Scale & Affine Invariant Interest Point Detectors View Full Text


Ontology type: schema:ScholarlyArticle     


Article Info

DATE

2004-10

AUTHORS

Krystian Mikolajczyk, Cordelia Schmid

ABSTRACT

In this paper we propose a novel approach for detecting interest points invariant to scale and affine transformations. Our scale and affine invariant detectors are based on the following recent results: (1) Interest points extracted with the Harris detector can be adapted to affine transformations and give repeatable results (geometrically stable). (2) The characteristic scale of a local structure is indicated by a local extremum over scale of normalized derivatives (the Laplacian). (3) The affine shape of a point neighborhood is estimated based on the second moment matrix.Our scale invariant detector computes a multi-scale representation for the Harris interest point detector and then selects points at which a local measure (the Laplacian) is maximal over scales. This provides a set of distinctive points which are invariant to scale, rotation and translation as well as robust to illumination changes and limited changes of viewpoint. The characteristic scale determines a scale invariant region for each point. We extend the scale invariant detector to affine invariance by estimating the affine shape of a point neighborhood. An iterative algorithm modifies location, scale and neighborhood of each point and converges to affine invariant points. This method can deal with significant affine transformations including large scale changes. The characteristic scale and the affine shape of neighborhood determine an affine invariant region for each point.We present a comparative evaluation of different detectors and show that our approach provides better results than existing methods. The performance of our detector is also confirmed by excellent matching results; the image is described by a set of scale/affine invariant descriptors computed on the regions associated with our points. More... »

PAGES

63-86

References to SciGraph publications

  • 2002-04-29. Class-Specific, Top-Down Segmentation in COMPUTER VISION — ECCV 2002
  • 1994. A framework for low level feature extraction in COMPUTER VISION — ECCV '94
  • 1994. Direct estimation of local surface shape in a fixating binocular vision system in COMPUTER VISION — ECCV '94
  • 1997-11. Affine Morphological Multiscale Analysis of Corners and Multiple Junctions in INTERNATIONAL JOURNAL OF COMPUTER VISION
  • 1993-12. Detecting salient blob-like image structures and their scales with a scale-space primal sketch: A method for focus-of-attention in INTERNATIONAL JOURNAL OF COMPUTER VISION
  • 1999. Content-Based Image Retrieval Based on Local Affinely Invariant Regions in VISUAL INFORMATION AND INFORMATION SYSTEMS
  • 1998-11. Feature Detection with Automatic Scale Selection in INTERNATIONAL JOURNAL OF COMPUTER VISION
  • 1990. Finding geometric and relational structures in an image in COMPUTER VISION — ECCV 90
  • 2002-04-29. An Affine Invariant Interest Point Detector in COMPUTER VISION — ECCV 2002
  • 2002-04-29. Multi-view Matching for Unordered Image Sets, or “How Do I Organize My Holiday Snaps?” in COMPUTER VISION — ECCV 2002
  • 2001-06-22. Tracking of Multi-state Hand Models Using Particle Filtering and a Hierarchy of Multi-scale Image Features⋆ in SCALE-SPACE AND MORPHOLOGY IN COMPUTER VISION
  • 2000-06. Evaluation of Interest Point Detectors in INTERNATIONAL JOURNAL OF COMPUTER VISION
  • 1993-04. A computational approach for corner and vertex detection in INTERNATIONAL JOURNAL OF COMPUTER VISION
  • 2002-04-29. Combining Appearance and Topology for Wide Baseline Matching in COMPUTER VISION — ECCV 2002
  • Journal

