Graph Cut Based Inference with Co-occurrence Statistics View Full Text


Ontology type: schema:Chapter      Open Access: True


Chapter Info

DATE

2010

AUTHORS

Lubor Ladicky , Chris Russell , Pushmeet Kohli , Philip H. S. Torr

ABSTRACT

Markov and Conditional random fields (crfs) used in computer vision typically model only local interactions between variables, as this is computationally tractable. In this paper we consider a class of global potentials defined over all variables in the crf. We show how they can be readily optimised using standard graph cut algorithms at little extra expense compared to a standard pairwise field. This result can be directly used for the problem of class based image segmentation which has seen increasing recent interest within computer vision. Here the aim is to assign a label to each pixel of a given image from a set of possible object classes. Typically these methods use random fields to model local interactions between pixels or super-pixels. One of the cues that helps recognition is global object co-occurrence statistics, a measure of which classes (such as chair or motorbike) are likely to occur in the same image together. There have been several approaches proposed to exploit this property, but all of them suffer from different limitations and typically carry a high computational cost, preventing their application on large images. We find that the new model we propose produces an improvement in the labelling compared to just using a pairwise model. More... »

PAGES

239-253

Book

TITLE

Computer Vision – ECCV 2010

ISBN

978-3-642-15554-3
978-3-642-15555-0

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/978-3-642-15555-0_18

DOI

http://dx.doi.org/10.1007/978-3-642-15555-0_18

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1028844592


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": [
            "Oxford Brookes"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Ladicky", 
        "givenName": "Lubor", 
        "id": "sg:person.011034367256.51", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011034367256.51"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "name": [
            "Oxford Brookes"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Russell", 
        "givenName": "Chris", 
        "id": "sg:person.014162633413.55", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014162633413.55"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "name": [
            "Microsoft Research"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Kohli", 
        "givenName": "Pushmeet", 
        "id": "sg:person.0606005504.21", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0606005504.21"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "name": [
            "Oxford Brookes"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Torr", 
        "givenName": "Philip H. S.", 
        "id": "sg:person.011757175441.72", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011757175441.72"
        ], 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "sg:pub.10.1007/978-3-540-88682-2_4", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1004295540", 
          "https://doi.org/10.1007/978-3-540-88682-2_4"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-540-88682-2_4", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1004295540", 
          "https://doi.org/10.1007/978-3-540-88682-2_4"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s10589-007-9048-6", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1014979091", 
          "https://doi.org/10.1007/s10589-007-9048-6"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s10589-007-9048-6", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1014979091", 
          "https://doi.org/10.1007/s10589-007-9048-6"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/11744023_1", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1017544873", 
          "https://doi.org/10.1007/11744023_1"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/11744023_1", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1017544873", 
          "https://doi.org/10.1007/11744023_1"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-642-15561-1_31", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1018304069", 
          "https://doi.org/10.1007/978-3-642-15561-1_31"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-642-15561-1_31", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1018304069", 
          "https://doi.org/10.1007/978-3-642-15561-1_31"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/11744047_2", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1021485887", 
          "https://doi.org/10.1007/11744047_2"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/11744047_2", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1021485887", 
          "https://doi.org/10.1007/11744047_2"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/11744047_1", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1027267363", 
          "https://doi.org/10.1007/11744047_1"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/11744047_1", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1027267363", 
          "https://doi.org/10.1007/11744047_1"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/18.910585", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061101592"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/34.1000236", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061155588"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tpami.2006.200", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061743038"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tpami.2008.105", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061743467"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cvpr.2007.383229", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1077867063"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cvpr.2005.130", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1093171528"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/iccv.2009.5459211", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1093296270"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/iccv.2003.1238354", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1093621895"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cvpr.2006.276", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1093703458"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cvpr.2008.4587799", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1093864237"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cvpr.2010.5540221", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1094015870"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cvpr.2007.383045", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1094236874"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/iccv.2009.5459248", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1094294309"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/iccv.2007.4408986", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1094860556"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cvpr.2010.5539897", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1094861969"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cvpr.2008.4587453", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1094986810"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cvpr.2008.4587417", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1095049126"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cvpr.2006.326", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1095068040"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.5244/c.22.22", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1099325554"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "2010", 
    "datePublishedReg": "2010-01-01", 
    "description": "Markov and Conditional random fields (crfs) used in computer vision typically model only local interactions between variables, as this is computationally tractable. In this paper we consider a class of global potentials defined over all variables in the crf. We show how they can be readily optimised using standard graph cut algorithms at little extra expense compared to a standard pairwise field. This result can be directly used for the problem of class based image segmentation which has seen increasing recent interest within computer vision. Here the aim is to assign a label to each pixel of a given image from a set of possible object classes. Typically these methods use random fields to model local interactions between pixels or super-pixels. One of the cues that helps recognition is global object co-occurrence statistics, a measure of which classes (such as chair or motorbike) are likely to occur in the same image together. There have been several approaches proposed to exploit this property, but all of them suffer from different limitations and typically carry a high computational cost, preventing their application on large images. We find that the new model we propose produces an improvement in the labelling compared to just using a pairwise model.", 
    "editor": [
      {
        "familyName": "Daniilidis", 
        "givenName": "Kostas", 
        "type": "Person"
      }, 
      {
        "familyName": "Maragos", 
        "givenName": "Petros", 
        "type": "Person"
      }, 
      {
        "familyName": "Paragios", 
        "givenName": "Nikos", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/978-3-642-15555-0_18", 
    "inLanguage": [
      "en"
    ], 
    "isAccessibleForFree": true, 
    "isPartOf": {
      "isbn": [
        "978-3-642-15554-3", 
        "978-3-642-15555-0"
      ], 
      "name": "Computer Vision \u2013 ECCV 2010", 
      "type": "Book"
    }, 
    "name": "Graph Cut Based Inference with Co-occurrence Statistics", 
    "pagination": "239-253", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1028844592"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/978-3-642-15555-0_18"
        ]
      }, 
      {
        "name": "readcube_id", 
        "type": "PropertyValue", 
        "value": [
          "89685f47ab7f794f0843b6869ee169bfa06b65edae0c17dad16789f5513208d1"
        ]
      }
    ], 
    "publisher": {
      "location": "Berlin, Heidelberg", 
      "name": "Springer Berlin Heidelberg", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/978-3-642-15555-0_18", 
      "https://app.dimensions.ai/details/publication/pub.1028844592"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2019-04-16T08:18", 
    "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/v90/0000000362_0000000362/records_87097_00000000.jsonl", 
    "type": "Chapter", 
    "url": "https://link.springer.com/10.1007%2F978-3-642-15555-0_18"
  }
]
 

