{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T08:06:53Z","timestamp":1788941213316,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":66,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032370402","type":"print"},{"value":"9783032370419","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-37041-9_12","type":"book-chapter","created":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T07:31:13Z","timestamp":1788939073000},"page":"216-234","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Global-Local Dual Perception for\u00a0MLLMs in\u00a0High-Resolution Text-Rich Image Translation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3653-0858","authenticated-orcid":false,"given":"Junxin","family":"Lu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tengfei","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhanglin","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pengfei","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaowei","family":"Liang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hui","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kun","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ning","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunfei","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0158-5330","authenticated-orcid":false,"given":"Shiliang","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daimeng","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,10]]},"reference":[{"key":"12_CR1","unstructured":"Bai, J., et al.: Qwen-vl: a frontier large vision-language model with versatile abilities. arXiv preprint arXiv:2308.12966, 1(2), 3 (2023)"},{"key":"12_CR2","unstructured":"Bai, S., et\u00a0al.: Qwen2.5-vl technical report. arXiv preprint arXiv:2502.13923 (2025)"},{"key":"12_CR3","unstructured":"Blecher, L., Cucurull, G., Scialom, T., Stojnic, R.: Nougat: neural optical understanding for academic documents (2023). arXiv:2308.13418 arXiv preprint"},{"key":"12_CR4","unstructured":"Cai, L., Kang, J., Li, S., Ma, W., Xie, B., Qin, Z., Liang, J.: From local details to global context: Advancing vision-language models with attention-based selection. In: Forty-second International Conference on Machine Learning"},{"issue":"4","key":"12_CR5","doi-asserted-by":"publisher","first-page":"986","DOI":"10.1017\/nlp.2024.7","volume":"31","author":"S Castilho","year":"2025","unstructured":"Castilho, S., Knowles, R.: A survey of context in neural machine translation and its evaluation. Nat. Lang. Process. 31(4), 986\u20131016 (2025)","journal-title":"Nat. Lang. Process."},{"key":"12_CR6","first-page":"24081","volume":"37","author":"B Chen","year":"2024","unstructured":"Chen, B., Mart\u00ed Mons\u00f3, D., Du, Y., Simchowitz, M., Tedrake, R., Sitzmann, V.: Diffusion forcing: Next-token prediction meets full-sequence diffusion. NIPS 37, 24081\u201324125 (2024)","journal-title":"NIPS"},{"key":"12_CR7","doi-asserted-by":"crossref","unstructured":"Chen, Z., et\u00a0al.: Internvl: scaling up vision foundation models and aligning for generic visual-linguistic tasks. In: CVPR, pp. 24185\u201324198 (2024)","DOI":"10.1109\/CVPR52733.2024.02283"},{"key":"12_CR8","unstructured":"Cui, C., et\u00a0al.: Paddleocr 3.0 technical report. arXiv preprint arXiv:2507.05595 (2025)"},{"key":"12_CR9","unstructured":"Dong, D., et\u00a0al.: Qianfan-vl: Domain-enhanced universal vision-language models. arXiv preprint arXiv:2509.18189 (2025)"},{"key":"12_CR10","doi-asserted-by":"crossref","unstructured":"Dong, H., Kang, Z., Yin, W., Liang, X., Feng, C., Ran, J.: Scalable vision language model training via high quality data curation (2025). arXiv:2501.05952 arXiv preprint","DOI":"10.18653\/v1\/2025.acl-long.1595"},{"key":"12_CR11","unstructured":"Dong, X., et\u00a0al.: Internlm-xcomposer2: Mastering free-form text-image composition and comprehension in vision-language large model. arXiv preprint arXiv:2401.16420 (2024)"},{"key":"12_CR12","unstructured":"Dosovitskiy, A.: An image is worth 16x16 words: Transformers for image recognition at scale (2020). arXiv:2010.11929 arXiv preprint"},{"key":"12_CR13","doi-asserted-by":"crossref","unstructured":"Fang, W., Wu, Q., Chen, J., Xue, Y.: guided mllm reasoning: enhancing mllm with knowledge and visual notes for visual question answering. In: CVPR, pp. 19597\u201319607 (2025)","DOI":"10.1109\/CVPR52734.2025.01825"},{"key":"12_CR14","doi-asserted-by":"crossref","unstructured":"Fang, Z., Lyu, P., Wu, J., Zhang, C., Yu, J., Lu, G., Pei, W.: Recognition-synergistic scene text editing. In: CVPR, pp. 13104\u201313113 (2025)","DOI":"10.1109\/CVPR52734.2025.01223"},{"key":"12_CR15","unstructured":"Feng, F., Yang, Y., Cer, D., Arivazhagan, N., Wang, W.: Language-agnostic bert sentence embedding (2020). arXiv:2007.01852 arXiv preprint"},{"key":"12_CR16","unstructured":"Feng, Z., et al.: Mt3: scaling mllm-based text image machine translation via multi-task reinforcement learning. arXiv preprint arXiv:2505.19714 (2025)"},{"key":"12_CR17","unstructured":"Gao, P., He, Z., Wu, H., Wang, H.: Towards boosting many-to-many multilingual machine translation with large language models (2024). arXiv:2401.05861 arXiv preprint"},{"key":"12_CR18","doi-asserted-by":"crossref","unstructured":"Gao, T., Yao, X., Chen, D.: Simcse: Simple contrastive learning of sentence embeddings. EMNLP, pp, 6894\u20136910 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.552"},{"key":"12_CR19","doi-asserted-by":"crossref","unstructured":"Gao, Y., Zhao, J., Sun, S., Qiao, X., Song, T., Yang, H.: Multimodal machine translation with text-image in-depth questioning. In: finding of ACL, pp. 9274\u20139287 (2025)","DOI":"10.18653\/v1\/2025.findings-acl.483"},{"key":"12_CR20","unstructured":"Guo, D., et\u00a0al.: Deepseek-r1: incentivizing reasoning capability in llms via reinforcement learning. arXiv preprint arXiv:2501.12948 (2025)"},{"key":"12_CR21","doi-asserted-by":"crossref","unstructured":"Hinami, R., Ishiwatari, S., Yasuda, K., Matsui, Y.: Towards fully automated manga translation. In: AAAI, vol.\u00a035, pp. 12998\u201313008 (2021)","DOI":"10.1609\/aaai.v35i14.17537"},{"key":"12_CR22","doi-asserted-by":"crossref","unstructured":"Hu, A., et al.: mplug-docowl2: High-resolution compressing for ocr-free multi-page document understanding. In: Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 5817\u20135834 (2025)","DOI":"10.18653\/v1\/2025.acl-long.291"},{"key":"12_CR23","unstructured":"Hurst, A., et al.: GPT-4o system card (2024). arXiv:2410.21276 arXiv preprint"},{"key":"12_CR24","doi-asserted-by":"crossref","unstructured":"Lan, Z., Niu, L., Meng, F., Zhou, J., Zhang, M., Su, J.: Translatotron-v (ison): an end-to-end model for in-image machine translation. In: Finding of ACL, pp. 5472\u20135485 (2024)","DOI":"10.18653\/v1\/2024.findings-acl.325"},{"key":"12_CR25","doi-asserted-by":"crossref","unstructured":"Lan, Z., Yu, J., Li, X., Zhang, W., Luan, J., Wang, B., Huang, D., Su, J.: Exploring better text image translation with multimodal codebook. ACL, pp, 3479\u20133491 (2023)","DOI":"10.18653\/v1\/2023.acl-long.192"},{"key":"12_CR26","unstructured":"Li, B., Zhu, S., Wen, L.: Mit-10m: a large scale parallel corpus of multilingual image translation. In: COLING, pp. 5154\u20135167 (2025)"},{"key":"12_CR27","doi-asserted-by":"crossref","unstructured":"Li, H., Jie, Z., Lu, W.: Non-autoregressive machine translation as constrained hmm. In: finding of ACL, pp. 12361\u201312372 (2024)","DOI":"10.18653\/v1\/2024.findings-acl.735"},{"key":"12_CR28","doi-asserted-by":"crossref","unstructured":"Liang, Y., et al.: Document image machine translation with dynamic multi-pre-trained models assembling. In: NAACL, pp. 7084\u20137095 (2024)","DOI":"10.18653\/v1\/2024.naacl-long.392"},{"key":"12_CR29","doi-asserted-by":"crossref","unstructured":"Liang, Y., et al.: Improving mllm\u2019s document image machine translation via synchronously self-reviewing its ocr proficiency. In: finding of ACL, pp. 23659\u201323678 (2025)","DOI":"10.18653\/v1\/2025.findings-acl.1213"},{"key":"12_CR30","doi-asserted-by":"crossref","unstructured":"Liang, Y., et al.: Single-to-mix modality alignment with multimodal large language model for document image machine translation. In: ACL, pp. 12391\u201312408 (2025)","DOI":"10.18653\/v1\/2025.acl-long.606"},{"key":"12_CR31","unstructured":"Lu, H., et\u00a0al.: Deepseek-vl: towards real-world vision-language understanding. arXiv preprint arXiv:2403.05525 (2024)"},{"key":"12_CR32","unstructured":"Luan, B., Feng, H., Chen, H., Wang, Y., Zhou, W., Li, H.: Textcot: Zoom in for enhanced multimodal text-rich image understanding (2024). arXiv:2404.09797 arXiv preprint"},{"key":"12_CR33","doi-asserted-by":"publisher","first-page":"2153","DOI":"10.1109\/TASLP.2023.3324540","volume":"32","author":"C Ma","year":"2023","unstructured":"Ma, C., Han, X., Wu, L., Zhang, Y., Zhao, Y., Zhou, Y., Zong, C.: Modal contrastive learning based end-to-end text image machine translation. ACM Trans. Audio Speech Lang. Process. 32, 2153\u20132165 (2023)","journal-title":"ACM Trans. Audio Speech Lang. Process."},{"key":"12_CR34","doi-asserted-by":"crossref","unstructured":"Ma, C., et al.: Improving end-to-end text image translation from the auxiliary text translation task. In: ICPR, pp. 1664\u20131670. IEEE (2022)","DOI":"10.1109\/ICPR56361.2022.9956695"},{"key":"12_CR35","doi-asserted-by":"crossref","unstructured":"Ma, C., Zhang, Y., Tu, M., Zhao, Y., Zhou, Y., Zong, C.: Multi-teacher knowledge distillation for end-to-end text image machine translation. In: ICDAR, pp. 484\u2013501. Springer (2023)","DOI":"10.1007\/978-3-031-41676-7_28"},{"key":"12_CR36","doi-asserted-by":"crossref","unstructured":"Mansimov, E., Stern, M., Chen, M.X., Firat, O., Uszkoreit, J., Jain, P.: Towards end-to-end in-image neural machine translation, pp. 70\u201374. NLPBW (2020)","DOI":"10.18653\/v1\/2020.nlpbt-1.8"},{"key":"12_CR37","doi-asserted-by":"crossref","unstructured":"Niu, L., Meng, F., Zhou, J.: Umtit: Unifying recognition, translation, and generation for multimodal text image translation. In: LREC-COLING, pp. 16953\u201316972 (2024)","DOI":"10.63317\/5nsvo6f6qimb"},{"key":"12_CR38","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: Bleu: a method for automatic evaluation of machine translation. ACL, pp, 311\u2013318 (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"12_CR39","doi-asserted-by":"crossref","unstructured":"Park, J., Choi, J.Y., Park, J., Han, B.: Hierarchical visual feature aggregation for ocr-free document understanding. In: NeurIPS, vol.