    Related Patents

  • Image Analysis Method And System
  • A Method And A System For Image Feature Point Description
  • Device, System And Method For Automatic Detection Of Contractile Activity In An Image Frame
  • Method For Searching Visually Similar Images In Collection Of Reference Images Such As Road Image, Involves Determining Similarity Between Two Images Corresponding To Formation Of N-Grams Or Gapped N-Grams
  • Object Retrieval Using Visual Query Context
  • Device, System And Method For Automatic Detection Of Contractile Activity In An Image Frame
  • Local Bi-Gram Model For Object Recognition
  • Digital Video Content Fingerprinting Based On Scale Invariant Interest Region Detection With An Array Of Anisotropic Filters
  • Method And Apparatus For Gaze Point Mapping
  • Kidney Glomeruli Measurement Systems And Methods
  • Systems And Methods For Evaluating Robustness
  • Device, System And Method For Automatic Detection Of Contractile Activity In An Image Frame
  • Surgical Microscope
  • Tracking System With Fused Motion And Object Detection
  • Method, System, And Device For Learned Invariant Feature Transform For Computer Images
  • Systems And Methods For Topological Representation Of Geometric Context In An Image By Discrete Texture Traces
  • Embedded Optical Flow Features
  • Transfusive Image Manipulation
  • Apparatus And Method For Finding A Change In A Scene
  • Method For Pose Invariant Vessel Fingerprinting
  • Digital Video Content Fingerprinting Based On Scale Invariant Interest Region Detection With An Array Of Anisotropic Filters
  • Device, System And Method For Automatic Detection Of Contractile Activity In An Image Frame
  • Method And System For Annotating Video Content
  • Method For Dynamically Detecting The Fill Level Of A Container, Therefor, And System For Dynamically Monitoring The Fill Level Of A Plurality Of Containers
  • Systems And Methods For Evaluating Robustness Of Saliency Predictions Of Regions In A Scene
  • Ordinal And Spatial Local Feature Vector Based Image Representation
  • Method And Apparatus For Gaze Point Mapping
  • Transfusive Image Manipulation
  • Image Processing Apparatus, Image Processing Method, And Program
  • Media Fingerprinting And Identification System
  • Continuous Linear Dynamic Systems
  • Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1023/b:visi.0000027790.02288.f2

