Hard negative mining for correlation filters in visual tracking View Full Text


Ontology type: schema:ScholarlyArticle     


Article Info

DATE

2019-01-16

AUTHORS

Zhuojin Sun, Yong Wang, Robert Laganière

ABSTRACT

Visual tracking is a fundamental computer vision task. Recent years have seen many tracking methods based on correlation filters exhibiting excellent performance. The strength of these methods comes from their ability to efficiently learn changes of the target appearance over time. A fundamental drawback to these methods is that the background of the object is not modeled over time which results in suboptimal results. In this paper, we propose a robust tracking method in which a hard negative mining scheme is employed in each frame. In addition, a target verification strategy is developed by introducing a peak signal-to-noise ratio (PSNR) criterion. The proposed method achieves strong tracking results, while maintaining a real-time speed of 30 frame per second without further optimization. Extensive experiments over multiple tracking datasets show the superior accuracy of our tracker compared to state-of-the-art methods including those based on deep learning features. More... »

PAGES

1-20

References to SciGraph publications

  • 2014. Fast Visual Tracking via Dense Spatio-temporal Context Learning in COMPUTER VISION – ECCV 2014
  • 2016. Fully-Convolutional Siamese Networks for Object Tracking in COMPUTER VISION – ECCV 2016 WORKSHOPS
  • 2016. Beyond Correlation Filters: Learning Continuous Convolution Operators for Visual Tracking in COMPUTER VISION – ECCV 2016
  • 2008-05. Incremental Learning for Robust Visual Tracking in INTERNATIONAL JOURNAL OF COMPUTER VISION
  • 2016. A Benchmark and Simulator for UAV Tracking in COMPUTER VISION – ECCV 2016
  • 2014. MEEM: Robust Tracking via Multiple Experts Using Entropy Minimization in COMPUTER VISION – ECCV 2014
  • 2012. Exploiting the Circulant Structure of Tracking-by-Detection with Kernels in COMPUTER VISION – ECCV 2012
  • 2015. A Scale Adaptive Kernel Correlation Filter Tracker with Feature Integration in COMPUTER VISION - ECCV 2014 WORKSHOPS
  • Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1007/s00138-019-01004-0

