{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T20:07:45Z","timestamp":1789157265974,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":75,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032374288","type":"print"},{"value":"9783032374295","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\/978-3-032-37429-5_24","type":"book-chapter","created":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T19:17:18Z","timestamp":1789154238000},"page":"413-431","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["MomentSeg: Moment-Centric Sampling for\u00a0Enhanced Referring Video Object Segmentation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-6133-0035","authenticated-orcid":false,"given":"Ming","family":"Dai","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-0152-6221","authenticated-orcid":false,"given":"Sen","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1697-5757","authenticated-orcid":false,"given":"Boqiang","family":"Duan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6385-6776","authenticated-orcid":false,"given":"Wankou","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4888-4445","authenticated-orcid":false,"given":"Jingdong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,12]]},"reference":[{"key":"24_CR1","unstructured":"Bai, S., et al.: Qwen2.5-Vl technical report. arXiv preprint: arXiv:2502.13923 (2025)"},{"key":"24_CR2","doi-asserted-by":"crossref","unstructured":"Bai, Z., et al.: One token to seg them all: language instructed reasoning segmentation in videos. NeurIPS (2024)","DOI":"10.52202\/079017-0219"},{"key":"24_CR3","doi-asserted-by":"crossref","unstructured":"Botach, A., Zheltonozhskii, E., Baskin, C.: End-to-end referring video object segmentation with multimodal transformers. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00493"},{"key":"24_CR4","doi-asserted-by":"crossref","unstructured":"Caba Heilbron, F., Escorcia, V., Ghanem, B., Carlos Niebles, J.: ActivityNet: a large-scale video benchmark for human activity understanding. In: CVPR, pp. 961\u2013970 (2015)","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"24_CR5","unstructured":"Chen, S., Lan, X., Yuan, Y., Jie, Z., Ma, L.: TimeMarker: a versatile Video-LLM for long and short video understanding with superior temporal localization ability. arXiv preprint: arXiv:2411.18211 (2024)"},{"key":"24_CR6","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":"24_CR7","doi-asserted-by":"crossref","unstructured":"Cheng, H.K., Schwing, A.G.: XMem: long-term video object segmentation with an Atkinson-Shiffrin memory model. In: ECCV (2022)","DOI":"10.1007\/978-3-031-19815-1_37"},{"key":"24_CR8","unstructured":"Cheng, W., Dai, M., Lu, H., Yang, W.: DeRVOS: decoupling consistent trajectory generation and multimodal understanding for referring video object segmentation. In: CVPR, pp. 24651\u201324662 (2026)"},{"key":"24_CR9","doi-asserted-by":"crossref","unstructured":"Cuttano, C., Trivigno, G., Rosi, G., Masone, C., Averta, G.: SAMWISE: infusing wisdom in SAM2 for text-driven video segmentation. In: CVPR, pp. 3395\u20133405 (2025)","DOI":"10.1109\/CVPR52734.2025.00322"},{"key":"24_CR10","unstructured":"Dai, M., et al.: Improving generalized visual grounding with instance-aware joint learning. TPAMI (2025)"},{"key":"24_CR11","doi-asserted-by":"crossref","unstructured":"Dai, M., et al.: DeRIS: decoupling perception and cognition for enhanced referring image segmentation through loopback synergy (2025)","DOI":"10.1109\/ICCV51701.2025.01854"},{"key":"24_CR12","doi-asserted-by":"crossref","unstructured":"Dai, M., Li, J., Zhuang, J., Zhang, X., Yang, W.: Multi-task visual grounding with coarse-to-fine consistency constraints. In: AAAI, vol. 39, pp. 2618\u20132626 (2025)","DOI":"10.1609\/aaai.v39i3.32265"},{"key":"24_CR13","unstructured":"Dai, M., et al.: VideoSEG-O3: a multi-turn reinforcement learning framework for reasoning video object segmentation. arXiv preprint: arXiv:2606.06819 (2026)"},{"key":"24_CR14","doi-asserted-by":"crossref","unstructured":"Deng, A., et al.: Motion-grounded video reasoning: understanding and perceiving motion at pixel level. In: CVPR, pp. 8625\u20138636 (2025)","DOI":"10.1109\/CVPR52734.2025.00806"},{"key":"24_CR15","doi-asserted-by":"crossref","unstructured":"Ding, H., Liu, C., He, S., Jiang, X., Loy, C.C.: MeViS: a large-scale benchmark for video segmentation with motion expressions. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00254"},{"key":"24_CR16","doi-asserted-by":"crossref","unstructured":"Fang, H., Cong, R., Lu, X., Zhou, X., Kwong, S., Zhang, W.: Decoupled motion expression video segmentation. In: CVPR, pp. 13821\u201313831 (2025)","DOI":"10.1109\/CVPR52734.2025.01290"},{"key":"24_CR17","doi-asserted-by":"crossref","unstructured":"Gao, J., Sun, C., Yang, Z., Nevatia, R.: TALL: temporal activity localization via language query. In: CVPR, pp. 5267\u20135275 (2017)","DOI":"10.1109\/ICCV.2017.563"},{"key":"24_CR18","doi-asserted-by":"crossref","unstructured":"Gavrilyuk, K., Ghodrati, A., Li, Z., Snoek, C.G.: Actor and action video segmentation from a sentence. In: CVPR, pp. 5958\u20135966 (2018)","DOI":"10.1109\/CVPR.2018.00624"},{"key":"24_CR19","unstructured":"Gong, S., Zhang, L., Zhuge, Y., Jia, X., Zhang, P., Lu, H.: Reinforcing video reasoning segmentation to think before it segments. arXiv preprint: arXiv:2508.11538 (2025)"},{"key":"24_CR20","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: CVPR, pp. 29183\u201329192 (2025)","DOI":"10.1109\/CVPR52734.2025.02717"},{"key":"24_CR21","doi-asserted-by":"crossref","unstructured":"Guo, Y., et al.: VTG-LLM: integrating timestamp knowledge into video LLMs for enhanced video temporal grounding. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a039, pp. 3302\u20133310 (2025)","DOI":"10.1609\/aaai.v39i3.32341"},{"key":"24_CR22","doi-asserted-by":"crossref","unstructured":"Guo, Y., Liu, J., Li, M., Tang, X., Chen, X., Zhao, B.: VTG-LLM: integrating timestamp knowledge into video LLMs for enhanced video temporal grounding. arXiv preprint: arXiv:2405.13382 (2024)","DOI":"10.1609\/aaai.v39i3.32341"},{"key":"24_CR23","doi-asserted-by":"crossref","unstructured":"He, S., Ding, H.: Decoupling static and hierarchical motion perception for referring video segmentation. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01266"},{"key":"24_CR24","unstructured":"Hu, E.J., et al.: LoRA: low-rank adaptation of large language models. ICLR (2021)"},{"key":"24_CR25","doi-asserted-by":"crossref","unstructured":"Huang, B., Wang, X., Chen, H., Song, Z., Zhu, W.: VTimeLLM: empower LLM to grasp video moments. In: CVPR, pp. 14271\u201314280 (2024)","DOI":"10.1109\/CVPR52733.2024.01353"},{"key":"24_CR26","unstructured":"Huang, D.A., et al.: LITA: language instructed temporal-localization assistant. arXiv preprint: arXiv:2403.19046 (2024)"},{"key":"24_CR27","doi-asserted-by":"crossref","unstructured":"Jin, P., Takanobu, R., Zhang, W., Cao, X., Yuan, L.: Chat-UniVi: unified visual representation empowers large language models with image and video understanding. