{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:22:09Z","timestamp":1792786929956,"version":"4.5.0"},"reference-count":48,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Natural Science Foundation of China","award":["62376075"],"award-info":[{"award-number":["62376075"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tmm.2026.3684992","type":"journal-article","created":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T19:54:00Z","timestamp":1776455640000},"page":"9178-9188","source":"Crossref","is-referenced-by-count":1,"title":["Can Multimodal Large Language Models Understand Graphic Design? A Comparative Study"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1178-6435","authenticated-orcid":false,"given":"Jieru","family":"Lin","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology","place":["Harbin, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9276-7548","authenticated-orcid":false,"given":"Danqing","family":"Huang","sequence":"additional","affiliation":[{"name":"Microsoft","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4659-4935","authenticated-orcid":false,"given":"Tiejun","family":"Zhao","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology","place":["Harbin, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5973-9542","authenticated-orcid":false,"given":"Dechen","family":"Zhan","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology","place":["Harbin, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0798-6365","authenticated-orcid":false,"given":"Chin-Yew","family":"Lin","sequence":"additional","affiliation":[{"name":"Microsoft","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhu","year":"2021"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3075323"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2013.2293424"},{"key":"ref5","article-title":"Dalle 3 system card","year":"2023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3077729"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2972856"},{"key":"ref8","first-page":"6629","article-title":"GANs trained by a two time-scale update rule converge to a local nash equilibrium","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Heusel","year":"2017"},{"key":"ref9","volume-title":"Basics of Design","author":"Graham","year":"2005"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00913"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"ref12","article-title":"GPT-4o system card","author":"Hurst","year":"2024"},{"key":"ref13","article-title":"Gemini: A family of highly capable multimodal models","author":"Team","year":"2023"},{"key":"ref14","article-title":"Expanding performance boundaries of open-source multimodal models with model, data, and test-time scaling","author":"Chen","year":"2024"},{"key":"ref15","article-title":"Seed-bench: Benchmarking multimodal LLMs with generative comprehension","author":"Li","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3390\/ai6020029"},{"key":"ref17","article-title":"DEsignBench: Exploring and benchmarking DALL-E 3 for imagining visual design","author":"Lin","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01728"},{"key":"ref19","first-page":"3731","article-title":"LayoutTransformer: Scene layout generation with conceptual and spatial diversity","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Yang","year":"2021"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00980"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3097900"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28128"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_27"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.13576"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3176942"},{"key":"ref26","article-title":"A survey for graphic design intelligence","author":"Huang","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/wacv56688.2023.00361"},{"key":"ref28","article-title":"Dafonts free dataset","author":"Virkus","year":"2022"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.13576"},{"key":"ref30","article-title":"Gemma 3 technical report","author":"Team","year":"2025"},{"key":"ref31","article-title":"Phi-3 technical report: A highly capable language model locally on your phone","author":"Abdin","year":"2024"},{"key":"ref32","doi-asserted-by":"crossref","DOI":"10.20944\/preprints202505.1993.v1","article-title":"Domain specific benchmarks for evaluating multimodal large language models","author":"Anjum","year":"2025"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00543"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3379337.3415825"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201355"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1075\/celcr"},{"key":"ref37","article-title":"Llava-onevision: Easy visual task transfer","volume":"2025","author":"Li","year":"2025","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"key":"ref39","first-page":"24185","article-title":"InternVL: Scaling up vision foundation models and aligning for generic visual-linguistic tasks","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Chen","year":"2024"},{"key":"ref40","article-title":"Qwen2 technical report","author":"Team","year":"2024"},{"key":"ref41","article-title":"Janus-Pro: Unified multimodal understanding and generation with data and model scaling","author":"Chen","year":"2025"},{"key":"ref42","article-title":"LLaVA-NeXT: Improved reasoning, OCR, and world knowledge","author":"Liu","year":"2024"},{"key":"ref43","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2023"},{"key":"ref44","article-title":"Qwen2. 5-VL technical report","author":"Bai","year":"2025"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1813"},{"key":"ref46","article-title":"SDXL: Improving latent diffusion models for high-resolution image synthesis","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Podell","year":"2024"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/2556288.2557052"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.intcom.2005.11.014"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/11342315\/11482886.pdf?arnumber=11482886","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T19:12:21Z","timestamp":1791313941000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11482886\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/tmm.2026.3684992","relation":{},"ISSN":["1941-0077","1520-9210"],"issn-type":[{"value":"1941-0077","type":"electronic"},{"value":"1520-9210","type":"print"}],"subject":[],"published":{"date-parts":[[2026]]}}}