{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T16:53:56Z","timestamp":1776272036054,"version":"3.50.1"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2020,6,1]],"date-time":"2020-06-01T00:00:00Z","timestamp":1590969600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,6,1]],"date-time":"2020-06-01T00:00:00Z","timestamp":1590969600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,6,1]],"date-time":"2020-06-01T00:00:00Z","timestamp":1590969600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Research Foundation, Prime Minister's Office, Singapore"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2020,6]]},"DOI":"10.1109\/tmm.2019.2943753","type":"journal-article","created":{"date-parts":[[2019,9,25]],"date-time":"2019-09-25T19:58:24Z","timestamp":1569441504000},"page":"1423-1432","source":"Crossref","is-referenced-by-count":91,"title":["Interact as You Intend: Intention-Driven Human-Object Interaction Detection"],"prefix":"10.1109","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2957-8204","authenticated-orcid":false,"given":"Bingjie","family":"Xu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5217-9204","authenticated-orcid":false,"given":"Junnan","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1239-4428","authenticated-orcid":false,"given":"Yongkang","family":"Wong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qi","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4846-2015","authenticated-orcid":false,"given":"Mohan S.","family":"Kankanhalli","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00676"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.370"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2010.00217"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00181"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_15"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_25"},{"key":"ref37","first-page":"199","article-title":"Where are they looking","author":"recasens","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2482819"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33718-5_23"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/S0042-6989(01)00102-X"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.325"},{"key":"ref40","article-title":"Detectron","author":"girshick","year":"2018"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.83"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2617079"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00872"},{"key":"ref14","article-title":"Visual semantic role labeling","author":"gupta","year":"2015"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00048"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2788210"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"1691","DOI":"10.1109\/TPAMI.2012.67","article-title":"Recognizing human-object interactions in still images by modeling the mutual context of objects and human poses","volume":"34","author":"yao","year":"2012","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.390"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.122"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.331"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2846411"},{"key":"ref27","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989778"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00718"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2015.09.042"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.289"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_51"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.142"},{"key":"ref20","first-page":"7631","article-title":"HCVRD: A benchmark for large-scale human-centered visual relationship detection","author":"zhuang","year":"0","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref45","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1006\/jesp.1996.1314"},{"key":"ref21","first-page":"41","article-title":"iCAN: Instance-centric attention network for human-object interaction detection","author":"gao","year":"0","journal-title":"Proc Brit Mach Vision Conf"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00711"},{"key":"ref42","first-page":"2787","article-title":"Translating embeddings for modeling multi-relational data","author":"bordes","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s002210100745"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.143"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.129"},{"key":"ref44","first-page":"740","article-title":"Microsoft COCO: Common objects in context","volume":"8693","author":"lin","year":"0","journal-title":"Proc Eur Conf Comput Vision"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2723009"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/9097818\/08848601.pdf?arnumber=8848601","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T15:56:13Z","timestamp":1651074973000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8848601\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,6]]},"references-count":45,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tmm.2019.2943753","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,6]]}}}