{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T10:06:26Z","timestamp":1789207586574,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":67,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032373342","type":"print"},{"value":"9783032373359","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\/978-3-032-37335-9_36","type":"book-chapter","created":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T09:08:13Z","timestamp":1789204093000},"page":"659-676","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["EXPLORE-Bench: Egocentric Scene Prediction with\u00a0Long-Horizon Reasoning"],"prefix":"10.1007","author":[{"given":"Chengjun","family":"Yu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuhan","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chaoqun","family":"Du","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pengfei","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Zhai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zheng-Jun","family":"Zha","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,13]]},"reference":[{"key":"36_CR1","unstructured":"An, X., et al.: LLaVA-OneVision-1.5: fully open framework for democratized multimodal training. arXiv preprint arXiv:2509.23661 (2025)"},{"key":"36_CR2","unstructured":"Bai, S., et\u00a0al.: Qwen3-VL Technical report. arXiv preprint arXiv:2511.21631 (2025)"},{"key":"36_CR3","unstructured":"Bai, S., et\u00a0al.: Qwen2.5-VL Technical report. arXiv preprint arXiv:2502.13923 (2025)"},{"issue":"3731","key":"36_CR4","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1126\/science.153.3731.34","volume":"153","author":"R Bellman","year":"1966","unstructured":"Bellman, R.: Dynamic programming. Science 153(3731), 34\u201337 (1966)","journal-title":"Science"},{"key":"36_CR5","doi-asserted-by":"crossref","unstructured":"Chen, Q., Di, S., Xie, W.: Grounded multi-hop videoqa in long-form egocentric videos. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 39, pp. 2159\u20132167 (2025)","DOI":"10.1609\/aaai.v39i2.32214"},{"key":"36_CR6","unstructured":"Chen, W., et\u00a0al.: MindGPT-4ov: an enhanced MLLM via a multi-stage post-training paradigm. arXiv preprint arXiv:2512.02895 (2025)"},{"key":"36_CR7","unstructured":"Chen, Y., et al.: EgoPlan-Bench: benchmarking egocentric embodied planning with multimodal large language models. arXiv preprint arXiv:2312.06722 (2023)"},{"key":"36_CR8","doi-asserted-by":"crossref","unstructured":"Cheng, S., et al.: EgoThink: evaluating first-person perspective thinking capability of vision-language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14291\u201314302 (2024)","DOI":"10.1109\/CVPR52733.2024.01355"},{"key":"36_CR9","doi-asserted-by":"crossref","unstructured":"Dang, R., et al.: ECBench: can multi-modal foundation models understand the egocentric world? a holistic embodied cognition benchmark. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 24593\u201324602 (2025)","DOI":"10.1109\/CVPR52734.2025.02290"},{"key":"36_CR10","unstructured":"Explosion: Spacy (2015). https:\/\/github.com\/explosion\/spaCy. Accessed 19 Feb 2026"},{"key":"36_CR11","doi-asserted-by":"crossref","unstructured":"Fan, C.: EgoVQA-an egocentric video question answering benchmark dataset. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops, pp.\u00a00\u20130 (2019)","DOI":"10.1109\/ICCVW.2019.00536"},{"key":"36_CR12","doi-asserted-by":"crossref","unstructured":"Fu, C., et\u00a0al.: Video-MME: the first-ever comprehensive evaluation benchmark of multi-modal LLMs in video analysis. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 24108\u201324118 (2025)","DOI":"10.1109\/CVPR52734.2025.02245"},{"key":"36_CR13","unstructured":"Google DeepMind: Gemini 3 (2025). https:\/\/deepmind.google\/models\/gemini\/. Accessed 16 Feb 2026"},{"key":"36_CR14","unstructured":"Grauman, K., et\u00a0al.: Ego4D: around the world in 3,000 hours of egocentric video. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 18995\u201319012 (2022)"},{"key":"36_CR15","unstructured":"Grauman, K., et al.: Ego-Exo4D: understanding skilled human activity from first-and third-person perspectives. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19383\u201319400 (2024)"},{"key":"36_CR16","unstructured":"Han, G., Zhai, W., Yang, Y., Cao, Y., Zha, Z.J.: Touch: text-guided controllable generation of free-form hand-object interactions. arXiv preprint arXiv:2510.14874 (2025)"},{"key":"36_CR17","unstructured":"Hong, W., et al.: GLM-4.5 V and GLM-4.1 V-thinking: towards versatile multimodal reasoning with scalable reinforcement learning. arXiv preprint arXiv:2507.01006 (2025)"},{"key":"36_CR18","doi-asserted-by":"crossref","unstructured":"Hou, L., Gao, L., Wu, Y., Chang, Y.: A survey on evaluation of embodied AI. Authorea Preprints (2026)","DOI":"10.22541\/au.177023340.02874343\/v1"},{"key":"36_CR19","unstructured":"Huang, A., et\u00a0al.: STEP3-VL-10B Technical report. arXiv preprint arXiv:2601.09668 (2026)"},{"key":"36_CR20","doi-asserted-by":"crossref","unstructured":"Huang, X., et al.: Open-set image tagging with multi-grained text supervision. In: Proceedings of the 33rd ACM International Conference on Multimedia, pp. 4117\u20134126 (2025)","DOI":"10.1145\/3746027.3755316"},{"key":"36_CR21","doi-asserted-by":"crossref","unstructured":"Huang, Z., et al.: Online video understanding: OVBench and VideoChat-online. In: Proceedings of the Computer Vision and Pattern Recognition Conference. pp. 3328\u20133338 (2025)","DOI":"10.1109\/CVPR52734.2025.00316"},{"key":"36_CR22","doi-asserted-by":"publisher","first-page":"3343","DOI":"10.52202\/068431-0242","volume":"35","author":"B Jia","year":"2022","unstructured":"Jia, B., Lei, T., Zhu, S.C., Huang, S.: EgoTASKQA: understanding human tasks in egocentric videos. Adv. Neural. Inf. Process. Syst. 35, 3343\u20133360 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"36_CR23","unstructured":"Li, M., et\u00a0al.: Qwen3-VL-Embedding and Qwen3-VL-Reranker: a unified framework for state-of-the-art multimodal retrieval and ranking. arXiv preprint arXiv:2601.04720 (2026)"},{"key":"36_CR24","unstructured":"Li, S., Kallidromitis, K., Gokul, A., Kato, Y., Kozuka, K., Grover, A.: Mobileworldbench: Towards semantic world modeling for mobile agents. arXiv preprint arXiv:2512.14014 (2025)"},{"key":"36_CR25","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: EgoCross: benchmarking multimodal large language models for cross-domain egocentric video question answering. arXiv preprint arXiv:2508.10729 (2025)","DOI":"10.1609\/aaai.v40i8.37589"},{"key":"36_CR26","doi-asserted-by":"publisher","first-page":"7575","DOI":"10.52202\/068431-0550","volume":"35","author":"KQ Lin","year":"2022","unstructured":"Lin, K.Q., et al.: Egocentric video-language pretraining. Adv. Neural. Inf. Process. Syst. 35, 7575\u20137586 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"36_CR27","doi-asserted-by":"crossref","unstructured":"Liu, S., et al.: Benchmarking egocentric clinical intent understanding capability for medical multimodal large language models. arXiv preprint arXiv:2601.06750 (2026)","DOI":"10.18653\/v1\/2026.acl-long.1228"},{"key":"36_CR28","doi-asserted-by":"crossref","unstructured":"Liu, S., et\u00a0al.: Grounding DINO: marrying DINO with grounded pre-training for open-set object detection. In: European conference on computer vision, pp. 38\u201355. Springer (2024)","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"36_CR29","doi-asserted-by":"crossref","unstructured":"Lu, F., et al.: Benchmarking large vision-language models via directed scene graph for comprehensive image captioning. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 19618\u201319627 (2025)","DOI":"10.1109\/CVPR52734.2025.01827"},{"key":"36_CR30","unstructured":"Lu, S., et\u00a0al.: Ovis2.5 Technical report. arXiv preprint arXiv:2508.11737 (2025)"},{"key":"36_CR31","doi-asserted-by":"crossref","unstructured":"Luo, H., Zhai, W., Zhang, J., Cao, Y., Tao, D.: Learning affordance grounding from exocentric images. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2252\u20132261 (2022)","DOI":"10.1109\/CVPR52688.2022.00229"},{"key":"36_CR32","doi-asserted-by":"crossref","unstructured":"Majumdar, A., et al.: OpenEQA: embodied question answering in the era of foundation models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16488\u201316498 (2024)","DOI":"10.1109\/CVPR52733.2024.01560"},{"key":"36_CR33","doi-asserted-by":"publisher","first-page":"46212","DOI":"10.52202\/075280-2004","volume":"36","author":"K Mangalam","year":"2023","unstructured":"Mangalam, K., Akshulakov, R., Malik, J.: EgoSchema: a diagnostic benchmark for very long-form video language understanding. Adv. Neural. Inf. Process. Syst. 36, 46212\u201346244 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"36_CR34","unstructured":"OpenAI: Introducing GPT-5.2 (2025). https:\/\/openai.com\/index\/introducing-gpt-5-2\/. Accessed 16 Feb 2026"},{"key":"36_CR35","doi-asserted-by":"crossref","unstructured":"Pei, B., et al.: EgoThinker: Unveiling egocentric reasoning with spatio-temporal cot. arXiv preprint arXiv:2510.23569 (2025)","DOI":"10.52202\/085713-1471"},{"key":"36_CR36","doi-asserted-by":"crossref","unstructured":"Perrett, T., et al.: HD-EPIC: a highly-detailed egocentric video dataset. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 23901\u201323913 (2025)","DOI":"10.1109\/CVPR52734.2025.02226"},{"key":"36_CR37","doi-asserted-by":"crossref","unstructured":"Reimers, N., Gurevych, I.: Sentence-BERT: sentence embeddings using siamese BERT-networks. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference On Natural Language Processing (EMNLP-IJCNLP), pp. 3982\u20133992 (2019)","DOI":"10.18653\/v1\/D19-1410"},{"key":"36_CR38","unstructured":"Shen, X., Chen, J., Zheng, L., Ma, H., Wei, T., Zhan, K.: Evolving from tool user to creator via training-free experience reuse in multimodal reasoning. arXiv preprint arXiv:2602.01983 (2026)"},{"key":"36_CR39","doi-asserted-by":"crossref","unstructured":"Song, E., et\u00a0al.: MovieChat: from dense token to sparse memory for long video understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18221\u201318232 (2024)","DOI":"10.1109\/CVPR52733.2024.01725"},{"key":"36_CR40","unstructured":"Team, G.R., et al.: Gemini Robotics: bringing AI into the physical world. arXiv preprint arXiv:2503.20020 (2025)"},{"key":"36_CR41","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":"36_CR42","unstructured":"Wang, S., Cui, C., Huang, Y., Chang, H.J., Cheng, Y.: Vl4Gaze: unleashing vision-language models for gaze following. arXiv preprint arXiv:2512.20735 (2025)"},{"key":"36_CR43","unstructured":"Wang, W., et al.: InternVL3. 5: advancing open-source multimodal models in versatility, reasoning, and efficiency. arXiv preprint arXiv:2508.18265 (2025)"},{"key":"36_CR44","unstructured":"Wang, Y., et al.: N3D-VLM: native 3D grounding enables accurate spatial reasoning in vision-language models. arXiv preprint arXiv:2512.16561 (2025)"},{"key":"36_CR45","doi-asserted-by":"publisher","first-page":"28828","DOI":"10.52202\/079017-0907","volume":"37","author":"H Wu","year":"2024","unstructured":"Wu, H., Li, D., Chen, B., Li, J.: LongVideoBench: a benchmark for long-context interleaved video-language understanding. Adv. Neural. Inf. Process. Syst. 37, 28828\u201328857 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"36_CR46","doi-asserted-by":"crossref","unstructured":"Wu, P., Liu, Y., Liu, M., Shen, J.: St-Think: how multimodal large language models reason about 4d worlds from ego-centric videos. arXiv preprint arXiv:2503.12542 (2025)","DOI":"10.1109\/WACV61042.2026.00502"},{"key":"36_CR47","unstructured":"Yan, J., et\u00a0al.: TeleEgo: benchmarking egocentric ai assistants in the wild. arXiv preprint arXiv:2510.23981 (2025)"},{"key":"36_CR48","unstructured":"Yang, A., et\u00a0al.: Qwen3 Technical report. arXiv preprint arXiv:2505.09388 (2025)"},{"key":"36_CR49","unstructured":"Yang, B., et al.: Kwai Keye-VL 1.5 Technical report. arXiv preprint arXiv:2509.01563 (2025)"},{"key":"36_CR50","doi-asserted-by":"crossref","unstructured":"Yang, J., et\u00a0al.: EgoLife: towards egocentric life assistant. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 28885\u201328900 (2025)","DOI":"10.1109\/CVPR52734.2025.02690"},{"key":"36_CR51","unstructured":"Yang, R., et\u00a0al.: EmbodiedBench: comprehensive benchmarking multi-modal large language models for vision-driven embodied agents. In: International Conference on Machine Learning, pp. 70576\u201370631. PMLR (2025)"},{"key":"36_CR52","doi-asserted-by":"crossref","unstructured":"Yang, Y., Zhai, W., Luo, H., Cao, Y., Luo, J., Zha, Z.J.: Grounding 3D object affordance from 2d interactions in images. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10905\u201310915 (2023)","DOI":"10.1109\/ICCV51070.2023.01001"},{"key":"36_CR53","doi-asserted-by":"publisher","first-page":"54529","DOI":"10.52202\/079017-1728","volume":"37","author":"Y Yang","year":"2024","unstructured":"Yang, Y., Zhai, W., Wang, C., Yu, C., Cao, Y., Zha, Z.J.: EgoChoir: capturing 3d human-object interaction regions from egocentric views. Adv. Neural. Inf. Process. Syst. 37, 54529\u201354557 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"36_CR54","doi-asserted-by":"crossref","unstructured":"Yu, C., Zhai, W., Yang, Y., Cao, Y., Zha, Z.J.: HERO: human reaction generation from videos. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10262\u201310274 (2025)","DOI":"10.1109\/ICCV51701.2025.00956"},{"key":"36_CR55","unstructured":"Yu, T., et\u00a0al.: MiniCPM-V 4.5: cooking efficient MLLMs via architecture, data, and training recipe. arXiv preprint arXiv:2509.18154 (2025)"},{"key":"36_CR56","doi-asserted-by":"crossref","unstructured":"Yuan, Y., et\u00a0al.: EOC-Bench: can MLLMs identify, recall, and forecast objects in an egocentric world? In: The Thirty-ninth Annual Conference on Neural Information Processing Systems Datasets and Benchmarks Track (2025)","DOI":"10.52202\/085713-4489"},{"key":"36_CR57","unstructured":"Yue, Z., et\u00a0al.: Mimo-VL Technical report. arXiv preprint arXiv:2506.03569 (2025)"},{"key":"36_CR58","doi-asserted-by":"crossref","unstructured":"Yue, Z., Zhang, Q., Hu, A., Zhang, L., Wang, Z., Jin, Q.: Movie101: a new movie understanding benchmark. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 4669\u20134684 (2023)","DOI":"10.18653\/v1\/2023.acl-long.257"},{"issue":"1","key":"36_CR59","doi-asserted-by":"publisher","first-page":"403","DOI":"10.1109\/TPAMI.2023.3325230","volume":"46","author":"W Zhai","year":"2023","unstructured":"Zhai, W., Cao, Y., Zhang, J., Xie, H., Tao, D., Zha, Z.J.: On exploring multiplicity of primitives and attributes for texture recognition in the wild. IEEE Trans. Pattern Anal. Mach. Intell. 46(1), 403\u2013420 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"36_CR60","unstructured":"Zhang, L., et\u00a0al.: EgoReact: egocentric video-driven 3d human reaction generation. arXiv preprint arXiv:2512.22808 (2025)"},{"key":"36_CR61","unstructured":"Zhang, Q., et\u00a0al.: A survey on test-time scaling in large language models: what, how, where, and how well? arXiv preprint arXiv:2503.24235 (2025)"},{"key":"36_CR62","unstructured":"Zhang, W., et\u00a0al.: Embodied-Reasoner: synergizing visual search, reasoning, and action for embodied interactive tasks. arXiv preprint arXiv:2503.21696 (2025)"},{"key":"36_CR63","doi-asserted-by":"crossref","unstructured":"Zhao, B., et\u00a0al.: UrbanVideo-Bench: benchmarking vision-language models on embodied intelligence with video data in urban spaces. In: Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 32400\u201332423 (2025)","DOI":"10.18653\/v1\/2025.acl-long.1558"},{"key":"36_CR64","doi-asserted-by":"publisher","first-page":"46595","DOI":"10.52202\/075280-2020","volume":"36","author":"L Zheng","year":"2023","unstructured":"Zheng, L., et al.: Judging LLM-as-a-judge with mt-bench and chatbot arena. Adv. Neural. Inf. Process. Syst. 36, 46595\u201346623 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"36_CR65","doi-asserted-by":"crossref","unstructured":"Zhou, J., et al.: MLVU: benchmarking multi-task long video understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13691\u201313701 (2025)","DOI":"10.1109\/CVPR52734.2025.01278"},{"key":"36_CR66","doi-asserted-by":"crossref","unstructured":"Zhou, S., et al.: EgoTextVQA: towards egocentric scene-text aware video question answering. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 3363\u20133373 (2025)","DOI":"10.1109\/CVPR52734.2025.00319"},{"key":"36_CR67","doi-asserted-by":"crossref","unstructured":"Zhou, W., et\u00a0al.: X-Lebench: a benchmark for extremely long egocentric video understanding. arXiv preprint arXiv:2501.06835 (2025)","DOI":"10.18653\/v1\/2025.findings-emnlp.822"}],"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\/978-3-032-37335-9_36","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T09:08:31Z","timestamp":1789204111000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37335-9_36"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032373342","9783032373359"],"references-count":67,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37335-9_36","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"}}]}}