{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T05:22:14Z","timestamp":1782364934048,"version":"3.54.5"},"reference-count":56,"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":["82202984,12326612"],"award-info":[{"award-number":["82202984,12326612"]}],"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\/iccv51701.2025.00332","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"3477-3487","source":"Crossref","is-referenced-by-count":1,"title":["OrderChain: Towards General Instruct-Tuning for Stimulating the Ordinal Understanding Ability of MLLM"],"prefix":"10.1109","author":[{"given":"Jinhong","family":"Wang","sequence":"first","affiliation":[{"name":"College of Computer Science & Technology, Zhejiang University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuo","family":"Tong","sequence":"additional","affiliation":[{"name":"Transvascular Implantation Devices Research Institute and Liangzhu Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Liu","sequence":"additional","affiliation":[{"name":"Ant Group"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongqi","family":"Tang","sequence":"additional","affiliation":[{"name":"Ant Group"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weiqiang","family":"Wang","sequence":"additional","affiliation":[{"name":"Ant Group"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wentong","family":"Li","sequence":"additional","affiliation":[{"name":"College of Computer Science & Technology, Zhejiang University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongxia","family":"Xu","sequence":"additional","affiliation":[{"name":"Transvascular Implantation Devices Research Institute and Liangzhu Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Danny Z.","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Notre Dame"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jintai","family":"Chen","sequence":"additional","affiliation":[{"name":"HKUST,Guangzhou"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Wu","sequence":"additional","affiliation":[{"name":"Transvascular Implantation Devices Research Institute and Liangzhu Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"GPT-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","article-title":"Qwen technical report","author":"Bai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref3","article-title":"Qwen technical report","author":"Bai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref4","author":"Bai","year":"2023","journal-title":"Qwen-vl: A frontier large vision-language model with versatile abilities"},{"key":"ref5","first-page":"411","article-title":"Unimodal probability distributions for deep ordinal classification","volume-title":"International Conference on Machine Learning","author":"Beckham","year":"2017"},{"key":"ref6","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.86"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/70"},{"key":"ref9","article-title":"Training verifiers to solve math word problems","author":"Cobbe","year":"2021","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00487"},{"key":"ref12","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73013-9_1"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-44795-4_13"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00214"},{"key":"ref16","article-title":"Facial age estimation by learning from label distributions","author":"Geng","year":"2013","journal-title":"TPAMI"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.4137\/cin.s17277"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00633"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2967829"},{"issue":"2","key":"ref20","article-title":"LoRA: Low-rank adaptation of large language models","volume":"1","author":"Edward","year":"2022","journal-title":"ICLR"},{"key":"ref21","volume-title":"APTOS 2019 blindness detection","author":"Karthik","year":"2019"},{"key":"ref22","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_40"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00128"},{"key":"ref25","article-title":"Deep repulsive clustering of ordered data based on order-identity decomposition","volume-title":"International Conference on Learning Representations","author":"Lee","year":"2020"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2015.7301352"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00057"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/7503.003.0113"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01368"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2559"},{"key":"ref31","article-title":"Order learning and its application to age estimation","volume-title":"International Conference on Learning Representations","author":"Lim","year":"2019"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02484"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref35","author":"Liu","year":"2024","journal-title":"LLaVA- NeXT: Improved reasoning, OCR, and world knowledge"},{"key":"ref36","first-page":"0","article-title":"Ordinal regression with neuron stick-breaking for medical diagnosis","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV) Workshops","author":"Liu","year":"2018"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/330"},{"key":"ref38","first-page":"831","article-title":"A constrained deep neural network for ordinal regression","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Liu","year":"2018"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00540"},{"key":"ref40","volume-title":"GPT-4V(ision) system card","year":"2023"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33783-3_36"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301679"},{"key":"ref43","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref44","article-title":"Learning multiple non-mutually-exclusive tasks for improved classification of inherently ordered labels","author":"Ratner","year":"2018","journal-title":"arXiv preprint"},{"key":"ref45","article-title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","author":"Reid","year":"2024","journal-title":"arXiv preprint"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0940-3"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01820"},{"key":"ref48","article-title":"Gemini: A family of highly capable multimodal models","author":"Team","year":"2023","journal-title":"arXiv preprint"},{"key":"ref49","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00539"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3361"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1800"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73411-3_10"},{"key":"ref54","article-title":"mPLUG- Owl: Modularization empowers large language models with multimodality","author":"Ye","year":"2023","journal-title":"arXiv preprint"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02664"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02664"}],"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\/11445418.pdf?arnumber=11445418","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:23:31Z","timestamp":1777530211000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445418\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00332","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}