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 N3a2de98da2144439b5d90c0f6e007c4c
    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 N0b5e33378d9445a795e182aa4c512288
    49 Ne65bd0fdeefb48c5909ebd8659ace207
    50 Nec80268fef404aaeb27aa8579c9280f4
    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 Nd91c362c29f24a6a92190d53045780d7
    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 N09001d7b079e4785b2259e7c9437a0b9 rdf:first Nb097529d347f415187534c8b7b8d28b3
    61 rdf:rest rdf:nil
    62 N0b5e33378d9445a795e182aa4c512288 schema:name dimensions_id
    63 schema:value pub.1112215350
    64 rdf:type schema:PropertyValue
    65 N3a2de98da2144439b5d90c0f6e007c4c rdf:first Nfac38759ae6c4db5a881a8636f9cf8b3
    66 rdf:rest Na5677de126db44b590c96728e424042c
    67 N4fa697f6840a45edafda992186c4ca8f rdf:first Nc9c11f0b970d4721a5512810a0ebfd7a
    68 rdf:rest N688fd2bf32db4317a6aefc0010585dea
    69 N688fd2bf32db4317a6aefc0010585dea rdf:first Nc403ff50b8874a03ababaa614ffb4b78
    70 rdf:rest N09001d7b079e4785b2259e7c9437a0b9
    71 N86bcd9321546409ba7dba0435d637673 schema:affiliation https://www.grid.ac/institutes/grid.36425.36
    72 schema:familyName Shu
    73 schema:givenName Zhixin
    74 rdf:type schema:Person
    75 N9bf581c3ee694e0a89982cb6f6c0f2ec rdf:first Nea8ed9af2b1a491cbcaab3face8ca64f
    76 rdf:rest N4fa697f6840a45edafda992186c4ca8f
    77 Na5677de126db44b590c96728e424042c rdf:first N86bcd9321546409ba7dba0435d637673
    78 rdf:rest N9bf581c3ee694e0a89982cb6f6c0f2ec
    79 Nb097529d347f415187534c8b7b8d28b3 schema:affiliation https://www.grid.ac/institutes/grid.7445.2
    80 schema:familyName Zafeiriou
    81 schema:givenName Stefanos
    82 rdf:type schema:Person
    83 Nc403ff50b8874a03ababaa614ffb4b78 schema:affiliation https://www.grid.ac/institutes/grid.36425.36
    84 schema:familyName Samaras
    85 schema:givenName Dimitris
    86 rdf:type schema:Person
    87 Nc9c11f0b970d4721a5512810a0ebfd7a schema:affiliation https://www.grid.ac/institutes/grid.15822.3c
    88 schema:familyName Panagakis
    89 schema:givenName Yannis
    90 rdf:type schema:Person
    91 Nd91c362c29f24a6a92190d53045780d7 schema:name Springer Nature - SN SciGraph project
    92 rdf:type schema:Organization
    93 Ne65bd0fdeefb48c5909ebd8659ace207 schema:name doi
    94 schema:value 10.1007/s11263-019-01163-7
    95 rdf:type schema:PropertyValue
    96 Nea8ed9af2b1a491cbcaab3face8ca64f schema:affiliation https://www.grid.ac/institutes/grid.7445.2
    97 schema:familyName Cheng
    98 schema:givenName Shiyang
    99 rdf:type schema:Person
    100 Nec80268fef404aaeb27aa8579c9280f4 schema:name readcube_id
    101 schema:value 57d6077bef145669995671ee6930eb00cb1536fb2b7cda075b8c8f4ef5b81350
    102 rdf:type schema:PropertyValue
    103 Nfac38759ae6c4db5a881a8636f9cf8b3 schema:affiliation https://www.grid.ac/institutes/grid.7445.2
    104 schema:familyName Wang
    105 schema:givenName Mengjiao
    106 rdf:type schema:Person
    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)


    ...