    DOI

    http://dx.doi.org/10.1023/b:visi.0000027790.02288.f2

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1024638466


    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/2008/08", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Information and Computing Sciences", 
            "type": "DefinedTerm"
          }, 
          {
            "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"
          }
        ], 
        "author": [
          {
            "affiliation": {
              "alternateName": "INRIA Rhne-Alpes GRAVIR-CNRS, 655 av. de l'Europe, 38330, Montbonnot, France", 
              "id": "http://www.grid.ac/institutes/None", 
              "name": [
                "INRIA Rhne-Alpes GRAVIR-CNRS, 655 av. de l'Europe, 38330, Montbonnot, France"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Mikolajczyk", 
            "givenName": "Krystian", 
            "id": "sg:person.011426512153.06", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011426512153.06"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "INRIA Rhne-Alpes GRAVIR-CNRS, 655 av. de l'Europe, 38330, Montbonnot, France", 
              "id": "http://www.grid.ac/institutes/None", 
              "name": [
                "INRIA Rhne-Alpes GRAVIR-CNRS, 655 av. de l'Europe, 38330, Montbonnot, France"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Schmid", 
            "givenName": "Cordelia", 
            "id": "sg:person.014001416002.35", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014001416002.35"
            ], 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "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": "sg:pub.10.1007/3-540-48762-x_61", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1048533486", 
              "https://doi.org/10.1007/3-540-48762-x_61"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/3-540-47969-4_5", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1050654059", 
              "https://doi.org/10.1007/3-540-47969-4_5"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/3-540-47969-4_28", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1037481186", 
              "https://doi.org/10.1007/3-540-47969-4_28"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/bf01420733", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1008241125", 
              "https://doi.org/10.1007/bf01420733"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/3-540-47778-0_6", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1047013349", 
              "https://doi.org/10.1007/3-540-47778-0_6"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/bfb0014886", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1031544293", 
              "https://doi.org/10.1007/bfb0014886"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/3-540-57956-7_40", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1031301274", 
              "https://doi.org/10.1007/3-540-57956-7_40"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1023/a:1007959616598", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1036604221", 
              "https://doi.org/10.1023/a:1007959616598"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/bf01469346", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1022603165", 
              "https://doi.org/10.1007/bf01469346"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1023/a:1008045108935", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1041767492", 
              "https://doi.org/10.1023/a:1008045108935"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/3-540-47969-4_9", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1046596731", 
              "https://doi.org/10.1007/3-540-47969-4_9"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/bfb0028370", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1023858761", 
              "https://doi.org/10.1007/bfb0028370"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/3-540-47967-8_8", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1026779540", 
              "https://doi.org/10.1007/3-540-47967-8_8"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2004-10", 
        "datePublishedReg": "2004-10-01", 
        "description": "In this paper we propose a novel approach for detecting interest points invariant to scale and affine transformations. Our scale and affine invariant detectors are based on the following recent results: (1) Interest points extracted with the Harris detector can be adapted to affine transformations and give repeatable results (geometrically stable). (2) The characteristic scale of a local structure is indicated by a local extremum over scale of normalized derivatives (the Laplacian). (3) The affine shape of a point neighborhood is estimated based on the second moment matrix.Our scale invariant detector computes a multi-scale representation for the Harris interest point detector and then selects points at which a local measure (the Laplacian) is maximal over scales. This provides a set of distinctive points which are invariant to scale, rotation