Improving bag-of-poses with semi-temporal pose descriptors for skeleton-based action recognition View Full Text


Ontology type: schema:ScholarlyArticle     


Article Info

DATE

2019-04

AUTHORS

Saeid Agahian, Farhood Negin, Cemal Köse

ABSTRACT

Over the last few decades, human action recognition has become one of the most challenging tasks in the field of computer vision. Effortless and accurate extraction of 3D skeleton information has been recently achieved by means of economical depth sensors and state-of-the-art deep learning approaches. In this study, we introduce a novel bag-of-poses framework for action recognition using 3D skeleton data. Our assumption is that any action can be represented by a set of predefined spatiotemporal poses. The pose descriptor is composed of three parts. The first part is concatenation of the normalized coordinate of the skeleton joints. The second part is consisted of temporal displacement of the joints constructed with predefined temporal offset, and the third part is temporal displacement with the previous frame in the sequence. In order to generate the key poses, we apply K-means clustering over all the training pose descriptors of the dataset. SVM classifier is trained with the generated key poses to classify an action pose. Accordingly, every action in the dataset is encoded with key pose histograms. ELM classifier is used for action recognition due to its fast, accurate and reliable performance compared to the other classifiers. The proposed framework is validated with five publicly available benchmark 3D action datasets and achieved state-of-the-art results on three of the datasets and competitive results on the other two datasets compared to the other methods. More... »