    DOI

    http://dx.doi.org/10.1007/s00138-019-01004-0

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1111455656


    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": [
                "Yuneec Aviation Technology, Shanghai, China"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Sun", 
            "givenName": "Zhuojin", 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "name": [
                "Yuneec Aviation Technology, Shanghai, China"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Wang", 
            "givenName": "Yong", 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "University of Ottawa", 
              "id": "https://www.grid.ac/institutes/grid.28046.38", 
              "name": [
                "School of Electrical Engineering and Computer Science, University of Ottawa, Ottawa, Canada"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Lagani\u00e8re", 
            "givenName": "Robert", 
            "id": "sg:person.01144533722.06", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01144533722.06"
            ], 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "sg:pub.10.1007/978-3-319-10599-4_13", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1010891849", 
              "https://doi.org/10.1007/978-3-319-10599-4_13"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-319-16181-5_18", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1012026564", 
              "https://doi.org/10.1007/978-3-319-16181-5_18"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-319-46454-1_29", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1019790801", 
              "https://doi.org/10.1007/978-3-319-46454-1_29"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s11263-007-0075-7", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1026285409", 
              "https://doi.org/10.1007/s11263-007-0075-7"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-319-10602-1_9", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1032277466", 
              "https://doi.org/10.1007/978-3-319-10602-1_9"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-319-46448-0_27", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1035710231", 
              "https://doi.org/10.1007/978-3-319-46448-0_27"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tpami.2013.230", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1038206748"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-642-33765-9_50", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1039884592", 
              "https://doi.org/10.1007/978-3-642-33765-9_50"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-319-48881-3_56", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1043811270", 
              "https://doi.org/10.1007/978-3-319-48881-3_56"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/34.655647", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061156724"
            ], 
            "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/tpami.2011.239", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061744121"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tpami.2014.2345390", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061744716"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tpami.2014.2388226", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061744808"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tpami.2016.2609928", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061745160"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1561/2200000016", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1068001405"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2016.89", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1093700510"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2010.5539960", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1093797592"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/iccv.2013.381", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1093822423"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/iccv.2015.352", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1093854374"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/iccvw.2015.83", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1093858919"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2014.143", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1093905082"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2015.7298675", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1094287264"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/iccv.2015.490", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095102108"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2016.465", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095213890"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2016.158", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095303030"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2015.7299094", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095443328"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/iccv.2011.6126251", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095713809"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2016.466", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095713935"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/iccv.2015.320", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095823695"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2015.7299177", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095825326"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2017.513", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095835929"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2017.733", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095837415"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.5244/c.23.91", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1099325712"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.5244/c.20.6", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1099325873"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.5244/c.28.65", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1099426743"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/iccv.2017.129", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1100060092"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2019-01-16", 
        "datePublishedReg": "2019-01-16", 
        "description": "Visual tracking is a fundamental computer vision task. Recent years have seen many tracking methods based on correlation filters exhibiting excellent performance. The strength of these methods comes from their ability to efficiently learn changes of the target appearance over time. A fundamental drawback to these methods is that the background of the object is not modeled over time which results in suboptimal results. In this paper, we propose a robust tracking method in which a hard negative mining scheme is employed in each frame. In addition, a target verification strategy is developed by introducing a peak signal-to-noise ratio (PSNR) criterion. The proposed method achieves strong tracking results, while maintaining a real-time speed of 30 frame per second without further optimization. Extensive experiments over multiple tracking datasets show the superior accuracy of our tracker compared to state-of-the-art methods including those based on deep learning features.", 
        "genre": "research_article", 
        "id": "sg:pub.10.1007/s00138-019-01004-0", 
        "inLanguage": [
          "en"
        ], 
        "isAccessibleForFree": false, 
        "isPartOf": [
          {
            "id": "sg:journal.1045266", 
            "issn": [
              "0932-8092", 
              "1432-1769"
            ], 
            "name": "Machine Vision and Applications", 
            "type": "Periodical"
          }
        ], 
        "name": "Hard negative mining for correlation filters in visual tracking", 
        "pagination": "1-20", 
        "productId": [
          {
            "name": "readcube_id", 
            "type": "PropertyValue", 
            "value": [
              "9be1ef5b4ac2c486b5b1c0902f4d4de9b55befa23aa93da76796179b65e56a23"
            ]
          }, 
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1007/s00138-019-01004-0"
            ]
          }, 
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1111455656"
            ]
          }
        ], 
        "sameAs": [
          "https://doi.org/10.1007/s00138-019-01004-0", 
          "https://app.dimensions.ai/details/publication/pub.1111455656"
        ], 
        "sdDataset": "articles", 
        "sdDatePublished": "2019-04-11T08:41", 
        "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/v90/0000000321_0000000321/records_74902_00000000.jsonl", 
        "type": "ScholarlyArticle", 
        "url": "https://link.springer.com/10.1007%2Fs00138-019-01004-0"
      }
    ]
     

    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/s00138-019-01004-0'

    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/s00138-019-01004-0'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/s00138-019-01004-0'

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

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/s00138-019-01004-0'


     