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01300"},{"key":"24_CR28","doi-asserted-by":"crossref","unstructured":"Khoreva, A., Rohrbach, A., Schiele, B.: Video object segmentation with language referring expressions. In: ACCV, pp. 123\u2013141 (2018)","DOI":"10.1007\/978-3-030-20870-7_8"},{"key":"24_CR29","doi-asserted-by":"crossref","unstructured":"Khoreva, A., Rohrbach, A., Schiele, B.: Video object segmentation with language referring expressions. In: ACCV. Springer (2019)","DOI":"10.1007\/978-3-030-20870-7_8"},{"key":"24_CR30","doi-asserted-by":"crossref","unstructured":"Lai, X., et al.: LISA: reasoning segmentation via large language model. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"24_CR31","doi-asserted-by":"crossref","unstructured":"Li, H., et al.: LLaVA-ST: a multimodal large language model for fine-grained spatial-temporal understanding. In: CVPR, pp. 8592\u20138603 (2025)","DOI":"10.1109\/CVPR52734.2025.00803"},{"key":"24_CR32","unstructured":"Li, J., et\u00a0al.: A survey on benchmarks of multimodal large language models. arXiv preprint: arXiv:2408.08632 (2024)"},{"key":"24_CR33","doi-asserted-by":"crossref","unstructured":"Li, Y., Wang, C., Jia, J.: LLaMA-VID: an image is worth 2 tokens in large language models. In: ECCV (2025)","DOI":"10.1007\/978-3-031-72952-2_19"},{"key":"24_CR34","doi-asserted-by":"crossref","unstructured":"Liang, T., Lin, K.Y., Tan, C., Zhang, J., Zheng, W.S., Hu, J.F.: ReferDINO: referring video object segmentation with visual grounding foundations. ICCV (2025)","DOI":"10.1109\/ICCV51701.2025.01861"},{"key":"24_CR35","doi-asserted-by":"crossref","unstructured":"Lin, L., Yu, X., Pang, Z., Wang, Y.X.: GLUS: global-local reasoning unified into a single large language model for video segmentation. In: CVPR, pp. 8658\u20138667 (2025)","DOI":"10.1109\/CVPR52734.2025.00809"},{"key":"24_CR36","doi-asserted-by":"crossref","unstructured":"Liu, C., Ding, H., Jiang, X.: GRES: generalized referring expression segmentation. In: CVPR, pp. 23592\u201323601 (2023)","DOI":"10.1109\/CVPR52729.2023.02259"},{"key":"24_CR37","doi-asserted-by":"crossref","unstructured":"Liu, S., et\u00a0al.: LLaVA-Plus: learning to use tools for creating multimodal agents. In: ECCV, pp. 126\u2013142. Springer (2024)","DOI":"10.1007\/978-3-031-72970-6_8"},{"key":"24_CR38","unstructured":"Liu, Y., Lin, K.Q., Chen, C.W., Shou, M.Z.: VideoMind: a chain-of-lora agent for long video reasoning. arXiv preprint: arXiv:2503.13444 (2025)"},{"key":"24_CR39","first-page":"126078","volume":"38","author":"Y Liu","year":"2026","unstructured":"Liu, Y., et al.: UniPixel: unified object referring and segmentation for pixel-level visual reasoning. NeurIPS 38, 126078\u2013126108 (2026)","journal-title":"NeurIPS"},{"key":"24_CR40","doi-asserted-by":"crossref","unstructured":"Luo, Z., et al.: SOC: semantic-assisted object cluster for referring video object segmentation. In: NeurIPS (2023)","DOI":"10.52202\/075280-1149"},{"key":"24_CR41","doi-asserted-by":"crossref","unstructured":"Mao, J., Huang, J., Toshev, A., Camburu, O., Yuille, A.L., Murphy, K.: Generation and comprehension of unambiguous object descriptions. In: CVPR, pp. 11\u201320 (2016)","DOI":"10.1109\/CVPR.2016.9"},{"key":"24_CR42","doi-asserted-by":"crossref","unstructured":"Munasinghe, S., et al.: VideoGLaMM: a large multimodal model for pixel-level visual grounding in videos. arXiv preprint: arXiv:2411.04923 (2024)","DOI":"10.1109\/CVPR52734.2025.01773"},{"key":"24_CR43","doi-asserted-by":"crossref","unstructured":"Nagaraja, V.K., Morariu, V.I., Davis, L.S.: Modeling context between objects for referring expression understanding. In: ECCV, pp. 792\u2013807 (2016)","DOI":"10.1007\/978-3-319-46493-0_48"},{"key":"24_CR44","doi-asserted-by":"crossref","unstructured":"Pan, F., et