Diagnosing Error in Object Detectors View Full Text


Ontology type: schema:Chapter      Open Access: True


Chapter Info

DATE

2012

AUTHORS

Derek Hoiem , Yodsawalai Chodpathumwan , Qieyun Dai

ABSTRACT

This paper shows how to analyze the influences of object characteristics on detection performance and the frequency and impact of different types of false positives. In particular, we examine effects of occlusion, size, aspect ratio, visibility of parts, viewpoint, localization error, and confusion with semantically similar objects, other labeled objects, and background. We analyze two classes of detectors: the Vedaldi et al. multiple kernel learning detector and different versions of the Felzenszwalb et al. detector. Our study shows that sensitivity to size, localization error, and confusion with similar objects are the most impactful forms of error. Our analysis also reveals that many different kinds of improvement are necessary to achieve large gains, making more detailed analysis essential for the progress of recognition research. By making our software and annotations available, we make it effortless for future researchers to perform similar analysis. More... »

PAGES

340-353

References to SciGraph publications

  • 2000-06. Evaluation of Interest Point Detectors in INTERNATIONAL JOURNAL OF COMPUTER VISION
  • 2010-10. A comparative evaluation of interest point detectors and local descriptors for visual SLAM in MACHINE VISION AND APPLICATIONS
  • 2010. Multiresolution Models for Object Detection in COMPUTER VISION – ECCV 2010
  • 2008. Searching the World’s Herbaria: A System for Visual Identification of Plant Species in COMPUTER VISION – ECCV 2008
  • 2010-06. The Pascal Visual Object Classes (VOC) Challenge in INTERNATIONAL JOURNAL OF COMPUTER VISION
  • Book