and translation as well as robust to illumination changes and limited changes of viewpoint. The characteristic scale determines a scale invariant region for each point. We extend the scale invariant detector to affine invariance by estimating the affine shape of a point neighborhood. An iterative algorithm modifies location, scale and neighborhood of each point and converges to affine invariant points. This method can deal with significant affine transformations including large scale changes. The characteristic scale and the affine shape of neighborhood determine an affine invariant region for each point.We present a comparative evaluation of different detectors and show that our approach provides better results than existing methods. The performance of our detector is also confirmed by excellent matching results; the image is described by a set of scale/affine invariant descriptors computed on the regions associated with our points.", 
        "genre": "article", 
        "id": "sg:pub.10.1023/b:visi.0000027790.02288.f2", 
        "inLanguage": "en", 
        "isAccessibleForFree": false, 
        "isPartOf": [
          {
            "id": "sg:journal.1032807", 
            "issn": [
              "0920-5691", 
              "1573-1405"
            ], 
            "name": "International Journal of Computer Vision", 
            "publisher": "Springer Nature", 
            "type": "Periodical"
          }, 
          {
            "issueNumber": "1", 
            "type": "PublicationIssue"
          }, 
          {
            "type": "PublicationVolume", 
            "volumeNumber": "60"
          }
        ], 
        "keywords": [
          "invariant detector", 
          "affine shape", 
          "invariant regions", 
          "points invariant", 
          "invariants", 
          "affine transformation", 
          "recent results", 
          "characteristic scale", 
          "local extrema", 
          "normalized derivatives", 
          "neighborhood", 
          "second moment matrix", 
          "moment matrix", 
          "multi-scale representation", 
          "converges", 
          "affine invariant regions", 
          "affine invariant descriptors", 
          "novel approach", 
          "approach", 
          "transformation", 
          "results", 
          "point", 
          "local structure", 
          "extrema", 
          "derivatives", 
          "point neighborhood", 
          "matrix", 
          "representation", 
          "local measures", 
          "set", 
          "illumination changes", 
          "viewpoint", 
          "invariance", 
          "invariant points", 
          "good results", 
          "performance", 
          "matching results", 
          "invariant descriptors", 
          "scale", 
          "detector", 
          "interest points", 
          "structure", 
          "shape", 
          "interest point detector", 
          "point detector", 
          "measures", 
          "distinctive points", 
          "rotation", 
          "translation", 
          "limited changes", 
          "region", 
          "location", 
          "large scale changes", 
          "scale changes", 
          "comparative evaluation", 
          "evaluation", 
          "different detectors", 
          "descriptors", 
          "paper", 
          "repeatable results", 
          "changes", 
          "method", 
          "images", 
          "interest points invariant", 
          "affine invariant detectors", 
          "Harris detector", 
          "scale invariant detector", 
          "Harris interest point detector", 
          "scale invariant region", 
          "iterative algorithm modifies location", 
          "algorithm modifies location", 
          "modifies location", 
          "significant affine transformations", 
          "excellent matching results", 
          "scale/affine invariant descriptors", 
          "Affine Invariant Interest Point Detectors", 
          "Invariant Interest Point Detectors"
        ], 
        "name": "Scale & Affine Invariant Interest Point Detectors", 
        "pagination": "63-86", 
        "productId": [
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1024638466"
            ]
          }, 
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1023/b:visi.0000027790.02288.f2"
            ]
          }
        ], 
        "sameAs": [
          "https://doi.org/10.1023/b:visi.0000027790.02288.f2", 
          "https://app.dimensions.ai/details/publication/pub.1024638466"
        ], 
        "sdDataset": "articles", 
        "sdDatePublished": "2021-11-01T18:07", 
        "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
        "sdPublisher": {
          "name": "Springer Nature - SN SciGraph project", 
          "type": "Organization"
        }, 
        "sdSource": "s3://com-springernature-scigraph/baseset/20211101/entities/gbq_results/article/article_390.jsonl", 
        "type": "ScholarlyArticle", 
        "url": "https://doi.org/10.1023/b:visi.0000027790.02288.f2"
      }
    ]
     

