{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T23:58:57Z","timestamp":1777939137083,"version":"3.51.4"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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 of China","doi-asserted-by":"publisher","award":["62233003"],"award-info":[{"award-number":["62233003"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science of China","doi-asserted-by":"publisher","award":["62073072"],"award-info":[{"award-number":["62073072"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science of China","doi-asserted-by":"publisher","award":["U25A20477"],"award-info":[{"award-number":["U25A20477"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100019014","name":"Shenzhen Science and Technology Program","doi-asserted-by":"publisher","award":["YCYJ20210324132202005"],"award-info":[{"award-number":["YCYJ20210324132202005"]}],"id":[{"id":"10.13039\/501100019014","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100019014","name":"Shenzhen Science and Technology Program","doi-asserted-by":"publisher","award":["YCYJ20220818101206014"],"award-info":[{"award-number":["YCYJ20220818101206014"]}],"id":[{"id":"10.13039\/501100019014","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100019014","name":"Shenzhen Science and Technology Program","doi-asserted-by":"publisher","award":["JCYJ20250604125459006"],"award-info":[{"award-number":["JCYJ20250604125459006"]}],"id":[{"id":"10.13039\/501100019014","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Sci. Eng."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tase.2026.3688262","type":"journal-article","created":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T19:50:43Z","timestamp":1777405843000},"page":"8776-8787","source":"Crossref","is-referenced-by-count":0,"title":["Expectation-Driven and Backtracking Chain-of-Thought With Structured Situational Knowledge Representation for Robotic Cognition and Industrial Situation Understanding"],"prefix":"10.1109","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-7425-6687","authenticated-orcid":false,"given":"Zhiwei","family":"Lv","sequence":"first","affiliation":[{"name":"Key Laboratory of Measurement and Control of CSE, School of Automation, Southeast University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1529-4537","authenticated-orcid":false,"given":"Xinde","family":"Li","sequence":"additional","affiliation":[{"name":"School of Automation, Southeast University, Nanjing, Jiangsu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5132-9502","authenticated-orcid":false,"given":"Kaixuan","family":"Wu","sequence":"additional","affiliation":[{"name":"Key Laboratory of Measurement and Control of CSE, School of Automation, Southeast University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3050-5582","authenticated-orcid":false,"given":"Erfeng","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Engineering, Southeast University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2025.3558616"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2025.3593068"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3475510"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3205212"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00309"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2026.3662386"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00500"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2025.3558847"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2025.3542447"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-92611-2_4"},{"key":"ref11","article-title":"Qwen2-VL: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv:2409.12191"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0010"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00035"},{"key":"ref14","article-title":"ResNetVLLM\u2014Multi-modal vision LLM for the video understanding task","author":"Khalil","year":"2025","journal-title":"arXiv:2504.14432"},{"key":"ref15","article-title":"Video-CCAM: Enhancing video-language understanding with causal cross-attention masks for short and long videos","author":"Fei","year":"2024","journal-title":"arXiv:2408.14023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.286"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2023.08.057"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3345172"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02714"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3212463"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.261"},{"key":"ref22","article-title":"Multimodal chain-of-thought reasoning in language models","author":"Zhang","year":"2023","journal-title":"arXiv:2302.00923"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0228"},{"key":"ref24","article-title":"Scaling video-language models to 10K frames via hierarchical differential distillation","author":"Cheng","year":"2025","journal-title":"arXiv:2504.02438"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1093\/nc\/niw018"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW69036.2025.00154"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00965"},{"key":"ref28","article-title":"STAR: A benchmark for situated reasoning in real-world videos","author":"Wu","year":"2024","journal-title":"arXiv:2405.09711"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01099"},{"key":"ref30","article-title":"Seed1.5-VL technical report","author":"Guo","year":"2025","journal-title":"arXiv:2505. 07062"},{"key":"ref31","article-title":"Ovis: Structural embedding alignment for multimodal large language model","author":"Lu","year":"2024","journal-title":"arXiv:2405.20797"},{"key":"ref32","article-title":"Enhancing the reasoning ability of multimodal large language models via mixed preference optimization","author":"Wang","year":"2024","journal-title":"arXiv:2411.10442"},{"key":"ref33","article-title":"VideoLLaMA 3: Frontier multimodal foundation models for image and video understanding","author":"Zhang","year":"2025","journal-title":"arXiv:2501.13106"},{"key":"ref34","article-title":"VideoChat-flash: Hierarchical compression for long-context video modeling","author":"Li","year":"2024","journal-title":"arXiv:2501.00574"},{"key":"ref35","article-title":"Valley2: Exploring multimodal models with scalable vision-language design","author":"Wu","year":"2025","journal-title":"arXiv:2501.05901"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3354"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1484"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3556422"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02709"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.544"},{"key":"ref41","article-title":"ENTER: Event based interpretable reasoning for VideoQA","author":"Ayyubi","year":"2025","journal-title":"arXiv:2501.14194"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680826"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i4.32416"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02707"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00310"}],"container-title":["IEEE Transactions on Automation Science and Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8856\/11323516\/11498350.pdf?arnumber=11498350","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T05:04:59Z","timestamp":1777698299000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11498350\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/tase.2026.3688262","relation":{},"ISSN":["1545-5955","1558-3783"],"issn-type":[{"value":"1545-5955","type":"print"},{"value":"1558-3783","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}