{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T11:26:11Z","timestamp":1764588371707,"version":"3.37.3"},"reference-count":111,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/100010661","name":"European Union\u2019s Horizon 2020 Programme","doi-asserted-by":"publisher","award":["832921","101021866"],"award-info":[{"award-number":["832921","101021866"]}],"id":[{"id":"10.13039\/100010661","id-type":"DOI","asserted-by":"publisher"}]},{"name":"QuaLiSID\u2014Quality of Life Support System for People with Intellectual Disability Project"},{"name":"European Union and Greek National Funds through the Operational Program Competitiveness, Entrepreneurship and Innovation, under the Call RESEARCH-CREATE-INNOVATE","award":["T2EDK-00306"],"award-info":[{"award-number":["T2EDK-00306"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/access.2022.3213652","type":"journal-article","created":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T20:08:36Z","timestamp":1665432516000},"page":"108797-108816","source":"Crossref","is-referenced-by-count":14,"title":["ViGAT: Bottom-Up Event Recognition and Explanation in Video Using Factorized Graph Attention Network"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6741-3334","authenticated-orcid":false,"given":"Nikolaos","family":"Gkalelis","sequence":"first","affiliation":[{"name":"Centre for Research and Technology Hellas (CERTH), Information Technologies Institute, Thermi, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dimitrios","family":"Daskalakis","sequence":"additional","affiliation":[{"name":"Centre for Research and Technology Hellas (CERTH), Information Technologies Institute, Thermi, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0121-4364","authenticated-orcid":false,"given":"Vasileios","family":"Mezaris","sequence":"additional","affiliation":[{"name":"Centre for Research and Technology Hellas (CERTH), Information Technologies Institute, Thermi, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3144035"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3155123"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3101175"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3014606"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00376"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01535"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58571-6_6"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2894161"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_25"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01332"},{"key":"ref11","first-page":"4","article-title":"Is space-time attention all you need for video understanding?","volume-title":"Proc. ICML","author":"Bertasius"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00675"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01325"},{"key":"ref15","first-page":"1","article-title":"Focused attention for action recognition","volume-title":"Proc. BMVC","author":"Sydorov"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01182"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00609"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00090"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01943"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(95)00025-9"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/34.730558"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1126\/science.1115593"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.83"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1037\/0096-3445.130.1.29"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2007.11.004"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01025"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref28","first-page":"6000","article-title":"Attention is all you need","volume-title":"Proc. NIPS","author":"Vaswani"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref30","first-page":"6511","article-title":"Compact generalized non-local network","volume-title":"Proc. NIPS","author":"Yue"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.90"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00335"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref34","first-page":"1","article-title":"Tying word vectors and word classifiers: A loss framework for language modeling","volume-title":"Proc. ICLR","author":"Inan"},{"key":"ref35","first-page":"1","article-title":"ALBERT: A lite BERT for self-supervised learning of language representations","volume-title":"Proc. ICLR","author":"Lan"},{"key":"ref36","first-page":"6437","article-title":"Training graph neural networks with 1000 layers","volume-title":"Proc. ICML","volume":"139","author":"Li"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2670560"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref40","article-title":"A comprehensive study of deep video action recognition","author":"Zhu","year":"2020","journal-title":"arXiv:2012.06567"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-020-09904-8"},{"key":"ref42","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","volume-title":"Proc. NIPS","volume":"1","author":"Simonyan"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018674"},{"key":"ref45","first-page":"13587","article-title":"Temporal-attentive covariance pooling networks for video recognition","volume-title":"Proc. NIPS","author":"Gao"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2682196"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540039"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.337"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2711011"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2959426"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2896029"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW.2018.8551529"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_24"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00137"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00632"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01047"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01508-1"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01594"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16235"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00807"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00685"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01212"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3134694"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3132916"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3189253"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3135868"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3099856"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00470"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00633"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00023"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.00028"},{"key":"ref76","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. ICML","volume":"97","author":"Tan"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01596"},{"key":"ref78","first-page":"1","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. ICLR","author":"Dosovitskiy"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3100842"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00037"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3070688"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01180"},{"key":"ref83","first-page":"379","article-title":"R-FCN: Object detection via region-based fully convolutional networks","volume-title":"Proc. NIPS","author":"Dai"},{"issue":"1","key":"ref84","first-page":"32","article-title":"Low-cost CNN for automatic violence recognition on embedded system","volume":"5","author":"Munkres","year":"1957","journal-title":"Algorithms Assignment Transp. Problems"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/icassp39728.2021.9414942"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3204236"},{"key":"ref87","first-page":"9240","article-title":"GNNExplainer: Generating explanations for graph neural networks","volume-title":"Proc. NIPS","author":"Ying"},{"key":"ref88","first-page":"8969","article-title":"Probing GNN explainers: A rigorous theoretical and empirical analysis of GNN explanation methods","volume-title":"Proc. IEEE\/CVF 25th Int. Conf. Artif. Intell. Statist.","volume":"151","author":"Agarwal"},{"key":"ref89","first-page":"1","article-title":"PGM-Explainer: Probabilistic graphical model explanations for graph neural networks","volume-title":"Proc. NIPS","author":"Vu"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3201170"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01103"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/wacv45572.2020.9093360"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2008.2005605"},{"key":"ref94","first-page":"1","article-title":"Graph attention networks","volume-title":"Proc. ICLR","author":"Velickovic"},{"key":"ref95","first-page":"1","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"Proc. ICLR","author":"Kipf"},{"key":"ref96","article-title":"Layer normalization","author":"Ba","year":"2016","journal-title":"arXiv:1607.06450"},{"key":"ref97","first-page":"3734","article-title":"Self-attention graph pooling","volume-title":"Proc. ICML","author":"Lee"},{"key":"ref98","first-page":"1263","article-title":"Neural message passing for quantum chemistry","volume-title":"Proc. 34th Int. Conf. Mach. Learn. (ICML)","volume":"70","author":"Gilmer"},{"key":"ref99","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017","journal-title":"arXiv:1705.06950"},{"key":"ref100","first-page":"1","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. NIPS","volume":"28","author":"Ren"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1007\/springerreference_63593"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00097"},{"volume-title":"Flop Counter for PyTorch Models","year":"2022","key":"ref105"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/WF-IoT48130.2020.9221150"},{"key":"ref108","first-page":"15475","article-title":"ResT: An efficient transformer for visual recognition","volume-title":"Proc. NIPS","volume":"34","author":"Zhang"},{"key":"ref109","first-page":"1725","article-title":"Simple and deep graph convolutional networks","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","volume":"119","author":"Chen"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2013.6738901"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00092"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9668973\/09915576.pdf?arnumber=9915576","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,24]],"date-time":"2024-01-24T02:07:51Z","timestamp":1706062071000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9915576\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":111,"URL":"https:\/\/doi.org\/10.1109\/access.2022.3213652","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2022]]}}}