Dataset Open Access

CAD 120 affordance dataset

Sawatzky, Johann; Srikantha, Abhilash; Gall, Juergen


DCAT Export

<?xml version='1.0' encoding='utf-8'?>
<rdf:RDF xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:adms="http://www.w3.org/ns/adms#" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:dct="http://purl.org/dc/terms/" xmlns:dctype="http://purl.org/dc/dcmitype/" xmlns:dcat="http://www.w3.org/ns/dcat#" xmlns:duv="http://www.w3.org/ns/duv#" xmlns:foaf="http://xmlns.com/foaf/0.1/" xmlns:frapo="http://purl.org/cerif/frapo/" xmlns:geo="http://www.w3.org/2003/01/geo/wgs84_pos#" xmlns:gsp="http://www.opengis.net/ont/geosparql#" xmlns:locn="http://www.w3.org/ns/locn#" xmlns:org="http://www.w3.org/ns/org#" xmlns:owl="http://www.w3.org/2002/07/owl#" xmlns:prov="http://www.w3.org/ns/prov#" xmlns:rdfs="http://www.w3.org/2000/01/rdf-schema#" xmlns:schema="http://schema.org/" xmlns:skos="http://www.w3.org/2004/02/skos/core#" xmlns:vcard="http://www.w3.org/2006/vcard/ns#" xmlns:wdrs="http://www.w3.org/2007/05/powder-s#">
  <rdf:Description rdf:about="https://doi.org/10.5281/zenodo.495570">
    <rdf:type rdf:resource="http://www.w3.org/ns/dcat#Dataset"/>
    <dct:type rdf:resource="http://purl.org/dc/dcmitype/Dataset"/>
    <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#anyURI">https://doi.org/10.5281/zenodo.495570</dct:identifier>
    <foaf:page rdf:resource="https://doi.org/10.5281/zenodo.495570"/>
    <dct:creator>
      <rdf:Description>
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <foaf:name>Sawatzky, Johann</foaf:name>
        <foaf:givenName>Johann</foaf:givenName>
        <foaf:familyName>Sawatzky</foaf:familyName>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>University of Bonn</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:creator>
      <rdf:Description>
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <foaf:name>Srikantha, Abhilash</foaf:name>
        <foaf:givenName>Abhilash</foaf:givenName>
        <foaf:familyName>Srikantha</foaf:familyName>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>Carl Zeiss AG</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:creator>
      <rdf:Description>
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <foaf:name>Gall, Juergen</foaf:name>
        <foaf:givenName>Juergen</foaf:givenName>
        <foaf:familyName>Gall</foaf:familyName>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>University of Bonn</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:title>CAD 120 affordance dataset</dct:title>
    <dct:publisher>
      <foaf:Agent>
        <foaf:name>Zenodo</foaf:name>
      </foaf:Agent>
    </dct:publisher>
    <dct:issued rdf:datatype="http://www.w3.org/2001/XMLSchema#gYear">2017</dct:issued>
    <dcat:keyword>computer vision</dcat:keyword>
    <dcat:keyword>affordances</dcat:keyword>
    <dcat:keyword>attributes</dcat:keyword>
    <dcat:keyword>semantic image segmentation</dcat:keyword>
    <dcat:keyword>robotics</dcat:keyword>
    <dcat:keyword>weakly supervised learning</dcat:keyword>
    <dcat:keyword>convolutional neural network</dcat:keyword>
    <dcat:keyword>anticipating human behavior</dcat:keyword>
    <dcat:keyword>mapping on demand</dcat:keyword>
    <dct:issued rdf:datatype="http://www.w3.org/2001/XMLSchema#date">2017-04-07</dct:issued>
    <owl:sameAs rdf:resource="https://zenodo.org/record/495570"/>
    <adms:identifier>
      <adms:Identifier>
        <skos:notation rdf:datatype="http://www.w3.org/2001/XMLSchema#anyURI">https://zenodo.org/record/495570</skos:notation>
        <adms:schemeAgency>url</adms:schemeAgency>
      </adms:Identifier>
    </adms:identifier>
    <dct:relation rdf:resource="https://pages.iai.uni-bonn.de/gall_juergen/download/jgall_affordancedetection_cvpr17.pdf"/>
    <dct:relation rdf:resource="https://github.com/ykztawas/Weakly-Supervised-Affordance-Detection"/>
    <dct:description>&lt;p&gt;% ==============================================================================&lt;br&gt; % CAD 120 Affordance Dataset&lt;br&gt; % Version 1.0&lt;br&gt; % ------------------------------------------------------------------------------&lt;br&gt; % If you use the dataset please cite:&lt;br&gt; %&lt;br&gt; % Johann Sawatzky, Abhilash Srikantha, Juergen Gall.&lt;br&gt; % Weakly Supervised Affordance Detection.&lt;br&gt; % IEEE Conference on Computer Vision and Pattern Recognition (CVPR'17)&lt;br&gt; %&lt;br&gt; % and&lt;br&gt; %&lt;br&gt; % H. S. Koppula and A. Saxena.&lt;br&gt; % Physically grounded spatio-temporal object affordances.&lt;br&gt; % European Conference on Computer Vision (ECCV'14)&lt;br&gt; %&lt;br&gt; % Any bugs or questions, please email sawatzky AT iai DOT uni-bonn DOT de.&lt;br&gt; % ==============================================================================&lt;/p&gt; &lt;p&gt;This is the CAD 120 Affordance Segmentation Dataset based on the Cornell Activity&lt;br&gt; Dataset CAD 120 (see http://pr.cs.cornell.edu/humanactivities/data.php).