            "givenName": "Zhixin", 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Imperial College London", 
              "id": "https://www.grid.ac/institutes/grid.7445.2", 
              "name": [
                "Imperial College London, London, UK"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Cheng", 
            "givenName": "Shiyang", 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Middlesex University", 
              "id": "https://www.grid.ac/institutes/grid.15822.3c", 
              "name": [
                "Imperial College London, London, UK", 
                "Middlesex University, London, UK"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Panagakis", 
            "givenName": "Yannis", 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Stony Brook University", 
              "id": "https://www.grid.ac/institutes/grid.36425.36", 
              "name": [
                "Stony Brook University, Stony Brook, USA"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Samaras", 
            "givenName": "Dimitris", 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Imperial College London", 
              "id": "https://www.grid.ac/institutes/grid.7445.2", 
              "name": [
                "Imperial College London, London, UK"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Zafeiriou", 
            "givenName": "Stefanos", 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "https://doi.org/10.1016/j.imavis.2009.08.002", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1001414620"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1117/12.7972479", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1008840170"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1023/b:visi.0000029666.37597.d3", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1022700327", 
              "https://doi.org/10.1023/b:visi.0000029666.37597.d3"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/3-540-47969-4_30", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1025400387", 
              "https://doi.org/10.1007/3-540-47969-4_30"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1037/h0071325", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1033321863"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-642-21735-7_6", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1049023394", 
              "https://doi.org/10.1007/978-3-642-21735-7_6"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-642-21735-7_6", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1049023394", 
              "https://doi.org/10.1007/978-3-642-21735-7_6"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1145/1964921.1964955", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1050755303"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1162/089976600300015349", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1053156407"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1080/01621459.1969.10501027", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1058300479"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/34.927467", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061157281"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tifs.2012.2224109", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061630071"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tpami.2008.111", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061743473"
            ], 
            "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/10.1137/07070111x", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1062851534"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1137/s0895479896305696", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1062882268"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1145/2010324.1964955", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1063159725"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2017.578", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1093493598"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2015.7298604", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1093631283"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/iccv.2013.404", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1094326457"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2017.580", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1094994663"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2016.531", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095039557"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/iccv.2015.425", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095764490"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2017.141", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095838548"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2017.641", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095850900"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2017.608", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095852599"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.24963/ijcai.2017/404", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1096024062"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1093/acprof:osobl/9780199734177.001.0001", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1098740802"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/iccv.2017.117", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1100060079"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/iccv.2017.401", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1100060395"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/iccv.2017.611", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1100060628"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/iccvw.2017.153", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1100555707"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-030-01264-9_33", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1107502734", 
              "https://doi.org/10.1007/978-3-030-01264-9_33"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-030-01264-9_33", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1107502734", 
              "https://doi.org/10.1007/978-3-030-01264-9_33"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2018.00270", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1110720404"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2018.00270", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1110720404"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2018.00537", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1110720671"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2018.00537", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1110720671"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2018.00767", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1110720901"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2018.00767", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1110720901"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2019-02-16", 
        "datePublishedReg": "2019-02-16", 
        "description": "Several factors contribute to the appearance of an object in a visual scene, including pose, illumination, and deformation, among others. Each factor accounts for a source of variability in the data, while the multiplicative interactions of these factors emulate the entangled variability, giving rise to the rich structure of visual object appearance. Disentangling such unobserved factors from visual data is a challenging task, especially when the data have been captured in uncontrolled recording conditions (also referred to as \u201cin-the-wild\u201d) and label information is not available. In this paper, we propose a pseudo-supervised deep learning method for disentangling multiple latent factors of variation in face images captured in-the-wild. To this end, we propose a deep latent variable model, where the multiplicative interactions of multiple latent factors of variation are explicitly modelled by means of multilinear (tensor) structure. We demonstrate that the proposed approach indeed learns disentangled representations of facial expressions and pose, which can be used in various applications, including face editing, as well as 3D face reconstruction and classification of facial expression, identity and pose.", 
        "genre": "research_article", 
        "id": "sg:pub.10.1007/s11263-019-01163-7", 
        "inLanguage": [
          "en"
        ], 
        "isAccessibleForFree": false, 
        "isFundedItemOf": [
          {
            "id": "sg:grant.6932897", 
            "type": "MonetaryGrant"
          }, 
          {
            "id": "sg:grant.7057430", 
            "type": "MonetaryGrant"
          }, 
          {
            "id": "sg:grant.7828535", 
            "type": "MonetaryGrant"
          }
        ], 
        "isPartOf": [
          {
            "id": "sg:journal.1032807", 
            "issn": [
              "0920-5691", 
              "1573-1405"
            ], 
            "name": "International Journal of Computer Vision", 
            "type": "Periodical"
          }
        ], 
        "name": "An Adversarial Neuro-Tensorial Approach for Learning Disentangled Representations", 
        "pagination": "1-20", 
        "productId": [
          {
            "name": "readcube_id", 
            "type": "PropertyValue", 
            "value": [
              "57d6077bef145669995671ee6930eb00cb1536fb2b7cda075b8c8f4ef5b81350"
            ]
          }, 
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1007/s11263-019-01163-7"
            ]
          }, 
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1112215350"
            ]
          }
        ], 
        "sameAs": [
          "https://doi.org/10.1007/s11263-019-01163-7", 
          "https://app.dimensions.ai/details/publication/pub.1112215350"
        ], 
        "sdDataset": "articles", 
        "sdDatePublished": "2019-04-11T09:09", 
        "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/v90/0000000338_0000000338/records_47966_00000002.jsonl", 
        "type": "ScholarlyArticle", 
        "url": "https://link.springer.com/10.1007%2Fs11263-019-01163-7"
      }
    ]
     

