Interactively Co-segmentating Topically Related Images with Intelligent Scribble Guidance View Full Text


Ontology type: schema:ScholarlyArticle     


Article Info

DATE

2011-07

AUTHORS

Dhruv Batra, Adarsh Kowdle, Devi Parikh, Jiebo Luo, Tsuhan Chen

ABSTRACT

We present an algorithm for Interactive Co-segmentation of a foreground object from a group of related images. While previous works in co-segmentation have focussed on unsupervised co-segmentation, we use successful ideas from the interactive object-cutout literature. We develop an algorithm that allows users to decide what foreground is, and then guide the output of the co-segmentation algorithm towards it via scribbles. Interestingly, keeping a user in the loop leads to simpler and highly parallelizable energy functions, allowing us to work with significantly more images per group. However, unlike the interactive single-image counterpart, a user cannot be expected to exhaustively examine all cutouts (from tens of images) returned by the system to make corrections. Hence, we propose iCoseg, an automatic recommendation system that intelligently recommends where the user should scribble next. We introduce and make publicly available the largest co-segmentation dataset yet, the CMU-Cornell iCoseg dataset, with 38 groups, 643 images, and pixelwise hand-annotated groundtruth. Through machine experiments and real user studies with our developed interface, we show that iCoseg can intelligently recommend regions to scribble on, and users following these recommendations can achieve good quality cutouts with significantly lower time and effort than exhaustively examining all cutouts. More... »

PAGES

273-292

References to SciGraph publications

  • 2010. Cosegmentation Revisited: Models and Optimization in COMPUTER VISION – ECCV 2010
  • 1998. Contour continuity in region based image segmentation in COMPUTER VISION — ECCV'98
  • 2008. Towards Scalable Dataset Construction: An Active Learning Approach in COMPUTER VISION – ECCV 2008
  • 2008. GeoS: Geodesic Image Segmentation in COMPUTER VISION – ECCV 2008
  • 2006. Shape-from-Silhouette with Two Mirrors and an Uncalibrated Camera in COMPUTER VISION – ECCV 2006
  • 2006. Inducing Semantic Segmentation from an Example in COMPUTER VISION – ACCV 2006
  • 1998. Automatic 3D Model Construction for Turn-Table Sequences in 3D STRUCTURE FROM MULTIPLE IMAGES OF LARGE-SCALE ENVIRONMENTS
  • 2007. Co-segmentation of Image Pairs with Quadratic Global Constraint in MRFs in COMPUTER VISION – ACCV 2007
  • Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1007/s11263-010-0415-x