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

    190 TRIPLES      21 PREDICATES      61 URIs      16 LITERALS      5 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1007/s00138-019-01004-0 schema:about anzsrc-for:08
    2 anzsrc-for:0801
    3 schema:author N1ebb7140c04a40648f0386076fa80890
    4 schema:citation sg:pub.10.1007/978-3-319-10599-4_13
    5 sg:pub.10.1007/978-3-319-10602-1_9
    6 sg:pub.10.1007/978-3-319-16181-5_18
    7 sg:pub.10.1007/978-3-319-46448-0_27
    8 sg:pub.10.1007/978-3-319-46454-1_29
    9 sg:pub.10.1007/978-3-319-48881-3_56
    10 sg:pub.10.1007/978-3-642-33765-9_50
    11 sg:pub.10.1007/s11263-007-0075-7
    12 https://doi.org/10.1109/34.655647
    13 https://doi.org/10.1109/cvpr.2010.5539960
    14 https://doi.org/10.1109/cvpr.2014.143
    15 https://doi.org/10.1109/cvpr.2015.7298675
    16 https://doi.org/10.1109/cvpr.2015.7299094
    17 https://doi.org/10.1109/cvpr.2015.7299177
    18 https://doi.org/10.1109/cvpr.2016.158
    19 https://doi.org/10.1109/cvpr.2016.465
    20 https://doi.org/10.1109/cvpr.2016.466
    21 https://doi.org/10.1109/cvpr.2016.89
    22 https://doi.org/10.1109/cvpr.2017.513
    23 https://doi.org/10.1109/cvpr.2017.733
    24 https://doi.org/10.1109/iccv.2011.6126251
    25 https://doi.org/10.1109/iccv.2013.381
    26 https://doi.org/10.1109/iccv.2015.320
    27 https://doi.org/10.1109/iccv.2015.352
    28 https://doi.org/10.1109/iccv.2015.490
    29 https://doi.org/10.1109/iccv.2017.129
    30 https://doi.org/10.1109/iccvw.2015.83
    31 https://doi.org/10.1109/tpami.2009.167
    32 https://doi.org/10.1109/tpami.2011.239
    33 https://doi.org/10.1109/tpami.2013.230
    34 https://doi.org/10.1109/tpami.2014.2345390
    35 https://doi.org/10.1109/tpami.2014.2388226
    36 https://doi.org/10.1109/tpami.2016.2609928
    37 https://doi.org/10.1561/2200000016
    38 https://doi.org/10.5244/c.20.6
    39 https://doi.org/10.5244/c.23.91
    40 https://doi.org/10.5244/c.28.65
    41 schema:datePublished 2019-01-16
    42 schema:datePublishedReg 2019-01-16
    43 schema:description Visual tracking is a fundamental computer vision task. Recent years have seen many tracking methods based on correlation filters exhibiting excellent performance. The strength of these methods comes from their ability to efficiently learn changes of the target appearance over time. A fundamental drawback to these methods is that the background of the object is not modeled over time which results in suboptimal results. In this paper, we propose a robust tracking method in which a hard negative mining scheme is employed in each frame. In addition, a target verification strategy is developed by introducing a peak signal-to-noise ratio (PSNR) criterion. The proposed method achieves strong tracking results, while maintaining a real-time speed of 30 frame per second without further optimization. Extensive experiments over multiple tracking datasets show the superior accuracy of our tracker compared to state-of-the-art methods including those based on deep learning features.
    44 schema:genre research_article
    45 schema:inLanguage en
    46 schema:isAccessibleForFree false
    47 schema:isPartOf sg:journal.1045266
    48 schema:name Hard negative mining for correlation filters in visual tracking
    49 schema:pagination 1-20
    50 schema:productId N58cd8e0d4c8549b381f05d2c7dc6b94b
    51 N971b7af2e494411cbbe21d7f762ef32f
    52 Nec3d3d0e4a4545a6be6d97d6dcb7fcf7
    53 schema:sameAs https://app.dimensions.ai/details/publication/pub.1111455656
    54 https://doi.org/10.1007/s00138-019-01004-0
    55 schema:sdDatePublished 2019-04-11T08:41
    56 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    57 schema:sdPublisher N1e08e946bd384951849077a3ba154eca
    58 schema:url https://link.springer.com/10.1007%2Fs00138-019-01004-0
    59 sgo:license sg:explorer/license/
    60 sgo:sdDataset articles
    61 rdf:type schema:ScholarlyArticle
    62 N07f20782fcd6465292089aeb94a7c8c6 schema:affiliation Neecd651c90724f77a71fb0c64b78d05d
    63 schema:familyName Wang
    64 schema:givenName Yong
    65 rdf:type schema:Person
    66 N1e08e946bd384951849077a3ba154eca schema:name Springer Nature - SN SciGraph project
