Disentangling Geometry and Appearance with Regularised Geometry-Aware Generative Adversarial Networks View Full Text


Ontology type: schema:ScholarlyArticle     


Article Info

DATE

2019-03-02

AUTHORS

Linh Tran, Jean Kossaifi, Yannis Panagakis, Maja Pantic

ABSTRACT

Deep generative models have significantly advanced image generation, enabling generation of visually pleasing images with realistic texture. Apart from the texture, it is the shape geometry of objects that strongly dictates their appearance. However, currently available generative models do not incorporate geometric information into the image generation process. This often yields visual objects of degenerated quality. In this work, we propose a regularized Geometry-Aware Generative Adversarial Network (GAGAN) which disentangles appearance and shape in the latent space. This regularized GAGAN enables the generation of images with both realistic texture and shape. Specifically, we condition the generator on a statistical shape prior. The prior is enforced through mapping the generated images onto a canonical coordinate frame using a differentiable geometric transformation. In addition to incorporating geometric information, this constrains the search space and increases the model’s robustness. We show that our approach is versatile, able to generalise across domains (faces, sketches, hands and cats) and sample sizes (from as little as ∼200-30,000 to more than 200, 000). We demonstrate superior performance through extensive quantitative and qualitative experiments in a variety of tasks and settings. Finally, we leverage our model to automatically and accurately detect errors or drifting in facial landmarks detection and tracking in-the-wild. More... »

