{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T17:20:28Z","timestamp":1765041628212,"version":"3.33.0"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,15]],"date-time":"2024-12-15T00:00:00Z","timestamp":1734220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,15]],"date-time":"2024-12-15T00:00:00Z","timestamp":1734220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,12,15]]},"DOI":"10.1109\/bigdata62323.2024.10825030","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:23Z","timestamp":1737052283000},"page":"456-461","source":"Crossref","is-referenced-by-count":1,"title":["Visual Summary Thought of Large Vision-Language Models for Multimodal Recommendation"],"prefix":"10.1109","author":[{"given":"Yuqing","family":"Liu","sequence":"first","affiliation":[{"name":"University of Illinois at Chicago,Chicago,IL,United States"}]},{"given":"Yu","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Illinois at Chicago,Chicago,IL,United States"}]},{"given":"Yuwei","family":"Cao","sequence":"additional","affiliation":[{"name":"Meta,Menlo Park,CA,United States"}]},{"given":"Lichao","family":"Sun","sequence":"additional","affiliation":[{"name":"Lehigh University,Bethlehem,PA,United States"}]},{"given":"Philip S.","family":"Yu","sequence":"additional","affiliation":[{"name":"University of Illinois at Chicago,Chicago,IL,United States"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583251"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.9973"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475259"},{"issue":"2","key":"ref4","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3680295","article-title":"Megcf: Multimodal entity graph collaborative filtering for personalized recommendation","volume":"41","author":"Liu","year":"2023","journal-title":"ACM Trans. Recomm. Syst."},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3217449"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3221949"},{"journal-title":"A comprehensive survey on multimodal recommender systems: Taxonomy, evaluation, and future directions","year":"2023","author":"Zhou","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3617827"},{"issue":"1","key":"ref9","first-page":"1","volume":"9","author":"Yang","year":"2023","journal-title":"The dawn of lmms: Preliminary explorations with gpt-4v (ision)"},{"article-title":"On the road with GPT-4v(ision): Explorations of utilizing visual-language model as autonomous driving agent","volume-title":"ICLR 2024 Workshop on Large Language Model (LLM) Agents","author":"Wen","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681464"},{"article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","volume-title":"The Twelfth International Conference on Learning Representations","author":"Zhu","key":"ref14"},{"key":"ref15","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"journal-title":"A comprehensive survey of ai-generated content (aigc): A history of generative ai from gan to chatgpt","year":"2023","author":"Cao","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-024-03185-2"},{"journal-title":"Tinygpt-v: Efficient multimodal large language model via small backbones","year":"2023","author":"Yuan","key":"ref18"},{"journal-title":"Instructiongpt-4: A 200-instruction paradigm for fine-tuning minigpt-4","year":"2023","author":"Wei","key":"ref19"},{"journal-title":"Artgpt-4: Towards artistic-understanding large vision-language models with enhanced adapter","year":"2023","author":"Yuan","key":"ref20"},{"journal-title":"Towards generic anomaly detection and understanding: Large-scale visual-linguistic model (gpt-4v) takes the lead","year":"2023","author":"Cao","key":"ref21"},{"journal-title":"Video understanding with large language models: A survey","year":"2023","author":"Tang","key":"ref22"},{"journal-title":"Contextual: Evaluating context-sensitive text-rich visual reasoning in large multimodal models","year":"2024","author":"Wadhawan","key":"ref23"},{"journal-title":"A foundational multimodal vision language ai assistant for human pathology","year":"2023","author":"Lu","key":"ref24"},{"journal-title":"Multimodal chatgpt for medical applications: an experimental study of gpt-4v","year":"2023","author":"Yan","key":"ref25"},{"journal-title":"A survey for in-context learning","year":"2022","author":"Dong","key":"ref26"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.759"},{"key":"ref28","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume-title":"Proceedings of the 36th International Conference on Neural Information Processing Systems","volume":"35","author":"Wei"},{"article-title":"Self-consistency improves chain of thought reasoning in language models","volume-title":"The Eleventh International Conference on Learning Representations","author":"Wang","key":"ref29"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-56060-6_24"},{"journal-title":"Drdt: Dynamic reflection with divergent thinking for llm-based sequential recommendation","year":"2023","author":"Wang","key":"ref31"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.644"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645537"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463036"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557268"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599821"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-2262-4_13"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/BigData55660.2022.10021075"}],"event":{"name":"2024 IEEE International Conference on Big Data (BigData)","start":{"date-parts":[[2024,12,15]]},"location":"Washington, DC, USA","end":{"date-parts":[[2024,12,18]]}},"container-title":["2024 IEEE International Conference on Big Data (BigData)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10824975\/10824942\/10825030.pdf?arnumber=10825030","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T07:53:33Z","timestamp":1737100413000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10825030\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,15]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/bigdata62323.2024.10825030","relation":{},"subject":[],"published":{"date-parts":[[2024,12,15]]}}}