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.10.1007/978-3-642-15555-0_18'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-642-15555-0_18'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-642-15555-0_18'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-642-15555-0_18'


 

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

182 TRIPLES      23 PREDICATES      52 URIs      20 LITERALS      8 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/978-3-642-15555-0_18 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author N6eb88620f1fb49dd90befb3ebaaa08ee
4 schema:citation sg:pub.10.1007/11744023_1
5 sg:pub.10.1007/11744047_1
6 sg:pub.10.1007/11744047_2
7 sg:pub.10.1007/978-3-540-88682-2_4
8 sg:pub.10.1007/978-3-642-15561-1_31
9 sg:pub.10.1007/s10589-007-9048-6
10 https://doi.org/10.1109/18.910585
11 https://doi.org/10.1109/34.1000236
12 https://doi.org/10.1109/cvpr.2005.130
13 https://doi.org/10.1109/cvpr.2006.276
14 https://doi.org/10.1109/cvpr.2006.326
15 https://doi.org/10.1109/cvpr.2007.383045
16 https://doi.org/10.1109/cvpr.2007.383229
17 https://doi.org/10.1109/cvpr.2008.4587417
18 https://doi.org/10.1109/cvpr.2008.4587453
19 https://doi.org/10.1109/cvpr.2008.4587799
20 https://doi.org/10.1109/cvpr.2010.5539897
21 https://doi.org/10.1109/cvpr.2010.5540221
22 https://doi.org/10.1109/iccv.2003.1238354
23 https://doi.org/10.1109/iccv.2007.4408986
24 https://doi.org/10.1109/iccv.2009.5459211
25 https://doi.org/10.1109/iccv.2009.5459248
26 https://doi.org/10.1109/tpami.2006.200
27 https://doi.org/10.1109/tpami.2008.105
28 https://doi.org/10.5244/c.22.22
29 schema:datePublished 2010
30 schema:datePublishedReg 2010-01-01
31 schema:description Markov and Conditional random fields (crfs) used in computer vision typically model only local interactions between variables, as this is computationally tractable. In this paper we consider a class of global potentials defined over all variables in the crf. We show how they can be readily optimised using standard graph cut algorithms at little extra expense compared to a standard pairwise field. This result can be directly used for the problem of class based image segmentation which has seen increasing recent interest within computer vision. Here the aim is to assign a label to each pixel of a given image from a set of possible object classes. Typically these methods use random fields to model local interactions between pixels or super-pixels. One of the cues that helps recognition is global object co-occurrence statistics, a measure of which classes (such as chair or motorbike) are likely to occur in the same image together. There have been several approaches proposed to exploit this property, but all of them suffer from different limitations and typically carry a high computational cost, preventing their application on large images. We find that the new model we propose produces an improvement in the labelling compared to just using a pairwise model.
32 schema:editor Na45ba3667858495ca336050e3b116fde
33 schema:genre chapter
34 schema:inLanguage en
35 schema:isAccessibleForFree true
36 schema:isPartOf N02785df72e314cd1bd236d7ae9ea5cc0
37 schema:name Graph Cut Based Inference with Co-occurrence Statistics
38 schema:pagination 239-253
39 schema:productId N3ca37b1a61f641ffaf0435ce8c5d40ab
40 N9b72ba954f6b42eba5be73f4a5679890
41 Ndca1a3f721e6494a9a1d7ddb368a2dd5
42 schema:publisher Ncd44341cb6494c4abbba6321cd220ff9
43 schema:sameAs https://app.dimensions.ai/details/publication/pub.1028844592
44 https://doi.org/10.1007/978-3-642-15555-0_18
45 schema:sdDatePublished 2019-04-16T08:18
46 schema:sdLicense https://scigraph.springernature.com/explorer/license/
47 schema:sdPublisher N3c36e1fccd9344a391e2305cb91b8fd0
48 schema:url https://link.springer.com/10.1007%2F978-3-642-15555-0_18
