Metric Learning for Large Scale Image Classification: Generalizing to New Classes at Near-Zero Cost View Full Text


Ontology type: schema:Chapter      Open Access: True


Chapter Info

DATE

2012

AUTHORS

Thomas Mensink , Jakob Verbeek , Florent Perronnin , Gabriela Csurka

ABSTRACT

We are interested in large-scale image classification and especially in the setting where images corresponding to new or existing classes are continuously added to the training set. Our goal is to devise classifiers which can incorporate such images and classes on-the-fly at (near) zero cost. We cast this problem into one of learning a metric which is shared across all classes and explore k-nearest neighbor (k-NN) and nearest class mean (NCM) classifiers. We learn metrics on the ImageNet 2010 challenge data set, which contains more than 1.2M training images of 1K classes. Surprisingly, the NCM classifier compares favorably to the more flexible k-NN classifier, and has comparable performance to linear SVMs. We also study the generalization performance, among others by using the learned metric on the ImageNet-10K dataset, and we obtain competitive performance. Finally, we explore zero-shot classification, and show how the zero-shot model can be combined very effectively with small training datasets. More... »

PAGES

488-501

Book

TITLE

Computer Vision – ECCV 2012

ISBN

978-3-642-33708-6
978-3-642-33709-3

Author Affiliations

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/978-3-642-33709-3_35

DOI

http://dx.doi.org/10.1007/978-3-642-33709-3_35

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1025918724


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": {
          "name": [
            "LEAR, INRIA Grenoble, 655 Avenue de l\u2019Europe, 38330\u00a0Montbonnot, France"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Mensink", 
        "givenName": "Thomas", 
        "id": "sg:person.010600141141.73", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010600141141.73"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "name": [
            "LEAR, INRIA Grenoble, 655 Avenue de l\u2019Europe, 38330\u00a0Montbonnot, France"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Verbeek", 
        "givenName": "Jakob", 
        "id": "sg:person.01122633347.88", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01122633347.88"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Xerox (France)", 
          "id": "https://www.grid.ac/institutes/grid.426471.2", 
          "name": [
            "TVPA, Xerox Research Centre Europe, 6 chemin de Maupertuis, 38240\u00a0Meylan, France"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Perronnin", 
        "givenName": "Florent", 
        "id": "sg:person.01320142425.13", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01320142425.13"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Xerox (France)", 
          "id": "https://www.grid.ac/institutes/grid.426471.2", 
          "name": [
            "TVPA, Xerox Research Centre Europe, 6 chemin de Maupertuis, 38240\u00a0Meylan, France"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Csurka", 
        "givenName": "Gabriela", 
        "id": "sg:person.010325517436.61", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010325517436.61"
        ], 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "https://doi.org/10.1016/j.sigpro.2009.06.015", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1002307711"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s11263-006-9794-4", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1008205152", 
          "https://doi.org/10.1007/s11263-006-9794-4"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-642-15555-0_6", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1017308440", 
          "https://doi.org/10.1007/978-3-642-15555-0_6"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-642-15555-0_6", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1017308440", 
          "https://doi.org/10.1007/978-3-642-15555-0_6"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s10791-009-9117-9", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1042356415", 
          "https://doi.org/10.1007/s10791-009-9117-9"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s10791-009-9117-9", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1042356415", 
          "https://doi.org/10.1007/s10791-009-9117-9"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s10791-009-9117-9", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1042356415", 
          "https://doi.org/10.1007/s10791-009-9117-9"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-642-15561-1_11", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1045344996", 
          "https://doi.org/10.1007/978-3-642-15561-1_11"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-642-15561-1_11", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1045344996", 