PAGES

1-17

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/s00371-018-1489-7

DOI

http://dx.doi.org/10.1007/s00371-018-1489-7

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1101142241


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": "Karadeniz Technical University", 
          "id": "https://www.grid.ac/institutes/grid.31564.35", 
          "name": [
            "Department of Computer Engineering, Faculty of Engineering, Karadeniz Technical University, 61080, Trabzon, Turkey"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Agahian", 
        "givenName": "Saeid", 
        "id": "sg:person.012402112645.25", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012402112645.25"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "name": [
            "INRIA Sophia Antipolis, 2004 Route des Lucioles, BP93, 06902, Sophia Antipolis Cedex, France"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Negin", 
        "givenName": "Farhood", 
        "id": "sg:person.015361664075.20", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015361664075.20"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Karadeniz Technical University", 
          "id": "https://www.grid.ac/institutes/grid.31564.35", 
          "name": [
            "Department of Computer Engineering, Faculty of Engineering, Karadeniz Technical University, 61080, Trabzon, Turkey"
          ], 
          "type": "Organization"
        }, 
        "familyName": "K\u00f6se", 
        "givenName": "Cemal", 
        "id": "sg:person.0715413177.67", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0715413177.67"
        ], 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "https://doi.org/10.1109/thms.2014.2377111", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1000191632"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.neucom.2010.01.020", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1003650446"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.cviu.2016.04.005", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1005090874"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1145/2964284.2967191", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1006787465"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s11263-016-0905-6", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1009812065", 
          "https://doi.org/10.1007/s11263-016-0905-6"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.patcog.2017.01.015", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1009835621"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1038/nature14539", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1010020120", 
          "https://doi.org/10.1038/nature14539"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1145/1922649.1922653", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1010328552"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.neucom.2013.10.046", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1013135277"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1145/1961189.1961199", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1013637525"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.jvcir.2014.04.007", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1021671430"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.imavis.2016.11.004", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1024434766"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.patrec.2016.05.032", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1025012845"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1145/2629483", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1025796123"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1145/2398356.2398381", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1026063546"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s11042-015-2448-1", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1026185623", 
          "https://doi.org/10.1007/s11042-015-2448-1"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1145/2207676.2208303", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1027964637"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.patrec.2014.04.011", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1028366752"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.patcog.2016.05.019", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1028710668"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.patcog.2016.08.022", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1031649924"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.3389/fnbot.2015.00003", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1033622469"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.patcog.2015.11.019", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1035547204"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.imavis.2009.11.014", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1035613888"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.image.2016.01.003", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1037182588"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-319-16814-2_28", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1038057488", 
          "https://doi.org/10.1007/978-3-319-16814-2_28"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.neucom.2005.12.126", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1038265102"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.eswa.2015.06.013", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1038358757"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s00371-015-1066-2", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1038762578", 
          "https://doi.org/10.1007/s00371-015-1066-2"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s00371-012-0752-6", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1040316085", 
          "https://doi.org/10.1007/s00371-012-0752-6"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.eswa.2013.08.009", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1045453021"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s00371-014-0923-8", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1052157236", 
          "https://doi.org/10.1007/s00371-014-0923-8"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.imavis.2016.06.007", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1052209661"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.cviu.2016.03.013", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1053138393"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/jsen.2015.2487358", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061324392"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tcsvt.2016.2628339", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061576932"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tcyb.2013.2265378", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061579490"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tcyb.2016.2519448", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061580217"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/thms.2014.2325871", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061614892"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tpami.2015.2439257", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061744882"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.cviu.2017.01.011", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1083527203"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.patrec.2017.02.001", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1083528177"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.patcog.2017.02.030", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1084100916"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.patrec.2017.05.004", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1085104142"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tpami.2017.2771306", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1092606368"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cvprw.2012.6239233", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1093193872"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/wacv.2017.24", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1093356859"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cvpr.2014.82", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1093487177"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cvpr.2001.990935", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1093612272"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cvpr.2016.289", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1093762029"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/iccvw.2015.48", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1093805559"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/acpr.2015.7486569", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1093858320"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cvpr.2013.123", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1094187924"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cvpr.2013.123", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1094187924"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/iccv.2013.342", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1094449597"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/dicta.2014.7008101", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1094483082"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/icip.2015.7350781", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1094540780"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cvpr.2012.6247806", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1094572393"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/iccv.2015.460", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1094735069"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cvpr.2012.6247813", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1094880165"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cvpr.2015.7298714", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1094903557"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/icme.2017.8019313", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1095144148"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/igcc.2014.7039171", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1095480035"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/arso.2014.7020983", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1095533640"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cvprw.2010.5543273", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1095719282"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cvpr.2017.143", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1095837104"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.5244/c.25.67", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1099341406"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/iccv.2017.115", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1100060077"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tcyb.2018.2794503", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1100757775"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tcyb.2018.2794503", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1100757775"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tcyb.2018.2794503", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1100757775"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "2019-04", 
    "datePublishedReg": "2019-04-01", 
    "description": "Over the last few decades, human action recognition has become one of the most challenging tasks in the field of computer vision. Effortless and accurate extraction of 3D skeleton information has been recently achieved by means of economical depth sensors and state-of-the-art deep learning approaches. In this study, we introduce a novel bag-of-poses framework for action recognition using 3D skeleton data. Our assumption is that any action can be represented by a set of predefined spatiotemporal poses. The pose descriptor is composed of three parts. The first part is concatenation of the normalized coordinate of the skeleton joints. The second part is consisted of temporal displacement of the joints constructed with predefined temporal offset, and the third part is temporal displacement with the previous frame in the sequence. In order to generate the key poses, we apply K-means clustering over all the training pose descriptors of the dataset. SVM classifier is trained with the generated key poses to classify an action pose. Accordingly, every action in the dataset is encoded with key pose histograms. ELM classifier is used for action recognition due to its fast, accurate and reliable performance compared to the other classifiers. The proposed framework is validated with five publicly available benchmark 3D action datasets and achieved state-of-the-art results on three of the datasets and competitive results on the other two datasets compared to the other methods.", 
    "genre": "research_article", 
    "id": "sg:pub.10.1007/s00371-018-1489-7", 
    "inLanguage": [
      "en"
    ], 
    "isAccessibleForFree": false, 
    "isPartOf": [
      {
        "id": "sg:journal.1046897", 
        "issn": [
          "0178-2789", 
          "1432-2315"
        ], 
        "name": "The Visual Computer", 
        "type": "Periodical"
      }, 
      {
        "issueNumber": "4", 
        "type": "PublicationIssue"
      }, 
      {
        "type": "PublicationVolume", 
        "volumeNumber": "35"
      }
    ], 
    "name": "Improving bag-of-poses with semi-temporal pose descriptors for skeleton-based action recognition", 
    "pagination": "1-17", 
    "productId": [
      {
        "name": "readcube_id", 
        "type": "PropertyValue", 
        "value": [
          "cf3da6a4192565abe7001cea9488a2c736f7f1209a6808279b5163bd58008396"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/s00371-018-1489-7"
        ]
      }, 
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1101142241"
        ]
      }
    ], 
    "sameAs": [
      "https://doi.org/10.1007/s00371-018-1489-7", 
      "https://app.dimensions.ai/details/publication/pub.1101142241"
    ], 
    "sdDataset": "articles", 
    "sdDatePublished": "2019-04-11T13:52", 
    "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/v90/0000000371_0000000371/records_130801_00000005.jsonl", 
    "type": "ScholarlyArticle", 
    "url": "https://link.springer.com/10.1007%2Fs00371-018-1489-7"
  }
]
 

