{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T00:03:12Z","timestamp":1742947392443,"version":"3.40.3"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031781186"},{"type":"electronic","value":"9783031781193"}],"license":[{"start":{"date-parts":[[2024,12,5]],"date-time":"2024-12-05T00:00:00Z","timestamp":1733356800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,5]],"date-time":"2024-12-05T00:00:00Z","timestamp":1733356800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-78119-3_13","type":"book-chapter","created":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T02:00:35Z","timestamp":1733277635000},"page":"183-196","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["SANS: Spatial-Aware Neural Solver for\u00a0Plane Geometry Problem"],"prefix":"10.1007","author":[{"given":"Zi-Hao","family":"Lin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shun-Xin","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zi-Rong","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian-Min","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Da-Han","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xu-Yao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,5]]},"reference":[{"key":"13_CR1","unstructured":"Achiam, J., et\u00a0al.: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"13_CR2","doi-asserted-by":"crossref","unstructured":"Antol, S., Agrawal, A., et al.: VQA: visual question answering. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2425\u20132433 (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"13_CR3","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1016\/j.procs.2018.05.095","volume":"132","author":"R Bajaj","year":"2018","unstructured":"Bajaj, R., Sharma, V.: Smart education with artificial intelligence based determination of learning styles. Procedia Comput. Sci. 132, 834\u2013842 (2018)","journal-title":"Procedia Comput. Sci."},{"key":"13_CR4","unstructured":"Bao, H., et\u00a0al.: UniLMv2: pseudo-masked language models for unified language model pre-training. In: International Conference on Machine Learning, pp. 642\u2013652. PMLR (2020)"},{"key":"13_CR5","doi-asserted-by":"crossref","unstructured":"Chen, J., et al.: UniGeo: unifying geometry logical reasoning via reformulating mathematical expression. In: Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pp. 3313\u20133323 (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.218"},{"key":"13_CR6","doi-asserted-by":"crossref","unstructured":"Chen, J., et al.: GeoQA: a geometric question answering benchmark towards multimodal numerical reasoning. In: Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pp. 513\u2013523 (2021)","DOI":"10.18653\/v1\/2021.findings-acl.46"},{"key":"13_CR7","unstructured":"Cho, J., Lei, J., Tan, H., Bansal, M.: Unifying vision-and-language tasks via text generation. In: Proceedings of the 38th International Conference on Machine Learning, vol.\u00a0139, pp. 1931\u20131942 (2021)"},{"issue":"4","key":"13_CR8","doi-asserted-by":"publisher","first-page":"398","DOI":"10.1007\/s11263-018-1116-0","volume":"127","author":"Y Goyal","year":"2019","unstructured":"Goyal, Y., Khot, T., Agrawal, A., Summers-Stay, D., Batra, D., Parikh, D.: Making the V in VQA matter: elevating the role of image understanding in visual question answering. Int. J. Comput. Vision 127(4), 398\u2013414 (2019)","journal-title":"Int. J. Comput. Vision"},{"key":"13_CR9","unstructured":"Grill, J.B., et\u00a0al.: Bootstrap your own latent a new approach to self-supervised learning. In: Proceedings of the 34th International Conference on Neural Information Processing Systems, pp. 21271\u201321284 (2020)"},{"key":"13_CR10","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"13_CR11","doi-asserted-by":"crossref","unstructured":"Huang, Y., Lv, T., Cui, L., Lu, Y., Wei, F.: LayoutLMv3: pre-training for document AI with unified text and image masking. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 4083\u20134091 (2022)","DOI":"10.1145\/3503161.3548112"},{"key":"13_CR12","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: Proceedings of the 38th International Conference on Machine Learning, pp. 4904\u20134916 (2021)"},{"key":"13_CR13","unstructured":"Kim, W., Son, B., Kim, I.: ViLT: vision-and-language transformer without convolution or region supervision. In: Proceedings of the 38th International Conference on Machine Learning, pp. 5583\u20135594 (2021)"},{"key":"13_CR14","unstructured":"Li, J., Selvaraju, R., Gotmare, A., Joty, S., Xiong, C., Hoi, S.C.H.: Align before fuse: vision and language representation learning with momentum distillation. In: Proceedings of the Neural Information Processing Systems, pp. 9694\u20139705 (2021)"},{"key":"13_CR15","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. Adv. Neural Inf. Process. Syst. 36 (2024)"},{"key":"13_CR16","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: Proceedings of the 36th International Conference on Learning Representations (2019)"},{"key":"13_CR17","doi-asserted-by":"crossref","unstructured":"Lu, P., et al.: Inter-GPS: interpretable geometry problem solving with formal language and symbolic reasoning. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, pp. 6774\u20136786 (2021)","DOI":"10.18653\/v1\/2021.acl-long.528"},{"key":"13_CR18","doi-asserted-by":"crossref","unstructured":"Ning, M., Wang, Q.F., Huang, K., Huang, X.: A symbolic characters aware model for solving geometry problems. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 7767\u20137775 (2023)","DOI":"10.1145\/3581783.3612570"},{"key":"13_CR19","doi-asserted-by":"crossref","unstructured":"Peng, S., Fu, D., Liang, Y., Gao, L., Tang, Z.: GeoDRL: a self-learning framework for geometry problem solving using reinforcement learning in deductive reasoning. In: Findings of the Association for Computational Linguistics: ACL-IJCNLP 2023, pp. 13468\u201313480 (2023)","DOI":"10.18653\/v1\/2023.findings-acl.850"},{"key":"13_CR20","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: Proceedings of the 38th International Conference on Machine Learning, pp. 8748\u20138763 (2021)"},{"key":"13_CR21","doi-asserted-by":"crossref","unstructured":"Sachan, M., Xing, E.: Learning to solve geometry problems from natural language demonstrations in textbooks. In: Proceedings of the 6th Joint Conference on Lexical and Computational Semantics, pp. 251\u2013261 (2017)","DOI":"10.18653\/v1\/S17-1029"},{"key":"13_CR22","doi-asserted-by":"crossref","unstructured":"Seo, M., Hajishirzi, H., Farhadi, A., Etzioni, O., Malcolm, C.: Solving geometry problems: combining text and diagram interpretation. In: Proceedings of the 2015 Conference on Empirical Methods in Natural Panguage Processing, pp. 1466\u20131476 (2015)","DOI":"10.18653\/v1\/D15-1171"},{"issue":"4","key":"13_CR23","doi-asserted-by":"publisher","first-page":"447","DOI":"10.1007\/s11633-022-1410-8","volume":"20","author":"X Wang","year":"2023","unstructured":"Wang, X., et al.: Large-scale multi-modal pre-trained models: a comprehensive survey. Mach. Intell. Res. 20(4), 447\u2013482 (2023)","journal-title":"Mach. Intell. Res."},{"key":"13_CR24","unstructured":"Waswani, A., et al.: Attention is all you need. In: Proceedings of the Conference on Neural Information Processing Systems (2017)"},{"key":"13_CR25","doi-asserted-by":"crossref","unstructured":"Wei, X., Zhang, T., Li, Y., Zhang, Y., Wu, F.: Multi-modality cross attention network for image and sentence matching. In: Proceedings of the 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10938\u201310947 (2020)","DOI":"10.1109\/CVPR42600.2020.01095"},{"key":"13_CR26","doi-asserted-by":"crossref","unstructured":"Wenjun, W.: Basic principles of mechanical theorem proving in elementary geometries. Selected Works Of Wen-Tsun Wu, p.\u00a0195 (2008)","DOI":"10.1142\/9789812791085_0012"},{"key":"13_CR27","doi-asserted-by":"crossref","unstructured":"Xu, Y., et\u00a0al.: LayoutLMv2: multi-modal pre-training for visually-rich document understanding. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, pp. 2579\u20132591 (2021)","DOI":"10.18653\/v1\/2021.acl-long.201"},{"key":"13_CR28","doi-asserted-by":"crossref","unstructured":"Xu, Y., Li, M., Cui, L., Huang, S., Wei, F., Zhou, M.: LayoutLM: pre-training of text and layout for document image understanding. In: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1192\u20131200 (2020)","DOI":"10.1145\/3394486.3403172"},{"key":"13_CR29","doi-asserted-by":"crossref","unstructured":"Zhang, M.L., Yin, F., Hao, Y.H., Liu, C.L.: Plane geometry diagram parsing. In: Proceedings of the Joint Conference on Artificial Intelligence (2022)","DOI":"10.24963\/ijcai.2022\/228"},{"key":"13_CR30","doi-asserted-by":"crossref","unstructured":"Zhang, M.L., Yin, F., Liu, C.L.: A multi-modal neural geometric solver with textual clauses parsed from diagram. In: Proceedings of the 32nd International Joint Conference on Artificial Intelligence, pp. 3374\u20133382 (2023)","DOI":"10.24963\/ijcai.2023\/376"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-78119-3_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T02:05:08Z","timestamp":1733277908000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78119-3_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,5]]},"ISBN":["9783031781186","9783031781193"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78119-3_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,12,5]]},"assertion":[{"value":"5 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kolkata","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}