    DOI

    http://dx.doi.org/10.1007/s11263-010-0415-x

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1051801565


    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": {
              "alternateName": "Carnegie Mellon University", 
              "id": "https://www.grid.ac/institutes/grid.147455.6", 
              "name": [
                "Carnegie Mellon University, Pittsburgh, PA, USA"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Batra", 
            "givenName": "Dhruv", 
            "id": "sg:person.016177260105.00", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016177260105.00"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Cornell University", 
              "id": "https://www.grid.ac/institutes/grid.5386.8", 
              "name": [
                "Cornell University, Ithaca, NY, USA"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Kowdle", 
            "givenName": "Adarsh", 
            "id": "sg:person.010315021706.95", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010315021706.95"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "name": [
                "Toyota Technological Institute, Chicago, IL, USA"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Parikh", 
            "givenName": "Devi", 
            "id": "sg:person.01310632454.16", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01310632454.16"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Kodak (United States)", 
              "id": "https://www.grid.ac/institutes/grid.418652.c", 
              "name": [
                "Eastman Kodak Company, Rochester, NY, USA"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Luo", 
            "givenName": "Jiebo", 
            "id": "sg:person.016713502333.92", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016713502333.92"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Cornell University", 
              "id": "https://www.grid.ac/institutes/grid.5386.8", 
              "name": [
                "Cornell University, Ithaca, NY, USA"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Chen", 
            "givenName": "Tsuhan", 
            "id": "sg:person.012245072625.31", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012245072625.31"
            ], 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "https://doi.org/10.1145/237170.237269", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1005380297"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1145/130385.130417", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1007225007"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.cviu.2008.07.002", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1008932526"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1145/1399504.1360696", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1014577890"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1145/344779.344849", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1019944005"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1145/1186562.1015720", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1022236987"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/s0167-8655(02)00370-7", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1026695583"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/11744047_13", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1031783594", 
              "https://doi.org/10.1007/11744047_13"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/11744047_13", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1031783594", 
              "https://doi.org/10.1007/11744047_13"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-642-15552-9_34", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1035291251", 
              "https://doi.org/10.1007/978-3-642-15552-9_34"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-642-15552-9_34", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1035291251", 
              "https://doi.org/10.1007/978-3-642-15552-9_34"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/11612704_38", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1035584643", 
              "https://doi.org/10.1007/11612704_38"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-540-76390-1_82", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1036908283", 
              "https://doi.org/10.1007/978-3-540-76390-1_82"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-540-76390-1_82", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1036908283", 
              "https://doi.org/10.1007/978-3-540-76390-1_82"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1145/1186562.1015719", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1040523957"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/0262-8856(92)90066-c", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1040803351"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/0262-8856(92)90066-c", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1040803351"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-540-88682-2_8", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1045945012", 
              "https://doi.org/10.1007/978-3-540-88682-2_8"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-540-88682-2_9", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1047173815", 
              "https://doi.org/10.1007/978-3-540-88682-2_9"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-540-88682-2_9", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1047173815", 
              "https://doi.org/10.1007/978-3-540-88682-2_9"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/bfb0055689", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1047873554", 
              "https://doi.org/10.1007/bfb0055689"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/3-540-49437-5_11", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1049334366", 
              "https://doi.org/10.1007/3-540-49437-5_11"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1006/ciun.1993.1029", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1049611659"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1145/1179352.1141964", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1052911580"
            ], 
            "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/10.1109/34.969114", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061157335"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/mcg.2007.68", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061391620"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tpami.2004.1262177", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061742646"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tpami.2004.60", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061742742"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2009.5206652", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1078373720"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2008.4587609", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1093346605"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/iccv.2007.4408931", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1093653145"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2006.91", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1093699646"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/iccv.2003.1238391", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1093735574"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2008.4587589", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1093787995"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/icpr.2008.4761602", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1093884142"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2009.5206705", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1094051431"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2010.5540080", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1094242240"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/iccv.2007.4408844", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1094384110"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/iccv.2005.107", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1094730474"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2010.5539772", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1094976438"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/iccv.2009.5459261", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095106826"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/iccv.2001.937505", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095383001"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tdpvt.2002.1024035", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095724068"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.5244/c.22.90", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1099325971"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.5244/c.17.32", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1099382978"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2011-07", 
        "datePublishedReg": "2011-07-01", 
        "description": "We present an algorithm for Interactive Co-segmentation of a foreground object from a group of related images. While previous works in co-segmentation have focussed on unsupervised co-segmentation, we use successful ideas from the interactive object-cutout literature. We develop an algorithm that allows users to decide what foreground is, and then guide the output of the co-segmentation algorithm towards it via scribbles. Interestingly, keeping a user in the loop leads to simpler and highly parallelizable energy functions, allowing us to work with significantly more images per group. However, unlike the interactive single-image counterpart, a user cannot be expected to exhaustively examine all cutouts (from tens of images) returned by the system to make corrections. Hence, we propose iCoseg, an automatic recommendation system that intelligently recommends where the user should scribble next. We introduce and make publicly available the largest co-segmentation dataset yet, the CMU-Cornell iCoseg dataset, with 38 groups, 643 images, and pixelwise hand-annotated groundtruth. Through machine experiments and real user studies with our developed interface, we show that iCoseg can intelligently recommend regions to scribble on, and users following these recommendations can achieve good quality cutouts with significantly lower time and effort than exhaustively examining all cutouts.", 
        "genre": "research_article", 
        "id": "sg:pub.10.1007/s11263-010-0415-x", 
        "inLanguage": [
          "en"
        ], 
        "isAccessibleForFree": false, 
        "isPartOf": [
          {
            "id": "sg:journal.1032807", 
            "issn": [
              "0920-5691", 
              "1573-1405"
            ], 
            "name": "International Journal of Computer Vision", 
            "type": "Periodical"
          }, 
          {
            "issueNumber": "3", 
            "type": "PublicationIssue"
          }, 
          {
            "type": "PublicationVolume", 
            "volumeNumber": "93"
          }
        ], 
        "name": "Interactively Co-segmentating Topically Related Images with Intelligent Scribble Guidance", 
        "pagination": "273-292", 
        "productId": [
          {
            "name": "readcube_id", 
            "type": "PropertyValue", 
            "value": [
              "f6c0fe304d877ff3136cb08f3e3585e666fb4860435e56d81abff83980f9e225"
            ]
          }, 
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1007/s11263-010-0415-x"
            ]
          }, 
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1051801565"
            ]
          }
        ], 
        "sameAs": [
          "https://doi.org/10.1007/s11263-010-0415-x", 
          "https://app.dimensions.ai/details/publication/pub.1051801565"
        ], 
        "sdDataset": "articles", 
        "sdDatePublished": "2019-04-10T20:50", 
        "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_8684_00000524.jsonl", 
        "type": "ScholarlyArticle", 
        "url": "http://link.springer.com/10.1007%2Fs11263-010-0415-x"
      }
    ]
     

