{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,24]],"date-time":"2026-01-24T15:03:18Z","timestamp":1769266998171,"version":"3.49.0"},"reference-count":54,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2025.3557720","type":"journal-article","created":{"date-parts":[[2025,4,10]],"date-time":"2025-04-10T17:17:07Z","timestamp":1744305427000},"page":"3105-3116","source":"Crossref","is-referenced-by-count":3,"title":["AutoGeo: Automating Geometric Image Dataset Creation for Enhanced Geometry Understanding"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-0116-7250","authenticated-orcid":false,"given":"Zihan","family":"Huang","sequence":"first","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-7917-8849","authenticated-orcid":false,"given":"Tao","family":"Wu","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8353-2392","authenticated-orcid":false,"given":"Wang","family":"Lin","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0030-8289","authenticated-orcid":false,"given":"Shengyu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0415-6937","authenticated-orcid":false,"given":"Jingyuan","family":"Chen","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2139-8807","authenticated-orcid":false,"given":"Fei","family":"Wu","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"GPT-4 technical report","year":"2023"},{"key":"ref2","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.521"},{"key":"ref4","article-title":"GPT can solve mathematical problems without a calculator","author":"Yang","year":"2023"},{"key":"ref5","article-title":"Multimodal chain-of-thought reasoning in language models","volume":"2024","author":"Zhang","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.836"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01402"},{"key":"ref8","first-page":"118182","article-title":"$E^{3}$: Exploring embodied emotion through a large-scale egocentric video dataset","volume-title":"Proc. 38th Conf. Neural Inf. Process. Syst.","author":"Lin","year":"2024"},{"key":"ref9","article-title":"How well do large language models perform in arithmetic tasks?","author":"Yuan","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3120194"},{"key":"ref11","first-page":"79792","article-title":"AQuA: A benchmarking tool for label quality assessment","volume-title":"Proc. Neural Inf. Process. Syst. Conf.","author":"Goswami","year":"2024"},{"key":"ref12","article-title":"Measuring mathematical problem solving with the math dataset","volume-title":"Proc Neural Inf. Process. Syst. Track Datasets Benchmarks 1, NeurIPS Datasets Benchmarks","author":"Hendrycks","year":"2021"},{"key":"ref13","first-page":"44976","article-title":"PTADisc: A cross-course dataset supporting personalized learning in cold-start scenarios","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hu","year":"2023"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.528"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1171"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1081"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.46"},{"key":"ref18","first-page":"1511","article-title":"An augmented benchmark dataset for geometric question answering through dual parallel text encoding","volume-title":"Proc. 29th Int. Conf. Comput. Linguistics","author":"Cao","year":"2022"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/228"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/376"},{"key":"ref21","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho","year":"2020"},{"key":"ref22","first-page":"1","article-title":"Effective data augmentation with diffusion models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Trabucco","year":"2023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3154149"},{"key":"ref24","first-page":"29935","article-title":"Non-confusing generation of customized concepts in diffusion models","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Lin","year":"2024"},{"key":"ref25","first-page":"12195","article-title":"Action imitation in common action space for customized action image synthesis","volume-title":"Proc. 38th Annu. Conf. Neural Inf. Process. Syst.","author":"Lin","year":"2024"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.207"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-13166-0_95"},{"key":"ref28","article-title":"Matlab version: 9.13.0 (r2022b)","year":"2022","journal-title":""},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/MCSE.2007.55"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.218"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73242-3_10"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2019.2892755"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.3390\/electronics12051199"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3378465"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3270637"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72667-5_5"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3364536"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3181116"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681014"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.eng.2021.08.016"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.850"},{"key":"ref42","article-title":"G-LLaVA: Solving geometric problem with multi-modal large language model","author":"Gao","year":"2023"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612570"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06747-5"},{"key":"ref45","first-page":"1","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hu","year":"2021"},{"key":"ref46","article-title":"Geomverse: A systematic evaluation of large models for geometric reasoning","author":"Kazemi","year":"2023"},{"key":"ref47","article-title":"MAVIS: Mathematical visual instruction tuning with an automatic data engine","author":"Zhang","year":"2024"},{"key":"ref48","first-page":"49250","article-title":"Visual instruction tuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu","year":"2023"},{"key":"ref49","first-page":"49250","article-title":"InstructBLIP: Towards general-purpose vision-language models with instruction tuning","volume-title":"Proc. 37th Int. Conf. Neural Inf. Process. Syst.","author":"Dai","year":"2023"},{"key":"ref50","article-title":"MiniGPT-v2: Large language model as a unified interface for vision-language multi-task learning","author":"Chen","year":"2023"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref52","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","volume-title":"Proc. Text Summarization Branches Out","author":"Lin","year":"2004"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/10960701.pdf?arnumber=10960701","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,29]],"date-time":"2025-05-29T17:30:51Z","timestamp":1748539851000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10960701\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3557720","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}