49 sgo:license sg:explorer/license/
50 sgo:sdDataset chapters
51 rdf:type schema:Chapter
52 N02785df72e314cd1bd236d7ae9ea5cc0 schema:isbn 978-3-642-15554-3
53 978-3-642-15555-0
54 schema:name Computer Vision – ECCV 2010
55 rdf:type schema:Book
56 N327300f76b5a4f5889d9a4fbd5c664cd schema:familyName Daniilidis
57 schema:givenName Kostas
58 rdf:type schema:Person
59 N3c36e1fccd9344a391e2305cb91b8fd0 schema:name Springer Nature - SN SciGraph project
60 rdf:type schema:Organization
61 N3ca37b1a61f641ffaf0435ce8c5d40ab schema:name readcube_id
62 schema:value 89685f47ab7f794f0843b6869ee169bfa06b65edae0c17dad16789f5513208d1
63 rdf:type schema:PropertyValue
64 N5b5b741da2fb4976ab279b752868e148 schema:name Microsoft Research
65 rdf:type schema:Organization
66 N639cbc586b1e47649954ea69994e015e schema:familyName Maragos
67 schema:givenName Petros
68 rdf:type schema:Person
69 N648e2565c18c441882c4f7c65555de13 rdf:first Ne8d6fc6b22434a8c9a9d0a490e23ba16
70 rdf:rest rdf:nil
71 N68da5bea8daf486291a93cd1e41f62e4 rdf:first sg:person.014162633413.55
72 rdf:rest Nb64cf3d2ce8741f59ce3cf1f60b316c1
73 N6922a57d0733424e920373a85297c529 schema:name Oxford Brookes
74 rdf:type schema:Organization
75 N6eb88620f1fb49dd90befb3ebaaa08ee rdf:first sg:person.011034367256.51
76 rdf:rest N68da5bea8daf486291a93cd1e41f62e4
77 N830d5f42712047138fa417f3d8a8484d schema:name Oxford Brookes
78 rdf:type schema:Organization
79 N9b72ba954f6b42eba5be73f4a5679890 schema:name dimensions_id
80 schema:value pub.1028844592
81 rdf:type schema:PropertyValue
82 Na45ba3667858495ca336050e3b116fde rdf:first N327300f76b5a4f5889d9a4fbd5c664cd
83 rdf:rest Nb8d448c3a5aa450cb521f85a76d34a6f
84 Nb64cf3d2ce8741f59ce3cf1f60b316c1 rdf:first sg:person.0606005504.21
85 rdf:rest Nb7997a9b5eaa4476b7b99ad00de928b4
86 Nb7997a9b5eaa4476b7b99ad00de928b4 rdf:first sg:person.011757175441.72
87 rdf:rest rdf:nil
88 Nb8d448c3a5aa450cb521f85a76d34a6f rdf:first N639cbc586b1e47649954ea69994e015e
89 rdf:rest N648e2565c18c441882c4f7c65555de13
90 Ncd44341cb6494c4abbba6321cd220ff9 schema:location Berlin, Heidelberg
91 schema:name Springer Berlin Heidelberg
92 rdf:type schema:Organisation
93 Ndca1a3f721e6494a9a1d7ddb368a2dd5 schema:name doi
94 schema:value 10.1007/978-3-642-15555-0_18
95 rdf:type schema:PropertyValue
96 Ndcd7a66461054addbf3a799153edab86 schema:name Oxford Brookes
97 rdf:type schema:Organization
98 Ne8d6fc6b22434a8c9a9d0a490e23ba16 schema:familyName Paragios
99 schema:givenName Nikos
100 rdf:type schema:Person
101 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
102 schema:name Information and Computing Sciences
103 rdf:type schema:DefinedTerm
104 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
105 schema:name Artificial Intelligence and Image Processing
106 rdf:type schema:DefinedTerm
107 sg:person.011034367256.51 schema:affiliation N6922a57d0733424e920373a85297c529
108 schema:familyName Ladicky
109 schema:givenName Lubor
110 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011034367256.51
111 rdf:type schema:Person
112 sg:person.011757175441.72 schema:affiliation Ndcd7a66461054addbf3a799153edab86
113 schema:familyName Torr
114 schema:givenName Philip H. S.
115 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011757175441.72
116 rdf:type schema:Person
117 sg:person.014162633413.55 schema:affiliation N830d5f42712047138fa417f3d8a8484d
118 schema:familyName Russell
119 schema:givenName Chris
120 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014162633413.55
121 rdf:type schema:Person
122 sg:person.0606005504.21 schema:affiliation N5b5b741da2fb4976ab279b752868e148
123 schema:familyName Kohli
124 schema:givenName Pushmeet
125 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0606005504.21
126 rdf:type schema:Person
127 sg:pub.10.1007/11744023_1 schema:sameAs https://app.dimensions.ai/details/publication/pub.1017544873
