{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T17:32:07Z","timestamp":1782408727651,"version":"3.54.5"},"reference-count":90,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00099","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"981-992","source":"Crossref","is-referenced-by-count":3,"title":["Aligning Vision to Language: Annotation-Free Multimodal Knowledge Graph Construction for Enhanced LLMs Reasoning"],"prefix":"10.1109","author":[{"given":"Junming","family":"Liu","sequence":"first","affiliation":[{"name":"Tongji University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siyuan","family":"Meng","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanting","family":"Gao","sequence":"additional","affiliation":[{"name":"Tongji University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Song","family":"Mao","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pinlong","family":"Cai","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guohang","family":"Yan","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yirong","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zilin","family":"Bian","sequence":"additional","affiliation":[{"name":"New York University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ding","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Botian","family":"Shi","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01469"},{"key":"ref2","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/icwsm.v12i1.14983"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1186\/s13054-023-04393-x"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.nlrse-1.7"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29728"},{"key":"ref9","first-page":"22243","article-title":"Big self-supervised models are strong semi-supervised learners","volume":"33","author":"Chen","year":"2020","journal-title":"Advances in neural information processing systems (NeurIPS)"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531992"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01368"},{"key":"ref12","article-title":"Continual multimodal knowledge graph construction","volume-title":"In Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence","author":"Chen","year":"2024"},{"key":"ref13","article-title":"Januspro: Unified multimodal understanding and generation with data and model scaling","author":"Chen","year":"2025","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3390\/math11081815"},{"key":"ref15","article-title":"Knowledge graphs meet multimodal learning: A comprehensive survey","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3345146"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3390\/electronics12122688"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2155"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-022-13644-y"},{"key":"ref20","article-title":"An image is worth 16 x 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv preprint"},{"key":"ref21","article-title":"From local to global: A graph rag approach to query-focused summarization","author":"Edge","year":"2024","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3220625"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3580501"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.809"},{"key":"ref25","article-title":"Deepseek-r1: Incentivizing reasoning capability in 11 ms via reinforcement learning","author":"Guo","year":"2025","journal-title":"arXiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01975"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-emnlp.568"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1142\/S1793351X23600048"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3082292"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.319"},{"key":"ref32","article-title":"Gpt-4o system card","author":"Hurst","year":"2024","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298990"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3618260.3649777"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3417439"},{"key":"ref36","article-title":"Scaling laws for neural language models","author":"Kaplan","year":"2020","journal-title":"arXiv preprint"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.579"},{"key":"ref39","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"In Proceedings of the 39th International Conference on Machine Learning","author":"Li","year":"2022"},{"key":"ref40","first-page":"19730","article-title":"BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"In Proceedings of the International Conference on Machine Learning (ICML)","author":"Li","year":"2023"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0591"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref43","article-title":"Mosaic: Data-free knowledge distillation via mixture-ofexperts for heterogeneous distributed environments","author":"Liu","year":"2025","journal-title":"arXiv preprint"},{"key":"ref44","article-title":"Fedrecon: Missing modality reconstruction in distributed heterogeneous environments","author":"Liu","year":"2025","journal-title":"arXiv preprint"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-21348-0_30"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0182"},{"key":"ref48","first-page":"43447","article-title":"Chameleon: Plug-and-play compositional reasoning with large language models","volume-title":"In Advances in Neural Information Processing Systems","author":"Lu","year":"2023"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1288"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00331"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.3390\/e25040657"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01367"},{"key":"ref53","article-title":"Reasoning with large language models, a survey","author":"Plaat","year":"2024","journal-title":"arXiv preprint"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3451215"},{"key":"ref56","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"In Proceedings of the 38th International Conference on Machine Learning","author":"Radford","year":"2021"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197389"},{"key":"ref58","article-title":"Leveraging large language models for multiple choice question answering","volume-title":"In Proceedings of the International Conference on Learning Representations (ICLR)","author":"Robinson","year":"2023"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.418"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3399746"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3411947"},{"key":"ref62","article-title":"Ernie 3.0: Large-scale knowledge enhanced pre-training for language understanding and generation","author":"Sun","year":"2021","journal-title":"arXiv preprint"},{"key":"ref63","article-title":"Gemini: a family of highly capable multimodal models","author":"Team","year":"2023","journal-title":"arXiv preprint"},{"key":"ref64","article-title":"Cambrian-1: A fully open, vision-centric exploration of multimodal LLMs","volume-title":"In The Thirty-eighth Annual Conference on Neural Information Processing Systems","author":"Tong","year":"2024"},{"key":"ref65","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref66","article-title":"Attention is all you need","volume-title":"In Advances in Neural Information Processing Systems","author":"Vaswani","year":"2017"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2754246"},{"key":"ref68","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612266"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3039388"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681014"},{"key":"ref72","article-title":"Retrieve-rewrite-answer: A kg-to-text enhanced 11 ms framework for knowledge graph question answering","author":"Wu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref73","article-title":"Chain-of-experts: When LLMs meet complex operations research problems","volume-title":"In The Twelfth International Conference on Learning Representations","author":"Xiao","year":"2024"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.296"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3275156"},{"key":"ref76","article-title":"Qwen2. 5 technical report","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref77","article-title":"Mm-bigbench: Evaluating multimodal models on multimodal content comprehension tasks","author":"Yang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref78","article-title":"mplug-owl: Modularization empowers large language models with multimodality","author":"Ye","year":"2023","journal-title":"arXiv preprint"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1093\/nsr\/nwae403"},{"key":"ref80","article-title":"RobuRCDet: Enhancing robustness of radar-camera fusion in bird\u2019s eye view for 3d object detection","volume-title":"In The Thirteenth International Conference on Learning Representations","author":"Yue","year":"2025"},{"key":"ref81","article-title":"Mygo: Discrete modality information as fine-grained tokens for multi-modal knowledge graph completion","author":"Zhang","year":"2024","journal-title":"CoRR"},{"key":"ref82","article-title":"Multimodal chain-of-thought reasoning in language models","author":"Zhang","year":"2024","journal-title":"Transactions on Machine Learning Research"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICME46284.2020.9102809"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3476968"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0228"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE60146.2024.00013"},{"key":"ref87","article-title":"Chatgpt asks, blip-2 answers: Automatic questioning towards enriched visual descriptions","author":"Zhu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref88","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","volume-title":"In The Twelfth International Conference on Learning Representations","author":"Zhu","year":"2024"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3224228"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2023.3238524"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444779.pdf?arnumber=11444779","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:30:14Z","timestamp":1777613414000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444779\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":90,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00099","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}