{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T13:15:27Z","timestamp":1772802927573,"version":"3.50.1"},"publisher-location":"Cham","reference-count":56,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031732256","type":"print"},{"value":"9783031732263","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"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\/978-3-031-73226-3_15","type":"book-chapter","created":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T15:02:57Z","timestamp":1730386977000},"page":"253-269","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["LLMCO4MR: LLMs-Aided Neural Combinatorial Optimization for\u00a0Ancient Manuscript Restoration from\u00a0Fragments with\u00a0Case Studies on\u00a0Dunhuang"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-7205-761X","authenticated-orcid":false,"given":"Yuqing","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8348-2331","authenticated-orcid":false,"given":"Hangqi","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0030-8289","authenticated-orcid":false,"given":"Shengyu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9566-738X","authenticated-orcid":false,"given":"Runzhong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7404-2009","authenticated-orcid":false,"given":"Baoyi","family":"He","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9499-3394","authenticated-orcid":false,"given":"Huaiyong","family":"Dou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9639-7679","authenticated-orcid":false,"given":"Junchi","family":"Yan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3065-7199","authenticated-orcid":false,"given":"Yongquan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2139-8807","authenticated-orcid":false,"given":"Fei","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,1]]},"reference":[{"issue":"3","key":"15_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3460961","volume":"14","author":"R Abitbol","year":"2021","unstructured":"Abitbol, R., Shimshoni, I., Ben-Dov, J.: Machine learning based assembly of fragments of ancient papyrus. J. Comput. Cultural Heritage (JOCCH) 14(3), 1\u201321 (2021)","journal-title":"J. Comput. Cultural Heritage (JOCCH)"},{"issue":"7900","key":"15_CR2","doi-asserted-by":"publisher","first-page":"280","DOI":"10.1038\/s41586-022-04448-z","volume":"603","author":"Y Assael","year":"2022","unstructured":"Assael, Y., et al.: Restoring and attributing ancient texts using deep neural networks. Nature 603(7900), 280\u2013283 (2022)","journal-title":"Nature"},{"key":"15_CR3","unstructured":"Bai, J., et al.: Qwen technical report (2023)"},{"key":"15_CR4","unstructured":"Bai, J., et al.: Qwen-VL: a versatile vision-language model for understanding, localization, text reading, and beyond (2023)"},{"issue":"2","key":"15_CR5","doi-asserted-by":"publisher","first-page":"405","DOI":"10.1016\/j.ejor.2020.07.063","volume":"290","author":"Y Bengio","year":"2021","unstructured":"Bengio, Y., Lodi, A., Prouvost, A.: Machine learning for combinatorial optimization: a methodological tour d\u2019horizon. Eur. J. Oper. Res. 290(2), 405\u2013421 (2021)","journal-title":"Eur. J. Oper. Res."},{"key":"15_CR6","unstructured":"Besl, P.J., McKay, N.D.: Method for registration of 3-D shapes. In: Sensor fusion IV: Control Paradigms and Data Structures, vol.\u00a01611, pp. 586\u2013606. Spie (1992)"},{"key":"15_CR7","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., et al.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877\u20131901 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"15_CR8","doi-asserted-by":"crossref","unstructured":"Buchbinder, N., Feldman, M., Naor, J., Schwartz, R.: Submodular maximization with cardinality constraints. In: Proceedings of the Twenty-fifth Annual ACM-SIAM Symposium on Discrete Algorithms, pp. 1433\u20131452. SIAM (2014)","DOI":"10.1137\/1.9781611973730.80"},{"key":"15_CR9","unstructured":"Cuturi, M.: Sinkhorn distances: lightspeed computation of optimal transport. Adv. Neural Inf. Process. Syst. 26 (2013)"},{"key":"15_CR10","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108065","volume":"119","author":"N Derech","year":"2021","unstructured":"Derech, N., Tal, A., Shimshoni, I.: Solving archaeological puzzles. Pattern Recogn. 