    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/s11263-019-01163-7'

    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/s11263-019-01163-7'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/s11263-019-01163-7'

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

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/s11263-019-01163-7'


     

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

    206 TRIPLES      21 PREDICATES      59 URIs      16 LITERALS      5 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1007/s11263-019-01163-7 schema:about anzsrc-for:08
    2 anzsrc-for:0801
    3 schema:author N116356cc0f094abf97829c3915e0165c
    4 schema:citation sg:pub.10.1007/3-540-47969-4_30
    5 sg:pub.10.1007/978-3-030-01264-9_33
    6 sg:pub.10.1007/978-3-642-21735-7_6
    7 sg:pub.10.1023/b:visi.0000029666.37597.d3
    8 https://doi.org/10.1016/j.imavis.2009.08.002
    9 https://doi.org/10.1037/h0071325
    10 https://doi.org/10.1080/01621459.1969.10501027
    11 https://doi.org/10.1093/acprof:osobl/9780199734177.001.0001
    12 https://doi.org/10.1109/34.927467
    13 https://doi.org/10.1109/cvpr.2015.7298604
    14 https://doi.org/10.1109/cvpr.2016.531
    15 https://doi.org/10.1109/cvpr.2017.141
    16 https://doi.org/10.1109/cvpr.2017.578
    17 https://doi.org/10.1109/cvpr.2017.580
    18 https://doi.org/10.1109/cvpr.2017.608
    19 https://doi.org/10.1109/cvpr.2017.641
    20 https://doi.org/10.1109/cvpr.2018.00270
    21 https://doi.org/10.1109/cvpr.2018.00537
    22 https://doi.org/10.1109/cvpr.2018.00767
    23 https://doi.org/10.1109/iccv.2013.404
    24 https://doi.org/10.1109/iccv.2015.425
    25 https://doi.org/10.1109/iccv.2017.117
    26 https://doi.org/10.1109/iccv.2017.401
    27 https://doi.org/10.1109/iccv.2017.611
    28 https://doi.org/10.1109/iccvw.2017.153
    29 https://doi.org/10.1109/tifs.2012.2224109
    30 https://doi.org/10.1109/tpami.2008.111
    31 https://doi.org/10.1109/tpami.2013.50
    32 https://doi.org/10.1117/12.7972479
    33 https://doi.org/10.1137/07070111x
    34 https://doi.org/10.1137/s0895479896305696
    35 https://doi.org/10.1145/1964921.1964955
    36 https://doi.org/10.1145/2010324.1964955
    37 https://doi.org/10.1162/089976600300015349
    38 https://doi.org/10.24963/ijcai.2017/404
    39 schema:datePublished 2019-02-16
    40 schema:datePublishedReg 2019-02-16
    41 schema:description Several factors contribute to the appearance of an object in a visual scene, including pose, illumination, and deformation, among others. Each factor accounts for a source of variability in the data, while the multiplicative interactions of these factors emulate the entangled variability, giving rise to the rich structure of visual object appearance. Disentangling such unobserved factors from visual data is a challenging task, especially when the data have been captured in uncontrolled recording conditions (also referred to as “in-the-wild”) and label information is not available. In this paper, we propose a pseudo-supervised deep learning method for disentangling multiple latent factors of variation in face images captured in-the-wild. To this end, we propose a deep latent variable model, where the multiplicative interactions of multiple latent factors of variation are explicitly modelled by means of multilinear (tensor) structure. We demonstrate that the proposed approach indeed learns disentangled representations of facial expressions and pose, which can be used in various applications, including face editing, as well as 3D face reconstruction and classification of facial expression, identity and pose.