    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.10.1023/b:visi.0000027790.02288.f2'

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

    curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1023/b:visi.0000027790.02288.f2'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1023/b:visi.0000027790.02288.f2'

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

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1023/b:visi.0000027790.02288.f2'


     

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

    198 TRIPLES      22 PREDICATES      117 URIs      95 LITERALS      6 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1023/b:visi.0000027790.02288.f2 schema:about anzsrc-for:08
    2 anzsrc-for:0801
    3 schema:author Nfe60cf92968e47b1833853c0b6408113
    4 schema:citation sg:pub.10.1007/3-540-47778-0_6
    5 sg:pub.10.1007/3-540-47967-8_8
    6 sg:pub.10.1007/3-540-47969-4_28
    7 sg:pub.10.1007/3-540-47969-4_5
    8 sg:pub.10.1007/3-540-47969-4_9
    9 sg:pub.10.1007/3-540-48762-x_61
    10 sg:pub.10.1007/3-540-57956-7_40
    11 sg:pub.10.1007/bf01420733
    12 sg:pub.10.1007/bf01469346
    13 sg:pub.10.1007/bfb0014886
    14 sg:pub.10.1007/bfb0028370
    15 sg:pub.10.1023/a:1007959616598
    16 sg:pub.10.1023/a:1008045108935
    17 sg:pub.10.1023/a:1008199403446
    18 schema:datePublished 2004-10
    19 schema:datePublishedReg 2004-10-01
    20 schema:description In this paper we propose a novel approach for detecting interest points invariant to scale and affine transformations. Our scale and affine invariant detectors are based on the following recent results: (1) Interest points extracted with the Harris detector can be adapted to affine transformations and give repeatable results (geometrically stable). (2) The characteristic scale of a local structure is indicated by a local extremum over scale of normalized derivatives (the Laplacian). (3) The affine shape of a point neighborhood is estimated based on the second moment matrix.Our scale invariant detector computes a multi-scale representation for the Harris interest point detector and then selects points at which a local measure (the Laplacian) is maximal over scales. This provides a set of distinctive points which are invariant to scale, rotation and translation as well as robust to illumination changes and limited changes of viewpoint. The characteristic scale determines a scale invariant region for each point. We extend the scale invariant detector to affine invariance by estimating the affine shape of a point neighborhood. An iterative algorithm modifies location, scale and neighborhood of each point and converges to affine invariant points. This method can deal with significant affine transformations including large scale changes. The characteristic scale and the affine shape of neighborhood determine an affine invariant region for each point.We present a comparative evaluation of different detectors and show that our approach provides better results than existing methods. The performance of our detector is also confirmed by excellent matching results; the image is described by a set of scale/affine invariant descriptors computed on the regions associated with our points.
    21 schema:genre article
    22 schema:inLanguage en
    23 schema:isAccessibleForFree false
    24 schema:isPartOf N1b01eef956024cfdbedbfac70663b62c
    25 Nc07769f6f424447a91b60a4653537091
    26 sg:journal.1032807
    27 schema:keywords Affine Invariant Interest Point Detectors
    28 Harris detector
    29 Harris interest point detector
    30 Invariant Interest Point Detectors
    31 affine invariant descriptors
    32 affine invariant detectors
    33 affine invariant regions
    34 affine shape
    35 affine transformation
    36 algorithm modifies location
    37 approach
    38 changes
    39 characteristic scale
    40 comparative evaluation
    41 converges
    42 derivatives
    43 descriptors
    44 detector
    45 different detectors
    46 distinctive points
    47 evaluation
    48 excellent matching results
    49 extrema
    50 good results
    51 illumination changes
    52 images
    53 interest point detector
    54 interest points
    55 interest points invariant
    56 invariance
    57 invariant descriptors
    58 invariant detector
    59 invariant points
    60 invariant regions
    61 invariants
    62 iterative algorithm modifies location
    63 large scale changes
    64 limited changes
    65 local extrema
    66 local measures
    67 local structure
    68 location
    69 matching results
    70 matrix
    71 measures
    72 method
    73 modifies location
    74 moment matrix
    75 multi-scale representation
    76 neighborhood
    77 normalized derivatives
    78 novel approach
    79 paper
    80 performance
    81 point
    82 point detector
    83 point neighborhood
    84 points invariant
    85 recent results
    86 region
    87 repeatable results
    88 representation
    89 results
    90 rotation
    91 scale
    92 scale changes
    93 scale invariant detector
    94 scale invariant region
    95 scale/affine invariant descriptors
    96 second moment matrix
    97 set
    98 shape
    99 significant affine transformations
    100 structure
    101 transformation
    102 translation
    103 viewpoint
    104 schema:name Scale & Affine Invariant Interest Point Detectors
    105 schema:pagination 63-86
    106 schema:productId Nb1d78353f07c4c32affbf2f1454cff76
