{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:21:37Z","timestamp":1761895297185,"version":"build-2065373602"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004772","name":"Natural Science Foundation of Ningxia Province","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004772","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11209220","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["UniBind: Leveraging LLM-Augmented Knowledge Base for Scene Integration"],"prefix":"10.1109","author":[{"given":"Zhonghao","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Information Engineering, Ningxia University,Yinchuan,China"}]},{"given":"Ruonan","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Advanced Interdisciplinary Studies, Ningxia University,Zhongwei,China"}]},{"given":"Libo","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Information Engineering, Ningxia University,Yinchuan,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.28017"},{"key":"ref2","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"article-title":"Vltseg: Simple transfer of clip-based vision-language representations for domain generalized semantic segmentation","year":"2023","author":"H\u00fcmmer","key":"ref3"},{"key":"ref4","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International conference on machine learning","author":"Li"},{"key":"ref5","first-page":"5583","article-title":"Vilt: Vision-and-language transformer without convolution or region supervision","volume-title":"International conference on machine learning","author":"Kim"},{"article-title":"Llm-grounded diffusion: Enhancing prompt understanding of text-to-image diffusion models with large language models","year":"2023","author":"Lian","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298990"},{"article-title":"Opt: Open pre-trained transformer language models","year":"2022","author":"Zhang","key":"ref8"},{"article-title":"When and why vision-language models behave like bags-of-words, and what to do about it?","volume-title":"The Eleventh International Conference on Learning Representations","author":"Yuksekgonul","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00677"},{"article-title":"Gpt-4 technical report","year":"2023","author":"Achiam","key":"ref11"},{"article-title":"Llama: Open and efficient foundation language models","year":"2023","author":"Touvron","key":"ref12"},{"article-title":"Llama-adapter: Efficient fine-tuning of language models with zero-init attention","year":"2023","author":"Zhang","key":"ref13"},{"article-title":"Caption anything: Interactive image description with diverse multimodal controls","year":"2023","author":"Wang","key":"ref14"},{"key":"ref15","article-title":"Improving multimodal datasets with image captioning","volume":"36","author":"Nguyen","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","year":"2018","author":"Devlin","key":"ref16"},{"key":"ref17","article-title":"Translating embeddings for modeling multi-relational data","volume":"26","author":"Bordes","year":"2013","journal-title":"Advances in neural information processing systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"article-title":"When and why vision-language models behave like bags-of-words, and what to do about it?","volume-title":"The Eleventh International Conference on Learning Representations","author":"Yuksekgonul","key":"ref20"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2025,6,30]]},"location":"Nantes, France","end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11209220.pdf?arnumber=11209220","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:47:12Z","timestamp":1761889632000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11209220\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11209220","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}