    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/s11263-010-0415-x'

    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/s11263-010-0415-x'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/s11263-010-0415-x'

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

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/s11263-010-0415-x'


     

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

    228 TRIPLES      21 PREDICATES      68 URIs      19 LITERALS      7 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1007/s11263-010-0415-x schema:about anzsrc-for:08
    2 anzsrc-for:0801
    3 schema:author Nc38ca6260dfc4760b6920eaf026a1220
    4 schema:citation sg:pub.10.1007/11612704_38
    5 sg:pub.10.1007/11744047_13
    6 sg:pub.10.1007/3-540-49437-5_11
    7 sg:pub.10.1007/978-3-540-76390-1_82
    8 sg:pub.10.1007/978-3-540-88682-2_8
    9 sg:pub.10.1007/978-3-540-88682-2_9
    10 sg:pub.10.1007/978-3-642-15552-9_34
    11 sg:pub.10.1007/bfb0055689
    12 https://doi.org/10.1006/ciun.1993.1029
    13 https://doi.org/10.1016/0262-8856(92)90066-c
    14 https://doi.org/10.1016/j.cviu.2008.07.002
    15 https://doi.org/10.1016/s0167-8655(02)00370-7
    16 https://doi.org/10.1109/34.1000236
    17 https://doi.org/10.1109/34.969114
    18 https://doi.org/10.1109/cvpr.2006.91
    19 https://doi.org/10.1109/cvpr.2008.4587589
    20 https://doi.org/10.1109/cvpr.2008.4587609
    21 https://doi.org/10.1109/cvpr.2009.5206652
    22 https://doi.org/10.1109/cvpr.2009.5206705
    23 https://doi.org/10.1109/cvpr.2010.5539772
    24 https://doi.org/10.1109/cvpr.2010.5540080
    25 https://doi.org/10.1109/iccv.2001.937505
    26 https://doi.org/10.1109/iccv.2003.1238391
    27 https://doi.org/10.1109/iccv.2005.107
    28 https://doi.org/10.1109/iccv.2007.4408844
    29 https://doi.org/10.1109/iccv.2007.4408931
    30 https://doi.org/10.1109/iccv.2009.5459261
    31 https://doi.org/10.1109/icpr.2008.4761602
    32 https://doi.org/10.1109/mcg.2007.68
    33 https://doi.org/10.1109/tdpvt.2002.1024035
    34 https://doi.org/10.1109/tpami.2004.1262177
    35 https://doi.org/10.1109/tpami.2004.60
    36 https://doi.org/10.1145/1179352.1141964
    37 https://doi.org/10.1145/1186562.1015719
    38 https://doi.org/10.1145/1186562.1015720
    39 https://doi.org/10.1145/130385.130417
    40 https://doi.org/10.1145/1399504.1360696
    41 https://doi.org/10.1145/237170.237269
    42 https://doi.org/10.1145/344779.344849
    43 https://doi.org/10.5244/c.17.32
    44 https://doi.org/10.5244/c.22.90
    45 schema:datePublished 2011-07
    46 schema:datePublishedReg 2011-07-01
    47 schema:description We present an algorithm for Interactive Co-segmentation of a foreground object from a group of related images. While previous works in co-segmentation have focussed on unsupervised co-segmentation, we use successful ideas from the interactive object-cutout literature. We develop an algorithm that allows users to decide what foreground is, and then guide the output of the co-segmentation algorithm towards it via scribbles. Interestingly, keeping a user in the loop leads to simpler and highly parallelizable energy functions, allowing us to work with significantly more images per group. However, unlike the interactive single-image counterpart, a user cannot be expected to exhaustively examine all cutouts (from tens of images) returned by the system to make corrections. Hence, we propose iCoseg, an automatic recommendation system that intelligently recommends where the user should scribble next. We introduce and make publicly available the largest co-segmentation dataset yet, the CMU-Cornell iCoseg dataset, with 38 groups, 643 images, and pixelwise hand-annotated groundtruth. Through machine experiments and real user studies with our developed interface, we show that iCoseg can intelligently recommend regions to scribble on, and users following these recommendations can achieve good quality cutouts with significantly lower time and effort than exhaustively examining all cutouts.
