{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T02:54:22Z","timestamp":1775184862521,"version":"3.50.1"},"reference-count":77,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004663","name":"Ministry of Science and Technology, R.O.C.","doi-asserted-by":"publisher","award":["MOST 110-2221-E-011-071-MY2"],"award-info":[{"award-number":["MOST 110-2221-E-011-071-MY2"]}],"id":[{"id":"10.13039\/501100004663","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004663","name":"Ministry of Science and Technology, R.O.C.","doi-asserted-by":"publisher","award":["MOST 109-2221-E-011-131"],"award-info":[{"award-number":["MOST 109-2221-E-011-131"]}],"id":[{"id":"10.13039\/501100004663","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/tip.2021.3113570","type":"journal-article","created":{"date-parts":[[2021,9,23]],"date-time":"2021-09-23T22:20:34Z","timestamp":1632435634000},"page":"8184-8199","source":"Crossref","is-referenced-by-count":18,"title":["Relational Reasoning for Group Activity Recognition via Self-Attention Augmented Conditional Random Field"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6668-5167","authenticated-orcid":false,"given":"Rizard Renanda Adhi","family":"Pramono","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6402-2688","authenticated-orcid":false,"given":"Wen-Hsien","family":"Fang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7221-1603","authenticated-orcid":false,"given":"Yie-Tarng","family":"Chen","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.620"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.228"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74936-3_22"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995707"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00734"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093500"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_19"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00054"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2778563"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2019.2923918"},{"key":"ref33","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"Proc North Amer Chapter Assoc Comput Linguistics Hum Lang Technol"},{"key":"ref32","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.601"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.179"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00584"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_5"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.2973720"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2945111"},{"key":"ref60","article-title":"Graph attention networks","author":"veli?kovi?","year":"2018","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref62","article-title":"StructPool: Structured graph pooling via conditional random fields","author":"yuan","year":"2020","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330888"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_33"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_35"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_39"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58598-3_13"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00902"},{"key":"ref66","author":"goodfellow","year":"2016","journal-title":"Deep Learning"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00092"},{"key":"ref67","first-page":"1","article-title":"Supervised contrastive learning","author":"khosla","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref68","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","author":"chen","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref69","first-page":"1282","article-title":"What are they doing?: Collective activity classification using spatio-temporal relationship among people","author":"choi","year":"2009","journal-title":"Proc IEEE 12th Int Conf Comput Vis Workshops (ICCV Workshops)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_44"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2894161"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2942030"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.173"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.783"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3034233"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00808"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/872"},{"key":"ref25","article-title":"Geom-GCN: Geometric graph convolutional networks","author":"pei","year":"2020","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995386"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1006\/cviu.2000.0896"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.573"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459248"},{"key":"ref57","first-page":"109","article-title":"Efficient inference in fully connected CRFs with Gaussian edge potentials","author":"kr\u00e4henb\u00fchl","year":"2011","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref56","first-page":"282","article-title":"Dynamic conditional random fields: Factorized probabilistic models for labeling and segmenting sequence data","author":"sutton","year":"2001","journal-title":"Proc 21st Int Conf Mach Learn (ICML)"},{"key":"ref55","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","author":"simonyan","year":"2014","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3031371"},{"key":"ref52","first-page":"10156","article-title":"G-TAD: Sub-graph localization for temporal action detection","author":"xu","year":"2020","journal-title":"Proc IEEE\/CVF Conf Comput Vis Pattern Recognit (CVPR)"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.313"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.516"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.453"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00180"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240572"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00106"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2930344"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2928540"},{"key":"ref18","first-page":"4997","article-title":"Learning semantics-preserving attention and contextual interaction for group activity recognition","volume":"28","author":"tang","year":"2019","journal-title":"IEEE Access"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2978942"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01020"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.365"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33765-9_16"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.217"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298875"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_37"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00015"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2918725"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459156"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3050918"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00125"},{"key":"ref47","article-title":"Universal transformers","author":"dehghani","year":"2019","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_6"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.683"},{"key":"ref44","first-page":"4263","article-title":"An end-to-end spatio-temporal attention model for human action recognition from skeleton data","author":"song","year":"2017","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3043093"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/9263394\/09547058.pdf?arnumber=9547058","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:50:19Z","timestamp":1652194219000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9547058\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":77,"URL":"https:\/\/doi.org\/10.1109\/tip.2021.3113570","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}