    TITLE

    Computer Vision – ECCV 2012

    ISBN

    978-3-642-33711-6
    978-3-642-33712-3

    Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1007/978-3-642-33712-3_25

    DOI

    http://dx.doi.org/10.1007/978-3-642-33712-3_25

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1027572846


    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/2008/1701", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Psychology", 
            "type": "DefinedTerm"
          }, 
          {
            "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/17", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Psychology and Cognitive Sciences", 
            "type": "DefinedTerm"
          }
        ], 
        "author": [
          {
            "affiliation": {
              "alternateName": "University of Illinois at Urbana Champaign", 
              "id": "https://www.grid.ac/institutes/grid.35403.31", 
              "name": [
                "Department of Computer Science, University of Illinois at Urbana-Champaign, USA"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Hoiem", 
            "givenName": "Derek", 
            "id": "sg:person.01302474045.37", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01302474045.37"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "University of Illinois at Urbana Champaign", 
              "id": "https://www.grid.ac/institutes/grid.35403.31", 
              "name": [
                "Department of Computer Science, University of Illinois at Urbana-Champaign, USA"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Chodpathumwan", 
            "givenName": "Yodsawalai", 
            "id": "sg:person.014547772355.99", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014547772355.99"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "University of Illinois at Urbana Champaign", 
              "id": "https://www.grid.ac/institutes/grid.35403.31", 
              "name": [
                "Department of Computer Science, University of Illinois at Urbana-Champaign, USA"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Dai", 
            "givenName": "Qieyun", 
            "id": "sg:person.01004205615.86", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01004205615.86"
            ], 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "sg:pub.10.1007/s11263-009-0275-4", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1014796149", 
              "https://doi.org/10.1007/s11263-009-0275-4"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s11263-009-0275-4", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1014796149", 
              "https://doi.org/10.1007/s11263-009-0275-4"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-540-88693-8_9", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1018648891", 
              "https://doi.org/10.1007/978-3-540-88693-8_9"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-540-88693-8_9", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1018648891", 
              "https://doi.org/10.1007/978-3-540-88693-8_9"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s00138-009-0195-x", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1024001053", 
              "https://doi.org/10.1007/s00138-009-0195-x"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s00138-009-0195-x", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1024001053", 
              "https://doi.org/10.1007/s00138-009-0195-x"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s00138-009-0195-x", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1024001053", 
              "https://doi.org/10.1007/s00138-009-0195-x"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-642-15561-1_18", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1028700063", 
              "https://doi.org/10.1007/978-3-642-15561-1_18"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-642-15561-1_18", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1028700063", 
              "https://doi.org/10.1007/978-3-642-15561-1_18"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1371/journal.pcbi.0040027", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1045861574"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1023/a:1008199403446", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1048406451", 
              "https://doi.org/10.1023/a:1008199403446"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tpami.2009.167", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061743745"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2009.5206532", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1093359846"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/iccv.2011.6126398", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1093601508"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2008.4587597", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1093614050"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/iccv.2009.5459207", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1093953720"
            ], 
            "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/cvpr.2011.5995347", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1094016389"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2009.5206631", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1094061126"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2000.855895", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1094232942"
            ], 
            "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/cvpr.2011.5995368", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1094538483"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2009.5206723", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1094680537"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/iccv.2009.5459183", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095015498"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/iccv.2005.74", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095161226"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2010.5540070", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095215209"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvprw.2009.5204220", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095393948"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvprw.2009.5204220", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095393948"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/afgr.2002.1004130", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095653154"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2007.383149", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095729121"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2012", 
        "datePublishedReg": "2012-01-01", 
        "description": "This paper shows how to analyze the influences of object characteristics on detection performance and the frequency and impact of different types of false positives. In particular, we examine effects of occlusion, size, aspect ratio, visibility of parts, viewpoint, localization error, and confusion with semantically similar objects, other labeled objects, and background. We analyze two classes of detectors: the Vedaldi et al. multiple kernel learning detector and different versions of the Felzenszwalb et al. detector. Our study shows that sensitivity to size, localization error, and confusion with similar objects are the most impactful forms of error. Our analysis also reveals that many different kinds of improvement are necessary to achieve large gains, making more detailed analysis essential for the progress of recognition research. By making our software and annotations available, we make it effortless for future researchers to perform similar analysis.", 
        "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.10.1007/978-3-642-33712-3_25", 
        "inLanguage": [
          "en"
        ], 
        "isAccessibleForFree": true, 
        "isFundedItemOf": [
          {
            "id": "sg:grant.3099649", 
            "type": "MonetaryGrant"
          }, 
          {
            "id": "sg:grant.3121438", 
            "type": "MonetaryGrant"
          }
        ], 
        "isPartOf": {
          "isbn": [
            "978-3-642-33711-6", 
            "978-3-642-33712-3"
          ], 
          "name": "Computer Vision \u2013 ECCV 2012", 
          "type": "Book"
        }, 
        "name": "Diagnosing Error in Object Detectors", 
        "pagination": "340-353", 
        "productId": [
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1007/978-3-642-33712-3_25"
            ]
          }, 
          {
            "name": "readcube_id", 
            "type": "PropertyValue", 
            "value": [
              "835978a90c3d525be1e36c9bb62398b93e678f8f51a3fc641a2f1ba4e4aa4c0c"
            ]
          }, 
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1027572846"
            ]
          }
        ], 
        "publisher": {
          "location": "Berlin, Heidelberg", 
          "name": "Springer Berlin Heidelberg", 
          "type": "Organisation"
        }, 
        "sameAs": [
          "https://doi.org/10.1007/978-3-642-33712-3_25", 
          "https://app.dimensions.ai/details/publication/pub.1027572846"
        ], 
        "sdDataset": "chapters", 
        "sdDatePublished": "2019-04-16T00:49", 
        "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_8700_00000260.jsonl", 
        "type": "Chapter", 
        "url": "http://link.springer.com/10.1007/978-3-642-33712-3_25"
      }
    ]
     

    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.10.1007/978-3-642-33712-3_25'

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

    curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-642-33712-3_25'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-642-33712-3_25'

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

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-642-33712-3_25'


     

