{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T14:55:57Z","timestamp":1784300157538,"version":"3.55.0"},"reference-count":52,"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":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62172452"],"award-info":[{"award-number":["62172452"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangxi Science and Technology Plan Project","award":["GuikeAD23026034"],"award-info":[{"award-number":["GuikeAD23026034"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2024.3443661","type":"journal-article","created":{"date-parts":[[2024,8,14]],"date-time":"2024-08-14T17:39:14Z","timestamp":1723657154000},"page":"11176-11190","source":"Crossref","is-referenced-by-count":2,"title":["HSSHG: Heuristic Semantics-Constrained Spatio-Temporal Heterogeneous Graph for VideoQA"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2712-4412","authenticated-orcid":false,"given":"Ruomei","family":"Wang","sequence":"first","affiliation":[{"name":"School of Software Engineering, Sun Yat-sen University, Zhuhai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8035-6737","authenticated-orcid":false,"given":"Yuanmao","family":"Luo","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, National Engineering Research Center of Digital Life, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0179-9988","authenticated-orcid":false,"given":"Fuwei","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, North University of China, Taiyuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3630-5821","authenticated-orcid":false,"given":"Mingyang","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, National Engineering Research Center of Digital Life, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0751-5045","authenticated-orcid":false,"given":"Xiaonan","family":"Luo","sequence":"additional","affiliation":[{"name":"School of Computer Science and Information Security, Guilin University of Electronic Technology, Guilin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3002667"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2935678"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_34"},{"key":"ref4","first-page":"2758","article-title":"Hierarchical conditional relation networks for video question answering","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Jang","year":"2017"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00999"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00685"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475193"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20184"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.730"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-017-1033-7"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/512"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2746267"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123427"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2859820"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240563"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00210"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00853"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00688"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_3"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3076556"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6767"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3185900"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019127"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d18-1167"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3321505"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018658"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6737"},{"key":"ref30","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611737"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00035"},{"key":"ref33","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Li","year":"2023"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2008.2005605"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/88"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3120544"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01527"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.481"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3097171"},{"key":"ref40","article-title":"YOLO by Ultralytics","author":"Jocher","year":"2023"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref42","article-title":"All-MPNet-base-V2","author":"Espejel","year":"2021"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref44","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. 3rd Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2940677"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2995959"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.repl4nlp-1.15"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3120867"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3142526"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3205212"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3366710"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10384483\/10636771.pdf?arnumber=10636771","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:26:07Z","timestamp":1732667167000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10636771\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/tmm.2024.3443661","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}