PAGES

1-21

References to SciGraph publications

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/s11263-019-01155-7

DOI

http://dx.doi.org/10.1007/s11263-019-01155-7

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1112504862


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": "Tran", 
        "givenName": "Linh", 
        "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": "Kossaifi", 
        "givenName": "Jean", 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Middlesex University", 
          "id": "https://www.grid.ac/institutes/grid.15822.3c", 
          "name": [
            "Imperial College London, London, UK", 
            "Middlesex University London, London, UK"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Panagakis", 
        "givenName": "Yannis", 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Imperial College London", 
          "id": "https://www.grid.ac/institutes/grid.7445.2", 
          "name": [
            "Imperial College London, London, UK", 
            "Samsung AI, Cambridge, UK"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Pantic", 
        "givenName": "Maja", 
        "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": "sg:pub.10.1007/s11263-016-0950-1", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1003296478", 
          "https://doi.org/10.1007/s11263-016-0950-1"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s11263-016-0950-1", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1003296478", 
          "https://doi.org/10.1007/s11263-016-0950-1"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.imavis.2016.01.002", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1006275968"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-319-06932-6_35", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1009320745", 
          "https://doi.org/10.1007/978-3-319-06932-6_35"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-319-46475-6_43", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1018034649", 
          "https://doi.org/10.1007/978-3-319-46475-6_43"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tip.2010.2050625", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1019629051"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1006/cviu.1995.1004", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1021804206"
        ], 
        "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.10.1186/1687-6180-2014-170", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1025331209", 
          "https://doi.org/10.1186/1687-6180-2014-170"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s11263-016-0920-7", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1031761518", 
          "https://doi.org/10.1007/s11263-016-0920-7"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s11263-016-0920-7", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1031761518", 
          "https://doi.org/10.1007/s11263-016-0920-7"
        ], 
        "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/s11042-015-2934-5", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1045414300", 
          "https://doi.org/10.1007/s11042-015-2934-5"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s11042-015-2934-5", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1045414300", 
          "https://doi.org/10.1007/s11042-015-2934-5"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1023/b:visi.0000029664.99615.94", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1052687286", 
          "https://doi.org/10.1023/b:visi.0000029664.99615.94"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/34.927467", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061157281"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/lsp.2014.2333544", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061378823"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tip.2015.2431445", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061644395"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tip.2016.2642828", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061645375"
        ], 
        "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.2012.40", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061744380"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.imavis.2017.02.001", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1083801569"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/iccv.2015.441", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1093190357"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/icip.2015.7350977", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1093247586"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cvpr.2012.6248014", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1093281279"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cvpr.2005.177", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1093997066"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/icip.2014.7025284", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1094111805"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cvpr.2011.5995602", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1094644672"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/iccvw.2013.59", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1094921794"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cvprw.2013.132", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1094959929"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/iccvw.2015.132", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1095025289"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/iccv.2013.131", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1095555051"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/afgr.1998.670965", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1095667372"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cvpr.2014.239", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1095669676"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cvpr.2016.278", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1095706293"
        ], 
        "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.2017.19", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1095836438"
        ], 
        "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/10.24963/ijcai.2017/404", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1096024062"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/iccv.2017.116", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1100060078"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/iccv.2017.244", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1100060220"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cvpr.2018.00098", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1110720232"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cvpr.2018.00098", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1110720232"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "2019-03-02", 
    "datePublishedReg": "2019-03-02", 
    "description": "Deep generative models have significantly advanced image generation, enabling generation of visually pleasing images with realistic texture. Apart from the texture, it is the shape geometry of objects that strongly dictates their appearance. However, currently available generative models do not incorporate geometric information into the image generation process. This often yields visual objects of degenerated quality. In this work, we propose a regularized Geometry-Aware Generative Adversarial Network (GAGAN) which disentangles appearance and shape in the latent space. This regularized GAGAN enables the generation of images with both realistic texture and shape. Specifically, we condition the generator on a statistical shape prior. The prior is enforced through mapping the generated images onto a canonical coordinate frame using a differentiable geometric transformation. In addition to incorporating geometric information, this constrains the search space and increases the model\u2019s robustness. We show that our approach is versatile, able to generalise across domains (faces, sketches, hands and cats) and sample sizes (from as little as \u223c200-30,000 to more than 200, 000). We demonstrate superior performance through extensive quantitative and qualitative experiments in a variety of tasks and settings. Finally, we leverage our model to automatically and accurately detect errors or drifting in facial landmarks detection and tracking in-the-wild.", 
    "genre": "research_article", 
    "id": "sg:pub.10.1007/s11263-019-01155-7", 
    "inLanguage": [
      "en"
    ], 
    "isAccessibleForFree": false, 
    "isFundedItemOf": [
      {
        "id": "sg:grant.5050885", 
        "type": "MonetaryGrant"
      }, 
      {
        "id": "sg:grant.3939294", 
        "type": "MonetaryGrant"
      }
    ], 
    "isPartOf": [
      {
        "id": "sg:journal.1032807", 
        "issn": [
          "0920-5691", 
          "1573-1405"
        ], 
        "name": "International Journal of Computer Vision", 
        "type": "Periodical"
      }
    ], 
    "name": "Disentangling Geometry and Appearance with Regularised Geometry-Aware Generative Adversarial Networks", 
    "pagination": "1-21", 
    "productId": [
      {
        "name": "readcube_id", 
        "type": "PropertyValue", 
        "value": [
          "a5f190cc77c59a10f0a24f48d47ec5de56b80acc4bde3fa710229e7b6929cdd9"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/s11263-019-01155-7"
        ]
      }, 
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1112504862"
        ]
      }
    ], 
    "sameAs": [
      "https://doi.org/10.1007/s11263-019-01155-7", 
      "https://app.dimensions.ai/details/publication/pub.1112504862"
    ], 
    "sdDataset": "articles", 
    "sdDatePublished": "2019-04-11T10:48", 
    "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/v90/0000000350_0000000350/records_77548_00000001.jsonl", 
    "type": "ScholarlyArticle", 
    "url": "https://link.springer.com/10.1007%2Fs11263-019-01155-7"
  }
]
 

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/s11263-019-01155-7'

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/s11263-019-01155-7'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/s11263-019-01155-7'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/s11263-019-01155-7'


 