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/s00371-018-1489-7'

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/s00371-018-1489-7'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/s00371-018-1489-7'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/s00371-018-1489-7'


 

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

285 TRIPLES      21 PREDICATES      94 URIs      19 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/s00371-018-1489-7 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author Ncf11545f2fc3475c9dbfc0560988e0d1
4 schema:citation sg:pub.10.1007/978-3-319-16814-2_28
5 sg:pub.10.1007/s00371-012-0752-6
6 sg:pub.10.1007/s00371-014-0923-8
7 sg:pub.10.1007/s00371-015-1066-2
8 sg:pub.10.1007/s11042-015-2448-1
9 sg:pub.10.1007/s11263-016-0905-6
10 sg:pub.10.1038/nature14539
11 https://doi.org/10.1016/j.cviu.2016.03.013
12 https://doi.org/10.1016/j.cviu.2016.04.005
13 https://doi.org/10.1016/j.cviu.2017.01.011
14 https://doi.org/10.1016/j.eswa.2013.08.009
15 https://doi.org/10.1016/j.eswa.2015.06.013
16 https://doi.org/10.1016/j.image.2016.01.003
17 https://doi.org/10.1016/j.imavis.2009.11.014
18 https://doi.org/10.1016/j.imavis.2016.06.007
19 https://doi.org/10.1016/j.imavis.2016.11.004
20 https://doi.org/10.1016/j.jvcir.2014.04.007
21 https://doi.org/10.1016/j.neucom.2005.12.126
22 https://doi.org/10.1016/j.neucom.2010.01.020
23 https://doi.org/10.1016/j.neucom.2013.10.046
24 https://doi.org/10.1016/j.patcog.2015.11.019
25 https://doi.org/10.1016/j.patcog.2016.05.019
26 https://doi.org/10.1016/j.patcog.2016.08.022
27 https://doi.org/10.1016/j.patcog.2017.01.015
28 https://doi.org/10.1016/j.patcog.2017.02.030
29 https://doi.org/10.1016/j.patrec.2014.04.011
30 https://doi.org/10.1016/j.patrec.2016.05.032
31 https://doi.org/10.1016/j.patrec.2017.02.001
32 https://doi.org/10.1016/j.patrec.2017.05.004
33 https://doi.org/10.1109/acpr.2015.7486569
34 https://doi.org/10.1109/arso.2014.7020983
35 https://doi.org/10.1109/cvpr.2001.990935
36 https://doi.org/10.1109/cvpr.2012.6247806
37 https://doi.org/10.1109/cvpr.2012.6247813
38 https://doi.org/10.1109/cvpr.2013.123
39 https://doi.org/10.1109/cvpr.2014.82
40 https://doi.org/10.1109/cvpr.2015.7298714
41 https://doi.org/10.1109/cvpr.2016.289
42 https://doi.org/10.1109/cvpr.2017.143
43 https://doi.org/10.1109/cvprw.2010.5543273
44 https://doi.org/10.1109/cvprw.2012.6239233
45 https://doi.org/10.1109/dicta.2014.7008101
46 https://doi.org/10.1109/iccv.2013.342
47 https://doi.org/10.1109/iccv.2015.460
48 https://doi.org/10.1109/iccv.2017.115
49 https://doi.org/10.1109/iccvw.2015.48
50 https://doi.org/10.1109/icip.2015.7350781
51 https://doi.org/10.1109/icme.2017.8019313
52 https://doi.org/10.1109/igcc.2014.7039171
53 https://doi.org/10.1109/jsen.2015.2487358
54 https://doi.org/10.1109/tcsvt.2016.2628339
55 https://doi.org/10.1109/tcyb.2013.2265378
56 https://doi.org/10.1109/tcyb.2016.2519448
57 https://doi.org/10.1109/tcyb.2018.2794503
58 https://doi.org/10.1109/thms.2014.2325871
59 https://doi.org/10.1109/thms.2014.2377111
60 https://doi.org/10.1109/tpami.2015.2439257
61 https://doi.org/10.1109/tpami.2017.2771306
62 https://doi.org/10.1109/wacv.2017.24
63 https://doi.org/10.1145/1922649.1922653
64 https://doi.org/10.1145/1961189.1961199
65 https://doi.org/10.1145/2207676.2208303
66 https://doi.org/10.1145/2398356.2398381
67 https://doi.org/10.1145/2629483
68 https://doi.org/10.1145/2964284.2967191
69 https://doi.org/10.3389/fnbot.2015.00003
70 https://doi.org/10.5244/c.25.67
71 schema:datePublished 2019-04
72 schema:datePublishedReg 2019-04-01