128 https://doi.org/10.1007/11744023_1
129 rdf:type schema:CreativeWork
130 sg:pub.10.1007/11744047_1 schema:sameAs https://app.dimensions.ai/details/publication/pub.1027267363
131 https://doi.org/10.1007/11744047_1
132 rdf:type schema:CreativeWork
133 sg:pub.10.1007/11744047_2 schema:sameAs https://app.dimensions.ai/details/publication/pub.1021485887
134 https://doi.org/10.1007/11744047_2
135 rdf:type schema:CreativeWork
136 sg:pub.10.1007/978-3-540-88682-2_4 schema:sameAs https://app.dimensions.ai/details/publication/pub.1004295540
137 https://doi.org/10.1007/978-3-540-88682-2_4
138 rdf:type schema:CreativeWork
139 sg:pub.10.1007/978-3-642-15561-1_31 schema:sameAs https://app.dimensions.ai/details/publication/pub.1018304069
140 https://doi.org/10.1007/978-3-642-15561-1_31
141 rdf:type schema:CreativeWork
142 sg:pub.10.1007/s10589-007-9048-6 schema:sameAs https://app.dimensions.ai/details/publication/pub.1014979091
143 https://doi.org/10.1007/s10589-007-9048-6
144 rdf:type schema:CreativeWork
145 https://doi.org/10.1109/18.910585 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061101592
146 rdf:type schema:CreativeWork
147 https://doi.org/10.1109/34.1000236 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061155588
148 rdf:type schema:CreativeWork
149 https://doi.org/10.1109/cvpr.2005.130 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093171528
150 rdf:type schema:CreativeWork
151 https://doi.org/10.1109/cvpr.2006.276 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093703458
152 rdf:type schema:CreativeWork
153 https://doi.org/10.1109/cvpr.2006.326 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095068040
154 rdf:type schema:CreativeWork
155 https://doi.org/10.1109/cvpr.2007.383045 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094236874
156 rdf:type schema:CreativeWork
157 https://doi.org/10.1109/cvpr.2007.383229 schema:sameAs https://app.dimensions.ai/details/publication/pub.1077867063
158 rdf:type schema:CreativeWork
159 https://doi.org/10.1109/cvpr.2008.4587417 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095049126
160 rdf:type schema:CreativeWork
161 https://doi.org/10.1109/cvpr.2008.4587453 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094986810
162 rdf:type schema:CreativeWork
163 https://doi.org/10.1109/cvpr.2008.4587799 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093864237
164 rdf:type schema:CreativeWork
165 https://doi.org/10.1109/cvpr.2010.5539897 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094861969
166 rdf:type schema:CreativeWork
167 https://doi.org/10.1109/cvpr.2010.5540221 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094015870
168 rdf:type schema:CreativeWork
169 https://doi.org/10.1109/iccv.2003.1238354 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093621895
170 rdf:type schema:CreativeWork
171 https://doi.org/10.1109/iccv.2007.4408986 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094860556
172 rdf:type schema:CreativeWork
173 https://doi.org/10.1109/iccv.2009.5459211 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093296270
174 rdf:type schema:CreativeWork
175 https://doi.org/10.1109/iccv.2009.5459248 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094294309
176 rdf:type schema:CreativeWork
177 https://doi.org/10.1109/tpami.2006.200 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061743038
178 rdf:type schema:CreativeWork
179 https://doi.org/10.1109/tpami.2008.105 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061743467
180 rdf:type schema:CreativeWork
181 https://doi.org/10.5244/c.22.22 schema:sameAs https://app.dimensions.ai/details/publication/pub.1099325554
182 rdf:type schema:CreativeWork
 




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


...