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

209 TRIPLES      21 PREDICATES      64 URIs      16 LITERALS      5 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/s11263-019-01155-7 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author N4972a2a0af1a43eb9c39ee94e61e3674
4 schema:citation sg:pub.10.1007/978-3-319-06932-6_35
5 sg:pub.10.1007/978-3-319-46475-6_43
6 sg:pub.10.1007/s11042-015-2934-5
7 sg:pub.10.1007/s11263-016-0920-7
8 sg:pub.10.1007/s11263-016-0950-1
9 sg:pub.10.1023/b:visi.0000029664.99615.94
10 sg:pub.10.1023/b:visi.0000029666.37597.d3
11 sg:pub.10.1186/1687-6180-2014-170
12 https://doi.org/10.1006/cviu.1995.1004
13 https://doi.org/10.1016/j.imavis.2009.08.002
14 https://doi.org/10.1016/j.imavis.2016.01.002
15 https://doi.org/10.1016/j.imavis.2017.02.001
16 https://doi.org/10.1109/34.927467
17 https://doi.org/10.1109/afgr.1998.670965
18 https://doi.org/10.1109/cvpr.2005.177
19 https://doi.org/10.1109/cvpr.2011.5995602
20 https://doi.org/10.1109/cvpr.2012.6248014
21 https://doi.org/10.1109/cvpr.2014.239
22 https://doi.org/10.1109/cvpr.2016.278
23 https://doi.org/10.1109/cvpr.2017.141
24 https://doi.org/10.1109/cvpr.2017.19
25 https://doi.org/10.1109/cvpr.2018.00098
26 https://doi.org/10.1109/cvprw.2013.132
27 https://doi.org/10.1109/iccv.2013.131
28 https://doi.org/10.1109/iccv.2015.425
29 https://doi.org/10.1109/iccv.2015.441
30 https://doi.org/10.1109/iccv.2017.116
31 https://doi.org/10.1109/iccv.2017.244
32 https://doi.org/10.1109/iccvw.2013.59
33 https://doi.org/10.1109/iccvw.2015.132
34 https://doi.org/10.1109/icip.2014.7025284
35 https://doi.org/10.1109/icip.2015.7350977
36 https://doi.org/10.1109/lsp.2014.2333544
37 https://doi.org/10.1109/tip.2010.2050625
38 https://doi.org/10.1109/tip.2015.2431445
39 https://doi.org/10.1109/tip.2016.2642828
40 https://doi.org/10.1109/tpami.2002.1017623
41 https://doi.org/10.1109/tpami.2012.40
42 https://doi.org/10.1145/1390156.1390294
43 https://doi.org/10.24963/ijcai.2017/404
44 schema:datePublished 2019-03-02
45 schema:datePublishedReg 2019-03-02
46 schema:description Deep generative models have significantly advanced image generation, enabling generation of visually pleasing images with realistic texture. Apart from the texture, it is the shape geometry of objects that strongly dictates their appearance. However, currently available generative models do not incorporate geometric information into the image generation process. This often yields visual objects of degenerated quality. In this work, we propose a regularized Geometry-Aware Generative Adversarial Network (GAGAN) which disentangles appearance and shape in the latent space. This regularized GAGAN enables the generation of images with both realistic texture and shape. Specifically, we condition the generator on a statistical shape prior. The prior is enforced through mapping the generated images onto a canonical coordinate frame using a differentiable geometric transformation. In addition to incorporating geometric information, this constrains the search space and increases the model’s robustness. We show that our approach is versatile, able to generalise across domains (faces, sketches, hands and cats) and sample sizes (from as little as ∼200-30,000 to more than 200, 000). We demonstrate superior performance through extensive quantitative and qualitative experiments in a variety of tasks and settings. Finally, we leverage our model to automatically and accurately detect errors or drifting in facial landmarks detection and tracking in-the-wild.
47 schema:genre research_article
48 schema:inLanguage en
49 schema:isAccessibleForFree false
50 schema:isPartOf sg:journal.1032807
51 schema:name Disentangling Geometry and Appearance with Regularised Geometry-Aware Generative Adversarial Networks
52 schema:pagination 1-21
53 schema:productId N128c97fe8ef9465b8231db9e366b049f
54 Na9e47c4e4d2f4896b0cd99f1d98ef6c9
55 Ne1c4966e2a5f449e95490fb96e87e101
56 schema:sameAs https://app.dimensions.ai/details/publication/pub.1112504862
57 https://doi.org/10.1007/s11263-019-01155-7
58 schema:sdDatePublished 2019-04-11T10:48
59 schema:sdLicense https://scigraph.springernature.com/explorer/license/
60 schema:sdPublisher N66de284e87394686a9ee10c3d22b3fed
61 schema:url https://link.springer.com/10.1007%2Fs11263-019-01155-7
62 sgo:license sg:explorer/license/
63 sgo:sdDataset articles
64 rdf:type schema:ScholarlyArticle
65 N128c97fe8ef9465b8231db9e366b049f schema:name doi
