{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T18:55:18Z","timestamp":1763060118331,"version":"3.45.0"},"reference-count":82,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Plan of China","award":["2023YFC3310700"],"award-info":[{"award-number":["2023YFC3310700"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62036012","62372387","61802053","62236008","U21B2044","62472422","U2333215"],"award-info":[{"award-number":["62036012","62372387","61802053","62236008","U21B2044","62472422","U2333215"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["4242051"],"award-info":[{"award-number":["4242051"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018542","name":"Natural Science Foundation of Sichuan Province","doi-asserted-by":"publisher","award":["2024NSFSC0508"],"award-info":[{"award-number":["2024NSFSC0508"]}],"id":[{"id":"10.13039\/501100018542","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Fund of National Laboratory on Adaptive Optics","award":["FNLAO-24-ZD-O02"],"award-info":[{"award-number":["FNLAO-24-ZD-O02"]}]},{"name":"Sichuan Science and Technology Program","award":["2024YFHZ0029"],"award-info":[{"award-number":["2024YFHZ0029"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2025.3604968","type":"journal-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:31:43Z","timestamp":1756834303000},"page":"7974-7987","source":"Crossref","is-referenced-by-count":0,"title":["Active Cross-Modal Domain Adaptation"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-8115-3954","authenticated-orcid":false,"given":"Xuan","family":"Yao","sequence":"first","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiao","family":"Peng","sequence":"additional","affiliation":[{"name":"School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8105-5497","authenticated-orcid":false,"given":"Junyu","family":"Gao","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4083-5155","authenticated-orcid":false,"given":"Zhaoquan","family":"Yuan","sequence":"additional","affiliation":[{"name":"School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8322-8558","authenticated-orcid":false,"given":"Xiao","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8343-9665","authenticated-orcid":false,"given":"Changsheng","family":"Xu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"Microsoft COCO captions: Data collection and evaluation server","year":"2015","author":"Chen","key":"ref1"},{"key":"ref2","first-page":"3128","article-title":"Deep visual-semantic alignments for generating image descriptions","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Karpathy","year":"2014"},{"key":"ref3","first-page":"23334","article-title":"LEAD: Learning decomposition for source-free universal domain adaptation","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Qu","year":"2024"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i12.29272"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01128"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.106394"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02309"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00047"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01716"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3399453"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3333206"},{"issue":"3","key":"ref12","first-page":"449","article-title":"The psychology and neuroscience of curiosity","volume-title":"Neuron","volume":"88","author":"Kidd","year":"2015"},{"article-title":"From psychological curiosity to artificial curiosity: Curiosity-driven learning in artificial intelligence tasks","year":"2022","author":"Sun","key":"ref13"},{"key":"ref14","first-page":"585","article-title":"Information-seeking, curiosity, and attention: Computational and neural mechanisms","volume-title":"Trends Cogn. Sci.","volume":"17","author":"Gottlieb","year":"2013"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654902"},{"key":"ref16","first-page":"3846","article-title":"Cross-media shared representation by hierarchical learning with multiple deep networks","volume-title":"Proc. Int. Joint Conf. Artif. Intell.","volume":"3846","author":"Peng","year":"2016"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240607"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00419"},{"key":"ref19","first-page":"201","article-title":"Stacked cross attention for image-text matching","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Lee","year":"2018"},{"key":"ref20","first-page":"1786","article-title":"W2VV++: Fully deep learning for ad-hoc video search","volume-title":"Proc. 27th ACM Int. Conf. Multimedia","author":"Li","year":"2019"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351053"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01267"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3091888"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00831"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00512"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00273"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3286710"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00475"},{"key":"ref29","first-page":"1218","article-title":"Similarity reasoning and filtration for image-text matching","volume-title":"Proc. AAAI Conf. Artif. Intell.","author":"Diao","year":"2021"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_40"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3149716"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00495"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3539597.3570481"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2022.3220297"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00969"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_34"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3281671"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806216"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01262"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547990"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612013"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01818"},{"key":"ref44","first-page":"57577","article-title":"Test-time adaptation against multi-modal reliability bias","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yang","year":"2024"},{"key":"ref45","first-page":"1072","article-title":"Mind-the-gap! Unsupervised domain adaptation for text-video retrieval","volume-title":"Proc. AAAI Conf. Artif. Intell.","author":"Chen","year":"2021"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.01.114"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01471"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2014.06.042"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-016-0460-3"},{"key":"ref50","first-page":"35","article-title":"Margin based active learning","volume-title":"Proc. Annu. Conf. Comput. Learn. Theory","author":"Balcan","year":"2007"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2014.6889457"},{"key":"ref52","first-page":"1183","article-title":"Deep Bayesian active learning with image data","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gal","year":"2017"},{"key":"ref53","first-page":"59","article-title":"Incorporating diversity in active learning with support vector machines","volume-title":"Proc. 20th Int. Conf. Mach. Learn.","author":"Brinker","year":"2003"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-40897-7_6"},{"key":"ref55","first-page":"2232","article-title":"Active learning for convolutional neural networks: A core-set approach","volume-title":"Int. Conf. Learn. Representations","author":"Sener","year":"2018"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00607"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/w17-2630"},{"key":"ref58","first-page":"12952","article-title":"Deep batch active learning by diverse, uncertain gradient lower bounds","volume-title":"Int. Conf. Learn. Representations","author":"Ash","year":"2020"},{"article-title":"Diverse mini-batch active learning","year":"2019","author":"Zhdanov","key":"ref59"},{"key":"ref60","first-page":"1027","article-title":"k-means++: The advantages of careful seeding","volume-title":"Proc. Soda","volume":"7","author":"Arthur","year":"2007"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612463"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00807"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00839"},{"key":"ref64","first-page":"8708","article-title":"Active learning for domain adaptation: An energy-based approach","volume-title":"Proc. AAAI Conf. Artif. Intell.","author":"Xie","year":"2022"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01708"},{"article-title":"Active learning literature survey","year":"2010","author":"Settles","key":"ref66"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/3472291"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00586"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-58347-1_10"},{"key":"ref70","first-page":"16857","article-title":"MPNet: Masked and permuted pre-training for language understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Song","year":"2020"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1145\/1772690.1772862"},{"key":"ref72","first-page":"4641","article-title":"TGIF: A new dataset and benchmark on animated GIF description","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Li","year":"2016"},{"key":"ref73","first-page":"5288","article-title":"MSR-VTT: A large video description dataset for bridging video and language","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Xu","year":"2016"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref75","first-page":"611","article-title":"An image is worth 16  16 words: Transformers for image recognition at scale","volume-title":"Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3234993"},{"key":"ref77","first-page":"93","article-title":"Learning loss for active learning","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Yoo","year":"2019"},{"key":"ref78","first-page":"37928","article-title":"Learnability matters: Active learning for video captioning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang","year":"2024"},{"key":"ref79","first-page":"28996","article-title":"Neural active learning beyond bandits","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ban","year":"2024"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01585"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28269"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1097\/00003643-201406001-00333"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/11146682.pdf?arnumber=11146682","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T18:44:35Z","timestamp":1763059475000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11146682\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":82,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3604968","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"type":"print","value":"1520-9210"},{"type":"electronic","value":"1941-0077"}],"subject":[],"published":{"date-parts":[[2025]]}}}