          "https://doi.org/10.1007/978-3-642-15561-1_11"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1145/1459359.1459391", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1050564265"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/18.720541", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061100773"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/89.279278", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061242233"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tpami.2005.182", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061742839"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tpami.2006.79", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061743121"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tpami.2010.57", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061743975"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tpami.2011.235", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061744117"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cvpr.2012.6248090", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1093355304"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/iccv.2009.5459266", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1094092743"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cvpr.2011.5995504", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1094246303"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cvpr.2007.382969", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1094428869"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cvpr.2009.5206594", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1094500840"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cvpr.2011.5995477", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1095578081"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cvpr.2011.5995627", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1095621790"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cvpr.2009.5206848", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1095689025"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1002/0470854774", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1098661187"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1002/0470854774", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1098661187"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.5244/c.23.80", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1099325700"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "2012", 
    "datePublishedReg": "2012-01-01", 
    "description": "We are interested in large-scale image classification and especially in the setting where images corresponding to new or existing classes are continuously added to the training set. Our goal is to devise classifiers which can incorporate such images and classes on-the-fly at (near) zero cost. We cast this problem into one of learning a metric which is shared across all classes and explore k-nearest neighbor (k-NN) and nearest class mean (NCM) classifiers. We learn metrics on the ImageNet 2010 challenge data set, which contains more than 1.2M training images of 1K classes. Surprisingly, the NCM classifier compares favorably to the more flexible k-NN classifier, and has comparable performance to linear SVMs. We also study the generalization performance, among others by using the learned metric on the ImageNet-10K dataset, and we obtain competitive performance. Finally, we explore zero-shot classification, and show how the zero-shot model can be combined very effectively with small training datasets.", 
    "editor": [
      {
        "familyName": "Fitzgibbon", 
        "givenName": "Andrew", 
        "type": "Person"
      }, 
      {
        "familyName": "Lazebnik", 
        "givenName": "Svetlana", 
        "type": "Person"
      }, 
      {
        "familyName": "Perona", 
        "givenName": "Pietro", 
        "type": "Person"
      }, 
      {
        "familyName": "Sato", 
        "givenName": "Yoichi", 
        "type": "Person"
      }, 
      {
        "familyName": "Schmid", 
        "givenName": "Cordelia", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/978-3-642-33709-3_35", 
    "inLanguage": [
      "en"
    ], 
    "isAccessibleForFree": true, 
    "isPartOf": {
      "isbn": [
        "978-3-642-33708-6", 
        "978-3-642-33709-3"
      ], 
      "name": "Computer Vision \u2013 ECCV 2012", 
      "type": "Book"
    }, 
    "name": "Metric Learning for Large Scale Image Classification: Generalizing to New Classes at Near-Zero Cost", 
    "pagination": "488-501", 
    "productId": [
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/978-3-642-33709-3_35"
        ]
      }, 
      {
        "name": "readcube_id", 
        "type": "PropertyValue", 
        "value": [
          "7b7a4ac4f5b935ff5823eb545912b25195d9a75bfbd094d91e277d48a5bc7308"
        ]
      }, 
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1025918724"
        ]
      }
    ], 
    "publisher": {
      "location": "Berlin, Heidelberg", 
      "name": "Springer Berlin Heidelberg", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/978-3-642-33709-3_35", 
      "https://app.dimensions.ai/details/publication/pub.1025918724"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2019-04-15T21:58", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-uberresearch-data-dimensions-target-20181106-alternative/cleanup/v134/2549eaecd7973599484d7c17b260dba0a4ecb94b/merge/v9/a6c9fde33151104705d4d7ff012ea9563521a3ce/jats-lookup/v90/0000000001_0000000264/records_8693_00000259.jsonl", 
    "type": "Chapter", 
    "url": "http://link.springer.com/10.1007/978-3-642-33709-3_35"
  }
]
 

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

HOW TO GET THIS DATA PROGRAMMATICALLY:

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

curl -H 'Accept: application/ld+json' 'https://scigraph.springernature.com/pub.10.1007/978-3-642-33709-3_35'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-642-33709-3_35'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-642-33709-3_35'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-642-33709-3_35'


 