al.: Semantic and sequential alignment for referring video object segmentation. In: CVPR, pp. 19067\u201319076 (2025)","DOI":"10.1109\/CVPR52734.2025.01776"},{"key":"24_CR45","unstructured":"Qian, L., et al.: Momentor: advancing video large language model with fine-grained temporal reasoning. In: ICML (2024)"},{"key":"24_CR46","unstructured":"Qian, L., et al.: Momentor: advancing video large language model with fine-grained temporal reasoning. arXiv preprint: arXiv:2402.11435 (2024)"},{"key":"24_CR47","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"key":"24_CR48","doi-asserted-by":"crossref","unstructured":"Rasheed, H., et al.: GLaMM: pixel grounding large multimodal model. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01236"},{"key":"24_CR49","unstructured":"Ravi, N., et al.: SAM 2: segment anything in images and videos. arXiv preprint: arXiv:2408.00714 (2024)"},{"key":"24_CR50","doi-asserted-by":"crossref","unstructured":"Ren, S., Yao, L., Li, S., Sun, X., Hou, L.: TimeChat: a time-sensitive multimodal large language model for long video understanding. In: CVPR, pp. 14313\u201314323 (2024)","DOI":"10.1109\/CVPR52733.2024.01357"},{"key":"24_CR51","doi-asserted-by":"crossref","unstructured":"Rong, F., Lan, M., Zhang, Q., Zhang, L.: MPG-SAM 2: adapting SAM 2 with mask priors and global context for referring video object segmentation. ICCV (2025)","DOI":"10.1109\/ICCV51701.2025.02223"},{"key":"24_CR52","doi-asserted-by":"crossref","unstructured":"Seo, S., Lee, J.Y., Han, B.: URVOS: unified referring video object segmentation network with a large-scale benchmark. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58555-6_13"},{"key":"24_CR53","doi-asserted-by":"crossref","unstructured":"Tang, J., Zheng, G., Yang, S.: Temporal collection and distribution for referring video object segmentation. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01418"},{"key":"24_CR54","doi-asserted-by":"crossref","unstructured":"Wang, H., et al.: Grounded-VideoLLM: sharpening fine-grained temporal grounding in video large language models. arXiv preprint: arXiv:2410.03290 (2024)","DOI":"10.18653\/v1\/2025.findings-emnlp.50"},{"key":"24_CR55","unstructured":"Wang, Y., Meng, X., Liang, J., Wang, Y., Liu, Q., Zhao, D.: HawkEye: training video-text LLMs for grounding text in videos. arXiv preprint: arXiv:2403.10228 (2024)"},{"key":"24_CR56","unstructured":"Wei, C., Tan, H., Zhong, Y., Yang, Y., Ma, L.: LaSagnA: language-based segmentation assistant for complex queries. arXiv preprint: arXiv:2404.08506 (2024)"},{"key":"24_CR57","unstructured":"Wei, C., et al.: HyperSeg: towards universal visual segmentation with large language model. CVPR (2025)"},{"key":"24_CR58","doi-asserted-by":"crossref","unstructured":"Wei, C., et al.: InstructSeg: unifying instructed visual segmentation with multi-modal large language models. ICCV (2025)","DOI":"10.1109\/ICCV51701.2025.01878"},{"key":"24_CR59","doi-asserted-by":"crossref","unstructured":"Wu, D., Wang, T., Zhang, Y., Zhang, X., Shen, J.: OnlineRefer: a simple online baseline for referring video object segmentation. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00259"},{"key":"24_CR60","doi-asserted-by":"crossref","unstructured":"Wu, J., Jiang, Y., Sun, P., Yuan, Z., Luo, P.: Language as queries for referring video object segmentation. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00492"},{"key":"24_CR61","doi-asserted-by":"crossref","unstructured":"Wu, J., Jiang, Y., Yan, B., Lu, H., Yuan, Z., Luo, P.: Segment every reference object in spatial and temporal spaces. In: ICCV, pp. 2538\u20132550 (2023)","DOI":"10.1109\/ICCV51070.2023.00240"},{"key":"24_CR62","doi-asserted-by":"crossref","unstructured":"Wu, Y., et al.: Number it: temporal grounding videos like flipping manga. In: CVPR, pp. 13754\u201313765 (2025)","DOI":"10.1109\/CVPR52734.2025.01284"},{"key":"24_CR63","doi-asserted-by":"crossref","unstructured":"Xu, Z., Guo, Y., Lu, Y., Yang, F., Li, J.: VideoSeg-R1: reasoning video object segmentation via reinforcement learning. arXiv preprint: arXiv:2511.16077 (2025)","DOI":"10.1609\/aaai.v40i14.38132"},{"key":"24_CR64","doi-asserted-by":"crossref","unstructured":"Yan, B., et al.: Universal instance perception as object discovery and retrieval. In: CVPR, pp. 15325\u201315336 (2023)","DOI":"10.1109\/CVPR52729.2023.01471"},{"key":"24_CR65","doi-asserted-by":"crossref","unstructured":"Yan, C., et al.: VISA: reasoning video object segmentation via large language models. ECCV (2024)","DOI":"10.1007\/978-3-031-72633-0_6"},{"key":"24_CR66","doi-asserted-by":"crossref","unstructured":"Yang, A., et al.: Vid2Seq: large-scale pretraining of a visual language model for dense video captioning. In: CVPR, pp. 10714\u201310726 (2023)","DOI":"10.1109\/CVPR52729.2023.01032"},{"key":"24_CR67","doi-asserted-by":"crossref","unstructured":"Yu, L., Poisson, P., Yang, S., Berg, A.C., Berg, T.L.: Modeling context in referring expressions. In: ECCV (2016)","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"24_CR68","doi-asserted-by":"crossref","unstructured":"Yuan, H., et al.: Sa2VA: marrying SAM2 with LLaVA for dense grounded understanding of images and videos. arXiv preprint: arXiv:2501.04001 (2025)","DOI":"10.1109\/TPAMI.2026.3720379"},{"key":"24_CR69","doi-asserted-by":"crossref","unstructured":"Yuan, L., Shi, M., Yue, Z., Chen, Q.: LoSh: long-short text joint prediction network for referring video object segmentation. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01328"},{"key":"24_CR70","doi-asserted-by":"crossref","unstructured":"Zala, A., et al.: Hierarchical video-moment retrieval and step-captioning. In: CVPR, pp. 23056\u201323065 (2023)","DOI":"10.1109\/CVPR52729.2023.02208"},{"key":"24_CR71","doi-asserted-by":"crossref","unstructured":"Zhang, K., et al.: LMMS-EVAL: reality check on the evaluation of large multimodal models (2024)","DOI":"10.18653\/v1\/2025.findings-naacl.51"},{"key":"24_CR72","doi-asserted-by":"crossref","unstructured":"Zheng, R., et al.: ViLLa: video reasoning segmentation with large language model. arXiv preprint: arXiv:2407.14500 (2024)","DOI":"10.1109\/ICCV51701.2025.02197"},{"key":"24_CR73","doi-asserted-by":"crossref","unstructured":"Zhong, H., et al.: Omni-R1: reinforcement learning for omnimodal reasoning via two-system collaboration. arXiv preprint: arXiv:2505.20256 (2025)","DOI":"10.52202\/085713-1508"},{"key":"24_CR74","unstructured":"Zhu, J., et al.: Tracking with human-intent reasoning. arXiv preprint: arXiv:2312.17448 (2023)"},{"key":"24_CR75","first-page":"19769","volume":"36","author":"X Zou","year":"2023","unstructured":"Zou, X., et al.: Segment everything everywhere all at once. NeurIPS 36, 19769\u201319782 (2023)","journal-title":"NeurIPS"}],"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\/978-3-032-37429-5_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T19:17:33Z","timestamp":1789154253000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37429-5_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032374288","9783032374295"],"references-count":75,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37429-5_24","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":"12 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"}}]}}