{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T05:17:14Z","timestamp":1737004634239,"version":"3.33.0"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,10,16]],"date-time":"2024-10-16T00:00:00Z","timestamp":1729036800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,16]],"date-time":"2024-10-16T00:00:00Z","timestamp":1729036800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,10,16]]},"DOI":"10.1109\/ictc62082.2024.10827294","type":"proceedings-article","created":{"date-parts":[[2025,1,14]],"date-time":"2025-01-14T19:40:10Z","timestamp":1736883610000},"page":"854-859","source":"Crossref","is-referenced-by-count":0,"title":["What is the True Performance of Large Multimodal Models in Visual Context-Based Mathematical Reasoning? An Analysis of Multiple Datasets and Future Research Directions"],"prefix":"10.1109","author":[{"given":"Jieun","family":"Park","sequence":"first","affiliation":[{"name":"Tutorus Labs Inc.,AI Lab,Daejeon,Republic of Korea"}]},{"given":"Sungeun","family":"Park","sequence":"additional","affiliation":[{"name":"Tutorus Labs Inc.,AI Lab,Daejeon,Republic of Korea"}]},{"given":"Hyungbae","family":"Jeon","sequence":"additional","affiliation":[{"name":"Tutorus Labs Inc.,AI Lab,Daejeon,Republic of Korea"}]},{"given":"Joon-Ho","family":"Lim","sequence":"additional","affiliation":[{"name":"Tutorus Labs Inc.,AI Lab,Daejeon,Republic of Korea"}]}],"member":"263","reference":[{"volume-title":"Open AI","year":"2024","article-title":"Hello GPT-4o","key":"ref1"},{"author":"Team","journal-title":"Jean-Baptiste Alayrac, Jiahui","key":"ref2"},{"volume-title":"Google. Bard","year":"2023","key":"ref3"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.18653\/v1\/D15-1171"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1109\/CVPR52733.2024.00913"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1007\/978-3-031-73242-3_10"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.18653\/v1\/2024.findings-emnlp.268"},{"year":"2023","author":"Lu","journal-title":"Mathvista: Evaluating mathematical reasoning of foundation models in visual contexts","key":"ref8"},{"key":"ref9","first-page":"13319","author":"Amini","year":"1905","journal-title":"Mathqa: Towards interpretable math word problem solving with operation-based formalisms"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1109\/ICCV.2015.279"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1007\/978-3-031-73242-3_10"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.18653\/v1\/2021.findings-acl.46"},{"year":"2023","journal-title":"Citekey: gptvision","article-title":"Gpt-4v (ision) system card","key":"ref13"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1109\/CVPR.2018.00592"},{"year":"2024","author":"Wang","journal-title":"Measuring multimodal mathematical reasoning with math-vision dataset","key":"ref15"},{"year":"2024","author":"Qiao","journal-title":"We-Math: Does Your Large Multimodal Model Achieve Human-like Mathematical Reasoning?","key":"ref16"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1036\/1097-8542.284200"},{"author":"Team","journal-title":"Jean-Baptiste Alayrac, Jiahui","key":"ref18"},{"year":"2023","author":"Bai","journal-title":"Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond","key":"ref19"},{"year":"2023","author":"Lin","journal-title":"Sphinx: The joint mixing of weights, tasks, and visual embeddings for multimodal large language models","key":"ref20"}],"event":{"name":"2024 15th International Conference on Information and Communication Technology Convergence (ICTC)","start":{"date-parts":[[2024,10,16]]},"location":"Jeju Island, Korea, Republic of","end":{"date-parts":[[2024,10,18]]}},"container-title":["2024 15th International Conference on Information and Communication Technology Convergence (ICTC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10826571\/10826594\/10827294.pdf?arnumber=10827294","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,15]],"date-time":"2025-01-15T07:04:52Z","timestamp":1736924692000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10827294\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,16]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/ictc62082.2024.10827294","relation":{},"subject":[],"published":{"date-parts":[[2024,10,16]]}}}