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

180 TRIPLES      23 PREDICATES      49 URIs      20 LITERALS      8 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/978-3-642-33709-3_35 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author N10875527267145f8ae8b53e66a574ee7
4 schema:citation sg:pub.10.1007/978-3-642-15555-0_6
5 sg:pub.10.1007/978-3-642-15561-1_11
6 sg:pub.10.1007/s10791-009-9117-9
7 sg:pub.10.1007/s11263-006-9794-4
8 https://doi.org/10.1002/0470854774
9 https://doi.org/10.1016/j.sigpro.2009.06.015
10 https://doi.org/10.1109/18.720541
11 https://doi.org/10.1109/89.279278
12 https://doi.org/10.1109/cvpr.2007.382969
13 https://doi.org/10.1109/cvpr.2009.5206594
14 https://doi.org/10.1109/cvpr.2009.5206848
15 https://doi.org/10.1109/cvpr.2011.5995477
16 https://doi.org/10.1109/cvpr.2011.5995504
17 https://doi.org/10.1109/cvpr.2011.5995627
18 https://doi.org/10.1109/cvpr.2012.6248090
19 https://doi.org/10.1109/iccv.2009.5459266
20 https://doi.org/10.1109/tpami.2005.182
21 https://doi.org/10.1109/tpami.2006.79
22 https://doi.org/10.1109/tpami.2010.57
23 https://doi.org/10.1109/tpami.2011.235
24 https://doi.org/10.1145/1459359.1459391
25 https://doi.org/10.5244/c.23.80
26 schema:datePublished 2012
27 schema:datePublishedReg 2012-01-01
28 schema:description We are interested in large-scale image classification and especially in the setting where images corresponding to new or existing classes are continuously added to the training set. Our goal is to devise classifiers which can incorporate such images and classes on-the-fly at (near) zero cost. We cast this problem into one of learning a metric which is shared across all classes and explore k-nearest neighbor (k-NN) and nearest class mean (NCM) classifiers. We learn metrics on the ImageNet 2010 challenge data set, which contains more than 1.2M training images of 1K classes. Surprisingly, the NCM classifier compares favorably to the more flexible k-NN classifier, and has comparable performance to linear SVMs. We also study the generalization performance, among others by using the learned metric on the ImageNet-10K dataset, and we obtain competitive performance. Finally, we explore zero-shot classification, and show how the zero-shot model can be combined very effectively with small training datasets.
29 schema:editor N61f398e7d6bb4c5f953352d751e4387d
30 schema:genre chapter
31 schema:inLanguage en
32 schema:isAccessibleForFree true
33 schema:isPartOf Ne4eee39455324ad4b502c1bb72fc3749
34 schema:name Metric Learning for Large Scale Image Classification: Generalizing to New Classes at Near-Zero Cost
35 schema:pagination 488-501
36 schema:productId Na41314b7cddb4df8b3483c53dbd50d54
37 Ndd4f56e1a99140dfbbf01ae21c86cd95
38 Ndd6bd4be399244388688228ed0286eeb
39 schema:publisher Nd918ef29dde64d9b80a94a63990050cc
40 schema:sameAs https://app.dimensions.ai/details/publication/pub.1025918724
41 https://doi.org/10.1007/978-3-642-33709-3_35
42 schema:sdDatePublished 2019-04-15T21:58
43 schema:sdLicense https://scigraph.springernature.com/explorer/license/
44 schema:sdPublisher Nfa36b58002004994b83305889a311dc4
45 schema:url http://link.springer.com/10.1007/978-3-642-33709-3_35
46 sgo:license sg:explorer/license/
47 sgo:sdDataset chapters
48 rdf:type schema:Chapter
49 N058ef26f280646aebca2e95f070d2e0a schema:familyName Perona
50 schema:givenName Pietro
51 rdf:type schema:Person
52 N10875527267145f8ae8b53e66a574ee7 rdf:first sg:person.010600141141.73
53 rdf:rest Neb16a33849ed4be8abd9e9ffcc3b6ebe
54 N1910b974d0de4603b79a2d2779aede5b schema:familyName Schmid
55 schema:givenName Cordelia
56 rdf:type schema:Person