&lt;/p&gt; &lt;p&gt;Content&lt;/p&gt; &lt;p&gt;frames/*.png:&lt;br&gt; RGB frames selected from Cornell Activity Dataset. To find out the location of the frame&lt;br&gt; in the original videos, see video_info.txt.&lt;/p&gt; &lt;p&gt;object_crop_images/*.png&lt;br&gt; image crops taken from the selected frames and resized to 321*321. Each crop is a padded&lt;br&gt; bounding box of an object the human interacts with in the video. Due to the padding,&lt;br&gt; the crops may contain background and other objects.&lt;br&gt; In each selected frame, each bounding box was processed. The bounding boxes are already&lt;br&gt; given in the Cornell Activity Dataset.&lt;br&gt; The 5-digit number gives the frame number, the second number gives the bounding box number&lt;br&gt; within the frame.&lt;/p&gt; &lt;p&gt;segmentation_mat/*.mat&lt;br&gt; 321*321*6 segmentation masks for the image crops. Each channel corresponds to an&lt;br&gt; affordance (openabe, cuttable, pourable, containable, supportable, holdable, in this order).&lt;br&gt; All pixels belonging to a particular affordance are labeled 1 in the respective channel,&lt;br&gt; otherwise 0.  &lt;/p&gt; &lt;p&gt;segmentation_png/*.png&lt;br&gt; 321*321 png images, each containing the binary mask for one of the affordances.&lt;/p&gt; &lt;p&gt;lists/*.txt&lt;br&gt; Lists containing the train and test sets for two splits. The actor split ensures that&lt;br&gt; train and test images stem from different videos with different actors while the object split ensures&lt;br&gt; that train and test data have no (central) object classes in common.&lt;br&gt; The train sets are additionally subdivided into 3 subsets A,B and C. For the actor split,&lt;br&gt; the subsets stem from different videos. For the object split, each subset contains&lt;br&gt; every third crop of the train set.&lt;/p&gt; &lt;p&gt;crop_coordinate_info.txt&lt;br&gt; Maps image crops to their coordinates in the frames.&lt;/p&gt; &lt;p&gt;hpose_info.txt&lt;br&gt; Maps frames to 2d human pose coordinates. Hand annotated by us.&lt;/p&gt; &lt;p&gt;object_info.txt&lt;br&gt; Maps image crops to the (central) object it contains.&lt;/p&gt; &lt;p&gt;visible_affordance_info.txt&lt;br&gt; Maps image crops to affordances visible in this crop&lt;/p&gt; &lt;p&gt; &lt;/p&gt; &lt;p&gt;%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%55&lt;br&gt; The crops contain the following object classes:&lt;br&gt; 1.table&lt;br&gt; 2.kettle&lt;br&gt; 3.plate&lt;br&gt; 4.bottle&lt;br&gt; 5.thermal cup&lt;br&gt; 6.knife&lt;br&gt; 7.medicine box&lt;br&gt; 8.can&lt;br&gt; 9.microwave&lt;br&gt; 10.paper box&lt;br&gt; 11.bowl&lt;br&gt; 12.mug&lt;/p&gt; &lt;p&gt;Affordances in our set:&lt;br&gt; 1.openable&lt;br&gt; 2.cuttable&lt;br&gt; 3.pourable&lt;br&gt; 4.containable&lt;br&gt; 5.supportable&lt;br&gt; 6.holdable&lt;/p&gt; &lt;p&gt;Note that our object affordance labeling differs from the Cornell Activity Dataset:&lt;br&gt; E.g. the cap of a pizza box is considered to be supportable.&lt;/p&gt; &lt;p&gt; &lt;/p&gt;</dct:description>
    <dct:description>Acknowledgments. The work has been financially sup- ported by the DFG projects GA 1927/5-1 (DFG Research Unit FOR 2535 Anticipating Human Behavior) and GA 1927/2-2 (DFG Research Unit FOR 1505 Mapping on De- mand).</dct:description>
    <dct:description>{"references": ["Sawatzky, J., Srikantha, A., Gall, J.: Weakly supervised affordance detection. CVPR (2017)"]}</dct:description>
    <dct:accessRights rdf:resource="http://publications.europa.eu/resource/authority/access-right/PUBLIC"/>
    <dct:accessRights>
      <dct:RightsStatement rdf:about="info:eu-repo/semantics/openAccess">
        <rdfs:label>Open Access</rdfs:label>
      </dct:RightsStatement>
    </dct:accessRights>
    <dcat:distribution>
      <dcat:Distribution>
        <dct:license rdf:resource="https://creativecommons.org/licenses/by/4.0/legalcode"/>
        <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.495570"/>
      </dcat:Distribution>
    </dcat:distribution>
    <dcat:distribution>
      <dcat:Distribution>
        <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.495570">https://doi.org/10.5281/zenodo.495570</dcat:accessURL>
        <dcat:byteSize>2570322318</dcat:byteSize>
        <dcat:downloadURL rdf:resource="https://zenodo.org/record/495570/files/CAD_release.tar.gz">https://zenodo.org/record/495570/files/CAD_release.tar.gz</dcat:downloadURL>
        <dcat:mediaType>application/x-tar</dcat:mediaType>
      </dcat:Distribution>
    </dcat:distribution>
  </rdf:Description>
</rdf:RDF>
2,931
1,961
views
downloads
All versions This version
Views 2,9312,933
Downloads 1,9611,961
Data volume 5.0 TB5.0 TB
Unique views 2,7142,716
Unique downloads 637637

Share

Cite as