73 schema:description Over the last few decades, human action recognition has become one of the most challenging tasks in the field of computer vision. Effortless and accurate extraction of 3D skeleton information has been recently achieved by means of economical depth sensors and state-of-the-art deep learning approaches. In this study, we introduce a novel bag-of-poses framework for action recognition using 3D skeleton data. Our assumption is that any action can be represented by a set of predefined spatiotemporal poses. The pose descriptor is composed of three parts. The first part is concatenation of the normalized coordinate of the skeleton joints. The second part is consisted of temporal displacement of the joints constructed with predefined temporal offset, and the third part is temporal displacement with the previous frame in the sequence. In order to generate the key poses, we apply K-means clustering over all the training pose descriptors of the dataset. SVM classifier is trained with the generated key poses to classify an action pose. Accordingly, every action in the dataset is encoded with key pose histograms. ELM classifier is used for action recognition due to its fast, accurate and reliable performance compared to the other classifiers. The proposed framework is validated with five publicly available benchmark 3D action datasets and achieved state-of-the-art results on three of the datasets and competitive results on the other two datasets compared to the other methods.
74 schema:genre research_article
75 schema:inLanguage en
76 schema:isAccessibleForFree false
77 schema:isPartOf N2dfdcaa7c27e4698956348e674cc1629
78 Ne2c53fe2136a43e782513ed001d8f28a
79 sg:journal.1046897
80 schema:name Improving bag-of-poses with semi-temporal pose descriptors for skeleton-based action recognition
81 schema:pagination 1-17
82 schema:productId N600ac3eaa12c4c1fa699725cff95cdc5
83 Ncf9f33268b074dc5a1689cd6eff8dbdf
84 Ne2caf31ac1b84654a2ec35660ddf6b27
85 schema:sameAs https://app.dimensions.ai/details/publication/pub.1101142241
86 https://doi.org/10.1007/s00371-018-1489-7
87 schema:sdDatePublished 2019-04-11T13:52
88 schema:sdLicense https://scigraph.springernature.com/explorer/license/
89 schema:sdPublisher Nb17acf1b35334ca38c560fdd62e48542
90 schema:url https://link.springer.com/10.1007%2Fs00371-018-1489-7
91 sgo:license sg:explorer/license/
92 sgo:sdDataset articles
93 rdf:type schema:ScholarlyArticle
94 N2dfdcaa7c27e4698956348e674cc1629 schema:volumeNumber 35
95 rdf:type schema:PublicationVolume
96 N600ac3eaa12c4c1fa699725cff95cdc5 schema:name dimensions_id
97 schema:value pub.1101142241
98 rdf:type schema:PropertyValue
99 Na8a66fc6adf548979bc06fc4a3863532 rdf:first sg:person.015361664075.20
100 rdf:rest Nc64cdabd6f7047b0bd97a475ff3dd540
101 Nb17acf1b35334ca38c560fdd62e48542 schema:name Springer Nature - SN SciGraph project
102 rdf:type schema:Organization
103 Nc64cdabd6f7047b0bd97a475ff3dd540 rdf:first sg:person.0715413177.67
104 rdf:rest rdf:nil
105 Ncf11545f2fc3475c9dbfc0560988e0d1 rdf:first sg:person.012402112645.25
106 rdf:rest Na8a66fc6adf548979bc06fc4a3863532
107 Ncf9f33268b074dc5a1689cd6eff8dbdf schema:name readcube_id
108 schema:value cf3da6a4192565abe7001cea9488a2c736f7f1209a6808279b5163bd58008396
109 rdf:type schema:PropertyValue
110 Nd4e534b75fd34ef880d64b1bb203179f schema:name INRIA Sophia Antipolis, 2004 Route des Lucioles, BP93, 06902, Sophia Antipolis Cedex, France
111 rdf:type schema:Organization
112 Ne2c53fe2136a43e782513ed001d8f28a schema:issueNumber 4
113 rdf:type schema:PublicationIssue
114 Ne2caf31ac1b84654a2ec35660ddf6b27 schema:name doi
115 schema:value 10.1007/s00371-018-1489-7
116 rdf:type schema:PropertyValue
117 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
118 schema:name Information and Computing Sciences
119 rdf:type schema:DefinedTerm
120 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
121 schema:name Artificial Intelligence and Image Processing
122 rdf:type schema:DefinedTerm
123 sg:journal.1046897 schema:issn 0178-2789
