{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T04:49:06Z","timestamp":1792039746488,"version":"4.4.0"},"reference-count":62,"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"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/tdmrep.html"}],"funder":[{"name":"2035 Innovation Mission","award":["E4J10102"],"award-info":[{"award-number":["E4J10102"]}]},{"name":"National Natural Science Foundations of China","award":["62376267"],"award-info":[{"award-number":["62376267"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tip.2026.3725719","type":"journal-article","created":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T19:09:54Z","timestamp":1790708994000},"page":"10829-10841","source":"Crossref","is-referenced-by-count":0,"title":["Advancing Scientific Chart Understanding: The SCI-CQA Benchmark and Beyond"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-6783-0766","authenticated-orcid":false,"given":"Lingdong","family":"Shen","sequence":"first","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"family":"Qigqi","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2256-8815","authenticated-orcid":false,"given":"Kun","family":"Ding","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1090-6207","authenticated-orcid":false,"given":"Jian","family":"Xu","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7103-6321","authenticated-orcid":false,"given":"Gaofeng","family":"Meng","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2089-9733","authenticated-orcid":false,"given":"Shiming","family":"Xiang","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"2263","article-title":"ChartQA: A benchmark for question answering about charts with visual and logical reasoning","volume-title":"Proc. Findings Assoc. Comput. Linguistics ACL","author":"Masry"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.619"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.401"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.277"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref6","article-title":"Qwen technical report","volume-title":"arXiv:2309.16609","author":"Bai","year":"2023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/tkde.2024.3513320"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00592"},{"key":"ref9","first-page":"1","article-title":"FigureQA: An annotated figure dataset for visual reasoning","volume-title":"Proc. ICLR","author":"Kahou"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093523"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3609"},{"key":"ref12","article-title":"ChartLlama: A multimodal LLM for chart understanding and generation","author":"Han","year":"2023","journal-title":"arXiv:2311.16483"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.52202\/085713-4899"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00913"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref17","article-title":"Video-MME: The first-ever comprehensive evaluation benchmark of multi-modal LLMs in video analysis","author":"Fu","year":"2024","journal-title":"arXiv:2405.21075"},{"key":"ref18","article-title":"MME-RealWorld: Could your multimodal LLM challenge high-resolution real-world scenarios that are difficult for humans?","author":"Zhang","year":"2024","journal-title":"arXiv:2408.13257"},{"key":"ref19","article-title":"Revisiting referring expression comprehension evaluation in the era of large multimodal models","author":"Chen","year":"2024","journal-title":"arXiv:2406.16866"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72390-2_38"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00445"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.78"},{"key":"ref23","article-title":"ChartX & ChartVLM: A versatile benchmark and foundation model for complicated chart reasoning","author":"Xia","year":"2024","journal-title":"arXiv:2402.12185"},{"key":"ref24","article-title":"MathVista: Evaluating mathematical reasoning of foundation models in visual contexts","author":"Lu","year":"2023","journal-title":"arXiv:2310.02255"},{"key":"ref25","article-title":"MapQA: A dataset for question answering on choropleth maps","author":"Chang","year":"2022","journal-title":"arXiv:2211.08545"},{"key":"ref26","article-title":"ChartBench: A benchmark for complex visual reasoning in charts","author":"Xu","year":"2023","journal-title":"arXiv:2312.15915"},{"key":"ref27","article-title":"MMC: Advancing multimodal chart understanding with large-scale instruction tuning","author":"Liu","year":"2023","journal-title":"arXiv:2311.10774"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2026.3669664"},{"key":"ref29","article-title":"ChartMoE: Mixture of diversely aligned expert connector for chart understanding","author":"Xu","year":"2024","journal-title":"arXiv:2409.03277"},{"key":"ref30","article-title":"TokenLearner: What can 8 learned tokens do for images and videos?","author":"Ryoo","year":"2021","journal-title":"arXiv:2106.11297"},{"key":"ref31","first-page":"13937","article-title":"DynamicViT: Efficient vision transformers with dynamic token sparsification","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Rao"},{"key":"ref32","article-title":"Not all patches are what you need: Expediting vision transformers via token reorganizations","author":"Liang","year":"2022","journal-title":"arXiv:2202.07800"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.5040\/9781501365072.12976"},{"key":"ref34","article-title":"Token transforming: A unified and training-free token compression framework for vision transformer acceleration","author":"Zeng","year":"2025","journal-title":"arXiv:2506.05709"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3535405"},{"key":"ref36","article-title":"VScan: Rethinking visual token reduction for efficient large vision-language models","author":"Zhang","year":"2025","journal-title":"arXiv:2505.22654"},{"key":"ref37","article-title":"GreedyPrune: Retenting critical visual token set for large vision language models","author":"Pei","year":"2025","journal-title":"arXiv:2506.13166"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00030"},{"key":"ref39","article-title":"Machine vision therapy: Multimodal large language models can enhance visual robustness via denoising in-context learning","author":"Huang","year":"2023","journal-title":"arXiv:2312.02546"},{"key":"ref40","volume-title":"ERNIE Bot 4.0","year":"2023"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1023\/b:visi.0000029664.99615.94"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/11744023_34"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126544"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2983686"},{"key":"ref45","article-title":"SPHINX: The joint mixing of weights, tasks, and visual embeddings for multi-modal large language models","author":"Lin","year":"2023","journal-title":"arXiv:2311.07575"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3860"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.175"},{"key":"ref48","article-title":"InternLM-XComposer2: Mastering free-form text-image composition and comprehension in vision-language large model","author":"Dong","year":"2024","journal-title":"arXiv:2401.16420"},{"key":"ref49","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"},{"key":"ref50","article-title":"Llava-next: Improved reasoning, OCR, and world knowledge","author":"Liu","year":"2024"},{"key":"ref51","article-title":"Mini-gemini: Mining the potential of multi-modality vision language models","author":"Li","year":"2024","journal-title":"arXiv:2403.18814"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01239"},{"key":"ref53","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":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01354"},{"key":"ref55","article-title":"Qwen3-VL technical report","volume-title":"arXiv:2511.21631","author":"Bai","year":"2025"},{"key":"ref56","article-title":"InternVL3: Exploring advanced training and test-time recipes for open-source multimodal models","author":"Zhu","year":"2025","journal-title":"arXiv:2504.10479"},{"key":"ref57","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref58","article-title":"Gemini 2.5: Pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities","author":"Comanici","year":"2025","journal-title":"arXiv:2507.06261"},{"key":"ref59","article-title":"LLaVA-PruMerge: Adaptive token reduction for efficient large multimodal models","author":"Shang","year":"2024","journal-title":"arXiv:2403.15388"},{"key":"ref60","first-page":"44960","article-title":"CrossGET: Cross-guided ensemble of tokens for accelerating vision-language transformers","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Shi"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01300"},{"key":"ref62","first-page":"1","article-title":"Token merging: Your vit but faster","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Bolya"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/11355710\/11715981.pdf?arnumber=11715981","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T04:35:17Z","timestamp":1792038917000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11715981\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":62,"URL":"https:\/\/doi.org\/10.1109\/tip.2026.3725719","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}