    67 rdf:type schema:Organization
    68 N1ebb7140c04a40648f0386076fa80890 rdf:first Nb6765283fa6c46d8b7e3637c9017d1d8
    69 rdf:rest Na5ac94d8494b419f8b79db54f54cd021
    70 N2abdeb19c4f54df891cd630a4c489304 rdf:first sg:person.01144533722.06
    71 rdf:rest rdf:nil
    72 N58cd8e0d4c8549b381f05d2c7dc6b94b schema:name readcube_id
    73 schema:value 9be1ef5b4ac2c486b5b1c0902f4d4de9b55befa23aa93da76796179b65e56a23
    74 rdf:type schema:PropertyValue
    75 N971b7af2e494411cbbe21d7f762ef32f schema:name doi
    76 schema:value 10.1007/s00138-019-01004-0
    77 rdf:type schema:PropertyValue
    78 Na1448f3739e24dd1adbd65c439650427 schema:name Yuneec Aviation Technology, Shanghai, China
    79 rdf:type schema:Organization
    80 Na5ac94d8494b419f8b79db54f54cd021 rdf:first N07f20782fcd6465292089aeb94a7c8c6
    81 rdf:rest N2abdeb19c4f54df891cd630a4c489304
    82 Nb6765283fa6c46d8b7e3637c9017d1d8 schema:affiliation Na1448f3739e24dd1adbd65c439650427
    83 schema:familyName Sun
    84 schema:givenName Zhuojin
    85 rdf:type schema:Person
    86 Nec3d3d0e4a4545a6be6d97d6dcb7fcf7 schema:name dimensions_id
    87 schema:value pub.1111455656
    88 rdf:type schema:PropertyValue
    89 Neecd651c90724f77a71fb0c64b78d05d schema:name Yuneec Aviation Technology, Shanghai, China
    90 rdf:type schema:Organization
    91 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
    92 schema:name Information and Computing Sciences
    93 rdf:type schema:DefinedTerm
    94 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
    95 schema:name Artificial Intelligence and Image Processing
    96 rdf:type schema:DefinedTerm
    97 sg:journal.1045266 schema:issn 0932-8092
    98 1432-1769
    99 schema:name Machine Vision and Applications
    100 rdf:type schema:Periodical
    101 sg:person.01144533722.06 schema:affiliation https://www.grid.ac/institutes/grid.28046.38
    102 schema:familyName Laganière
    103 schema:givenName Robert
    104 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01144533722.06
    105 rdf:type schema:Person
    106 sg:pub.10.1007/978-3-319-10599-4_13 schema:sameAs https://app.dimensions.ai/details/publication/pub.1010891849
    107 https://doi.org/10.1007/978-3-319-10599-4_13
    108 rdf:type schema:CreativeWork
    109 sg:pub.10.1007/978-3-319-10602-1_9 schema:sameAs https://app.dimensions.ai/details/publication/pub.1032277466
    110 https://doi.org/10.1007/978-3-319-10602-1_9
    111 rdf:type schema:CreativeWork
    112 sg:pub.10.1007/978-3-319-16181-5_18 schema:sameAs https://app.dimensions.ai/details/publication/pub.1012026564
    113 https://doi.org/10.1007/978-3-319-16181-5_18
    114 rdf:type schema:CreativeWork
    115 sg:pub.10.1007/978-3-319-46448-0_27 schema:sameAs https://app.dimensions.ai/details/publication/pub.1035710231
    116 https://doi.org/10.1007/978-3-319-46448-0_27
    117 rdf:type schema:CreativeWork
    118 sg:pub.10.1007/978-3-319-46454-1_29 schema:sameAs https://app.dimensions.ai/details/publication/pub.1019790801
    119 https://doi.org/10.1007/978-3-319-46454-1_29
    120 rdf:type schema:CreativeWork
    121 sg:pub.10.1007/978-3-319-48881-3_56 schema:sameAs https://app.dimensions.ai/details/publication/pub.1043811270
    122 https://doi.org/10.1007/978-3-319-48881-3_56
    123 rdf:type schema:CreativeWork
    124 sg:pub.10.1007/978-3-642-33765-9_50 schema:sameAs https://app.dimensions.ai/details/publication/pub.1039884592
    125 https://doi.org/10.1007/978-3-642-33765-9_50
    126 rdf:type schema:CreativeWork
    127 sg:pub.10.1007/s11263-007-0075-7 schema:sameAs https://app.dimensions.ai/details/publication/pub.1026285409
    128 https://doi.org/10.1007/s11263-007-0075-7
    129 rdf:type schema:CreativeWork
    130 https://doi.org/10.1109/34.655647 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061156724
    131 rdf:type schema:CreativeWork
    132 https://doi.org/10.1109/cvpr.2010.5539960 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093797592
    133 rdf:type schema:CreativeWork
    134 https://doi.org/10.1109/cvpr.2014.143 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093905082
    135 rdf:type schema:CreativeWork