    42 schema:genre research_article
    43 schema:inLanguage en
    44 schema:isAccessibleForFree false
    45 schema:isPartOf sg:journal.1032807
    46 schema:name An Adversarial Neuro-Tensorial Approach for Learning Disentangled Representations
    47 schema:pagination 1-20
    48 schema:productId N56a52e8aaac442cbb9e87948c1dfb78f
    49 Nf801cd007cc74b52b3676adbf2f73e4e
    50 Nfa716d4a37384d2f93fb81a372203d93
    51 schema:sameAs https://app.dimensions.ai/details/publication/pub.1112215350
    52 https://doi.org/10.1007/s11263-019-01163-7
    53 schema:sdDatePublished 2019-04-11T09:09
    54 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    55 schema:sdPublisher Nec8ca85641b54c0eafad47edb1249e5e
    56 schema:url https://link.springer.com/10.1007%2Fs11263-019-01163-7
    57 sgo:license sg:explorer/license/
    58 sgo:sdDataset articles
    59 rdf:type schema:ScholarlyArticle
    60 N116356cc0f094abf97829c3915e0165c rdf:first N5b41f455c04844b0a4fe16567182d120
    61 rdf:rest Ncd4a042ae77348168ed032a116a12c9a
    62 N1812269f352c4e668591e4a94eeb08cc schema:affiliation https://www.grid.ac/institutes/grid.15822.3c
    63 schema:familyName Panagakis
    64 schema:givenName Yannis
    65 rdf:type schema:Person
    66 N322e953eca8f406b8a953e52fc59ee3c schema:affiliation https://www.grid.ac/institutes/grid.36425.36
    67 schema:familyName Samaras
    68 schema:givenName Dimitris
    69 rdf:type schema:Person
    70 N374b378438aa4108bb07720c0d7891d6 rdf:first N1812269f352c4e668591e4a94eeb08cc
    71 rdf:rest N913f00a0a63840fb8eb581bac4200101
    72 N49370de717e24de8852086888784610b rdf:first N78b4e4f7bb4e4a949bf8c5ac5b8ef706
    73 rdf:rest N374b378438aa4108bb07720c0d7891d6
    74 N56a52e8aaac442cbb9e87948c1dfb78f schema:name readcube_id
    75 schema:value 57d6077bef145669995671ee6930eb00cb1536fb2b7cda075b8c8f4ef5b81350
    76 rdf:type schema:PropertyValue
    77 N5915d1c09d2c4278ad358847b1b42920 schema:affiliation https://www.grid.ac/institutes/grid.36425.36
    78 schema:familyName Shu
    79 schema:givenName Zhixin
    80 rdf:type schema:Person
    81 N5b41f455c04844b0a4fe16567182d120 schema:affiliation https://www.grid.ac/institutes/grid.7445.2
    82 schema:familyName Wang
    83 schema:givenName Mengjiao
    84 rdf:type schema:Person
    85 N78b4e4f7bb4e4a949bf8c5ac5b8ef706 schema:affiliation https://www.grid.ac/institutes/grid.7445.2
    86 schema:familyName Cheng
    87 schema:givenName Shiyang
    88 rdf:type schema:Person
    89 N7dc3340296024101b96c9bcd61abc7dc schema:affiliation https://www.grid.ac/institutes/grid.7445.2
    90 schema:familyName Zafeiriou
    91 schema:givenName Stefanos
    92 rdf:type schema:Person
    93 N913f00a0a63840fb8eb581bac4200101 rdf:first N322e953eca8f406b8a953e52fc59ee3c
    94 rdf:rest Nd43d6c74fb2640559fe9b967efb52fe3
    95 Ncd4a042ae77348168ed032a116a12c9a rdf:first N5915d1c09d2c4278ad358847b1b42920
    96 rdf:rest N49370de717e24de8852086888784610b
    97 Nd43d6c74fb2640559fe9b967efb52fe3 rdf:first N7dc3340296024101b96c9bcd61abc7dc
    98 rdf:rest rdf:nil
    99 Nec8ca85641b54c0eafad47edb1249e5e schema:name Springer Nature - SN SciGraph project
    100 rdf:type schema:Organization
    101 Nf801cd007cc74b52b3676adbf2f73e4e schema:name dimensions_id
    102 schema:value pub.1112215350
    103 rdf:type schema:PropertyValue
    104 Nfa716d4a37384d2f93fb81a372203d93 schema:name doi
    105 schema:value 10.1007/s11263-019-01163-7