57 N23def4cc405f4f888adf348170841119 rdf:first N058ef26f280646aebca2e95f070d2e0a
58 rdf:rest Na9847a00bc454e9c83683f86879a33d7
59 N24962b37bee545ceb5466f8b39050055 rdf:first N1910b974d0de4603b79a2d2779aede5b
60 rdf:rest rdf:nil
61 N30d4a69a5e3b4a71b5e67c7b45db0b9b schema:familyName Sato
62 schema:givenName Yoichi
63 rdf:type schema:Person
64 N415400d2340a4f1ab133526fd6261269 schema:name LEAR, INRIA Grenoble, 655 Avenue de l’Europe, 38330 Montbonnot, France
65 rdf:type schema:Organization
66 N4eadee8726404768b7b5cb002f63528d rdf:first sg:person.010325517436.61
67 rdf:rest rdf:nil
68 N61f398e7d6bb4c5f953352d751e4387d rdf:first N6516870cf25443ee9c21d2273db256c6
69 rdf:rest Nddb125eac7dd402087e3503c05f2f234
70 N6516870cf25443ee9c21d2273db256c6 schema:familyName Fitzgibbon
71 schema:givenName Andrew
72 rdf:type schema:Person
73 N95fa127f7ab9479082acca5f0bc04d0d schema:familyName Lazebnik
74 schema:givenName Svetlana
75 rdf:type schema:Person
76 Na41314b7cddb4df8b3483c53dbd50d54 schema:name dimensions_id
77 schema:value pub.1025918724
78 rdf:type schema:PropertyValue
79 Na9847a00bc454e9c83683f86879a33d7 rdf:first N30d4a69a5e3b4a71b5e67c7b45db0b9b
80 rdf:rest N24962b37bee545ceb5466f8b39050055
81 Ncebef7279a9c4f9d86593af5a981343f schema:name LEAR, INRIA Grenoble, 655 Avenue de l’Europe, 38330 Montbonnot, France
82 rdf:type schema:Organization
83 Nd918ef29dde64d9b80a94a63990050cc schema:location Berlin, Heidelberg
84 schema:name Springer Berlin Heidelberg
85 rdf:type schema:Organisation
86 Ndd4f56e1a99140dfbbf01ae21c86cd95 schema:name readcube_id
87 schema:value 7b7a4ac4f5b935ff5823eb545912b25195d9a75bfbd094d91e277d48a5bc7308
88 rdf:type schema:PropertyValue
89 Ndd6bd4be399244388688228ed0286eeb schema:name doi
90 schema:value 10.1007/978-3-642-33709-3_35
91 rdf:type schema:PropertyValue
92 Nddb125eac7dd402087e3503c05f2f234 rdf:first N95fa127f7ab9479082acca5f0bc04d0d
93 rdf:rest N23def4cc405f4f888adf348170841119
94 Nde888952ea364d0b93fd31dc2a2d03f4 rdf:first sg:person.01320142425.13
95 rdf:rest N4eadee8726404768b7b5cb002f63528d
96 Ne4eee39455324ad4b502c1bb72fc3749 schema:isbn 978-3-642-33708-6
97 978-3-642-33709-3
98 schema:name Computer Vision – ECCV 2012
99 rdf:type schema:Book
100 Neb16a33849ed4be8abd9e9ffcc3b6ebe rdf:first sg:person.01122633347.88
101 rdf:rest Nde888952ea364d0b93fd31dc2a2d03f4
102 Nfa36b58002004994b83305889a311dc4 schema:name Springer Nature - SN SciGraph project
103 rdf:type schema:Organization
104 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
105 schema:name Information and Computing Sciences
106 rdf:type schema:DefinedTerm
107 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
108 schema:name Artificial Intelligence and Image Processing
109 rdf:type schema:DefinedTerm
110 sg:person.010325517436.61 schema:affiliation https://www.grid.ac/institutes/grid.426471.2
111 schema:familyName Csurka
112 schema:givenName Gabriela
113 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010325517436.61
114 rdf:type schema:Person
115 sg:person.010600141141.73 schema:affiliation Ncebef7279a9c4f9d86593af5a981343f
116 schema:familyName Mensink
117 schema:givenName Thomas
118 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010600141141.73
119 rdf:type schema:Person
120 sg:person.01122633347.88 schema:affiliation N415400d2340a4f1ab133526fd6261269
121 schema:familyName Verbeek
122 schema:givenName Jakob
123 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01122633347.88
124 rdf:type schema:Person
125 sg:person.01320142425.13 schema:affiliation https://www.grid.ac/institutes/grid.426471.2
126 schema:familyName Perronnin
127 schema:givenName Florent
128 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01320142425.13
