{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T15:44:48Z","timestamp":1784821488903,"version":"3.55.0"},"reference-count":102,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100014219","name":"National Science Fund for Distinguished Young Scholars","doi-asserted-by":"publisher","award":["62025603"],"award-info":[{"award-number":["62025603"]}],"id":[{"id":"10.13039\/501100014219","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U21B2037"],"award-info":[{"award-number":["U21B2037"]}],"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":["U22B2051"],"award-info":[{"award-number":["U22B2051"]}],"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":["U23A20383"],"award-info":[{"award-number":["U23A20383"]}],"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":["62176222"],"award-info":[{"award-number":["62176222"]}],"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":["62176223"],"award-info":[{"award-number":["62176223"]}],"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":["62176226"],"award-info":[{"award-number":["62176226"]}],"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":["62072386"],"award-info":[{"award-number":["62072386"]}],"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":["62072387"],"award-info":[{"award-number":["62072387"]}],"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":["62072389"],"award-info":[{"award-number":["62072389"]}],"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":["62002305"],"award-info":[{"award-number":["62002305"]}],"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":["62272401"],"award-info":[{"award-number":["62272401"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Science Foundation of Fujian Province of China","award":["2021J06003"],"award-info":[{"award-number":["2021J06003"]}]},{"name":"Natural Science Foundation of Fujian Province of China","award":["2022J06001"],"award-info":[{"award-number":["2022J06001"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1109\/tpami.2025.3548704","type":"journal-article","created":{"date-parts":[[2025,3,14]],"date-time":"2025-03-14T17:48:01Z","timestamp":1741974481000},"page":"4878-4896","source":"Crossref","is-referenced-by-count":7,"title":["CLIP-Driven Transformer for Weakly Supervised Object Localization"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5474-3630","authenticated-orcid":false,"given":"Zhiwei","family":"Chen","sequence":"first","affiliation":[{"name":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3970-7519","authenticated-orcid":false,"given":"Yunhang","family":"Shen","sequence":"additional","affiliation":[{"name":"Youtu Laboratory, Tencent, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7645-9606","authenticated-orcid":false,"given":"Liujuan","family":"Cao","sequence":"additional","affiliation":[{"name":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shengchuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9163-2932","authenticated-orcid":false,"given":"Rongrong","family":"Ji","sequence":"additional","affiliation":[{"name":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3338533.3372209"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3074313"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00288"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01386"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_36"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3309621"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58598-3_8"},{"key":"ref8","first-page":"7005","article-title":"UWSOD: Toward fully-supervised-level capacity weakly supervised object detection","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Shen"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01134"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00711"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00302"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01875"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01469"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00208"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00307"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00809"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00320"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3356174"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00144"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00669"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00879"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475211"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01147"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00732"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.204"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2017.381"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00232"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58529-7_17"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00042"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19918"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref35","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00682"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00071"},{"key":"ref38","article-title":"Auxiliary tasks in multi-task learning","author":"Liebel","year":"2018"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00611"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00020"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01385"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01423"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01347"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20056-4_12"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3505244"},{"key":"ref46","first-page":"1","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00427"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01474"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"ref50","article-title":"ISTR: End-to-end instance segmentation with transformers","author":"Hu","year":"2021"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547764"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00177"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00455"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2816021"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/285"},{"key":"ref56","first-page":"434","article-title":"TS2C: Tight box mining with surrounding segmentation context for weakly supervised object detection","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Wei"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2876304"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00838"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.49"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_26"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0620-5"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.311"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.326"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01061"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3402981"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3125130"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00230"},{"key":"ref68","first-page":"9834","article-title":"C-MIDN: Coupled multiple instance detection network with segmentation guidance for weakly supervised object detection","volume-title":"Proc. Int. Conf. Comput. Vis.","author":"Gao"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00983"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00103"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00448"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3145238"},{"key":"ref73","article-title":"Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lee"},{"key":"ref74","first-page":"529","article-title":"Semi-supervised learning by entropy minimization","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Grandvalet"},{"key":"ref75","first-page":"3365","article-title":"Learning with pseudo-ensembles","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Bachman"},{"key":"ref76","first-page":"1171","article-title":"Regularization with stochastic transformations and perturbations for deep semi-supervised learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Sajjadi"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00126"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01269"},{"key":"ref79","first-page":"596","article-title":"Fixmatch: Simplifying semi-supervised learning with consistency and confidence","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Sohn"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i11.17155"},{"key":"ref81","first-page":"7115","article-title":"TapNet: Neural network augmented with task-adaptive projection for few-shot learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yoon"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3079209"},{"key":"ref83","article-title":"Supervision exists everywhere: A data efficient contrastive language-image pre-training paradigm","author":"Li","year":"2021"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref87","article-title":"VT-clip: Enhancing vision-language models with visual-guided texts","author":"Qiu","year":"2021"},{"key":"ref88","article-title":"Tip-adapter: Training-free clip-adapter for better vision-language modeling","author":"Zhang","year":"2021"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00444"},{"key":"ref90","article-title":"The Caltech-UCSD birds-200\u20132011 dataset","author":"Wah","year":"2011"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2999099"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00337"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3230902"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58574-7_29"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25292"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref98","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron"},{"key":"ref99","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00593"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1016\/j.apsusc.2013.09.002"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2023.3321602"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10990047\/10927651.pdf?arnumber=10927651","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,8]],"date-time":"2025-05-08T04:26:41Z","timestamp":1746678401000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10927651\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6]]},"references-count":102,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3548704","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6]]}}}