\u00a037, pp. 105972\u2013105996 (2024)","DOI":"10.52202\/079017-3362"},{"key":"12_CR40","doi-asserted-by":"crossref","unstructured":"Qian, Z., et al.: Anytrans: Translate anytext in the image with large scale models. In: finding of EMNLP, pp. 2432\u20132444 (2024)","DOI":"10.18653\/v1\/2024.findings-emnlp.137"},{"key":"12_CR41","doi-asserted-by":"crossref","unstructured":"Rafailov, R., Sharma, A., Mitchell, E., Manning, C.D., Ermon, S., Finn, C.: Direct preference optimization: Your language model is secretly a reward model. In: NeurIPS (2023). https:\/\/arxiv.org\/abs\/2305.18290","DOI":"10.52202\/075280-2338"},{"key":"12_CR42","doi-asserted-by":"crossref","unstructured":"Rei, R., Stewart, C., Farinha, A.C., Lavie, A.: Comet: A neural framework for mt evaluation. In: EMNLP, pp, 2685\u20132702 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.213"},{"key":"12_CR43","doi-asserted-by":"crossref","unstructured":"Shen, H., Zhao, K., Zhao, T., Xu, R., Zhang, Z., Zhu, M., Yin, J.: Zoomeye: Enhancing multimodal llms with human-like zooming capabilities through tree-based image exploration. In: Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pp. 6613\u20136629 (2025)","DOI":"10.18653\/v1\/2025.emnlp-main.335"},{"key":"12_CR44","doi-asserted-by":"crossref","unstructured":"Su, T., Liu, S., Zhou, S.: Rtnet: An end-to-end method for handwritten text image translation. In: ICDAR, pp. 99\u2013113. Springer (2021)","DOI":"10.1007\/978-3-030-86331-9_7"},{"key":"12_CR45","doi-asserted-by":"crossref","unstructured":"Tian, Y., Li, X., Liu, Z., Guo, Y., Wang, B.: In-image neural machine translation with segmented pixel sequence-to-sequence model. In: finding of EMNLP, pp. 15046\u201315057 (2023)","DOI":"10.18653\/v1\/2023.findings-emnlp.1004"},{"key":"12_CR46","doi-asserted-by":"crossref","unstructured":"Tian, Y., Han, Y., Chen, X., Wang, W., Chawla, N.V.: Beyond answers: Transferring reasoning capabilities to smaller llms using multi-teacher knowledge distillation. WSDM, pp, 251\u2013260 (2025)","DOI":"10.1145\/3701551.3703577"},{"key":"12_CR47","doi-asserted-by":"crossref","unstructured":"Vu, Y.L., et\u00a0al.: Describe anything model for visual question answering on text-rich images. arXiv preprint arXiv:2507.12441 (2025)","DOI":"10.1109\/ICCVW69036.2025.00776"},{"key":"12_CR48","unstructured":"Wang, B., et\u00a0al.: Mineru: an open-source solution for precise document content extraction. arXiv preprint arXiv:2409.18839 (2024)"},{"key":"12_CR49","unstructured":"Wang, P., et\u00a0al.: Qwen2-vl: enhancing vision-language model\u2019s perception of the world at any resolution. arXiv preprint arXiv:2409.12191 (2024)"},{"key":"12_CR50","doi-asserted-by":"crossref","unstructured":"Wang, W., et\u00a0al.: Cogvlm: visual expert for pretrained language models. In: NeurIPS, pp. 121475\u2013121499 (2024)","DOI":"10.52202\/079017-3860"},{"key":"12_CR51","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: Divide, conquer and combine: a training-free framework for high-resolution image perception in multimodal large language models. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 39, pp. 7907\u20137915 (2025)","DOI":"10.1609\/aaai.v39i8.32852"},{"key":"12_CR52","doi-asserted-by":"crossref","unstructured":"Wu, H., et al.: Flashbias: fast computation of attention with bias. arXiv preprint arXiv:2505.12044 (2025)","DOI":"10.52202\/085713-0699"},{"key":"12_CR53","doi-asserted-by":"crossref","unstructured":"Wu, P., Xie, S.: V*: Guided visual search as a core mechanism in multimodal llms. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13084\u201313094 (2024)","DOI":"10.1109\/CVPR52733.2024.01243"},{"key":"12_CR54","unstructured":"Yang, A., et\u00a0al.: Qwen3 technical report. arXiv preprint arXiv:2505.09388 (2025)"},{"key":"12_CR55","unstructured":"Yang, W., Wu, J., Wang, C., Zong, C., Zhang, J.: Language imbalance driven rewarding for multilingual self-improving, p. ICLR (2025)"},{"key":"12_CR56","doi-asserted-by":"crossref","unstructured":"Ye, J., et\u00a0al.: Ureader: universal ocr-free visually-situated language understanding with multimodal large language model. In: Finding of EMNLP, pp. 2841\u20132858 (2023)","DOI":"10.18653\/v1\/2023.findings-emnlp.187"},{"key":"12_CR57","unstructured":"Ye, J., et al.: mplug-owl3: towards long image-sequence understanding in multi-modal large language models. In: ICLR"},{"key":"12_CR58","doi-asserted-by":"crossref","unstructured":"Zhang, H., Chen, K., Bai, X., Xiang, Y., Zhang, M.: Paying more attention to source context: Mitigating unfaithful translations from large language model. In: finding of ACL (2024)","DOI":"10.18653\/v1\/2024.findings-acl.821"},{"key":"12_CR59","doi-asserted-by":"crossref","unstructured":"Zhang, Z., et al.: Layoutdit: layout-aware end-to-end document image translation with multi-step conductive decoder. In: Finding of EMNLP, pp. 10043\u201310053 (2023)","DOI":"10.18653\/v1\/2023.findings-emnlp.673"},{"key":"12_CR60","unstructured":"Zhang, Z., et al.: From chaotic ocr words to coherent document: a fine-to-coarse zoom-out network for complex-layout document image translation. In: COLING, pp. 10877\u201310890 (2025)"},{"key":"12_CR61","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Zhang, Y., Xiang, L., Zhao, Y., Zhou, Y., Zong, C.: A novel dataset and benchmark analysis on document image translation. In: CCMT, pp. 103\u2013115. Springer (2023)","DOI":"10.1007\/978-981-99-7894-6_10"},{"key":"12_CR62","doi-asserted-by":"crossref","unstructured":"Zhao, H.H., Zhou, P., Gao, D., Bai, Z., Shou, M.Z.: Lova3: learning to visual question answering, asking and assessment. In: NeurIPS 37, 115146\u2013115175 (2024)","DOI":"10.52202\/079017-3656"},{"key":"12_CR63","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Zhang, J., Zhou, Y., Zong, C.: Knowledge graphs enhanced neural machine translation. IJCAI, pp, 4039\u20134045 (2021)","DOI":"10.24963\/ijcai.2020\/559"},{"key":"12_CR64","unstructured":"Zhu, J., et al.: Internvl3: exploring advanced training and test-time recipes for open-source multimodal models (2025). arXiv:2504.10479 arXiv preprint"},{"key":"12_CR65","doi-asserted-by":"crossref","unstructured":"Zhu, S., Li, S., Lei, Y., Xiong, D.: Peit: bridging the modality gap with pre-trained models for end-to-end image translation. In: ACL, pp. 13433\u201313447 (2023)","DOI":"10.18653\/v1\/2023.acl-long.751"},{"key":"12_CR66","doi-asserted-by":"crossref","unstructured":"Zuo, F., Chen, K., Zhang, Y., Xue, Z., Zhang, M.: Inimagetrans: multimodal llm-based text image machine translation. In: Finding of ACL, pp. 20256\u201320277 (2025)","DOI":"10.18653\/v1\/2025.findings-acl.1039"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37041-9_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T07:31:30Z","timestamp":1788939090000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37041-9_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032370402","9783032370419"],"references-count":66,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37041-9_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"10 September 2026","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":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}