119, 108065 (2021)","journal-title":"Pattern Recogn."},{"key":"15_CR11","unstructured":"Driess, D., et al.: PaLM-E: an embodied multimodal language model (2023)"},{"key":"15_CR12","doi-asserted-by":"crossref","unstructured":"Galambos, I.: Dunhuang Manuscript Culture: End of the First Millennium, vol.\u00a022. Walter de Gruyter GmbH & Co KG (2020)","DOI":"10.1515\/9783110726572"},{"issue":"9","key":"15_CR13","doi-asserted-by":"publisher","first-page":"1239","DOI":"10.1109\/TPAMI.2002.1033215","volume":"24","author":"HC da Gama Leitao","year":"2002","unstructured":"da Gama Leitao, H.C., Stolfi, J.: A multiscale method for the reassembly of two-dimensional fragmented objects. IEEE Trans. Pattern Anal. Mach. Intell. 24(9), 1239\u20131251 (2002)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"15_CR14","unstructured":"Ge, J., Luo, H., Qian, S., Gan, Y., Fu, J., Zhang, S.: Chain of thought prompt tuning in vision language models (2023)"},{"key":"15_CR15","unstructured":"Guo, P.F., Chen, Y.H., Tsai, Y.D., Lin, S.D.: Towards optimizing with large language models. arXiv preprint arXiv:2310.05204 (2023)"},{"key":"15_CR16","unstructured":"Guo, Q., et al.: Connecting large language models with evolutionary algorithms yields powerful prompt optimizers. arXiv preprint arXiv:2309.08532 (2023)"},{"key":"15_CR17","unstructured":"Hossieni, S.S., Shabani, M.A., Irandoust, S., Furukawa, Y.: PuzzleFusion: unleashing the power of diffusion models for spatial puzzle solving. Adv. Neural Inf. Process. Syst. 36 (2024)"},{"key":"15_CR18","first-page":"6659","volume":"33","author":"N Karalias","year":"2020","unstructured":"Karalias, N., Loukas, A.: Erdos goes neural: an unsupervised learning framework for combinatorial optimization on graphs. Adv. Neural. Inf. Process. Syst. 33, 6659\u20136672 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"8","key":"15_CR19","doi-asserted-by":"publisher","first-page":"4000","DOI":"10.1109\/TIP.2019.2903298","volume":"28","author":"C Le","year":"2019","unstructured":"Le, C., Li, X.: Jigsawnet: shredded image reassembly using convolutional neural network and loop-based composition. IEEE Trans. Image Process. 28(8), 4000\u20134015 (2019)","journal-title":"IEEE Trans. Image Process."},{"key":"15_CR20","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning (2023)"},{"key":"15_CR21","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. Adv. Neural Inf. Process. Syst. 36 (2024)"},{"key":"15_CR22","unstructured":"Lu, J., Sun, Y., Huang, Q.: Jigsaw: Learning to assemble multiple fractured objects. arXiv preprint arXiv:2305.17975 (2023)"},{"key":"15_CR23","unstructured":"Lyu, C., et al.: Macaw-LLM: multi-modal language modeling with image, audio, video, and text integration (2023)"},{"key":"15_CR24","doi-asserted-by":"crossref","unstructured":"Maaz, M., Rasheed, H., Khan, S., Khan, F.S.: Video-chatGPT: towards detailed video understanding via large vision and language models (2023)","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"15_CR25","doi-asserted-by":"crossref","unstructured":"Markaki, S., Panagiotakis, C.: Jigsaw puzzle solving techniques and applications: a survey. Vis. Comput. 1\u201317 (2022)","DOI":"10.1007\/s00371-022-02598-9"},{"key":"15_CR26","unstructured":"OpenAI: Gpt-4 technical report (2023)"},{"issue":"6","key":"15_CR27","doi-asserted-by":"publisher","first-page":"1439","DOI":"10.1007\/s10596-022-10175-1","volume":"26","author":"C Panagiotakis","year":"2022","unstructured":"Panagiotakis, C., Markaki, S., Kokinou, E., Papadakis, H.: Coastline matching via a graph-based approach. Comput. Geosci. 26(6), 1439\u20131448 (2022)","journal-title":"Comput. Geosci."