{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T14:30:14Z","timestamp":1774449014567,"version":"3.50.1"},"reference-count":73,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tpami.2024.3447778","type":"journal-article","created":{"date-parts":[[2024,8,22]],"date-time":"2024-08-22T18:25:54Z","timestamp":1724351154000},"page":"10697-10714","source":"Crossref","is-referenced-by-count":5,"title":["Multimodal Cross-Lingual Summarization for Videos: A Revisit in Knowledge Distillation Induced Triple-Stage Training Method"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7664-9856","authenticated-orcid":false,"given":"Nayu","family":"Liu","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Tiangong University, Tianjin, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5830-0802","authenticated-orcid":false,"given":"Kaiwen","family":"Wei","sequence":"additional","affiliation":[{"name":"College of Computer Science, Chongqing University, Chongqing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9467-0942","authenticated-orcid":false,"given":"Yong","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Tiangong University, Tianjin, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9344-6428","authenticated-orcid":false,"given":"Jianhua","family":"Tao","sequence":"additional","affiliation":[{"name":"Department of Automation, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0038-9816","authenticated-orcid":false,"given":"Xian","family":"Sun","sequence":"additional","affiliation":[{"name":"Key Laboratory of Network Information System Technology (NIST), Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4187-9755","authenticated-orcid":false,"given":"Fanglong","family":"Yao","sequence":"additional","affiliation":[{"name":"Key Laboratory of Network Information System Technology (NIST), Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8138-1372","authenticated-orcid":false,"given":"Hongfeng","family":"Yu","sequence":"additional","affiliation":[{"name":"Key Laboratory of Network Information System Technology (NIST), Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8833-4862","authenticated-orcid":false,"given":"Li","family":"Jin","sequence":"additional","affiliation":[{"name":"Key Laboratory of Network Information System Technology (NIST), Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9727-366X","authenticated-orcid":false,"given":"Zhao","family":"Lv","sequence":"additional","affiliation":[{"name":"Anhui Province Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei, Anhui, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6318-8803","authenticated-orcid":false,"given":"Cunhang","family":"Fan","sequence":"additional","affiliation":[{"name":"Anhui Province Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei, Anhui, China"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1","article-title":"Multimodal abstractive summarization for open-domain videos","volume-title":"Proc. Workshop Visually Grounded Interaction Lang.","author":"Libovick\u1ef3"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1659"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.144"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3157993"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.326"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.752"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3296196"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICAST.2008.4747690"},{"key":"ref9","first-page":"894","article-title":"Soft-DTW: A differentiable loss function for time-series","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Cuturi"},{"key":"ref10","article-title":"How2: A large-scale dataset for multimodal language understanding","author":"Sanabria"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.468"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2018.10.028"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1210"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.nlpbt-1.7"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1114"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-45442-5_24"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1448"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1438"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/577"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6332"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CEI57409.2022.9950133"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.33"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6525"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591633"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.165"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"ref28","first-page":"862","article-title":"MCLS: A large-scale multimodal cross-lingual summarization dataset","volume-title":"Proc. 22nd Chin. Nat. Conf. Comput. Linguistics","author":"Xiaorui"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.994"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3286259"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475321"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.107152"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9534082"},{"key":"ref34","article-title":"MHMS: Multimodal hierarchical multimedia summarization","author":"Qiu","year":"2022"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-eacl.67"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00520"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/979872.979877"},{"key":"ref38","first-page":"1546","article-title":"Using bilingual information for cross-language document summarization","volume-title":"Proc. Conf. 49th Annu. Meeting Assoc. Comput. Linguistics Hum. Lang. Technol.","author":"Wan"},{"key":"ref39","first-page":"2114","article-title":"Evaluation of a cross-lingual romanian-english multi-document summariser","volume-title":"Proc. Int. Conf. Lang. Resour. Eval.","author":"Orasan"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2586608"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1012"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.339"},{"key":"ref43","first-page":"917","article-title":"Cross-language document summarization based on machine translation quality prediction","volume-title":"Proc. 48th Annu. Meeting Assoc. Comput. Linguistics","author":"Wan"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.360"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1302"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.121"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21359"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.154"},{"key":"ref49","first-page":"3008","article-title":"Multi-task learning for cross-lingual abstractive summarization","volume-title":"Proc. 13th Lang. Resour. Eval. Conf.","author":"Takase"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.148"},{"key":"ref51","first-page":"536","article-title":"Mixed-lingual pre-training for cross-lingual summarization","volume-title":"Proc. 1st Conf. Asia-Pacific Chapter Assoc. Comput. Linguistics, 10th Int. Joint Conf. Natural Lang. Process.","author":"Xu"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.newsum-1.2"},{"key":"ref53","first-page":"27 730","article-title":"Training language models to follow instructions with human feedback","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ouyang"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00685"},{"key":"ref55","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3181116"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3234170"},{"key":"ref59","first-page":"15 530","article-title":"TAeKD: Teacher assistant enhanced knowledge distillation for closed-source multilingual neural machine translation","volume-title":"Proc. Joint Int. Conf. Comput. Linguistics Lang. Resour. Eval.","author":"Lv"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.303"},{"key":"ref62","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","volume-title":"Proc. Workshop Text Summarization Branches Out","author":"Lin"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref64","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proc. ACL Workshop Intrinsic Extrinsic Eval. Measures Mach. Transl. Summarization","author":"Banerjee"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3159811"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1302"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00911"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00343"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref72","article-title":"A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions","author":"Huang","year":"2023"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-short.69"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10746266\/10643687.pdf?arnumber=10643687","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:31:39Z","timestamp":1732667499000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10643687\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":73,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3447778","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":[[2024,12]]}}}