{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T16:21:43Z","timestamp":1791303703340,"version":"4.1.0"},"reference-count":70,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Shenzhen Science and Technology","award":["JCYJ20220818103006012"],"award-info":[{"award-number":["JCYJ20220818103006012"]}]},{"name":"Shenzhen Science and Technology","award":["ZDSYS20211021111415025"],"award-info":[{"award-number":["ZDSYS20211021111415025"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2023.3283879","type":"journal-article","created":{"date-parts":[[2023,6,7]],"date-time":"2023-06-07T13:35:59Z","timestamp":1686144959000},"page":"1613-1625","source":"Crossref","is-referenced-by-count":18,"title":["End-to-End Video Scene Graph Generation With Temporal Propagation Transformer"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5396-4549","authenticated-orcid":false,"given":"Yong","family":"Zhang","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4344-8898","authenticated-orcid":false,"given":"Yingwei","family":"Pan","sequence":"additional","affiliation":[{"name":"HiDream.ai Inc., China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7587-101X","authenticated-orcid":false,"given":"Ting","family":"Yao","sequence":"additional","affiliation":[{"name":"HiDream.ai Inc., China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7950-1662","authenticated-orcid":false,"given":"Rui","family":"Huang","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2497-7732","authenticated-orcid":false,"given":"Tao","family":"Mei","sequence":"additional","affiliation":[{"name":"HiDream.ai Inc., China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6720-234X","authenticated-orcid":false,"given":"Chang-Wen","family":"Chen","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University, Hong Kong, SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00611"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_41"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.330"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00678"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00377"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01888"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3514041"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01894"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298990"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01094"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2896516"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01098"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00271"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00857"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3169065"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00133"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01025"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01343"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3463944.3469097"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475636"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00800"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00510"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01350"},{"key":"ref25","first-page":"23345","article-title":"Video-based human-object interaction detection from tubelet tokens","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Tu","year":"2022"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00507"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref30","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhu","year":"2020"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3155928"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58592-1_36"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01180"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_24"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123380"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3109430"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_25"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2943753"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref40","article-title":"An image is worth 16  16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2020"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3164083"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19806-9_19"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2023.3268446"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3551581"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i10.17034"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02237"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00014"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01165"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_38"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00864"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00857"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_32"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3141891"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_1"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7533003"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2074"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00956"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01606"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/3323873.3325056"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_51"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.142"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00380"},{"key":"ref67","article-title":"Motchallenge 2015: Towards a benchmark for multi-target tracking","author":"Leal-Taix","year":"2015"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01375-2"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1115\/1.3662552"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_31"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10145598.pdf?arnumber=10145598","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T03:31:10Z","timestamp":1725679870000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10145598\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":70,"URL":"https:\/\/doi.org\/10.1109\/tmm.2023.3283879","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}