    48 schema:genre research_article
    49 schema:inLanguage en
    50 schema:isAccessibleForFree false
    51 schema:isPartOf N51c32a85b84f44fa8b90a8db7f375534
    52 Nc5cdebdfea394c13ba1063f35dd82cb4
    53 sg:journal.1032807
    54 schema:name Interactively Co-segmentating Topically Related Images with Intelligent Scribble Guidance
    55 schema:pagination 273-292
    56 schema:productId N37a77efc5c1e4820a03fc39128fa37f2
    57 Nb08b5c31ec764d198c0f658000980ef1
    58 Nb12f1c09b3a84955ba05984c087e8f5a
    59 schema:sameAs https://app.dimensions.ai/details/publication/pub.1051801565
    60 https://doi.org/10.1007/s11263-010-0415-x
    61 schema:sdDatePublished 2019-04-10T20:50
    62 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    63 schema:sdPublisher Nad4bd01d9b3c4ae8a485754a915ba14e
    64 schema:url http://link.springer.com/10.1007%2Fs11263-010-0415-x
    65 sgo:license sg:explorer/license/
    66 sgo:sdDataset articles
    67 rdf:type schema:ScholarlyArticle
    68 N3694aae1ac334c1e9e4bc46a40261ebc schema:name Toyota Technological Institute, Chicago, IL, USA
    69 rdf:type schema:Organization
    70 N37a77efc5c1e4820a03fc39128fa37f2 schema:name readcube_id
    71 schema:value f6c0fe304d877ff3136cb08f3e3585e666fb4860435e56d81abff83980f9e225
    72 rdf:type schema:PropertyValue
    73 N49fe57829e0d48e5bc18c3350265e34a rdf:first sg:person.010315021706.95
    74 rdf:rest Nd7254f4d3ffc4d538a090bd681dcc5e4
    75 N51c32a85b84f44fa8b90a8db7f375534 schema:volumeNumber 93
    76 rdf:type schema:PublicationVolume
    77 Nab1f1b96a6fe4969a95201bf3549b42d rdf:first sg:person.012245072625.31
    78 rdf:rest rdf:nil
    79 Nad4bd01d9b3c4ae8a485754a915ba14e schema:name Springer Nature - SN SciGraph project
    80 rdf:type schema:Organization
    81 Nb08b5c31ec764d198c0f658000980ef1 schema:name dimensions_id
    82 schema:value pub.1051801565
    83 rdf:type schema:PropertyValue
    84 Nb12f1c09b3a84955ba05984c087e8f5a schema:name doi
    85 schema:value 10.1007/s11263-010-0415-x
    86 rdf:type schema:PropertyValue
    87 Nc38ca6260dfc4760b6920eaf026a1220 rdf:first sg:person.016177260105.00
    88 rdf:rest N49fe57829e0d48e5bc18c3350265e34a
    89 Nc5cdebdfea394c13ba1063f35dd82cb4 schema:issueNumber 3
    90 rdf:type schema:PublicationIssue
    91 Nd7254f4d3ffc4d538a090bd681dcc5e4 rdf:first sg:person.01310632454.16
    92 rdf:rest Nf706807959e347299145ba7fa3cff8df
    93 Nf706807959e347299145ba7fa3cff8df rdf:first sg:person.016713502333.92
    94 rdf:rest Nab1f1b96a6fe4969a95201bf3549b42d
    95 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
    96 schema:name Information and Computing Sciences
    97 rdf:type schema:DefinedTerm
    98 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
    99 schema:name Artificial Intelligence and Image Processing
    100 rdf:type schema:DefinedTerm
    101 sg:journal.1032807 schema:issn 0920-5691
    102 1573-1405
    103 schema:name International Journal of Computer Vision
    104 rdf:type schema:Periodical
    105 sg:person.010315021706.95 schema:affiliation https://www.grid.ac/institutes/grid.5386.8
    106 schema:familyName Kowdle
    107 schema:givenName Adarsh
    108 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010315021706.95
    109 rdf:type schema:Person
    110 sg:person.012245072625.31 schema:affiliation https://www.grid.ac/institutes/grid.5386.8
    111 schema:familyName Chen
    112 schema:givenName Tsuhan
    113 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012245072625.31
    114 rdf:type schema:Person
    115 sg:person.01310632454.16 schema:affiliation N3694aae1ac334c1e9e4bc46a40261ebc
    116 schema:familyName Parikh
    117 schema:givenName Devi
    118 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01310632454.16
    119 rdf:type schema:Person
