{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T09:06:40Z","timestamp":1780477600985,"version":"3.54.1"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"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. Knowl. Data Eng."],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1109\/tkde.2025.3608071","type":"journal-article","created":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T17:34:03Z","timestamp":1757439243000},"page":"7076-7089","source":"Crossref","is-referenced-by-count":8,"title":["Efficient and Effective Adaptation of Multimodal Foundation Models in Sequential Recommendation"],"prefix":"10.1109","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4759-2042","authenticated-orcid":false,"given":"Junchen","family":"Fu","sequence":"first","affiliation":[{"name":"School of Computing Science, University of Glasgow, Glasgow, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3925-4951","authenticated-orcid":false,"given":"Xuri","family":"Ge","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Shandong University, Jinan, Shandong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4703-7356","authenticated-orcid":false,"given":"Xin","family":"Xin","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Shandong University, Jinan, Shandong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexandros","family":"Karatzoglou","sequence":"additional","affiliation":[{"name":"Amazon, Barcelona, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2528-6597","authenticated-orcid":false,"given":"Ioannis","family":"Arapakis","sequence":"additional","affiliation":[{"name":"Telefonica Scientific Research, Barcelona, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-2516-8407","authenticated-orcid":false,"given":"Kaiwen","family":"Zheng","sequence":"additional","affiliation":[{"name":"School of Computing Science, University of Glasgow, Glasgow, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongxin","family":"Ni","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9228-1759","authenticated-orcid":false,"given":"Joemon M.","family":"Jose","sequence":"additional","affiliation":[{"name":"School of Computing Science, University of Glasgow, Glasgow, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591932"},{"key":"ref3","article-title":"An empirical study of training id-agnostic multi-modal sequential recommenders","author":"Li","year":"2024"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/icde60146.2024.00380"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583434"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3616855.3635845"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-30761-2"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.644"},{"key":"ref9","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Alayrac"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3616855.3635805"},{"key":"ref11","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Houlsby"},{"key":"ref12","article-title":"LoRA: Low-rank adaptation of large language models","author":"Hu","year":"2021"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-short.1"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657725"},{"key":"ref15","first-page":"7480","article-title":"Scaling vision transformers to 22 billion parameters","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Dehghani"},{"key":"ref16","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref17","article-title":"Scaling laws for deep learning","author":"Rosenfeld","year":"2021"},{"key":"ref18","article-title":"A content-driven micro-video recommendation dataset at scale","author":"Ni","year":"2023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2025.103124"},{"key":"ref20","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671473"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-7235-3_13"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611978032.49"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2018.00035"},{"key":"ref26","article-title":"Session-based recommendations with recurrent neural networks","author":"Hidasi","year":"2015"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357895"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-24755-2_2"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539381"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351034"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413598"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.121"},{"key":"ref34","first-page":"11285","article-title":"TinyTL: Reduce memory, not parameters for efficient on-device learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Cai"},{"key":"ref35","first-page":"12991","article-title":"LST: Ladder side-tuning for parameter and memory efficient transfer learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sung"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00288"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00228"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3311618"},{"key":"ref39","article-title":"M6-Rec: Generative pretrained language models are open-ended recommender systems","author":"Cui","year":"2022"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3604915.3608857"},{"key":"ref41","article-title":"Towards efficient and effective adaptation of large language models for sequential recommendation","author":"Peng","year":"2023"},{"key":"ref42","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/2.268884"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2964711"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1018"},{"key":"ref46","article-title":"Exploring the upper limits of text-based collaborative filtering using large language models: Discoveries and insights","author":"Li","year":"2023"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3373868"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052569"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/2505515.2505665"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401063"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/239"},{"key":"ref52","article-title":"A simple but hard-to-beat baseline for session-based recommendations","author":"Yuan","year":"2018"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/2959100.2959190"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413556"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3682075"}],"container-title":["IEEE Transactions on Knowledge and Data Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/69\/11233837\/11153882.pdf?arnumber=11153882","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,10]],"date-time":"2025-11-10T19:46:54Z","timestamp":1762804014000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11153882\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12]]},"references-count":55,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tkde.2025.3608071","relation":{},"ISSN":["1041-4347","1558-2191","2326-3865"],"issn-type":[{"value":"1041-4347","type":"print"},{"value":"1558-2191","type":"electronic"},{"value":"2326-3865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12]]}}}