{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T02:29:36Z","timestamp":1775096976835,"version":"3.50.1"},"reference-count":60,"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":[{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2023TQ0344"],"award-info":[{"award-number":["2023TQ0344"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2023M733387"],"award-info":[{"award-number":["2023M733387"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62401447"],"award-info":[{"award-number":["62401447"]}],"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":["62306101"],"award-info":[{"award-number":["62306101"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"State Energy Key Laboratory for Carbonate Oil and Gas","award":["33550000-24-ZC0613-0101"],"award-info":[{"award-number":["33550000-24-ZC0613-0101"]}]},{"DOI":"10.13039\/501100015401","name":"Key Research and Development Projects of Shaanxi Province","doi-asserted-by":"publisher","award":["2024GX-YBXM-051"],"award-info":[{"award-number":["2024GX-YBXM-051"]}],"id":[{"id":"10.13039\/501100015401","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2025.3557615","type":"journal-article","created":{"date-parts":[[2025,4,3]],"date-time":"2025-04-03T19:59:13Z","timestamp":1743710353000},"page":"2949-2960","source":"Crossref","is-referenced-by-count":7,"title":["Multimodal Large Models are Effective Action Anticipators"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9266-4685","authenticated-orcid":false,"given":"Binglu","family":"Wang","sequence":"first","affiliation":[{"name":"College of Information and Control Engineering, Xi'an University of Architecture and Technology, Xi'an, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4208-4710","authenticated-orcid":false,"given":"Yao","family":"Tian","sequence":"additional","affiliation":[{"name":"College of Information and Control Engineering, Xi'an University of Architecture and Technology, Xi'an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5401-043X","authenticated-orcid":false,"given":"Shunzhou","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Electronic and Computer Engineering, Shenzhen Graduate School, Peking University, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5922-877X","authenticated-orcid":false,"given":"Le","family":"Yang","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-71278-5_12"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3232021"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00661"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10445978"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00151"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00560"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01016"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_10"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00306"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19830-4_32"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3421848"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3330794"},{"issue":"240","key":"ref13","first-page":"1","article-title":"Palm: Scaling language modeling with pathways","volume":"24","author":"Chowdhery","year":"2023","journal-title":"J. Mach. Learn. Res."},{"issue":"8","key":"ref14","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref15","volume-title":"Llama: Open and Efficient Foundation Language Models","volume":"abs\/2302.13971","author":"Touvron","year":"2023"},{"key":"ref16","first-page":"2024","article-title":"Timemixer: Decomposable multiscale mixing for time series forecasting","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang"},{"key":"ref17","first-page":"19622","article-title":"Large language models are zero-shot time series forecasters","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Gruver","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3352388"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3146005"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3330296"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.paerosci.2024.100984"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.105"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02042"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01799"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2992889"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00383"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-11021-5_24"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00852"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01794"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7008"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01656"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72667-5_5"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3262578"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3225573"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-59713-9_22"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3233258"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3291588"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3061289"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00601"},{"key":"ref42","first-page":"23765","article-title":"Learning state-aware visual representations from audible interactions","volume":"35","author":"Mittal","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3428317"},{"issue":"PMLR","key":"ref44","first-page":"2790","article-title":"Parameter-efficient transfer learning for nlp","volume-title":"Int. Conf. Mach. Learn.","author":"Houlsby","year":"2019"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acllong.353"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2023.08.012"},{"key":"ref48","article-title":"Lora: Low-rank adaptation of large language models","volume-title":"Int. Conf. Learn. Representations","author":"Hu","year":"2021"},{"key":"ref49","first-page":"32100","article-title":"Dora: Weight-decomposed low-rank adaptation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liu","year":"2024"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-8792-0_19"},{"key":"ref51","first-page":"29615","article-title":"Cheap and quick: Efficient vision-language instruction tuning for large language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Luo","year":"2023"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73007-8_9"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2024.103248"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_21"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/2493432.2493482"},{"key":"ref57","article-title":"Phi-2: The surprising power of small language models","author":"Javaheripi","year":"2023"},{"key":"ref58","first-page":"10755","article-title":"Falcon-40b: An Open Large Language Model With State-of-The-Art Performance","volume-title":"Findings of the Association for Computational Linguistics","volume":"2023","author":"Almazrouei","year":"2023"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/10948357.pdf?arnumber=10948357","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,29]],"date-time":"2025-05-29T17:30:46Z","timestamp":1748539846000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10948357\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3557615","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}