    120 sg:person.016177260105.00 schema:affiliation https://www.grid.ac/institutes/grid.147455.6
    121 schema:familyName Batra
    122 schema:givenName Dhruv
    123 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016177260105.00
    124 rdf:type schema:Person
    125 sg:person.016713502333.92 schema:affiliation https://www.grid.ac/institutes/grid.418652.c
    126 schema:familyName Luo
    127 schema:givenName Jiebo
    128 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016713502333.92
    129 rdf:type schema:Person
    130 sg:pub.10.1007/11612704_38 schema:sameAs https://app.dimensions.ai/details/publication/pub.1035584643
    131 https://doi.org/10.1007/11612704_38
    132 rdf:type schema:CreativeWork
    133 sg:pub.10.1007/11744047_13 schema:sameAs https://app.dimensions.ai/details/publication/pub.1031783594
    134 https://doi.org/10.1007/11744047_13
    135 rdf:type schema:CreativeWork
    136 sg:pub.10.1007/3-540-49437-5_11 schema:sameAs https://app.dimensions.ai/details/publication/pub.1049334366
    137 https://doi.org/10.1007/3-540-49437-5_11
    138 rdf:type schema:CreativeWork
    139 sg:pub.10.1007/978-3-540-76390-1_82 schema:sameAs https://app.dimensions.ai/details/publication/pub.1036908283
    140 https://doi.org/10.1007/978-3-540-76390-1_82
    141 rdf:type schema:CreativeWork
    142 sg:pub.10.1007/978-3-540-88682-2_8 schema:sameAs https://app.dimensions.ai/details/publication/pub.1045945012
    143 https://doi.org/10.1007/978-3-540-88682-2_8
    144 rdf:type schema:CreativeWork
    145 sg:pub.10.1007/978-3-540-88682-2_9 schema:sameAs https://app.dimensions.ai/details/publication/pub.1047173815
    146 https://doi.org/10.1007/978-3-540-88682-2_9
    147 rdf:type schema:CreativeWork
    148 sg:pub.10.1007/978-3-642-15552-9_34 schema:sameAs https://app.dimensions.ai/details/publication/pub.1035291251
    149 https://doi.org/10.1007/978-3-642-15552-9_34
    150 rdf:type schema:CreativeWork
    151 sg:pub.10.1007/bfb0055689 schema:sameAs https://app.dimensions.ai/details/publication/pub.1047873554
    152 https://doi.org/10.1007/bfb0055689
    153 rdf:type schema:CreativeWork
    154 https://doi.org/10.1006/ciun.1993.1029 schema:sameAs https://app.dimensions.ai/details/publication/pub.1049611659
    155 rdf:type schema:CreativeWork
    156 https://doi.org/10.1016/0262-8856(92)90066-c schema:sameAs https://app.dimensions.ai/details/publication/pub.1040803351
    157 rdf:type schema:CreativeWork
    158 https://doi.org/10.1016/j.cviu.2008.07.002 schema:sameAs https://app.dimensions.ai/details/publication/pub.1008932526
    159 rdf:type schema:CreativeWork
    160 https://doi.org/10.1016/s0167-8655(02)00370-7 schema:sameAs https://app.dimensions.ai/details/publication/pub.1026695583
    161 rdf:type schema:CreativeWork
    162 https://doi.org/10.1109/34.1000236 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061155588
    163 rdf:type schema:CreativeWork
    164 https://doi.org/10.1109/34.969114 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061157335
    165 rdf:type schema:CreativeWork
    166 https://doi.org/10.1109/cvpr.2006.91 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093699646
    167 rdf:type schema:CreativeWork
    168 https://doi.org/10.1109/cvpr.2008.4587589 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093787995
    169 rdf:type schema:CreativeWork
    170 https://doi.org/10.1109/cvpr.2008.4587609 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093346605
    171 rdf:type schema:CreativeWork
    172 https://doi.org/10.1109/cvpr.2009.5206652 schema:sameAs https://app.dimensions.ai/details/publication/pub.1078373720
    173 rdf:type schema:CreativeWork
    174 https://doi.org/10.1109/cvpr.2009.5206705 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094051431
    175 rdf:type schema:CreativeWork
    176 https://doi.org/10.1109/cvpr.2010.5539772 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094976438