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

    180 TRIPLES      23 PREDICATES      51 URIs      20 LITERALS      8 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1007/978-3-642-33712-3_25 schema:about anzsrc-for:17
    2 anzsrc-for:1701
    3 schema:author N4aedc8a2b8ab42fdad3c7df32d261404
    4 schema:citation sg:pub.10.1007/978-3-540-88693-8_9
    5 sg:pub.10.1007/978-3-642-15561-1_18
    6 sg:pub.10.1007/s00138-009-0195-x
    7 sg:pub.10.1007/s11263-009-0275-4
    8 sg:pub.10.1023/a:1008199403446
    9 https://doi.org/10.1109/afgr.2002.1004130
    10 https://doi.org/10.1109/cvpr.2000.855895
    11 https://doi.org/10.1109/cvpr.2005.177
    12 https://doi.org/10.1109/cvpr.2007.383045
    13 https://doi.org/10.1109/cvpr.2007.383149
    14 https://doi.org/10.1109/cvpr.2008.4587597
    15 https://doi.org/10.1109/cvpr.2009.5206532
    16 https://doi.org/10.1109/cvpr.2009.5206631
    17 https://doi.org/10.1109/cvpr.2009.5206723
    18 https://doi.org/10.1109/cvpr.2010.5540070
    19 https://doi.org/10.1109/cvpr.2011.5995347
    20 https://doi.org/10.1109/cvpr.2011.5995368
    21 https://doi.org/10.1109/cvprw.2009.5204220
    22 https://doi.org/10.1109/iccv.2005.74
    23 https://doi.org/10.1109/iccv.2009.5459183
    24 https://doi.org/10.1109/iccv.2009.5459207
    25 https://doi.org/10.1109/iccv.2011.6126398
    26 https://doi.org/10.1109/tpami.2009.167
    27 https://doi.org/10.1371/journal.pcbi.0040027
    28 schema:datePublished 2012
    29 schema:datePublishedReg 2012-01-01
    30 schema:description This paper shows how to analyze the influences of object characteristics on detection performance and the frequency and impact of different types of false positives. In particular, we examine effects of occlusion, size, aspect ratio, visibility of parts, viewpoint, localization error, and confusion with semantically similar objects, other labeled objects, and background. We analyze two classes of detectors: the Vedaldi et al. multiple kernel learning detector and different versions of the Felzenszwalb et al. detector. Our study shows that sensitivity to size, localization error, and confusion with similar objects are the most impactful forms of error. Our analysis also reveals that many different kinds of improvement are necessary to achieve large gains, making more detailed analysis essential for the progress of recognition research. By making our software and annotations available, we make it effortless for future researchers to perform similar analysis.
    31 schema:editor Na302d2ebc13a4269afcd121d33a46611
    32 schema:genre chapter
    33 schema:inLanguage en
    34 schema:isAccessibleForFree true
    35 schema:isPartOf N334eb3453a5342739e41683b5453fd28
    36 schema:name Diagnosing Error in Object Detectors
    37 schema:pagination 340-353
    38 schema:productId N3815bc303322438390d3d4de8f1826e7
    39 Nb9525fa1ddb648ae9ac1853ebe3d6c16
    40 Nf642a4a2156f441d8b9ab132e697dabb
    41 schema:publisher Nd6607ee0f8bb4eae966064cd03161b16
    42 schema:sameAs https://app.dimensions.ai/details/publication/pub.1027572846
    43 https://doi.org/10.1007/978-3-642-33712-3_25
    44 schema:sdDatePublished 2019-04-16T00:49
    45 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    46 schema:sdPublisher N5c1b086341cc49b3a96ed18c61cf545c
    47 schema:url http://link.springer.com/10.1007/978-3-642-33712-3_25
    48 sgo:license sg:explorer/license/
    49 sgo:sdDataset chapters
    50 rdf:type schema:Chapter
    51 N334eb3453a5342739e41683b5453fd28 schema:isbn 978-3-642-33711-6
    52 978-3-642-33712-3
    53 schema:name Computer Vision – ECCV 2012
    54 rdf:type schema:Book
    55 N3815bc303322438390d3d4de8f1826e7 schema:name readcube_id
    56 schema:value 835978a90c3d525be1e36c9bb62398b93e678f8f51a3fc641a2f1ba4e4aa4c0c
    57 rdf:type schema:PropertyValue