124 1432-2315
125 schema:name The Visual Computer
126 rdf:type schema:Periodical
127 sg:person.012402112645.25 schema:affiliation https://www.grid.ac/institutes/grid.31564.35
128 schema:familyName Agahian
129 schema:givenName Saeid
130 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012402112645.25
131 rdf:type schema:Person
132 sg:person.015361664075.20 schema:affiliation Nd4e534b75fd34ef880d64b1bb203179f
133 schema:familyName Negin
134 schema:givenName Farhood
135 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015361664075.20
136 rdf:type schema:Person
137 sg:person.0715413177.67 schema:affiliation https://www.grid.ac/institutes/grid.31564.35
138 schema:familyName Köse
139 schema:givenName Cemal
140 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0715413177.67
141 rdf:type schema:Person
142 sg:pub.10.1007/978-3-319-16814-2_28 schema:sameAs https://app.dimensions.ai/details/publication/pub.1038057488
143 https://doi.org/10.1007/978-3-319-16814-2_28
144 rdf:type schema:CreativeWork
145 sg:pub.10.1007/s00371-012-0752-6 schema:sameAs https://app.dimensions.ai/details/publication/pub.1040316085
146 https://doi.org/10.1007/s00371-012-0752-6
147 rdf:type schema:CreativeWork
148 sg:pub.10.1007/s00371-014-0923-8 schema:sameAs https://app.dimensions.ai/details/publication/pub.1052157236
149 https://doi.org/10.1007/s00371-014-0923-8
150 rdf:type schema:CreativeWork
151 sg:pub.10.1007/s00371-015-1066-2 schema:sameAs https://app.dimensions.ai/details/publication/pub.1038762578
152 https://doi.org/10.1007/s00371-015-1066-2
153 rdf:type schema:CreativeWork
154 sg:pub.10.1007/s11042-015-2448-1 schema:sameAs https://app.dimensions.ai/details/publication/pub.1026185623
155 https://doi.org/10.1007/s11042-015-2448-1
156 rdf:type schema:CreativeWork
157 sg:pub.10.1007/s11263-016-0905-6 schema:sameAs https://app.dimensions.ai/details/publication/pub.1009812065
158 https://doi.org/10.1007/s11263-016-0905-6
159 rdf:type schema:CreativeWork
160 sg:pub.10.1038/nature14539 schema:sameAs https://app.dimensions.ai/details/publication/pub.1010020120
161 https://doi.org/10.1038/nature14539
162 rdf:type schema:CreativeWork
163 https://doi.org/10.1016/j.cviu.2016.03.013 schema:sameAs https://app.dimensions.ai/details/publication/pub.1053138393
164 rdf:type schema:CreativeWork
165 https://doi.org/10.1016/j.cviu.2016.04.005 schema:sameAs https://app.dimensions.ai/details/publication/pub.1005090874
166 rdf:type schema:CreativeWork
167 https://doi.org/10.1016/j.cviu.2017.01.011 schema:sameAs https://app.dimensions.ai/details/publication/pub.1083527203
168 rdf:type schema:CreativeWork
169 https://doi.org/10.1016/j.eswa.2013.08.009 schema:sameAs https://app.dimensions.ai/details/publication/pub.1045453021
170 rdf:type schema:CreativeWork
171 https://doi.org/10.1016/j.eswa.2015.06.013 schema:sameAs https://app.dimensions.ai/details/publication/pub.1038358757
172 rdf:type schema:CreativeWork
173 https://doi.org/10.1016/j.image.2016.01.003 schema:sameAs https://app.dimensions.ai/details/publication/pub.1037182588
174 rdf:type schema:CreativeWork
175 https://doi.org/10.1016/j.imavis.2009.11.014 schema:sameAs https://app.dimensions.ai/details/publication/pub.1035613888
176 rdf:type schema:CreativeWork
177 https://doi.org/10.1016/j.imavis.2016.06.007 schema:sameAs https://app.dimensions.ai/details/publication/pub.1052209661
178 rdf:type schema:CreativeWork
179 https://doi.org/10.1016/j.imavis.2016.11.004 schema:sameAs https://app.dimensions.ai/details/publication/pub.1024434766
180 rdf:type schema:CreativeWork
181 https://doi.org/10.1016/j.jvcir.2014.04.007 schema:sameAs https://app.dimensions.ai/details/publication/pub.1021671430
182 rdf:type schema:CreativeWork
183 https://doi.org/10.1016/j.neucom.2005.12.126 schema:sameAs https://app.dimensions.ai/details/publication/pub.1038265102