},{"key":"15_CR28","doi-asserted-by":"crossref","unstructured":"Paumard, M.M., Picard, D., Tabia, H.: Jigsaw puzzle solving using local feature co-occurrences in deep neural networks. In: 2018 25th IEEE International Conference on Image Processing (ICIP), pp. 1018\u20131022. IEEE (2018)","DOI":"10.1109\/ICIP.2018.8451094"},{"key":"15_CR29","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1007\/s10032-016-0277-z","volume":"20","author":"G Pengcheng","year":"2017","unstructured":"Pengcheng, G., Gang, G., Jiangqin, W., Baogang, W.: Chinese calligraphic style representation for recognition. Int. J. Doc. Anal. Recogn. (IJDAR) 20, 59\u201368 (2017)","journal-title":"Int. J. Doc. Anal. Recogn. (IJDAR)"},{"key":"15_CR30","doi-asserted-by":"crossref","unstructured":"Pirrone, A., Aimar, M.B., Journet, N.: Papy-S-Net: a siamese network to match papyrus fragments. In: Proceedings of the 5th International Workshop on Historical Document Imaging and Processing, pp. 78\u201383 (2019)","DOI":"10.1145\/3352631.3352646"},{"issue":"3","key":"15_CR31","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1007\/s10032-021-00369-1","volume":"24","author":"A Pirrone","year":"2021","unstructured":"Pirrone, A., Beurton-Aimar, M., Journet, N.: Self-supervised deep metric learning for ancient papyrus fragments retrieval. Int. J. Doc. Anal. Recogn. (IJDAR) 24(3), 219\u2013234 (2021)","journal-title":"Int. J. Doc. Anal. Recogn. (IJDAR)"},{"key":"15_CR32","doi-asserted-by":"crossref","unstructured":"Rusinkiewicz, S., Levoy, M.: Efficient variants of the ICP algorithm. In: Proceedings Third International Conference on 3-D Digital Imaging and Modeling, pp. 145\u2013152. IEEE (2001)","DOI":"10.1109\/IM.2001.924423"},{"key":"15_CR33","unstructured":"Savelka, J., Ashley, K.D., Gray, M.A., Westermann, H., Xu, H.: Explaining legal concepts with augmented large language models (GPT-4) (2023)"},{"key":"15_CR34","doi-asserted-by":"publisher","first-page":"511","DOI":"10.1016\/j.culher.2015.11.005","volume":"19","author":"P Savino","year":"2016","unstructured":"Savino, P., Tonazzini, A.: Digital restoration of ancient color manuscripts from geometrically misaligned recto-verso pairs. J. Cult. Herit. 19, 511\u2013521 (2016)","journal-title":"J. Cult. Herit."},{"key":"15_CR35","doi-asserted-by":"publisher","unstructured":"Shuai, R.W., Ruffolo, J.A., Gray, J.J.: Generative language modeling for antibody design. bioRxiv (2022). https:\/\/doi.org\/10.1101\/2021.12.13.472419, https:\/\/www.biorxiv.org\/content\/early\/2022\/12\/20\/2021.12.13.472419","DOI":"10.1101\/2021.12.13.472419"},{"key":"15_CR36","unstructured":"Singhal, K., et al.: Large language models encode clinical knowledge (2022)"},{"key":"15_CR37","doi-asserted-by":"crossref","unstructured":"Sommerschield, T., et al.: Machine learning for ancient languages: a survey. Comput. Linguist. 49(3), 1\u201344 (2023)","DOI":"10.1162\/coli_a_00481"},{"key":"15_CR38","unstructured":"Touvron, H., et\u00a0al.: LLaMA: open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"issue":"3","key":"15_CR39","doi-asserted-by":"publisher","first-page":"680","DOI":"10.1109\/TIP.2009.2035840","volume":"19","author":"E Tsamoura","year":"2009","unstructured":"Tsamoura, E., Pitas, I.: Automatic color based reassembly of fragmented images and paintings. IEEE Trans. Image Process. 19(3), 680\u2013690 (2009)","journal-title":"IEEE Trans. Image Process."},{"key":"15_CR40","unstructured":"Vinyals, O., Fortunato, M., Jaitly, N.: Pointer networks. Adv. Neural Inf. Process. Syst. 28 (2015)"},{"key":"15_CR41","unstructured":"Wang, R., Shen, L., Chen, Y., Yang, X., Tao, D., Yan, J.: Towards one-shot neural combinatorial solvers: theoretical and empirical notes on the cardinality-constrained case. In: The Eleventh International Conference on Learning Representations (2022)"},{"key":"15_CR42","doi-asserted-by":"crossref","unstructured":"Wang, R., Yan, J., Yang, X.: Learning combinatorial embedding networks for deep graph matching. In: Proceedings of the IEEE\/CVF International Conference