{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T16:24:42Z","timestamp":1791303882923,"version":"4.1.0"},"reference-count":78,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"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":"crossref","award":["62076092"],"award-info":[{"award-number":["62076092"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1109\/tcsvt.2026.3676204","type":"journal-article","created":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T20:00:34Z","timestamp":1774036834000},"page":"11197-11214","source":"Crossref","is-referenced-by-count":1,"title":["Generating Multi-Modal Knowledge Clues as an Image: Toward Improving Image-Sequence Reasoning With Assisted Visual Input"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-7713-6550","authenticated-orcid":false,"given":"Guanghui","family":"Ye","sequence":"first","affiliation":[{"name":"Hunan University","place":["Changsha, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6286-5868","authenticated-orcid":false,"given":"Huan","family":"Zhao","sequence":"additional","affiliation":[{"name":"Hunan University","place":["Changsha, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8447-872X","authenticated-orcid":false,"given":"Yixian","family":"Shen","sequence":"additional","affiliation":[{"name":"University of Amsterdam","place":["Amsterdam, The Netherlands"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8509-5528","authenticated-orcid":false,"given":"Jiaqi","family":"Li","sequence":"additional","affiliation":[{"name":"University of Warwick","place":["Coventry, U.K."],"department":["Department of Computer Science"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1439-7876","authenticated-orcid":false,"given":"Fengnan","family":"Li","sequence":"additional","affiliation":[{"name":"Duke University","place":["Durham, NC, USA"],"department":["Department of Biostatistics and Bioinformatics"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4216-106X","authenticated-orcid":false,"given":"Zhihua","family":"Jiang","sequence":"additional","affiliation":[{"name":"Jinan University","place":["Guangzhou, China"],"department":["Department of Computer Science"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5224-4048","authenticated-orcid":false,"given":"Keqin","family":"Li","sequence":"additional","affiliation":[{"name":"State University of New York at New Paltz","place":["New Paltz, NY, USA"],"department":["Department of Computer Science"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1631\/FITEE.2400250"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02323"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02506"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s00146-024-01990-4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2025.113281"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3527032"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3538860"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3291379"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3514820"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3462433"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00363"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i5.32513"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.1250"},{"key":"ref14","first-page":"1","article-title":"mPLUG-Owl3: Towards long image-sequence understanding in multi-modal large language models","volume-title":"Proc. ICLR","author":"Ye"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2789"},{"key":"ref16","first-page":"1","article-title":"MANTIS: Interleaved multi-image instruction tuning","volume":"2024","author":"Jiang","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32301"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i6.32708"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i10.33115"},{"key":"ref20","article-title":"LLaVA-NeXT-interleave: Tackling multi-image, video, and 3D in large multimodal models","author":"Li","year":"2024","journal-title":"arXiv:2407.07895"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20215"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01438"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27888"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2025.113063"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s11280-024-01320-0"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-025-11439-9"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2025.113811"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2025.113466"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2025.112243"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2025.112221"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3397997"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3530436"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755008"},{"key":"ref34","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3401451"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1644"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1365"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01050"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00965"},{"issue":"1","key":"ref41","first-page":"1","article-title":"Novel dataset for fine-grained image categorization: Stanford dogs","volume-title":"Proc. CVPR Workshop Fine-Grained Vis. Categorization (FGVC)","volume":"2","author":"Khosla"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i11.26598"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.925"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01600"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref47","article-title":"Qwen-VL: A versatile vision-language model for understanding, localization, text reading, and beyond","author":"Bai","year":"2023","journal-title":"arXiv:2308.12966"},{"key":"ref48","article-title":"MPLUG-owl: Modularization empowers large language models with multimodality","author":"Ye","year":"2023","journal-title":"arXiv:2304.14178"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i2.32158"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02667"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.1107"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.1023"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i4.32454"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611987"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.207"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3409384"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref58","article-title":"DeepSeek-r1: Incentivizing reasoning capability in LLMs via reinforcement learning","author":"Guo","year":"2025","journal-title":"arXiv:2501.12948"},{"key":"ref59","first-page":"1","article-title":"Making llama SEE and draw with SEED tokenizer","volume-title":"Proc. ICLR","author":"Ge"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32240"},{"key":"ref61","article-title":"SEED-X: Multimodal models with unified multi-granularity comprehension and generation","author":"Ge","year":"2024","journal-title":"arXiv:2404.14396"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref63","article-title":"Qwen2 technical report","volume-title":"arXiv:2407.10671","author":"Yang","year":"2024"},{"key":"ref64","article-title":"Mini-gemini: Mining the potential of multi-modality vision language models","author":"Li","year":"2024","journal-title":"arXiv:2403.18814"},{"key":"ref65","first-page":"1","article-title":"LLaVA-MoD: Making LLaVA tiny via MoE knowledge distillation","volume-title":"Proc. 13th Int. Conf. Learn. Represent.","author":"Shu"},{"key":"ref66","first-page":"71683","article-title":"OBELICS: An open Web-scale filtered dataset of interleaved image-text documents","volume-title":"Proc. Adv. Neural Inf. Process. Syst. 36","author":"Bekman"},{"key":"ref67","article-title":"MPLUG-owl2: Revolutionizing multi-modal large language model with modality collaboration","author":"Ye","year":"2023","journal-title":"arXiv:2311.04257"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3547436"},{"key":"ref70","first-page":"1","article-title":"Combatting dimensional collapse in LLM pre-training data via submodular file selection","volume-title":"Proc. 13th Int. Conf. Learn. Represent.","author":"Fan"},{"key":"ref71","first-page":"1","article-title":"Does reinforcement learning really incentivize reasoning capacity in LLMs beyond the base model?","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Chen"},{"key":"ref72","article-title":"OPT: Open pre-trained transformer language models","author":"Zhang","year":"2022","journal-title":"arXiv:2205.01068"},{"key":"ref73","first-page":"1","article-title":"Language models are few-shot learners","volume-title":"Proc. NeurIPS","author":"Brown"},{"key":"ref74","first-page":"1","article-title":"Scimage: How good are multimodal large language models at scientific text-to-image generation?","volume-title":"Proc. ICLR","author":"Zhang"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref77","article-title":"Are you talking to a machine? Dataset and methods for multilingual image question answering","author":"Gao","year":"2015","journal-title":"arXiv:1505.05612"},{"key":"ref78","first-page":"1","article-title":"IconQA: A new benchmark for abstract diagram understanding and visual language reasoning","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Lu"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11643439\/11449284.pdf?arnumber=11449284","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T19:07:14Z","timestamp":1786043234000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11449284\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":78,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2026.3676204","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8]]}}}