66 schema:value 10.1007/s11263-019-01155-7
67 rdf:type schema:PropertyValue
68 N40611620d9784474a64b7b084c103f73 rdf:first Nf9c8a0433a8d4e6db8e6680e405808ec
69 rdf:rest N6b56da2d922146e989deb0fa2e150ae5
70 N4972a2a0af1a43eb9c39ee94e61e3674 rdf:first Ned0fb31a789b4069bec476910050b065
71 rdf:rest Nc2c9642c50b64969a33e5ba3014680f6
72 N66de284e87394686a9ee10c3d22b3fed schema:name Springer Nature - SN SciGraph project
73 rdf:type schema:Organization
74 N6b56da2d922146e989deb0fa2e150ae5 rdf:first Ne62b029341d14188b195f350e32fc681
75 rdf:rest rdf:nil
76 N9d432dffcea04e049fcc638434ce26bd schema:affiliation https://www.grid.ac/institutes/grid.7445.2
77 schema:familyName Kossaifi
78 schema:givenName Jean
79 rdf:type schema:Person
80 Na9e47c4e4d2f4896b0cd99f1d98ef6c9 schema:name readcube_id
81 schema:value a5f190cc77c59a10f0a24f48d47ec5de56b80acc4bde3fa710229e7b6929cdd9
82 rdf:type schema:PropertyValue
83 Nc2c9642c50b64969a33e5ba3014680f6 rdf:first N9d432dffcea04e049fcc638434ce26bd
84 rdf:rest N40611620d9784474a64b7b084c103f73
85 Ne1c4966e2a5f449e95490fb96e87e101 schema:name dimensions_id
86 schema:value pub.1112504862
87 rdf:type schema:PropertyValue
88 Ne62b029341d14188b195f350e32fc681 schema:affiliation https://www.grid.ac/institutes/grid.7445.2
89 schema:familyName Pantic
90 schema:givenName Maja
91 rdf:type schema:Person
92 Ned0fb31a789b4069bec476910050b065 schema:affiliation https://www.grid.ac/institutes/grid.7445.2
93 schema:familyName Tran
94 schema:givenName Linh
95 rdf:type schema:Person
96 Nf9c8a0433a8d4e6db8e6680e405808ec schema:affiliation https://www.grid.ac/institutes/grid.15822.3c
97 schema:familyName Panagakis
98 schema:givenName Yannis
99 rdf:type schema:Person
100 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
101 schema:name Information and Computing Sciences
102 rdf:type schema:DefinedTerm
103 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
104 schema:name Artificial Intelligence and Image Processing
105 rdf:type schema:DefinedTerm
106 sg:grant.3939294 http://pending.schema.org/fundedItem sg:pub.10.1007/s11263-019-01155-7
107 rdf:type schema:MonetaryGrant
108 sg:grant.5050885 http://pending.schema.org/fundedItem sg:pub.10.1007/s11263-019-01155-7
109 rdf:type schema:MonetaryGrant
110 sg:journal.1032807 schema:issn 0920-5691
111 1573-1405
112 schema:name International Journal of Computer Vision
113 rdf:type schema:Periodical
114 sg:pub.10.1007/978-3-319-06932-6_35 schema:sameAs https://app.dimensions.ai/details/publication/pub.1009320745
115 https://doi.org/10.1007/978-3-319-06932-6_35
116 rdf:type schema:CreativeWork
117 sg:pub.10.1007/978-3-319-46475-6_43 schema:sameAs https://app.dimensions.ai/details/publication/pub.1018034649
118 https://doi.org/10.1007/978-3-319-46475-6_43
119 rdf:type schema:CreativeWork
120 sg:pub.10.1007/s11042-015-2934-5 schema:sameAs https://app.dimensions.ai/details/publication/pub.1045414300
121 https://doi.org/10.1007/s11042-015-2934-5
122 rdf:type schema:CreativeWork
123 sg:pub.10.1007/s11263-016-0920-7 schema:sameAs https://app.dimensions.ai/details/publication/pub.1031761518
124 https://doi.org/10.1007/s11263-016-0920-7
125 rdf:type schema:CreativeWork
126 sg:pub.10.1007/s11263-016-0950-1 schema:sameAs https://app.dimensions.ai/details/publication/pub.1003296478
127 https://doi.org/10.1007/s11263-016-0950-1
128 rdf:type schema:CreativeWork
129 sg:pub.10.1023/b:visi.0000029664.99615.94 schema:sameAs https://app.dimensions.ai/details/publication/pub.1052687286
130 https://doi.org/10.1023/b:visi.0000029664.99615.94
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 sg:pub.10.1186/1687-6180-2014-170 schema:sameAs https://app.dimensions.ai/details/publication/pub.1025331209
136 https://doi.org/10.1186/1687-6180-2014-170
137 rdf:type schema:CreativeWork
138 https://doi.org/10.1006/cviu.1995.1004 schema:sameAs https://app.dimensions.ai/details/publication/pub.1021804206
139 rdf:type schema:CreativeWork
140 https://doi.org/10.1016/j.imavis.2009.08.002 schema:sameAs https://app.dimensions.ai/details/publication/pub.1001414620
141 rdf:type schema:CreativeWork
142 https://doi.org/10.1016/j.imavis.2016.01.002 schema:sameAs https://app.dimensions.ai/details/publication/pub.1006275968
143 rdf:type schema:CreativeWork
144 https://doi.org/10.1016/j.imavis.2017.02.001 schema:sameAs https://app.dimensions.ai/details/publication/pub.1083801569
145 rdf:type schema:CreativeWork
