{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,2]],"date-time":"2025-11-02T12:58:59Z","timestamp":1762088339508,"version":"build-2065373602"},"reference-count":70,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2018AAA0102503"],"award-info":[{"award-number":["2018AAA0102503"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U2001202","62132006"],"award-info":[{"award-number":["U2001202","62132006"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017610","name":"Shenzhen Science and Technology Program","doi-asserted-by":"publisher","award":["20220016"],"award-info":[{"award-number":["20220016"]}],"id":[{"id":"10.13039\/501100017610","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tip.2023.3270040","type":"journal-article","created":{"date-parts":[[2023,4,28]],"date-time":"2023-04-28T18:30:56Z","timestamp":1682706656000},"page":"2468-2480","source":"Crossref","is-referenced-by-count":5,"title":["Cognition Guided Human-Object Relationship Detection"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9716-5626","authenticated-orcid":false,"given":"Zhitao","family":"Zeng","sequence":"first","affiliation":[{"name":"State Key Laboratory of Information Security, Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6262-982X","authenticated-orcid":false,"given":"Pengwen","family":"Dai","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Technology, Shenzhen Campus, Sun Yat-sen University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7800-363X","authenticated-orcid":false,"given":"Xuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Academy for Advanced Interdisciplinary Studies, Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Zhang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Information Security, Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7141-708X","authenticated-orcid":false,"given":"Xiaochun","family":"Cao","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Technology, Shenzhen Campus, Sun Yat-sen University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","first-page":"670","article-title":"Graph R-CNN for scene graph generation","author":"yang","year":"2018","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref57","first-page":"41","article-title":"iCAN: Instance-centric attention network for human-object interaction detection","author":"gao","year":"2018","journal-title":"Proc BMVC"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref56","article-title":"Exploiting long-term dependencies for generating dynamic scene graphs","author":"feng","year":"2021","journal-title":"arXiv 2112 09828"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00377"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01180"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00093"},{"key":"ref53","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1109\/TNN.2008.2005605","article-title":"The graph neural network model","volume":"20","author":"scarselli","year":"2016","journal-title":"IEEE Trans Neural Netw"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00678"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3216476"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01606"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3216198"},{"key":"ref54","first-page":"346","article-title":"Factorizable net: An efficient subgraph-based framework for scene graph generation","author":"li","year":"2018","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00048"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01568"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00056"},{"key":"ref18","first-page":"401","article-title":"Learning human-object interactions by graph parsing neural networks","author":"qi","year":"2018","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00611"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00058"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.331"},{"key":"ref45","first-page":"2787","article-title":"Translating embeddings for modeling multi-relational data","author":"bordes","year":"2013","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2992222"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803106"},{"key":"ref42","first-page":"282","article-title":"Conditional random fields: Probabilistic models for segmenting and labeling sequence data","author":"lafferty","year":"2001","journal-title":"Proc 18th Int Conf Mach Learn (ICML)"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01311"},{"key":"ref44","article-title":"Scene graph generation via conditional random fields","author":"cong","year":"2018","journal-title":"arXiv 1811 08075"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.352"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00217"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00037"},{"key":"ref7","first-page":"335","article-title":"Actor-centric relation network","author":"sun","year":"2018","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00033"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3113114"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206205"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00053"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3028207"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2868668"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.213"},{"key":"ref36","first-page":"803","article-title":"Temporal relational reasoning in videos","author":"zhou","year":"2018","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01025"},{"key":"ref33","first-page":"813","article-title":"Is space-time attention all you need for video understanding?","volume":"2","author":"bertasius","year":"0","journal-title":"Proc 38th Int Conf Mach Learn (ICML)"},{"key":"ref32","article-title":"An image is worth 16×16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2021","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/COMM48946.2020.9141973"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00800"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"ref38","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","author":"simonyan","year":"2014","journal-title":"Proc 27th Int Conf Neural Inf Process Syst"},{"key":"ref70","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"2019","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1038\/384074a0"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.142"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3205182"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_51"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/S0896-6273(04)00267-3"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1152\/jn.00822.2006"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00380"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01165"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01352"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP46576.2022.9897219"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2022.3220250"},{"key":"ref66","first-page":"5998","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref21","article-title":"Global-and-Local collaborative learning for co-salient object detection","author":"cong","year":"2022","journal-title":"arXiv 2204 08917"},{"key":"ref65","first-page":"39","article-title":"Computing Euler angles from a rotation matrix","volume":"6","author":"slabaugh","year":"1999","journal-title":"Retrieved August"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.preteyeres.2007.03.004"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2006.05.025"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1038\/359318a0"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00525"},{"journal-title":"Detectron2","year":"2019","author":"wu","key":"ref61"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/9991910\/10112623.pdf?arnumber=10112623","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T17:48:27Z","timestamp":1685382507000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10112623\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":70,"URL":"https:\/\/doi.org\/10.1109\/tip.2023.3270040","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"type":"print","value":"1057-7149"},{"type":"electronic","value":"1941-0042"}],"subject":[],"published":{"date-parts":[[2023]]}}}