184 rdf:type schema:CreativeWork
185 https://doi.org/10.1016/j.neucom.2010.01.020 schema:sameAs https://app.dimensions.ai/details/publication/pub.1003650446
186 rdf:type schema:CreativeWork
187 https://doi.org/10.1016/j.neucom.2013.10.046 schema:sameAs https://app.dimensions.ai/details/publication/pub.1013135277
188 rdf:type schema:CreativeWork
189 https://doi.org/10.1016/j.patcog.2015.11.019 schema:sameAs https://app.dimensions.ai/details/publication/pub.1035547204
190 rdf:type schema:CreativeWork
191 https://doi.org/10.1016/j.patcog.2016.05.019 schema:sameAs https://app.dimensions.ai/details/publication/pub.1028710668
192 rdf:type schema:CreativeWork
193 https://doi.org/10.1016/j.patcog.2016.08.022 schema:sameAs https://app.dimensions.ai/details/publication/pub.1031649924
194 rdf:type schema:CreativeWork
195 https://doi.org/10.1016/j.patcog.2017.01.015 schema:sameAs https://app.dimensions.ai/details/publication/pub.1009835621
196 rdf:type schema:CreativeWork
197 https://doi.org/10.1016/j.patcog.2017.02.030 schema:sameAs https://app.dimensions.ai/details/publication/pub.1084100916
198 rdf:type schema:CreativeWork
199 https://doi.org/10.1016/j.patrec.2014.04.011 schema:sameAs https://app.dimensions.ai/details/publication/pub.1028366752
200 rdf:type schema:CreativeWork
201 https://doi.org/10.1016/j.patrec.2016.05.032 schema:sameAs https://app.dimensions.ai/details/publication/pub.1025012845
202 rdf:type schema:CreativeWork
203 https://doi.org/10.1016/j.patrec.2017.02.001 schema:sameAs https://app.dimensions.ai/details/publication/pub.1083528177
204 rdf:type schema:CreativeWork
205 https://doi.org/10.1016/j.patrec.2017.05.004 schema:sameAs https://app.dimensions.ai/details/publication/pub.1085104142
206 rdf:type schema:CreativeWork
207 https://doi.org/10.1109/acpr.2015.7486569 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093858320
208 rdf:type schema:CreativeWork
209 https://doi.org/10.1109/arso.2014.7020983 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095533640
210 rdf:type schema:CreativeWork
211 https://doi.org/10.1109/cvpr.2001.990935 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093612272
212 rdf:type schema:CreativeWork
213 https://doi.org/10.1109/cvpr.2012.6247806 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094572393
214 rdf:type schema:CreativeWork
215 https://doi.org/10.1109/cvpr.2012.6247813 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094880165
216 rdf:type schema:CreativeWork
217 https://doi.org/10.1109/cvpr.2013.123 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094187924
218 rdf:type schema:CreativeWork
219 https://doi.org/10.1109/cvpr.2014.82 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093487177
220 rdf:type schema:CreativeWork
221 https://doi.org/10.1109/cvpr.2015.7298714 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094903557
222 rdf:type schema:CreativeWork
223 https://doi.org/10.1109/cvpr.2016.289 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093762029
224 rdf:type schema:CreativeWork
225 https://doi.org/10.1109/cvpr.2017.143 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095837104
226 rdf:type schema:CreativeWork
227 https://doi.org/10.1109/cvprw.2010.5543273 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095719282
228 rdf:type schema:CreativeWork
229 https://doi.org/10.1109/cvprw.2012.6239233 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093193872
230 rdf:type schema:CreativeWork
231 https://doi.org/10.1109/dicta.2014.7008101 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094483082
232 rdf:type schema:CreativeWork
233 https://doi.org/10.1109/iccv.2013.342 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094449597
234 rdf:type schema:CreativeWork
