{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T23:05:05Z","timestamp":1789254305877,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":67,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032375735","type":"print"},{"value":"9783032375742","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\/978-3-032-37574-2_32","type":"book-chapter","created":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T22:22:59Z","timestamp":1789251779000},"page":"577-595","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Exploring Efficient Reasoning Segmentation with\u00a0Small Language Models"],"prefix":"10.1007","author":[{"given":"Changsong","family":"Wen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zelin","family":"Peng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaokang","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,13]]},"reference":[{"key":"32_CR1","unstructured":"Abdin, M., et\u00a0al.: Phi-3 technical report: a highly capable language model locally on your phone. arXiv preprint arXiv:2404.14219 (2024)"},{"key":"32_CR2","unstructured":"Achiam, J., et al.: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"32_CR3","doi-asserted-by":"crossref","unstructured":"Caesar, H., Uijlings, J., Ferrari, V.: Coco-stuff: thing and stuff classes in context. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1209\u20131218 (2018)","DOI":"10.1109\/CVPR.2018.00132"},{"key":"32_CR4","doi-asserted-by":"publisher","first-page":"53168","DOI":"10.52202\/079017-1684","volume":"37","author":"K Chandrasegaran","year":"2024","unstructured":"Chandrasegaran, K., et al.: Hourvideo: 1-hour video-language understanding. Adv. Neural. Inf. Process. Syst. 37, 53168\u201353197 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"32_CR5","doi-asserted-by":"crossref","unstructured":"Chen, L., et al.: An image is worth 1\/2 tokens after layer 2: plug-and-play inference acceleration for large vision-language models. In: European Conference on Computer Vision, pp. 19\u201335 (2024)","DOI":"10.1007\/978-3-031-73004-7_2"},{"key":"32_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Y.C., Li, W.H., Sun, C., Wang, Y.C.F., Chen, C.S.: Sam4mllm: enhance multi-modal large language model for referring expression segmentation. In: European Conference on Computer Vision, pp. 323\u2013340 (2024)","DOI":"10.1007\/978-3-031-73004-7_19"},{"key":"32_CR7","doi-asserted-by":"crossref","unstructured":"Cheng, B., Misra, I., Schwing, A.G., Kirillov, A., Girdhar, R.: Masked-attention mask transformer for universal image segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1290\u20131299 (2022)","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"32_CR8","doi-asserted-by":"crossref","unstructured":"Ding, H., Liu, C., Wang, S., Jiang, X.: Vision-language transformer and query generation for referring segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 16321\u201316330 (2021)","DOI":"10.1109\/ICCV48922.2021.01601"},{"key":"32_CR9","unstructured":"Dong, H., Li, J., Wu, B., Wang, J., Zhang, Y., Guo, H.: Benchmarking and improving detail image caption. arXiv preprint arXiv:2405.19092 (2024)"},{"key":"32_CR10","doi-asserted-by":"crossref","unstructured":"Gong, S., Zhuge, Y., Zhang, L., Yang, Z., Zhang, P., Lu, H.: The devil is in temporal token: high quality video reasoning segmentation. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 29183\u201329192 (2025)","DOI":"10.1109\/CVPR52734.2025.02717"},{"key":"32_CR11","doi-asserted-by":"crossref","unstructured":"Guan, T., et al.: A token-level text image foundation model for document understanding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 23210\u201323220 (2025)","DOI":"10.1109\/ICCV51701.2025.02155"},{"key":"32_CR12","unstructured":"Guan, T., et\u00a0al.: Codepercept: code-grounded visual stem perception for MLLMs. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 33542\u201333552 (2026)"},{"key":"32_CR13","doi-asserted-by":"crossref","unstructured":"He, J., et al.: Multi-modal instruction tuned LLMs with fine-grained visual perception. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13980\u201313990 (2024)","DOI":"10.1109\/CVPR52733.2024.01326"},{"issue":"1","key":"32_CR14","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1007\/s41701-025-00204-6","volume":"10","author":"B Hu","year":"2026","unstructured":"Hu, B., Zhang, Y.: How ai and humans express comfort differently: a corpus-based appraisal analysis. Corpus Pragmatics 10(1), 16 (2026)","journal-title":"Corpus Pragmatics"},{"key":"32_CR15","unstructured":"Jang, D., Cho, Y., Lee, S., Kim, T., Kim, D.S.: MMR: a large-scale benchmark dataset for multi-target and multi-granularity reasoning segmentation. In: Proceedings of the International Conference on Learning Representations (2025)"},{"key":"32_CR16","unstructured":"Jia, J., et\u00a0al.: Tinyllava factory: a modularized codebase for small-scale large multimodal models. arXiv preprint arXiv:2405.11788 (2024)"},{"key":"32_CR17","unstructured":"Kirillov, A., et al.: Segment anything. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4015\u20134026 (2023)"},{"key":"32_CR18","doi-asserted-by":"crossref","unstructured":"Kong, L., Liu, Y., Ng, L.X., Cottereau, B.R., Ooi, W.T.: Openess: event-based semantic scene understanding with open vocabularies. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15686\u201315698 (2024)","DOI":"10.1109\/CVPR52733.2024.01485"},{"key":"32_CR19","doi-asserted-by":"crossref","unstructured":"Lai, X., et al.: Lisa: reasoning segmentation via large language model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9579\u20139589 (2024)","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"32_CR20","doi-asserted-by":"crossref","unstructured":"Lauren\u00e7on, H., Marafioti, A., Sanh, V., Tronchon, L.: Building and better understanding vision-language models: insights and future directions. arXiv preprint arXiv:2408.12637 (2024)","DOI":"10.52202\/079017-2789"},{"key":"32_CR21","unstructured":"Li, B., et al.: Llava-onevision: easy visual task transfer. arXiv preprint arXiv:2408.03326 (2024)"},{"key":"32_CR22","doi-asserted-by":"crossref","unstructured":"Li, J., Dai, H., Han, H., Ding, Y.: Mseg3D: multi-modal 3D semantic segmentation for autonomous driving. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21694\u201321704 (2023)","DOI":"10.1109\/CVPR52729.2023.02078"},{"key":"32_CR23","doi-asserted-by":"crossref","unstructured":"Li, X., et al.: Omg-seg: is one model good enough for all segmentation? In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 27948\u201327959 (2024)","DOI":"10.1109\/CVPR52733.2024.02640"},{"key":"32_CR24","doi-asserted-by":"crossref","unstructured":"Liang, F., et al.: Open-vocabulary semantic segmentation with mask-adapted clip. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7061\u20137070 (2023)","DOI":"10.1109\/CVPR52729.2023.00682"},{"key":"32_CR25","doi-asserted-by":"crossref","unstructured":"Liu, C., Ding, H., Jiang, X.: Gres: generalized referring expression segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 23592\u201323601 (2023)","DOI":"10.1109\/CVPR52729.2023.02259"},{"key":"32_CR26","doi-asserted-by":"publisher","first-page":"34892","DOI":"10.52202\/075280-1516","volume":"36","author":"H Liu","year":"2023","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. Adv. Neural. Inf. Process. Syst. 36, 34892\u201334916 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"32_CR27","unstructured":"Liu, Y., et al.: Seg-zero: reasoning-chain guided segmentation via cognitive reinforcement. arXiv preprint arXiv:2503.06520 (2025)"},{"key":"32_CR28","unstructured":"Liu, Y., et al.: Visionreasoner: unified visual perception and reasoning via reinforcement learning. arXiv preprint arXiv:2505.12081 (2025)"},{"key":"32_CR29","unstructured":"Lu, H., et\u00a0al.: Deepseek-VL: towards real-world vision-language understanding. arXiv preprint arXiv:2403.05525 (2024)"},{"key":"32_CR30","doi-asserted-by":"crossref","unstructured":"Luo, G., et al.: Multi-task collaborative network for joint referring expression comprehension and segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10034\u201310043 (2020)","DOI":"10.1109\/CVPR42600.2020.01005"},{"key":"32_CR31","unstructured":"Marafioti, A., et al.: Smolvlm: redefining small and efficient multimodal models. arXiv preprint arXiv:2504.05299 (2025)"},{"key":"32_CR32","doi-asserted-by":"crossref","unstructured":"Nagaraja, V.K., Morariu, V.I., Davis, L.S.: Modeling context between objects for referring expression understanding. In: Proceedings of the European Conference on Computer Vision, pp. 792\u2013807 (2016)","DOI":"10.1007\/978-3-319-46493-0_48"},{"key":"32_CR33","doi-asserted-by":"crossref","unstructured":"Peng, Z., et al.: Understanding fine-tuning clip for open-vocabulary semantic segmentation in hyperbolic space. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 4562\u20134572 (2025)","DOI":"10.1109\/CVPR52734.2025.00430"},{"key":"32_CR34","doi-asserted-by":"crossref","unstructured":"Qian, R., Yin, X., Dou, D.: Reasoning to attend: try to understand how $$<$$seg$$>$$ token works. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 24722\u201324731 (2025)","DOI":"10.1109\/CVPR52734.2025.02302"},{"key":"32_CR35","doi-asserted-by":"crossref","unstructured":"Ramanathan, V., et al.: Paco: parts and attributes of common objects. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7141\u20137151 (2023)","DOI":"10.1109\/CVPR52729.2023.00690"},{"key":"32_CR36","doi-asserted-by":"crossref","unstructured":"Rasheed, H., et al.: Glamm: pixel grounding large multimodal model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13009\u201313018 (2024)","DOI":"10.1109\/CVPR52733.2024.01236"},{"key":"32_CR37","unstructured":"Ren, T., et\u00a0al.: Grounded SAM: assembling open-world models for diverse visual tasks. arXiv preprint arXiv:2401.14159 (2024)"},{"key":"32_CR38","doi-asserted-by":"crossref","unstructured":"Ren, Z., et al.: Pixellm: pixel reasoning with large multimodal model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 26374\u201326383 (2024)","DOI":"10.1109\/CVPR52733.2024.02491"},{"key":"32_CR39","doi-asserted-by":"crossref","unstructured":"Sharma, P., Ding, N., Goodman, S., Soricut, R.: Conceptual captions: a cleaned, hypernymed, image alt-text dataset for automatic image captioning. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 2556\u20132565 (2018)","DOI":"10.18653\/v1\/P18-1238"},{"key":"32_CR40","unstructured":"Sim\u00e9oni, O., et\u00a0al.: Dinov3. arXiv preprint arXiv:2508.10104 (2025)"},{"key":"32_CR41","doi-asserted-by":"crossref","unstructured":"Su, Y., Wang, Y., Hu, Q., Yang, C., Chau, L.P.: Annexe: unified analyzing, answering, and pixel grounding for egocentric interaction. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 9027\u20139038 (2025)","DOI":"10.1109\/CVPR52734.2025.00844"},{"key":"32_CR42","unstructured":"Team, G., et al.: Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805 (2023)"},{"key":"32_CR43","unstructured":"Team, Q., et\u00a0al.: Qwen2 technical report. arXiv preprint arXiv:2407.10671, vol. 2, no. 3 (2024)"},{"key":"32_CR44","doi-asserted-by":"crossref","unstructured":"Tong, P., et\u00a0al.: Cambrian-1: a fully open, vision-centric exploration of multimodal LLMs. In: Advances in Neural Information Processing Systems, vol. 37, pp. 87310\u201387356 (2024)","DOI":"10.52202\/079017-2771"},{"key":"32_CR45","unstructured":"Wang, X., et al.: Segllm: multi-round reasoning segmentation with large language models. In: International Conference on Learning Representations (2025)"},{"key":"32_CR46","doi-asserted-by":"crossref","unstructured":"Wang, Y., Ding, H., He, S., Jiang, X., Wei, B., Liu, J.: Hierarchical alignment-enhanced adaptive grounding network for generalized referring expression comprehension. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 39, pp. 8042\u20138050 (2025)","DOI":"10.1609\/aaai.v39i8.32867"},{"key":"32_CR47","doi-asserted-by":"crossref","unstructured":"Wang, Z., et al.: Cris: clip-driven referring image segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11686\u201311695 (2022)","DOI":"10.1109\/CVPR52688.2022.01139"},{"key":"32_CR48","unstructured":"Wei, C., et al.: Hyperseg: towards universal visual segmentation with large language model. In: Proceedings of the Computer Vision and Pattern Recognition Conference (2025)"},{"key":"32_CR49","doi-asserted-by":"crossref","unstructured":"Wei, C., et al.: Instructseg: unifying instructed visual segmentation with multi-modal large language models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 20193\u201320203 (2025)","DOI":"10.1109\/ICCV51701.2025.01878"},{"key":"32_CR50","doi-asserted-by":"crossref","unstructured":"Wen, C., Peng, Z., Huang, Y., Shen, W.: Efficient segmentation with multimodal large language model via token routing. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 40, pp. 10593\u201310602 (2026)","DOI":"10.1609\/aaai.v40i13.38032"},{"key":"32_CR51","unstructured":"Wu, Z., et\u00a0al.: Deepseek-vl2: mixture-of-experts vision-language models for advanced multimodal understanding. arXiv preprint arXiv:2412.10302 (2024)"},{"key":"32_CR52","doi-asserted-by":"crossref","unstructured":"Xia, Z., Han, D., Han, Y., Pan, X., Song, S., Huang, G.: GSVA: generalized segmentation via multimodal large language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3858\u20133869 (2024)","DOI":"10.1109\/CVPR52733.2024.00370"},{"key":"32_CR53","doi-asserted-by":"crossref","unstructured":"Yan, C., et al.: Visa: reasoning video object segmentation via large language models. In: European Conference on Computer Vision, pp. 98\u2013115 (2024)","DOI":"10.1007\/978-3-031-72633-0_6"},{"key":"32_CR54","unstructured":"Yang, A., et\u00a0al.: Qwen2.5 technical report. arXiv preprint arXiv:2412.15115 (2024)"},{"key":"32_CR55","doi-asserted-by":"crossref","unstructured":"Yang, Z., Wang, J., Tang, Y., Chen, K., Zhao, H., Torr, P.H.: Lavt: language-aware vision transformer for referring image segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18155\u201318165 (2022)","DOI":"10.1109\/CVPR52688.2022.01762"},{"key":"32_CR56","doi-asserted-by":"crossref","unstructured":"Yu, L., Poirson, P., Yang, S., Berg, A.C., Berg, T.L.: Modeling context in referring expressions. In: European Conference on Computer Vision, pp. 69\u201385. Springer, Cham (2016)","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"32_CR57","unstructured":"Yuan, Z., Li, Z., Huang, W., Ye, Y., Sun, L.: Tinygpt-v: efficient multimodal large language model via small backbones. arXiv preprint arXiv:2312.16862 (2023)"},{"key":"32_CR58","doi-asserted-by":"crossref","unstructured":"Yue, X., et\u00a0al.: MMMU: s massive multi-discipline multimodal understanding and reasoning benchmark for expert AGI. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9556\u20139567 (2024)","DOI":"10.1109\/CVPR52733.2024.00913"},{"key":"32_CR59","unstructured":"Zhang, J., Khayatkhoei, M., Chhikara, P., Ilievski, F.: MLLMs know where to look: Training-free perception of small visual details with multimodal LLMs. In: International Conference on Learning Representations (2025)"},{"key":"32_CR60","unstructured":"Zhang, S., Fang, Q., Yang, Z., Feng, Y.: Llava-mini: efficient image and video large multimodal models with one vision token. In: International Conference on Learning Representations (2025)"},{"key":"32_CR61","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Ma, Y., Zhang, E., Bai, X.: Psalm: pixelwise segmentation with large multi-modal model. In: European Conference on Computer Vision, pp. 74\u201391 (2024)","DOI":"10.1007\/978-3-031-72754-2_5"},{"key":"32_CR62","unstructured":"Zhou, B., et al.: Tinyllava: a framework of small-scale large multimodal models. arXiv preprint arXiv:2402.14289 (2024)"},{"key":"32_CR63","doi-asserted-by":"crossref","unstructured":"Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., Torralba, A.: Scene parsing through ade20k dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 633\u2013641 (2017)","DOI":"10.1109\/CVPR.2017.544"},{"key":"32_CR64","unstructured":"Zhu, J., et al.: Internvl3: Exploring advanced training and test-time recipes for open-source multimodal models. arXiv preprint arXiv:2504.10479 (2025)"},{"key":"32_CR65","doi-asserted-by":"crossref","unstructured":"Zhu, L., et al.: Popen: preference-based optimization and ensemble for LVLM-based reasoning segmentation. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 30231\u201330240 (2025)","DOI":"10.1109\/CVPR52734.2025.02814"},{"key":"32_CR66","doi-asserted-by":"crossref","unstructured":"Zou, X., et\u00a0al.: Generalized decoding for pixel, image, and language. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15116\u201315127 (2023)","DOI":"10.1109\/CVPR52729.2023.01451"},{"key":"32_CR67","doi-asserted-by":"publisher","first-page":"19769","DOI":"10.52202\/075280-0868","volume":"36","author":"X Zou","year":"2023","unstructured":"Zou, X., et al.: Segment everything everywhere all at once. Adv. Neural. Inf. Process. Syst. 36, 19769\u201319782 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."}],"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\/978-3-032-37574-2_32","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T22:23:10Z","timestamp":1789251790000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37574-2_32"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032375735","9783032375742"],"references-count":67,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37574-2_32","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":"13 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"}}]}}