{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T08:04:27Z","timestamp":1773734667602,"version":"3.50.1"},"reference-count":72,"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 Foundation of China","doi-asserted-by":"publisher","award":["62173189"],"award-info":[{"award-number":["62173189"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62573244"],"award-info":[{"award-number":["62573244"]}],"id":[{"id":"10.13039\/501100001809","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.2026.3670430","type":"journal-article","created":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T20:52:50Z","timestamp":1772657570000},"page":"5968-5981","source":"Crossref","is-referenced-by-count":0,"title":["PipeCLIP: Defect-Conditioned and Cross-Focus-Driven Vision-Language Model for Video-Based Sewer Defect Inspection"],"prefix":"10.1109","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-5437-4593","authenticated-orcid":false,"given":"Chenyang","family":"Zhao","sequence":"first","affiliation":[{"name":"Institute of Robotics and Automatic Information System, Tianjin Key Laboratory of Intelligent Robotics, and the TBI Center, Nankai University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1669-9429","authenticated-orcid":false,"given":"Chuanfei","family":"Hu","sequence":"additional","affiliation":[{"name":"Faculty of Intelligence Technology, Shanghai Institute of Technology, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6038-4147","authenticated-orcid":false,"given":"Zhenzhong","family":"Cao","sequence":"additional","affiliation":[{"name":"Institute of Robotics and Automatic Information System, Tianjin Key Laboratory of Intelligent Robotics, and the TBI Center, Nankai University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6804-1293","authenticated-orcid":false,"given":"Yinuo","family":"Song","sequence":"additional","affiliation":[{"name":"Institute of Robotics and Automatic Information System, Tianjin Key Laboratory of Intelligent Robotics, and the TBI Center, Nankai University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2645-5655","authenticated-orcid":false,"given":"Jingtai","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Robotics and Automatic Information System, Tianjin Key Laboratory of Intelligent Robotics, and the TBI Center, Nankai University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2024.3516710"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2025.3597580"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2020.3022402"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2006.873225"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1080\/15732479.2013.807845"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2019.2900170"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2019.2941848"},{"key":"ref8","first-page":"339","article-title":"AR overlay: Training image pose estimation on curved surface in a synthetic way","volume-title":"CS IT Conf. Proc.","author":"Huang"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202306"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmst.2024.03.003"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.compind.2018.03.020"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.autcon.2021.103823"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.autcon.2019.103061"},{"key":"ref14","article-title":"AI-augmented context-aware generative pipelines for 3D content","author":"Huang","year":"2025","journal-title":"Preprints"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICIR68135.2025.11361557"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2024.3383451"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2024.3482362"},{"key":"ref18","article-title":"Rag-instruct: Boosting llms with diverse retrieval-augmented instructions","author":"Liu","year":"2024","journal-title":"arXiv:2501.00353"},{"key":"ref19","article-title":"Qfft, question-free fine-tuning for adaptive reasoning","author":"Liu","year":"2025","journal-title":"arXiv:2506.12860"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2024.3369659"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3354928"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2023.3260281"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3141255"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3306601"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3271124"},{"key":"ref26","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3433415"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR56361.2022.9956055"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2998126"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2018.2873237"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2955567"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2019.2900993"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2012.6252482"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.autcon.2019.102967"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.autcon.2022.104163"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.conbuildmat.2022.126584"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2023.3250306"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2023.3264284"},{"key":"ref39","article-title":"A comprehensive study of deep video action recognition","author":"Zhu","year":"2020","journal-title":"arXiv:2012.06567"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrmms.2024.105933"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00556"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00301"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01941"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755837"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.tust.2023.105432"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.tust.2025.107291"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680690"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01434"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3479207"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3331841"},{"key":"ref51","first-page":"13627","article-title":"Alignment-guided temporal attention for video action recognition","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Zhao"},{"key":"ref52","first-page":"26462","article-title":"St-adapter: Parameter-efficient image-to-video transfer learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Pan"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_1"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_7"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01878"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72761-0_4"},{"key":"ref57","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"arXiv:2010.11929","author":"Dosovitskiy","year":"2020"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref59","volume-title":"Fotomanualen: TV-inspektion Af Afl\u00f8bsledninger","year":"2010"},{"issue":"6","key":"ref60","first-page":"1","article-title":"Scikit-multilearn: A Python library for multi-label classification","volume":"20","author":"Szyma\u0144ski","year":"2019","journal-title":"J. Mach. Learn. Res."},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6872"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01345"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2023.3307594"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096569"},{"key":"ref68","article-title":"2nd place winners: ICPR videopipe challenge\u2013track on video defect classification","author":"Fang","year":"2022"},{"key":"ref69","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv:1711.05101"},{"key":"ref70","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017","journal-title":"arXiv:1705.06950"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02008"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01721"}],"container-title":["IEEE Transactions on Automation Science and Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8856\/11323516\/11421421.pdf?arnumber=11421421","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T05:46:28Z","timestamp":1773726388000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11421421\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":72,"URL":"https:\/\/doi.org\/10.1109\/tase.2026.3670430","relation":{},"ISSN":["1545-5955","1558-3783"],"issn-type":[{"value":"1545-5955","type":"print"},{"value":"1558-3783","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}