{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T18:52:20Z","timestamp":1772823140806,"version":"3.50.1"},"reference-count":64,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T00:00:00Z","timestamp":1688169600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T00:00:00Z","timestamp":1688169600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T00:00:00Z","timestamp":1688169600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Project of China","award":["2021ZD0110700"],"award-info":[{"award-number":["2021ZD0110700"]}]},{"name":"Shanghai Municipal Science and Technology","award":["2021SHZDZX0102"],"award-info":[{"award-number":["2021SHZDZX0102"]}]},{"name":"Shanghai Qi Zhi Institute"},{"DOI":"10.13039\/501100008838","name":"Shanghai Municipal Commission of Economy and Informatization","doi-asserted-by":"publisher","award":["2018-RGZN-02046"],"award-info":[{"award-number":["2018-RGZN-02046"]}],"id":[{"id":"10.13039\/501100008838","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2023,7,1]]},"DOI":"10.1109\/tpami.2022.3232797","type":"journal-article","created":{"date-parts":[[2022,12,29]],"date-time":"2022-12-29T18:42:13Z","timestamp":1672339333000},"page":"8494-8506","source":"Crossref","is-referenced-by-count":26,"title":["HAKE: A Knowledge Engine Foundation for Human Activity Understanding"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0478-0692","authenticated-orcid":false,"given":"Yong-Lu","family":"Li","sequence":"first","affiliation":[{"name":"Qing Yuan Research Institute, Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7525-3243","authenticated-orcid":false,"given":"Xinpeng","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1566-3811","authenticated-orcid":false,"given":"Xiaoqian","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8463-979X","authenticated-orcid":false,"given":"Yizhuo","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"}]},{"given":"Zuoyu","family":"Qiu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6441-4443","authenticated-orcid":false,"given":"Liang","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7489-7269","authenticated-orcid":false,"given":"Yue","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0758-0293","authenticated-orcid":false,"given":"Hao-Shu","family":"Fang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4023-9257","authenticated-orcid":false,"given":"Cewu","family":"Lu","sequence":"additional","affiliation":[{"name":"Shanghai Digital Medicine Innovation Center, Ruijin Hospital, Shanghai, China"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00633"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref12","article-title":"Visual semantic role labeling","author":"gupta","year":"2015"},{"key":"ref56","first-page":"3788","article-title":"End-to-end differentiable proving","author":"rockt\u00e4schel","year":"2017","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref15","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","author":"soomro","year":"2012"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_51"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2723009"},{"key":"ref52","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.122"},{"key":"ref55","first-page":"6000","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1017\/S0140525X16001837"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3411949"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.82"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.396"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref18","first-page":"1110","article-title":"Hierarchical recurrent neural network for skeleton based action recognition","author":"du","year":"2015","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref51","article-title":"Learning to describe scenes with programs","author":"liu","year":"2019","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00650"},{"key":"ref46","article-title":"Neural-symbolic VQA: Disentangling reasoning from vision and language understanding","author":"yi","year":"2018"},{"key":"ref45","article-title":"Learning by abstraction: The neural state machine","author":"hudson","year":"2019"},{"key":"ref48","article-title":"Neural logic machines","author":"dong","year":"2019"},{"key":"ref47","article-title":"The neuro-symbolic concept learner: Interpreting scenes, words, and sentences from natural supervision","author":"mao","year":"2019","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540235"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2014.2331759"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.12"},{"key":"ref43","article-title":"Neural-symbolic computing: An effective methodology for principled integration of machine learning and reasoning","author":"garcez","year":"2019"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1180"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/0010-0277(84)90022-2"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s00429-017-1469-0"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1037\/0033-295X.94.2.115"},{"key":"ref4","article-title":"AVID: Learning multi-stage tasks via pixel-level translation of human videos","author":"smith","year":"2019"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-2669-y"},{"key":"ref6","article-title":"From system 1 deep learning to system 2 deep learning","author":"bengio","year":"2019","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00046"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_4"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_5"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_35"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00056"},{"key":"ref36","article-title":"HOI analysis: Integrating and decomposing human-object interaction","author":"li","year":"2020","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00370"},{"key":"ref30","article-title":"iCAN: Instance-centric attention network for human-object interaction detection","author":"gao","year":"2018","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref33","first-page":"1981","article-title":"Detecting rare visual relations using analogies","author":"peyre","year":"2019","journal-title":"Proc IEEE Int Conf Comput Vis"},{"key":"ref32","first-page":"407","article-title":"Learning human-object interactions by graph parsing neural networks","author":"qi","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref2","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00048"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.367"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01027"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.213"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.522"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref20","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":"ref64","author":"pearl","year":"2016","journal-title":"Causal Inference in Statistics A Primer"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref22","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","author":"simonyan","year":"2014","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.284"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.256"},{"key":"ref27","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":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00872"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01018"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00037"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10144448\/10002711.pdf?arnumber=10002711","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,7]],"date-time":"2025-04-07T21:39:39Z","timestamp":1744061979000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10002711\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,1]]},"references-count":64,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2022.3232797","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":[[2023,7,1]]}}}