    106 rdf:type schema:PropertyValue
    107 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
    108 schema:name Information and Computing Sciences
    109 rdf:type schema:DefinedTerm
    110 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
    111 schema:name Artificial Intelligence and Image Processing
    112 rdf:type schema:DefinedTerm
    113 sg:grant.6932897 http://pending.schema.org/fundedItem sg:pub.10.1007/s11263-019-01163-7
    114 rdf:type schema:MonetaryGrant
    115 sg:grant.7057430 http://pending.schema.org/fundedItem sg:pub.10.1007/s11263-019-01163-7
    116 rdf:type schema:MonetaryGrant
    117 sg:grant.7828535 http://pending.schema.org/fundedItem sg:pub.10.1007/s11263-019-01163-7
    118 rdf:type schema:MonetaryGrant
    119 sg:journal.1032807 schema:issn 0920-5691
    120 1573-1405
    121 schema:name International Journal of Computer Vision
    122 rdf:type schema:Periodical
    123 sg:pub.10.1007/3-540-47969-4_30 schema:sameAs https://app.dimensions.ai/details/publication/pub.1025400387
    124 https://doi.org/10.1007/3-540-47969-4_30
    125 rdf:type schema:CreativeWork
    126 sg:pub.10.1007/978-3-030-01264-9_33 schema:sameAs https://app.dimensions.ai/details/publication/pub.1107502734
    127 https://doi.org/10.1007/978-3-030-01264-9_33
    128 rdf:type schema:CreativeWork
    129 sg:pub.10.1007/978-3-642-21735-7_6 schema:sameAs https://app.dimensions.ai/details/publication/pub.1049023394
    130 https://doi.org/10.1007/978-3-642-21735-7_6
    131 rdf:type schema:CreativeWork
    132 sg:pub.10.1023/b:visi.0000029666.37597.d3 schema:sameAs https://app.dimensions.ai/details/publication/pub.1022700327
    133 https://doi.org/10.1023/b:visi.0000029666.37597.d3
    134 rdf:type schema:CreativeWork
    135 https://doi.org/10.1016/j.imavis.2009.08.002 schema:sameAs https://app.dimensions.ai/details/publication/pub.1001414620
    136 rdf:type schema:CreativeWork
    137 https://doi.org/10.1037/h0071325 schema:sameAs https://app.dimensions.ai/details/publication/pub.1033321863
    138 rdf:type schema:CreativeWork
    139 https://doi.org/10.1080/01621459.1969.10501027 schema:sameAs https://app.dimensions.ai/details/publication/pub.1058300479
    140 rdf:type schema:CreativeWork
    141 https://doi.org/10.1093/acprof:osobl/9780199734177.001.0001 schema:sameAs https://app.dimensions.ai/details/publication/pub.1098740802
    142 rdf:type schema:CreativeWork
    143 https://doi.org/10.1109/34.927467 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061157281
    144 rdf:type schema:CreativeWork
    145 https://doi.org/10.1109/cvpr.2015.7298604 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093631283
    146 rdf:type schema:CreativeWork
    147 https://doi.org/10.1109/cvpr.2016.531 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095039557
    148 rdf:type schema:CreativeWork
    149 https://doi.org/10.1109/cvpr.2017.141 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095838548
    150 rdf:type schema:CreativeWork
    151 https://doi.org/10.1109/cvpr.2017.578 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093493598
    152 rdf:type schema:CreativeWork
    153 https://doi.org/10.1109/cvpr.2017.580 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094994663
    154 rdf:type schema:CreativeWork
    155 https://doi.org/10.1109/cvpr.2017.608 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095852599
    156 rdf:type schema:CreativeWork
    157 https://doi.org/10.1109/cvpr.2017.641 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095850900