235 https://doi.org/10.1109/iccv.2015.460 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094735069
236 rdf:type schema:CreativeWork
237 https://doi.org/10.1109/iccv.2017.115 schema:sameAs https://app.dimensions.ai/details/publication/pub.1100060077
238 rdf:type schema:CreativeWork
239 https://doi.org/10.1109/iccvw.2015.48 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093805559
240 rdf:type schema:CreativeWork
241 https://doi.org/10.1109/icip.2015.7350781 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094540780
242 rdf:type schema:CreativeWork
243 https://doi.org/10.1109/icme.2017.8019313 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095144148
244 rdf:type schema:CreativeWork
245 https://doi.org/10.1109/igcc.2014.7039171 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095480035
246 rdf:type schema:CreativeWork
247 https://doi.org/10.1109/jsen.2015.2487358 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061324392
248 rdf:type schema:CreativeWork
249 https://doi.org/10.1109/tcsvt.2016.2628339 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061576932
250 rdf:type schema:CreativeWork
251 https://doi.org/10.1109/tcyb.2013.2265378 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061579490
252 rdf:type schema:CreativeWork
253 https://doi.org/10.1109/tcyb.2016.2519448 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061580217
254 rdf:type schema:CreativeWork
255 https://doi.org/10.1109/tcyb.2018.2794503 schema:sameAs https://app.dimensions.ai/details/publication/pub.1100757775
256 rdf:type schema:CreativeWork
257 https://doi.org/10.1109/thms.2014.2325871 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061614892
258 rdf:type schema:CreativeWork
259 https://doi.org/10.1109/thms.2014.2377111 schema:sameAs https://app.dimensions.ai/details/publication/pub.1000191632
260 rdf:type schema:CreativeWork
261 https://doi.org/10.1109/tpami.2015.2439257 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061744882
262 rdf:type schema:CreativeWork
263 https://doi.org/10.1109/tpami.2017.2771306 schema:sameAs https://app.dimensions.ai/details/publication/pub.1092606368
264 rdf:type schema:CreativeWork
265 https://doi.org/10.1109/wacv.2017.24 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093356859
266 rdf:type schema:CreativeWork
267 https://doi.org/10.1145/1922649.1922653 schema:sameAs https://app.dimensions.ai/details/publication/pub.1010328552
268 rdf:type schema:CreativeWork
269 https://doi.org/10.1145/1961189.1961199 schema:sameAs https://app.dimensions.ai/details/publication/pub.1013637525
270 rdf:type schema:CreativeWork
271 https://doi.org/10.1145/2207676.2208303 schema:sameAs https://app.dimensions.ai/details/publication/pub.1027964637
272 rdf:type schema:CreativeWork
273 https://doi.org/10.1145/2398356.2398381 schema:sameAs https://app.dimensions.ai/details/publication/pub.1026063546
274 rdf:type schema:CreativeWork
275 https://doi.org/10.1145/2629483 schema:sameAs https://app.dimensions.ai/details/publication/pub.1025796123
276 rdf:type schema:CreativeWork
277 https://doi.org/10.1145/2964284.2967191 schema:sameAs https://app.dimensions.ai/details/publication/pub.1006787465
278 rdf:type schema:CreativeWork
279 https://doi.org/10.3389/fnbot.2015.00003 schema:sameAs https://app.dimensions.ai/details/publication/pub.1033622469
280 rdf:type schema:CreativeWork
281 https://doi.org/10.5244/c.25.67 schema:sameAs https://app.dimensions.ai/details/publication/pub.1099341406
282 rdf:type schema:CreativeWork
283 https://www.grid.ac/institutes/grid.31564.35 schema:alternateName Karadeniz Technical University
284 schema:name Department of Computer Engineering, Faculty of Engineering, Karadeniz Technical University, 61080, Trabzon, Turkey
285 rdf:type schema:Organization
 




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


...