{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T13:27:49Z","timestamp":1772026069660,"version":"3.50.1"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"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":["2020YFF0304900"],"award-info":[{"award-number":["2020YFF0304900"]}],"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":["62072358,62073252"],"award-info":[{"award-number":["62072358,62073252"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,7,18]]},"DOI":"10.1109\/ijcnn55064.2022.9892087","type":"proceedings-article","created":{"date-parts":[[2022,9,30]],"date-time":"2022-09-30T19:56:04Z","timestamp":1664567764000},"page":"1-8","source":"Crossref","is-referenced-by-count":4,"title":["Spatial Parsing and Dynamic Temporal Pooling networks for Human-Object Interaction detection"],"prefix":"10.1109","author":[{"given":"Hongsheng","family":"Li","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Xidian University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guangming","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Xidian University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wu","family":"Zhen","sequence":"additional","affiliation":[{"name":"Beijing Roborock Technology Co.,Ltd."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lan","family":"Ni","sequence":"additional","affiliation":[{"name":"Shanghai University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peiyi","family":"Shen","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Xidian University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Xidian University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ning","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Xidian University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cong","family":"Hua","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Xidian University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00113"},{"key":"ref32","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"ar Xiv preprint"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351040"},{"key":"ref30","article-title":"Graph attention networks","author":"velickovic","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3028207"},{"key":"ref36","first-page":"399","article-title":"Videos as space-time region graphs","author":"wang","year":"2018","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"ref35","first-page":"14","article-title":"Anticipating human activities using object affordances for reactive robotic response","volume":"38","year":"2015","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref10","article-title":"Care about you: towards large-scale human-centric visual relationship detection","author":"zhuang","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref11","article-title":"ican: Instance-centric attention network for human-object interaction detection","author":"gao","year":"2018","journal-title":"ar Xiv preprint"},{"key":"ref12","first-page":"401","article-title":"Learning human-object interactions by graph parsing neural networks","author":"qi","year":"2018","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00048"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.4324\/9781315740218"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913478446"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.573"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3463944.3469097"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.11"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.200"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.234"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00142"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.344"},{"key":"ref3","article-title":"Unsupervised learning of object structure and dynamics from videos","author":"minderer","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_41"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413778"},{"key":"ref5","first-page":"850","article-title":"Fully-convolutional siamese networks for object tracking","author":"bertinetto","year":"0","journal-title":"European Conference on Computer Vision"},{"key":"ref8","first-page":"7297","article-title":"Densepose: Dense human pose estimation in the wild","author":"guler","year":"2018","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2019.00052"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00811"},{"key":"ref9","article-title":"Visual semantic role labeling","author":"gupta","year":"2015","journal-title":"ArXiv Preprint"},{"key":"ref1","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"ar Xiv preprint"},{"key":"ref20","article-title":"Convolutional neural networks on graphs with fast localized spectral filtering","author":"defferrard","year":"0","journal-title":"ar Xiv preprint"},{"key":"ref22","first-page":"1785","article-title":"Learning deep structured models","author":"chen","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","article-title":"Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs","volume":"40","author":"chen","year":"2017","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.448"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_8"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.330"},{"key":"ref25","article-title":"The more you know: Using knowledge graphs for image classification","author":"marino","year":"2016","journal-title":"ArXiv Preprint"}],"event":{"name":"2022 International Joint Conference on Neural Networks (IJCNN)","location":"Padua, Italy","start":{"date-parts":[[2022,7,18]]},"end":{"date-parts":[[2022,7,23]]}},"container-title":["2022 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9891857\/9889787\/09892087.pdf?arnumber=9892087","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T22:56:34Z","timestamp":1667516194000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9892087\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,18]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/ijcnn55064.2022.9892087","relation":{},"subject":[],"published":{"date-parts":[[2022,7,18]]}}}