{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,6]],"date-time":"2025-11-06T11:45:29Z","timestamp":1762429529733,"version":"3.37.3"},"reference-count":66,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"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":["62273203","U1813215"],"award-info":[{"award-number":["62273203","U1813215"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Special Fund for the Taishan Scholars Program of Shandong Province","award":["ts201511005"],"award-info":[{"award-number":["ts201511005"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,6]]},"DOI":"10.1109\/tcsvt.2023.3339292","type":"journal-article","created":{"date-parts":[[2023,12,4]],"date-time":"2023-12-04T19:01:58Z","timestamp":1701716518000},"page":"4957-4972","source":"Crossref","is-referenced-by-count":4,"title":["An Active Task Cognition Method for Home Service Robot Using Multi-Graph Attention Fusion Mechanism"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8302-2907","authenticated-orcid":false,"given":"Yongcheng","family":"Cui","sequence":"first","affiliation":[{"name":"School of Control Science and Engineering, Shandong University, Jinan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8332-3064","authenticated-orcid":false,"given":"Guohui","family":"Tian","sequence":"additional","affiliation":[{"name":"School of Control Science and Engineering, Shandong University, Jinan, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2651-2354","authenticated-orcid":false,"given":"Zhengsong","family":"Jiang","sequence":"additional","affiliation":[{"name":"School of Control Science and Engineering, Shandong University, Jinan, China"}]},{"given":"Mengyang","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Shandong Normal University, Jinan, China"}]},{"given":"Yu","family":"Gu","sequence":"additional","affiliation":[{"name":"School of Control Science and Engineering, Shandong University, Jinan, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-2679-4266","authenticated-orcid":false,"given":"Yifei","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Information, University of California at Berkeley, Berkeley, CA, USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2577031"},{"key":"ref3","article-title":"YOLOv3: An incremental improvement","author":"Redmon","year":"2018","journal-title":"arXiv:1804.02767"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00312"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.330"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.352"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAR49639.2020.9108083"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981735"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3218790"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3086066"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1017\/S0263574722001205"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00611"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref14","article-title":"Incorporating external knowledge to answer open-domain visual questions with dynamic memory networks","author":"Li","year":"2017","journal-title":"arXiv:1712.00733"},{"key":"ref15","first-page":"23318","article-title":"OFA: Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220036"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2995959"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341186"},{"key":"ref19","first-page":"53","article-title":"Neural modular control for embodied question answering","volume-title":"Proc. Conf. Robot Learn.","author":"Das"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3139957"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.40"},{"key":"ref22","article-title":"Image captioning and visual question answering based on attributes and external knowledge","author":"Wu","year":"2016","journal-title":"arXiv:1603.02814"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.344"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3579051.3579053"},{"key":"ref25","first-page":"8344","article-title":"Learning conditioned graph structures for interpretable visual question answering","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Norcliffe-Brown"},{"key":"ref26","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"arXiv:2301.12597"},{"key":"ref27","article-title":"Florence: A new foundation model for computer vision","author":"Yuan","year":"2021","journal-title":"arXiv:2111.11432"},{"key":"ref28","article-title":"Semi-supervised classification with graph convolutional networks","author":"Kipf","year":"2016","journal-title":"arXiv:1609.02907"},{"key":"ref29","article-title":"Graph attention networks","author":"Veli\u010dkovi\u0107","year":"2017","journal-title":"arXiv:1710.10903"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00532"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00052"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3112551"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00475"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3118983"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ROBIO54168.2021.9739429"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3189242"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3142260"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3176880"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3247159"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref41","article-title":"Efficient estimation of word representations in vector space","author":"Mikolov","year":"2013","journal-title":"arXiv:1301.3781"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2019.09.020"},{"volume-title":"Sparql Protocol for RDF","year":"2008","key":"ref43"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00197"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.106059"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00887"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206537"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2723009"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968108"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636700"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636024"},{"key":"ref53","article-title":"Places: An image database for deep scene understanding","author":"Zhou","year":"2016","journal-title":"arXiv:1610.02055"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00502"},{"key":"ref55","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"34","author":"Li"},{"key":"ref56","article-title":"Prismer: A vision-language model with an ensemble of experts","author":"Liu","year":"2023","journal-title":"arXiv:2303.02506"},{"key":"ref57","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Alayrac"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.488"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00012"},{"key":"ref60","article-title":"Query2Label: A simple transformer way to multi-label classification","author":"Liu","year":"2021","journal-title":"arXiv:2107.10834"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3300537"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00700"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01187"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.117954"},{"issue":"529","key":"ref65","first-page":"1","article-title":"Reinforcement learning based graph-to-sequence model for natural question generation","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Chen"},{"article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","year":"2023","key":"ref66"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10550083\/10341288.pdf?arnumber=10341288","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,25]],"date-time":"2024-06-25T21:18:25Z","timestamp":1719350305000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10341288\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6]]},"references-count":66,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2023.3339292","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"type":"print","value":"1051-8215"},{"type":"electronic","value":"1558-2205"}],"subject":[],"published":{"date-parts":[[2024,6]]}}}