    107 Nf01bb0f8256d43888b5ce5933597d8d7
    108 schema:sameAs https://app.dimensions.ai/details/publication/pub.1024638466
    109 https://doi.org/10.1023/b:visi.0000027790.02288.f2
    110 schema:sdDatePublished 2021-11-01T18:07
    111 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    112 schema:sdPublisher N6b7a5a06913843f09e645f1dd9d8a931
    113 schema:url https://doi.org/10.1023/b:visi.0000027790.02288.f2
    114 sgo:license sg:explorer/license/
    115 sgo:sdDataset articles
    116 rdf:type schema:ScholarlyArticle
    117 N1b01eef956024cfdbedbfac70663b62c schema:volumeNumber 60
    118 rdf:type schema:PublicationVolume
    119 N3984b51d02be488b90afb90d1fbbe32b rdf:first sg:person.014001416002.35
    120 rdf:rest rdf:nil
    121 N6b7a5a06913843f09e645f1dd9d8a931 schema:name Springer Nature - SN SciGraph project
    122 rdf:type schema:Organization
    123 Nb1d78353f07c4c32affbf2f1454cff76 schema:name dimensions_id
    124 schema:value pub.1024638466
    125 rdf:type schema:PropertyValue
    126 Nc07769f6f424447a91b60a4653537091 schema:issueNumber 1
    127 rdf:type schema:PublicationIssue
    128 Nf01bb0f8256d43888b5ce5933597d8d7 schema:name doi
    129 schema:value 10.1023/b:visi.0000027790.02288.f2
    130 rdf:type schema:PropertyValue
    131 Nfe60cf92968e47b1833853c0b6408113 rdf:first sg:person.011426512153.06
    132 rdf:rest N3984b51d02be488b90afb90d1fbbe32b
    133 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
    134 schema:name Information and Computing Sciences
    135 rdf:type schema:DefinedTerm
    136 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
    137 schema:name Artificial Intelligence and Image Processing
    138 rdf:type schema:DefinedTerm
    139 sg:journal.1032807 schema:issn 0920-5691
    140 1573-1405
    141 schema:name International Journal of Computer Vision
    142 schema:publisher Springer Nature
    143 rdf:type schema:Periodical
    144 sg:person.011426512153.06 schema:affiliation grid-institutes:None
    145 schema:familyName Mikolajczyk
    146 schema:givenName Krystian
    147 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011426512153.06
    148 rdf:type schema:Person
    149 sg:person.014001416002.35 schema:affiliation grid-institutes:None
    150 schema:familyName Schmid
    151 schema:givenName Cordelia
    152 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014001416002.35
    153 rdf:type schema:Person
    154 sg:pub.10.1007/3-540-47778-0_6 schema:sameAs https://app.dimensions.ai/details/publication/pub.1047013349
    155 https://doi.org/10.1007/3-540-47778-0_6
    156 rdf:type schema:CreativeWork
    157 sg:pub.10.1007/3-540-47967-8_8 schema:sameAs https://app.dimensions.ai/details/publication/pub.1026779540
    158 https://doi.org/10.1007/3-540-47967-8_8
    159 rdf:type schema:CreativeWork
    160 sg:pub.10.1007/3-540-47969-4_28 schema:sameAs https://app.dimensions.ai/details/publication/pub.1037481186
    161 https://doi.org/10.1007/3-540-47969-4_28
    162 rdf:type schema:CreativeWork
    163 sg:pub.10.1007/3-540-47969-4_5 schema:sameAs https://app.dimensions.ai/details/publication/pub.1050654059
    164 https://doi.org/10.1007/3-540-47969-4_5
    165 rdf:type schema:CreativeWork
    166 sg:pub.10.1007/3-540-47969-4_9 schema:sameAs https://app.dimensions.ai/details/publication/pub.1046596731
    167 https://doi.org/10.1007/3-540-47969-4_9
    168 rdf:type schema:CreativeWork
    169 sg:pub.10.1007/3-540-48762-x_61 schema:sameAs https://app.dimensions.ai/details/publication/pub.1048533486
    170 https://doi.org/10.1007/3-540-48762-x_61
    171 rdf:type schema:CreativeWork
    172 sg:pub.10.1007/3-540-57956-7_40 schema:sameAs https://app.dimensions.ai/details/publication/pub.1031301274
    173 https://doi.org/10.1007/3-540-57956-7_40
    174 rdf:type schema:CreativeWork
    175 sg:pub.10.1007/bf01420733 schema:sameAs https://app.dimensions.ai/details/publication/pub.1008241125
    176 https://doi.org/10.1007/bf01420733
    177 rdf:type schema:CreativeWork
    178 sg:pub.10.1007/bf01469346 schema:sameAs https://app.dimensions.ai/details/publication/pub.1022603165
    179 https://doi.org/10.1007/bf01469346
    180 rdf:type schema:CreativeWork
    181 sg:pub.10.1007/bfb0014886 schema:sameAs https://app.dimensions.ai/details/publication/pub.1031544293
    182 https://doi.org/10.1007/bfb0014886
    183 rdf:type schema:CreativeWork
    184 sg:pub.10.1007/bfb0028370 schema:sameAs https://app.dimensions.ai/details/publication/pub.1023858761
    185 https://doi.org/10.1007/bfb0028370
    186 rdf:type schema:CreativeWork
    187 sg:pub.10.1023/a:1007959616598 schema:sameAs https://app.dimensions.ai/details/publication/pub.1036604221
    188 https://doi.org/10.1023/a:1007959616598
    189 rdf:type schema:CreativeWork
    190 sg:pub.10.1023/a:1008045108935 schema:sameAs https://app.dimensions.ai/details/publication/pub.1041767492
    191 https://doi.org/10.1023/a:1008045108935
    192 rdf:type schema:CreativeWork
    193 sg:pub.10.1023/a:1008199403446 schema:sameAs https://app.dimensions.ai/details/publication/pub.1048406451
    194 https://doi.org/10.1023/a:1008199403446
    195 rdf:type schema:CreativeWork
    196 grid-institutes:None schema:alternateName INRIA Rhne-Alpes GRAVIR-CNRS, 655 av. de l'Europe, 38330, Montbonnot, France
    197 schema:name INRIA Rhne-Alpes GRAVIR-CNRS, 655 av. de l'Europe, 38330, Montbonnot, France
    198 rdf:type schema:Organization
     




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


    ...