{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T04:48:00Z","timestamp":1780634880324,"version":"3.54.1"},"reference-count":106,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"German Science Foundation (DFG), Collaborative Research Center","award":["SFB 1528"],"award-info":[{"award-number":["SFB 1528"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3509674","type":"journal-article","created":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T18:41:02Z","timestamp":1733164862000},"page":"180328-180360","source":"Crossref","is-referenced-by-count":3,"title":["A Hierarchical Graph-Based Approach for Recognition and Description Generation of Bimanual Actions in Videos"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1159-3588","authenticated-orcid":false,"given":"Fatemeh","family":"Ziaeetabar","sequence":"first","affiliation":[{"name":"Department of Computer Science, School of Mathematics, Statistics and Computer Science, College of Science, University of Tehran, Tehran, Iran"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2996-3612","authenticated-orcid":false,"given":"Minija","family":"Tamosiunaite","sequence":"additional","affiliation":[{"name":"Faculty of Informatics, Vytautas Magnus University, Kaunas, Lithuania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8206-9738","authenticated-orcid":false,"given":"Florentin","family":"W\u00f6rg\u00f6tter","sequence":"additional","affiliation":[{"name":"Department for Computational Neuroscience, Bernstein Center for Computational Neuroscience, III Physikalisches Institut-Biophysik, Georg-August-Universität Göttingen, Göttingen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1964897.1964918"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MPRV.2014.52"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2009.11.014"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2019.08.100"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-020-01868-8"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmsy.2020.04.007"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2018.07.028"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2018.07.059"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.368"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/431"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-11880-8"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1126\/science.aat8414"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1561\/2300000049"},{"key":"ref14","article-title":"Hands deep in deep learning for hand pose estimation","author":"Oberweger","year":"2015","journal-title":"arXiv:1502.06807"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3390\/app10196850"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/6614.003.0014"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00998"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00462"},{"key":"ref20","first-page":"193","article-title":"Functional hand type prior for 3D hand pose estimation and action recognition from egocentric view monocular videos","volume-title":"Proc. BMVC","author":"Roh"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aaw0955"},{"key":"ref22","first-page":"2327","article-title":"Deep imitation learning for bimanual robotic manipulation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Xie"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2017.12.011"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3285478"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TOH.2023.3272698"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2010.5509319"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01020"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01025"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.330"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_41"},{"issue":"1","key":"ref31","first-page":"1","article-title":"A survey of scene graph: Generation and application","volume":"31","author":"Xu","year":"2020","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01883"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02184"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01791"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02652"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00838"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01606"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00510"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/SKIMA57145.2022.10029570"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01423"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6783"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01096"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812179"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2018.12.027"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00819"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301865"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1023\/A:1020346032608"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.3115\/991813.991856"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.3115\/991719.991737"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2008.4562954"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-017-5438-7"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.450"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.07.029"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/877"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s42979-021-00487-x"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123448"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01295"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00911"},{"key":"ref59","first-page":"847","article-title":"TVT: Two-view transformer network for video Captioning","volume-title":"Proc. Asian Conf. Mach. Learn.","author":"Chen"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.233"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01742"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01743"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01032"},{"key":"ref64","article-title":"A better use of audio-visual cues: Dense video captioning with bi-modal transformer","author":"Iashin","year":"2020","journal-title":"arXiv:2005.08271"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00487"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19781-9_24"},{"key":"ref67","article-title":"YOLOv3: An incremental improvement","author":"Redmon","year":"2018","journal-title":"arXiv:1804.02767"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2929257"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6517"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1177\/0278364911410459"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989536"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2018.10.005"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2949221"},{"key":"ref74","article-title":"Efficient estimation of word representations in vector space","author":"Mikolov","year":"2013","journal-title":"arXiv:1301.3781"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3196158"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00458-8"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.ltedi-1.8"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6523"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01044"},{"key":"ref80","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"arXiv:2005.14165"},{"key":"ref81","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref82","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","author":"Raffel","year":"2019","journal-title":"arXiv:1910.10683"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00417"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00014"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01774"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00661"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12342"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00207"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2018.xiv.019"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2012.6239175"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02035"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161336"},{"key":"ref97","article-title":"AIM: Adapting image models for efficient video action recognition","author":"Yang","year":"2023","journal-title":"arXiv:2302.03024"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917700714"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.116287"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_31"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref102","first-page":"190","article-title":"Collecting highly parallel data for paraphrase evaluation","volume-title":"Proc. 49th Annu. Meeting Assoc. Comput. Linguistics, Hum. Lang. Technol.","author":"Chen"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00795"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01727"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01426"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1002\/mma.9091"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10380310\/10772037.pdf?arnumber=10772037","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,12]],"date-time":"2024-12-12T06:36:52Z","timestamp":1733985412000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10772037\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":106,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3509674","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}