129 rdf:type schema:Person
130 sg:pub.10.1007/978-3-642-15555-0_6 schema:sameAs https://app.dimensions.ai/details/publication/pub.1017308440
131 https://doi.org/10.1007/978-3-642-15555-0_6
132 rdf:type schema:CreativeWork
133 sg:pub.10.1007/978-3-642-15561-1_11 schema:sameAs https://app.dimensions.ai/details/publication/pub.1045344996
134 https://doi.org/10.1007/978-3-642-15561-1_11
135 rdf:type schema:CreativeWork
136 sg:pub.10.1007/s10791-009-9117-9 schema:sameAs https://app.dimensions.ai/details/publication/pub.1042356415
137 https://doi.org/10.1007/s10791-009-9117-9
138 rdf:type schema:CreativeWork
139 sg:pub.10.1007/s11263-006-9794-4 schema:sameAs https://app.dimensions.ai/details/publication/pub.1008205152
140 https://doi.org/10.1007/s11263-006-9794-4
141 rdf:type schema:CreativeWork
142 https://doi.org/10.1002/0470854774 schema:sameAs https://app.dimensions.ai/details/publication/pub.1098661187
143 rdf:type schema:CreativeWork
144 https://doi.org/10.1016/j.sigpro.2009.06.015 schema:sameAs https://app.dimensions.ai/details/publication/pub.1002307711
145 rdf:type schema:CreativeWork
146 https://doi.org/10.1109/18.720541 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061100773
147 rdf:type schema:CreativeWork
148 https://doi.org/10.1109/89.279278 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061242233
149 rdf:type schema:CreativeWork
150 https://doi.org/10.1109/cvpr.2007.382969 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094428869
151 rdf:type schema:CreativeWork
152 https://doi.org/10.1109/cvpr.2009.5206594 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094500840
153 rdf:type schema:CreativeWork
154 https://doi.org/10.1109/cvpr.2009.5206848 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095689025
155 rdf:type schema:CreativeWork
156 https://doi.org/10.1109/cvpr.2011.5995477 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095578081
157 rdf:type schema:CreativeWork
158 https://doi.org/10.1109/cvpr.2011.5995504 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094246303
159 rdf:type schema:CreativeWork
160 https://doi.org/10.1109/cvpr.2011.5995627 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095621790
161 rdf:type schema:CreativeWork
162 https://doi.org/10.1109/cvpr.2012.6248090 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093355304
163 rdf:type schema:CreativeWork
164 https://doi.org/10.1109/iccv.2009.5459266 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094092743
165 rdf:type schema:CreativeWork
166 https://doi.org/10.1109/tpami.2005.182 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061742839
167 rdf:type schema:CreativeWork
168 https://doi.org/10.1109/tpami.2006.79 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061743121
169 rdf:type schema:CreativeWork
170 https://doi.org/10.1109/tpami.2010.57 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061743975
171 rdf:type schema:CreativeWork
172 https://doi.org/10.1109/tpami.2011.235 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061744117
173 rdf:type schema:CreativeWork
174 https://doi.org/10.1145/1459359.1459391 schema:sameAs https://app.dimensions.ai/details/publication/pub.1050564265
175 rdf:type schema:CreativeWork
176 https://doi.org/10.5244/c.23.80 schema:sameAs https://app.dimensions.ai/details/publication/pub.1099325700
177 rdf:type schema:CreativeWork
178 https://www.grid.ac/institutes/grid.426471.2 schema:alternateName Xerox (France)
179 schema:name TVPA, Xerox Research Centre Europe, 6 chemin de Maupertuis, 38240 Meylan, France
180 rdf:type schema:Organization
 




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


...