{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T12:22:40Z","timestamp":1780057360707,"version":"3.54.0"},"reference-count":55,"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"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62201058,62475016,62306311"],"award-info":[{"award-number":["62201058,62475016,62306311"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00023","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"166-176","source":"Crossref","is-referenced-by-count":1,"title":["IRGPT: Understanding Real-World Infrared Image with Bi-Cross-Modal Curriculum on Large-Scale Benchmark"],"prefix":"10.1109","author":[{"given":"Zhe","family":"Cao","sequence":"first","affiliation":[{"name":"Beijing Institute of Technology,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jin","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruiheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2244"},{"key":"ref4","article-title":"The (r) evolution of multimodal large language models: A survey","author":"Caffagni","year":"2024","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01149"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref7","article-title":"Cross-lingual language model pretraining","author":"Conneau","year":"2019","journal-title":"Advances in neural information processing systems, 32"},{"key":"ref8","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2010","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00393"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.109088"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"ref12","first-page":"29406","article-title":"Learning with noisy correspondence for cross-modal matching","volume":"34","author":"Huang","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1654"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.501"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02310"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref17","article-title":"What matters when building vision-language models?","author":"Lauren\u00e7on","year":"2025","journal-title":"Advances in Neural Information Processing Systems 37:87874\u201387907"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161210"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01263"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1939"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00566"},{"key":"ref22","first-page":"1973019742. PMLR","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","year":"2023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72649-1_24"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref25","article-title":"A survey on hallucination in large vision-language models","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413922"},{"key":"ref27","article-title":"Let\u2019s learn step by step: Enhancing in-context learning ability with curriculum learning","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref28","article-title":"Decoupled weight decay regularization","volume-title":"International Conference on Learning Representations","author":"Loshchilov","year":"2019"},{"key":"ref29","first-page":"512","article-title":"What is being transferred in transfer learning","author":"Neyshabur","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref30","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1833"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01611-x"},{"key":"ref33","first-page":"751","article-title":"From baby steps to leapfrog: How \u201cless is more\u201d in unsupervised dependency parsing","volume-title":"Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics","author":"Spitkovsky","year":"2010"},{"key":"ref34","article-title":"Pandagpt: One model to instruction-follow them all","author":"Su","year":"2023","journal-title":"arXiv preprint"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i7.32838"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3410542"},{"key":"ref37","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":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.689"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3093468"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3069908"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00538"},{"key":"ref42","article-title":"Deepseek-vl2: Mixture-ofexperts vision-language models for advanced multimodal understanding","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref43","first-page":"5403054048","article-title":"Training large language models for reasoning through reverse curriculum reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Xi","year":"2024"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.542"},{"key":"ref45","article-title":"Qwen2","author":"Yang","year":"2024","journal-title":"5 technical report. arXiv preprint"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01904"},{"key":"ref47","article-title":"Mind the boundary: Coreset selection via reconstructing the decision boundary","volume-title":"Forty-first International Conference on Machine Learning","author":"Yang","year":"2024"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72855-6_14"},{"key":"ref50","article-title":"Coverage-centric coreset selection for high pruning rates","volume-title":"11th International Conference on Learning Representations","author":"Zheng","year":"2023"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612468"},{"key":"ref52","article-title":"Languagebind: Extending video-language pretraining to n -modality by language-based semantic alignment","volume-title":"The Twelfth International Conference on Learning Representations","author":"Zhu","year":"2024"},{"key":"ref53","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","volume-title":"12th International Conference on Learning Representations, ICLR 2024","author":"Zhu","year":"2024"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00678"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.3004555"}],"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\/11444298.pdf?arnumber=11444298","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:10:06Z","timestamp":1777612206000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444298\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00023","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}