    177 rdf:type schema:CreativeWork
    178 https://doi.org/10.1109/cvpr.2010.5540080 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094242240
    179 rdf:type schema:CreativeWork
    180 https://doi.org/10.1109/iccv.2001.937505 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095383001
    181 rdf:type schema:CreativeWork
    182 https://doi.org/10.1109/iccv.2003.1238391 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093735574
    183 rdf:type schema:CreativeWork
    184 https://doi.org/10.1109/iccv.2005.107 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094730474
    185 rdf:type schema:CreativeWork
    186 https://doi.org/10.1109/iccv.2007.4408844 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094384110
    187 rdf:type schema:CreativeWork
    188 https://doi.org/10.1109/iccv.2007.4408931 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093653145
    189 rdf:type schema:CreativeWork
    190 https://doi.org/10.1109/iccv.2009.5459261 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095106826
    191 rdf:type schema:CreativeWork
    192 https://doi.org/10.1109/icpr.2008.4761602 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093884142
    193 rdf:type schema:CreativeWork
    194 https://doi.org/10.1109/mcg.2007.68 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061391620
    195 rdf:type schema:CreativeWork
    196 https://doi.org/10.1109/tdpvt.2002.1024035 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095724068
    197 rdf:type schema:CreativeWork
    198 https://doi.org/10.1109/tpami.2004.1262177 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061742646
    199 rdf:type schema:CreativeWork
    200 https://doi.org/10.1109/tpami.2004.60 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061742742
    201 rdf:type schema:CreativeWork
    202 https://doi.org/10.1145/1179352.1141964 schema:sameAs https://app.dimensions.ai/details/publication/pub.1052911580
    203 rdf:type schema:CreativeWork
    204 https://doi.org/10.1145/1186562.1015719 schema:sameAs https://app.dimensions.ai/details/publication/pub.1040523957
    205 rdf:type schema:CreativeWork
    206 https://doi.org/10.1145/1186562.1015720 schema:sameAs https://app.dimensions.ai/details/publication/pub.1022236987
    207 rdf:type schema:CreativeWork
    208 https://doi.org/10.1145/130385.130417 schema:sameAs https://app.dimensions.ai/details/publication/pub.1007225007
    209 rdf:type schema:CreativeWork
    210 https://doi.org/10.1145/1399504.1360696 schema:sameAs https://app.dimensions.ai/details/publication/pub.1014577890
    211 rdf:type schema:CreativeWork
    212 https://doi.org/10.1145/237170.237269 schema:sameAs https://app.dimensions.ai/details/publication/pub.1005380297
    213 rdf:type schema:CreativeWork
    214 https://doi.org/10.1145/344779.344849 schema:sameAs https://app.dimensions.ai/details/publication/pub.1019944005
    215 rdf:type schema:CreativeWork
    216 https://doi.org/10.5244/c.17.32 schema:sameAs https://app.dimensions.ai/details/publication/pub.1099382978
    217 rdf:type schema:CreativeWork
    218 https://doi.org/10.5244/c.22.90 schema:sameAs https://app.dimensions.ai/details/publication/pub.1099325971
    219 rdf:type schema:CreativeWork
    220 https://www.grid.ac/institutes/grid.147455.6 schema:alternateName Carnegie Mellon University
    221 schema:name Carnegie Mellon University, Pittsburgh, PA, USA
    222 rdf:type schema:Organization
    223 https://www.grid.ac/institutes/grid.418652.c schema:alternateName Kodak (United States)
    224 schema:name Eastman Kodak Company, Rochester, NY, USA
    225 rdf:type schema:Organization
    226 https://www.grid.ac/institutes/grid.5386.8 schema:alternateName Cornell University
    227 schema:name Cornell University, Ithaca, NY, USA
    228 rdf:type schema:Organization
     




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


    ...