    58 N4aedc8a2b8ab42fdad3c7df32d261404 rdf:first sg:person.01302474045.37
    59 rdf:rest Ndddc146ffd5146c5a24525f7f63cd779
    60 N5c1b086341cc49b3a96ed18c61cf545c schema:name Springer Nature - SN SciGraph project
    61 rdf:type schema:Organization
    62 N62b5502a594d415589e25dd8acfcfb8f rdf:first Ncddc657340d64b1f87fa8ffdab942e35
    63 rdf:rest N99bb005fd6d14d1186a68600329c58aa
    64 N7757174859714894b20c7335b116ca32 schema:familyName Schmid
    65 schema:givenName Cordelia
    66 rdf:type schema:Person
    67 N99bb005fd6d14d1186a68600329c58aa rdf:first N9a4e8b8d1ad943a49cbaec1681750651
    68 rdf:rest Nb3e8e75c17a743c88634b45cc93f7dc7
    69 N9a4e8b8d1ad943a49cbaec1681750651 schema:familyName Sato
    70 schema:givenName Yoichi
    71 rdf:type schema:Person
    72 Na302d2ebc13a4269afcd121d33a46611 rdf:first Na4faa115d6d74455a2dd3e299ab49d63
    73 rdf:rest Nd13a302cd1e54d1a929c62f6859446f2
    74 Na4faa115d6d74455a2dd3e299ab49d63 schema:familyName Fitzgibbon
    75 schema:givenName Andrew
    76 rdf:type schema:Person
    77 Na6e8cbb6b09a46cfbcc176644f53c4c2 schema:familyName Lazebnik
    78 schema:givenName Svetlana
    79 rdf:type schema:Person
    80 Nb3e8e75c17a743c88634b45cc93f7dc7 rdf:first N7757174859714894b20c7335b116ca32
    81 rdf:rest rdf:nil
    82 Nb9525fa1ddb648ae9ac1853ebe3d6c16 schema:name doi
    83 schema:value 10.1007/978-3-642-33712-3_25
    84 rdf:type schema:PropertyValue
    85 Nccd575ec2c0e4446b7eb9f798ad9200a rdf:first sg:person.01004205615.86
    86 rdf:rest rdf:nil
    87 Ncddc657340d64b1f87fa8ffdab942e35 schema:familyName Perona
    88 schema:givenName Pietro
    89 rdf:type schema:Person
    90 Nd13a302cd1e54d1a929c62f6859446f2 rdf:first Na6e8cbb6b09a46cfbcc176644f53c4c2
    91 rdf:rest N62b5502a594d415589e25dd8acfcfb8f
    92 Nd6607ee0f8bb4eae966064cd03161b16 schema:location Berlin, Heidelberg
    93 schema:name Springer Berlin Heidelberg
    94 rdf:type schema:Organisation
    95 Ndddc146ffd5146c5a24525f7f63cd779 rdf:first sg:person.014547772355.99
    96 rdf:rest Nccd575ec2c0e4446b7eb9f798ad9200a
    97 Nf642a4a2156f441d8b9ab132e697dabb schema:name dimensions_id
    98 schema:value pub.1027572846
    99 rdf:type schema:PropertyValue
    100 anzsrc-for:17 schema:inDefinedTermSet anzsrc-for:
    101 schema:name Psychology and Cognitive Sciences
    102 rdf:type schema:DefinedTerm
    103 anzsrc-for:1701 schema:inDefinedTermSet anzsrc-for:
    104 schema:name Psychology
    105 rdf:type schema:DefinedTerm
    106 sg:grant.3099649 http://pending.schema.org/fundedItem sg:pub.10.1007/978-3-642-33712-3_25
    107 rdf:type schema:MonetaryGrant
    108 sg:grant.3121438 http://pending.schema.org/fundedItem sg:pub.10.1007/978-3-642-33712-3_25
    109 rdf:type schema:MonetaryGrant
    110 sg:person.01004205615.86 schema:affiliation https://www.grid.ac/institutes/grid.35403.31
    111 schema:familyName Dai
    112 schema:givenName Qieyun
    113 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01004205615.86
    114 rdf:type schema:Person
    115 sg:person.01302474045.37 schema:affiliation https://www.grid.ac/institutes/grid.35403.31
    116 schema:familyName Hoiem
    117 schema:givenName Derek
    118 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01302474045.37
    119 rdf:type schema:Person
    120 sg:person.014547772355.99 schema:affiliation https://www.grid.ac/institutes/grid.35403.31
    121 schema:familyName Chodpathumwan
    122 schema:givenName Yodsawalai
    123 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014547772355.99
    124 rdf:type schema:Person
    125 sg:pub.10.1007/978-3-540-88693-8_9 schema:sameAs https://app.dimensions.ai/details/publication/pub.1018648891
    126 https://doi.org/10.1007/978-3-540-88693-8_9
    127 rdf:type schema:CreativeWork
    128 sg:pub.10.1007/978-3-642-15561-1_18 schema:sameAs https://app.dimensions.ai/details/publication/pub.1028700063