146 https://doi.org/10.1109/34.927467 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061157281
147 rdf:type schema:CreativeWork
148 https://doi.org/10.1109/afgr.1998.670965 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095667372
149 rdf:type schema:CreativeWork
150 https://doi.org/10.1109/cvpr.2005.177 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093997066
151 rdf:type schema:CreativeWork
152 https://doi.org/10.1109/cvpr.2011.5995602 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094644672
153 rdf:type schema:CreativeWork
154 https://doi.org/10.1109/cvpr.2012.6248014 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093281279
155 rdf:type schema:CreativeWork
156 https://doi.org/10.1109/cvpr.2014.239 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095669676
157 rdf:type schema:CreativeWork
158 https://doi.org/10.1109/cvpr.2016.278 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095706293
159 rdf:type schema:CreativeWork
160 https://doi.org/10.1109/cvpr.2017.141 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095838548
161 rdf:type schema:CreativeWork
162 https://doi.org/10.1109/cvpr.2017.19 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095836438
163 rdf:type schema:CreativeWork
164 https://doi.org/10.1109/cvpr.2018.00098 schema:sameAs https://app.dimensions.ai/details/publication/pub.1110720232
165 rdf:type schema:CreativeWork
166 https://doi.org/10.1109/cvprw.2013.132 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094959929
167 rdf:type schema:CreativeWork
168 https://doi.org/10.1109/iccv.2013.131 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095555051
169 rdf:type schema:CreativeWork
170 https://doi.org/10.1109/iccv.2015.425 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095764490
171 rdf:type schema:CreativeWork
172 https://doi.org/10.1109/iccv.2015.441 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093190357
173 rdf:type schema:CreativeWork
174 https://doi.org/10.1109/iccv.2017.116 schema:sameAs https://app.dimensions.ai/details/publication/pub.1100060078
175 rdf:type schema:CreativeWork
176 https://doi.org/10.1109/iccv.2017.244 schema:sameAs https://app.dimensions.ai/details/publication/pub.1100060220
177 rdf:type schema:CreativeWork
178 https://doi.org/10.1109/iccvw.2013.59 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094921794
179 rdf:type schema:CreativeWork
180 https://doi.org/10.1109/iccvw.2015.132 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095025289
181 rdf:type schema:CreativeWork
182 https://doi.org/10.1109/icip.2014.7025284 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094111805
183 rdf:type schema:CreativeWork
184 https://doi.org/10.1109/icip.2015.7350977 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093247586
185 rdf:type schema:CreativeWork
186 https://doi.org/10.1109/lsp.2014.2333544 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061378823
187 rdf:type schema:CreativeWork
188 https://doi.org/10.1109/tip.2010.2050625 schema:sameAs https://app.dimensions.ai/details/publication/pub.1019629051
189 rdf:type schema:CreativeWork
190 https://doi.org/10.1109/tip.2015.2431445 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061644395
191 rdf:type schema:CreativeWork
192 https://doi.org/10.1109/tip.2016.2642828 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061645375
193 rdf:type schema:CreativeWork
194 https://doi.org/10.1109/tpami.2002.1017623 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061742396
195 rdf:type schema:CreativeWork
196 https://doi.org/10.1109/tpami.2012.40 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061744380
197 rdf:type schema:CreativeWork
198 https://doi.org/10.1145/1390156.1390294 schema:sameAs https://app.dimensions.ai/details/publication/pub.1034603392
199 rdf:type schema:CreativeWork
200 https://doi.org/10.24963/ijcai.2017/404 schema:sameAs https://app.dimensions.ai/details/publication/pub.1096024062
201 rdf:type schema:CreativeWork
202 https://www.grid.ac/institutes/grid.15822.3c schema:alternateName Middlesex University
203 schema:name Imperial College London, London, UK
204 Middlesex University London, London, UK
205 rdf:type schema:Organization
206 https://www.grid.ac/institutes/grid.7445.2 schema:alternateName Imperial College London
207 schema:name Imperial College London, London, UK
208 Samsung AI, Cambridge, UK
209 rdf:type schema:Organization
 




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


...