    158 rdf:type schema:CreativeWork
    159 https://doi.org/10.1109/cvpr.2018.00270 schema:sameAs https://app.dimensions.ai/details/publication/pub.1110720404
    160 rdf:type schema:CreativeWork
    161 https://doi.org/10.1109/cvpr.2018.00537 schema:sameAs https://app.dimensions.ai/details/publication/pub.1110720671
    162 rdf:type schema:CreativeWork
    163 https://doi.org/10.1109/cvpr.2018.00767 schema:sameAs https://app.dimensions.ai/details/publication/pub.1110720901
    164 rdf:type schema:CreativeWork
    165 https://doi.org/10.1109/iccv.2013.404 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094326457
    166 rdf:type schema:CreativeWork
    167 https://doi.org/10.1109/iccv.2015.425 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095764490
    168 rdf:type schema:CreativeWork
    169 https://doi.org/10.1109/iccv.2017.117 schema:sameAs https://app.dimensions.ai/details/publication/pub.1100060079
    170 rdf:type schema:CreativeWork
    171 https://doi.org/10.1109/iccv.2017.401 schema:sameAs https://app.dimensions.ai/details/publication/pub.1100060395
    172 rdf:type schema:CreativeWork
    173 https://doi.org/10.1109/iccv.2017.611 schema:sameAs https://app.dimensions.ai/details/publication/pub.1100060628
    174 rdf:type schema:CreativeWork
    175 https://doi.org/10.1109/iccvw.2017.153 schema:sameAs https://app.dimensions.ai/details/publication/pub.1100555707
    176 rdf:type schema:CreativeWork
    177 https://doi.org/10.1109/tifs.2012.2224109 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061630071
    178 rdf:type schema:CreativeWork
    179 https://doi.org/10.1109/tpami.2008.111 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061743473
    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/10.1117/12.7972479 schema:sameAs https://app.dimensions.ai/details/publication/pub.1008840170
    184 rdf:type schema:CreativeWork
    185 https://doi.org/10.1137/07070111x schema:sameAs https://app.dimensions.ai/details/publication/pub.1062851534
    186 rdf:type schema:CreativeWork
    187 https://doi.org/10.1137/s0895479896305696 schema:sameAs https://app.dimensions.ai/details/publication/pub.1062882268
    188 rdf:type schema:CreativeWork
    189 https://doi.org/10.1145/1964921.1964955 schema:sameAs https://app.dimensions.ai/details/publication/pub.1050755303
    190 rdf:type schema:CreativeWork
    191 https://doi.org/10.1145/2010324.1964955 schema:sameAs https://app.dimensions.ai/details/publication/pub.1063159725
    192 rdf:type schema:CreativeWork
    193 https://doi.org/10.1162/089976600300015349 schema:sameAs https://app.dimensions.ai/details/publication/pub.1053156407
    194 rdf:type schema:CreativeWork
    195 https://doi.org/10.24963/ijcai.2017/404 schema:sameAs https://app.dimensions.ai/details/publication/pub.1096024062
    196 rdf:type schema:CreativeWork
    197 https://www.grid.ac/institutes/grid.15822.3c schema:alternateName Middlesex University
    198 schema:name Imperial College London, London, UK
    199 Middlesex University, London, UK
    200 rdf:type schema:Organization
    201 https://www.grid.ac/institutes/grid.36425.36 schema:alternateName Stony Brook University
    202 schema:name Stony Brook University, Stony Brook, USA
    203 rdf:type schema:Organization
    204 https://www.grid.ac/institutes/grid.7445.2 schema:alternateName Imperial College London
    205 schema:name Imperial College London, London, UK
    206 rdf:type schema:Organization
     




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


    ...