{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T10:39:26Z","timestamp":1774435166934,"version":"3.50.1"},"reference-count":79,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"CCF-Baidu Open Fund"},{"name":"Zhejiang Lab's Open Fund","award":["2019KD0AB04"],"award-info":[{"award-number":["2019KD0AB04"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2022,6,1]]},"DOI":"10.1109\/tpami.2021.3049156","type":"journal-article","created":{"date-parts":[[2021,1,5]],"date-time":"2021-01-05T23:02:15Z","timestamp":1609887735000},"page":"2827-2840","source":"Crossref","is-referenced-by-count":83,"title":["Cascaded Parsing of Human-Object Interaction Recognition"],"prefix":"10.1109","volume":"44","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5475-1473","authenticated-orcid":false,"given":"Tianfei","family":"Zhou","sequence":"first","affiliation":[{"name":"ETH Zurich, Zurich, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4070-733X","authenticated-orcid":false,"given":"Siyuan","family":"Qi","sequence":"additional","affiliation":[{"name":"Google, Mountain View, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0802-9567","authenticated-orcid":false,"given":"Wenguan","family":"Wang","sequence":"additional","affiliation":[{"name":"ETH Zurich, Zurich, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2656-3082","authenticated-orcid":false,"given":"Jianbing","family":"Shen","sequence":"additional","affiliation":[{"name":"State Key Laboratory of IOTSC, Department of Computer and Information Science, University of Macau, Macau, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1925-5973","authenticated-orcid":false,"given":"Song-Chun","family":"Zhu","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01363"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00895"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_39"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_41"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4012"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.4324\/9781315740218"},{"key":"ref39","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00611"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00872"},{"key":"ref78","first-page":"1","article-title":"Gated graph sequence neural networks","author":"li","year":"2016","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref79","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.390"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33765-9_12"},{"key":"ref31","first-page":"1503","article-title":"Learning person-object interactions for action recognition in still images","author":"delaitre","year":"2011","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126386"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00048"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_25"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00056"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2731842"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2008.2005605"},{"key":"ref61","first-page":"1785","article-title":"Learning deep structured models","author":"chen","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref63","article-title":"Representation learning on graphs: Methods and applications","author":"hamilton","year":"2017"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.83"},{"key":"ref64","first-page":"1263","article-title":"Neural message passing for quantum chemistry","author":"gilmer","year":"2017","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383331"},{"key":"ref65","first-page":"1","article-title":"Graph attention networks","author":"velickovic","year":"2018","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.10"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540234"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.330"},{"key":"ref68","article-title":"Group-wise semantic mining for weakly supervised semantic segmentation","author":"li","year":"2020"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00933"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00432"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_25"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.122"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00212"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01021"},{"key":"ref24","first-page":"7710","article-title":"Probabilistic logic neural networks for reasoning","author":"qu","year":"2019","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00370"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00093"},{"key":"ref25","article-title":"Object affordances graph network for action recognition","author":"tan","year":"2019","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01167"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01247-4"},{"key":"ref59","first-page":"1799","article-title":"Joint training of a convolutional network and a graphical model for human pose estimation","author":"tompson","year":"2014","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_29"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.214"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00511"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00644"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000013087.49260.fb"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.1315141"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_13"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01020"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00956"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00582"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6855"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00710"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00269"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1126\/science.220.4598.671"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539906"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-006-7899-4"},{"key":"ref19","article-title":"Visual semantic role labeling","author":"gupta","year":"2015"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01041"},{"key":"ref3","first-page":"8334","article-title":"Learning conditioned graph structures for interpretable visual question answering","author":"norcliffe-brown","year":"2018","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00449"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00683"},{"key":"ref8","article-title":"Learning pose grammar to encode human body configuration for 3D pose estimation","author":"fang","year":"2018","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00207"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00580"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00133"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_15"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00207"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00181"},{"key":"ref47","first-page":"7631","article-title":"HCVRD: A benchmark for large-scale human-centered visual relationship detection","author":"zhuang","year":"2018","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00977"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_4"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00579"},{"key":"ref43","first-page":"1","article-title":"iCAN: Instance-centric attention network for human-object interaction detection","author":"gao","year":"2018","journal-title":"Proc Brit Mach Vis Conf"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/9769881\/09314241.pdf?arnumber=9314241","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,6]],"date-time":"2022-06-06T20:17:17Z","timestamp":1654546637000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9314241\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,1]]},"references-count":79,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2021.3049156","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,6,1]]}}}