    136 https://doi.org/10.1109/cvpr.2015.7298675 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094287264
    137 rdf:type schema:CreativeWork
    138 https://doi.org/10.1109/cvpr.2015.7299094 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095443328
    139 rdf:type schema:CreativeWork
    140 https://doi.org/10.1109/cvpr.2015.7299177 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095825326
    141 rdf:type schema:CreativeWork
    142 https://doi.org/10.1109/cvpr.2016.158 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095303030
    143 rdf:type schema:CreativeWork
    144 https://doi.org/10.1109/cvpr.2016.465 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095213890
    145 rdf:type schema:CreativeWork
    146 https://doi.org/10.1109/cvpr.2016.466 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095713935
    147 rdf:type schema:CreativeWork
    148 https://doi.org/10.1109/cvpr.2016.89 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093700510
    149 rdf:type schema:CreativeWork
    150 https://doi.org/10.1109/cvpr.2017.513 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095835929
    151 rdf:type schema:CreativeWork
    152 https://doi.org/10.1109/cvpr.2017.733 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095837415
    153 rdf:type schema:CreativeWork
    154 https://doi.org/10.1109/iccv.2011.6126251 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095713809
    155 rdf:type schema:CreativeWork
    156 https://doi.org/10.1109/iccv.2013.381 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093822423
    157 rdf:type schema:CreativeWork
    158 https://doi.org/10.1109/iccv.2015.320 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095823695
    159 rdf:type schema:CreativeWork
    160 https://doi.org/10.1109/iccv.2015.352 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093854374
    161 rdf:type schema:CreativeWork
    162 https://doi.org/10.1109/iccv.2015.490 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095102108
    163 rdf:type schema:CreativeWork
    164 https://doi.org/10.1109/iccv.2017.129 schema:sameAs https://app.dimensions.ai/details/publication/pub.1100060092
    165 rdf:type schema:CreativeWork
    166 https://doi.org/10.1109/iccvw.2015.83 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093858919
    167 rdf:type schema:CreativeWork
    168 https://doi.org/10.1109/tpami.2009.167 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061743745
    169 rdf:type schema:CreativeWork
    170 https://doi.org/10.1109/tpami.2011.239 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061744121
    171 rdf:type schema:CreativeWork
    172 https://doi.org/10.1109/tpami.2013.230 schema:sameAs https://app.dimensions.ai/details/publication/pub.1038206748
    173 rdf:type schema:CreativeWork
    174 https://doi.org/10.1109/tpami.2014.2345390 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061744716
    175 rdf:type schema:CreativeWork
    176 https://doi.org/10.1109/tpami.2014.2388226 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061744808
    177 rdf:type schema:CreativeWork
    178 https://doi.org/10.1109/tpami.2016.2609928 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061745160
    179 rdf:type schema:CreativeWork
    180 https://doi.org/10.1561/2200000016 schema:sameAs https://app.dimensions.ai/details/publication/pub.1068001405
    181 rdf:type schema:CreativeWork
    182 https://doi.org/10.5244/c.20.6 schema:sameAs https://app.dimensions.ai/details/publication/pub.1099325873
    183 rdf:type schema:CreativeWork
    184 https://doi.org/10.5244/c.23.91 schema:sameAs https://app.dimensions.ai/details/publication/pub.1099325712
    185 rdf:type schema:CreativeWork
    186 https://doi.org/10.5244/c.28.65 schema:sameAs https://app.dimensions.ai/details/publication/pub.1099426743
    187 rdf:type schema:CreativeWork
    188 https://www.grid.ac/institutes/grid.28046.38 schema:alternateName University of Ottawa
    189 schema:name School of Electrical Engineering and Computer Science, University of Ottawa, Ottawa, Canada
    190 rdf:type schema:Organization
     




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


    ...