On Computer Vision, pp. 3056\u20133065 (2019)","DOI":"10.1109\/ICCV.2019.00315"},{"key":"15_CR43","unstructured":"Wang, R., Zhang, Y., Guo, Z., Chen, T., Yang, X., Yan, J.: LinSATNet: the positive linear satisfiability neural networks. In: International Conference on Machine Learning (ICML) (2023)"},{"issue":"1","key":"15_CR44","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1007\/BF02186360","volume":"12","author":"H Wolfson","year":"1988","unstructured":"Wolfson, H., Schonberg, E., Kalvin, A., Lamdan, Y.: Solving jigsaw puzzles by computer. Ann. Oper. Res. 12(1), 51\u201364 (1988)","journal-title":"Ann. Oper. Res."},{"key":"15_CR45","unstructured":"Xi, Z., et\u00a0al.: The rise and potential of large language model based agents: a survey. arXiv preprint arXiv:2309.07864 (2023)"},{"key":"15_CR46","first-page":"20520","volume":"33","author":"Y Xie","year":"2020","unstructured":"Xie, Y., et al.: Differentiable top-k with optimal transport. Adv. Neural. Inf. Process. Syst. 33, 20520\u201320531 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"15_CR47","unstructured":"Yang, A., et al.: Baichuan 2: open large-scale language models (2023)"},{"key":"15_CR48","unstructured":"Yang, Z., et al.: The dawn of LMMs: preliminary explorations with GPT-4V(ision) (2023)"},{"key":"15_CR49","unstructured":"Yang, Z., et al.: MM-REACT: prompting chatGPT for multimodal reasoning and action (2023)"},{"key":"15_CR50","unstructured":"Yu, F., Quartey, L., Schilder, F.: Legal prompting: teaching a language model to think like a lawyer (2022)"},{"key":"15_CR51","doi-asserted-by":"crossref","unstructured":"Zhang, C., et al.: Data-driven oracle bone rejoining: a dataset and practical self-supervised learning scheme. In: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pp. 4482\u20134492 (2022)","DOI":"10.1145\/3534678.3539050"},{"key":"15_CR52","doi-asserted-by":"crossref","unstructured":"Zhang, C., Zong, R., Cao, S., Men, Y., Mo, B.: AI-powered oracle bone inscriptions recognition and fragments rejoining. In: Proceedings of the Twenty-Ninth International Conference on International Joint Conferences on Artificial Intelligence, pp. 5309\u20135311 (2021)","DOI":"10.24963\/ijcai.2020\/779"},{"issue":"5","key":"15_CR53","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1016\/j.gmod.2014.03.001","volume":"76","author":"K Zhang","year":"2014","unstructured":"Zhang, K., Li, X.: A graph-based optimization algorithm for fragmented image reassembly. Graph. Models 76(5), 484\u2013495 (2014)","journal-title":"Graph. Models"},{"key":"15_CR54","doi-asserted-by":"crossref","unstructured":"Zhang, Y., et al.: Reconnecting the broken civilization: patchwork integration of fragments from ancient manuscripts. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 1157\u20131166 (2023)","DOI":"10.1145\/3581783.3613804"},{"key":"15_CR55","doi-asserted-by":"publisher","unstructured":"Zhang, Z., Wang, Y.T., Li, B., Guo, A., Liu, C.L.: Deep rejoining model for oracle bone fragment image. In: Asian Conference on Pattern Recognition, pp. 3\u201315. Springer (2021). https:\/\/doi.org\/10.1007\/978-3-031-02444-3_1","DOI":"10.1007\/978-3-031-02444-3_1"},{"key":"15_CR56","unstructured":"Zhu, D., Chen, J., Shen, X., Li, X., Elhoseiny, M.: MiniGPT-4: enhancing vision-language understanding with advanced large language models (2023)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73226-3_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T15:16:12Z","timestamp":1730387772000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73226-3_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,1]]},"ISBN":["9783031732256","9783031732263"],"references-count":56,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73226-3_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,1]]},"assertion":[{"value":"1 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","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":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}