    129 https://doi.org/10.1007/978-3-642-15561-1_18
    130 rdf:type schema:CreativeWork
    131 sg:pub.10.1007/s00138-009-0195-x schema:sameAs https://app.dimensions.ai/details/publication/pub.1024001053
    132 https://doi.org/10.1007/s00138-009-0195-x
    133 rdf:type schema:CreativeWork
    134 sg:pub.10.1007/s11263-009-0275-4 schema:sameAs https://app.dimensions.ai/details/publication/pub.1014796149
    135 https://doi.org/10.1007/s11263-009-0275-4
    136 rdf:type schema:CreativeWork
    137 sg:pub.10.1023/a:1008199403446 schema:sameAs https://app.dimensions.ai/details/publication/pub.1048406451
    138 https://doi.org/10.1023/a:1008199403446
    139 rdf:type schema:CreativeWork
    140 https://doi.org/10.1109/afgr.2002.1004130 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095653154
    141 rdf:type schema:CreativeWork
    142 https://doi.org/10.1109/cvpr.2000.855895 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094232942
    143 rdf:type schema:CreativeWork
    144 https://doi.org/10.1109/cvpr.2005.177 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093997066
    145 rdf:type schema:CreativeWork
    146 https://doi.org/10.1109/cvpr.2007.383045 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094236874
    147 rdf:type schema:CreativeWork
    148 https://doi.org/10.1109/cvpr.2007.383149 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095729121
    149 rdf:type schema:CreativeWork
    150 https://doi.org/10.1109/cvpr.2008.4587597 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093614050
    151 rdf:type schema:CreativeWork
    152 https://doi.org/10.1109/cvpr.2009.5206532 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093359846
    153 rdf:type schema:CreativeWork
    154 https://doi.org/10.1109/cvpr.2009.5206631 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094061126
    155 rdf:type schema:CreativeWork
    156 https://doi.org/10.1109/cvpr.2009.5206723 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094680537
    157 rdf:type schema:CreativeWork
    158 https://doi.org/10.1109/cvpr.2010.5540070 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095215209
    159 rdf:type schema:CreativeWork
    160 https://doi.org/10.1109/cvpr.2011.5995347 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094016389
    161 rdf:type schema:CreativeWork
    162 https://doi.org/10.1109/cvpr.2011.5995368 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094538483
    163 rdf:type schema:CreativeWork
    164 https://doi.org/10.1109/cvprw.2009.5204220 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095393948
    165 rdf:type schema:CreativeWork
    166 https://doi.org/10.1109/iccv.2005.74 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095161226
    167 rdf:type schema:CreativeWork
    168 https://doi.org/10.1109/iccv.2009.5459183 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095015498
    169 rdf:type schema:CreativeWork
    170 https://doi.org/10.1109/iccv.2009.5459207 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093953720
    171 rdf:type schema:CreativeWork
    172 https://doi.org/10.1109/iccv.2011.6126398 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093601508
    173 rdf:type schema:CreativeWork
    174 https://doi.org/10.1109/tpami.2009.167 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061743745
    175 rdf:type schema:CreativeWork
    176 https://doi.org/10.1371/journal.pcbi.0040027 schema:sameAs https://app.dimensions.ai/details/publication/pub.1045861574
    177 rdf:type schema:CreativeWork
    178 https://www.grid.ac/institutes/grid.35403.31 schema:alternateName University of Illinois at Urbana Champaign
    179 schema:name Department of Computer Science, University of Illinois at Urbana-Champaign, USA
    180 rdf:type schema:Organization
     




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


    ...