{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T17:04:47Z","timestamp":1789578287441,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":56,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032375162","type":"print"},{"value":"9783032375179","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\/978-3-032-37517-9_17","type":"book-chapter","created":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T16:42:43Z","timestamp":1789576963000},"page":"298-316","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Structured-Noise Masked Modeling for\u00a0Video, Audio and\u00a0Beyond"],"prefix":"10.1007","author":[{"given":"Aritra","family":"Bhowmik","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9286-9587","authenticated-orcid":false,"given":"Carlos","family":"Hinojosa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2517-0220","authenticated-orcid":false,"given":"Fida Mohammad","family":"Thoker","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5534-587X","authenticated-orcid":false,"given":"Bernard","family":"Ghanem","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9092-1556","authenticated-orcid":false,"given":"Cees G. M.","family":"Snoek","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,17]]},"reference":[{"issue":"6","key":"17_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3414685.3417881","volume":"39","author":"AG Ahmed","year":"2020","unstructured":"Ahmed, A.G., Wonka, P.: Screen-space blue-noise diffusion of monte carlo sampling error via hierarchical ordering of pixels. ACM Trans. Graph. (TOG) 39(6), 1\u201315 (2020)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"17_CR2","doi-asserted-by":"crossref","unstructured":"Baade, A., Peng, P., Harwath, D.: Mae-ast: masked autoencoding audio spectrogram transformer. arXiv preprint arXiv:2203.16691 (2022)","DOI":"10.21437\/Interspeech.2022-10961"},{"key":"17_CR3","doi-asserted-by":"publisher","unstructured":"Bachmann, R., Mizrahi, D., Atanov, A., Zamir, A.: Multimae: multi-modal multi-task masked autoencoders. In: European Conference on Computer Vision, pp. 348\u2013367. Springer, Heidelberg (2022). https:\/\/doi.org\/10.1007\/978-3-031-19836-6_20","DOI":"10.1007\/978-3-031-19836-6_20"},{"key":"17_CR4","unstructured":"Baevski, A., Hsu, W.N., Xu, Q., Babu, A., Gu, J., Auli, M.: Data2vec: a general framework for self-supervised learning in speech, vision and language. In: International Conference on Machine Learning, pp. 1298\u20131312. PMLR (2022)"},{"key":"17_CR5","unstructured":"Baevski, A., Zhou, Y., Mohamed, A., Auli, M.: wav2vec 2.0: a framework for self-supervised learning of speech representations. Adv. Neural Inf. Process. Syst. 33, 12449\u201312460 (2020)"},{"key":"17_CR6","doi-asserted-by":"crossref","unstructured":"Bandara, W.G.C., Patel, N., Gholami, A., Nikkhah, M., Agrawal, M., Patel, V.M.: Adamae: adaptive masking for efficient spatiotemporal learning with masked autoencoders. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14507\u201314517 (2023)","DOI":"10.1109\/CVPR52729.2023.01394"},{"key":"17_CR7","unstructured":"Bao, H., Dong, L., Piao, S., Wei, F.: Beit: bert pre-training of image transformers. arXiv preprint arXiv:2106.08254 (2021)"},{"key":"17_CR8","doi-asserted-by":"publisher","unstructured":"Chen, H., Zhang, W., Wang, Y., Yang, X.: Improving masked autoencoders by learning where to mask. In: Chinese Conference on Pattern Recognition and Computer Vision (PRCV), pp. 377\u2013390. Springer, Heidelberg (2023). https:\/\/doi.org\/10.1007\/978-981-99-8543-2_31","DOI":"10.1007\/978-981-99-8543-2_31"},{"key":"17_CR9","doi-asserted-by":"crossref","unstructured":"Chen, H., Xie, W., Vedaldi, A., Zisserman, A.: Vggsound: a large-scale audio-visual dataset. In: ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 721\u2013725. IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9053174"},{"key":"17_CR10","doi-asserted-by":"crossref","unstructured":"Chong, D., Wang, H., Zhou, P., Zeng, Q.: Masked spectrogram prediction for self-supervised audio pre-training. In: ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.\u00a01\u20135. IEEE (2023)","DOI":"10.1109\/ICASSP49357.2023.10095691"},{"issue":"12","key":"17_CR11","doi-asserted-by":"publisher","first-page":"2312","DOI":"10.1364\/JOSAA.33.002312","volume":"33","author":"CV Correa","year":"2016","unstructured":"Correa, C.V., Arguello, H., Arce, G.R.: Spatiotemporal blue noise coded aperture design for multi-shot compressive spectral imaging. J. Opt. Soc. Am. A 33(12), 2312\u20132322 (2016)","journal-title":"J. Opt. Soc. Am. A"},{"key":"17_CR12","doi-asserted-by":"crossref","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, vol. 1 (long and short papers), pp. 4171\u20134186 (2019)","DOI":"10.18653\/v1\/N19-1423"},{"key":"17_CR13","doi-asserted-by":"crossref","unstructured":"Fan, D., et al.: Motion-guided masking for spatiotemporal representation learning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5619\u20135629 (2023)","DOI":"10.1109\/ICCV51070.2023.00517"},{"key":"17_CR14","doi-asserted-by":"crossref","unstructured":"Gemmeke, J.F., et al.: Audio set: an ontology and human-labeled dataset for audio events. In: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 776\u2013780. IEEE (2017)","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"17_CR15","doi-asserted-by":"crossref","unstructured":"Girdhar, R., El-Nouby, A., Singh, M., Alwala, K.V., Joulin, A., Misra, I.: Omnimae: single model masked pretraining on images and videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10406\u201310417 (2023)","DOI":"10.1109\/CVPR52729.2023.01003"},{"key":"17_CR16","doi-asserted-by":"crossref","unstructured":"Gong, Y., Lai, C.I., Chung, Y.A., Glass, J.: Ssast: self-supervised audio spectrogram transformer. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a036, pp. 10699\u201310709 (2022)","DOI":"10.1609\/aaai.v36i10.21315"},{"key":"17_CR17","unstructured":"Gong, Y., et al.: Contrastive audio-visual masked autoencoder. arXiv preprint arXiv:2210.07839 (2022)"},{"key":"17_CR18","doi-asserted-by":"crossref","unstructured":"Goyal, R., et\u00a0al.: The \u201csomething something\" video database for learning and evaluating visual common sense. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5842\u20135850 (2017)","DOI":"10.1109\/ICCV.2017.622"},{"key":"17_CR19","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16000\u201316009 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"17_CR20","doi-asserted-by":"publisher","unstructured":"Hernandez, J., Villegas, R., Ordonez, V.: Vic-mae: self-supervised representation learning from images and video with contrastive masked autoencoders. In: European Conference on Computer Vision (ECCV). pp. 444\u2013463. Springer, Heidelberg (2024). https:\/\/doi.org\/10.1007\/978-3-031-73235-5_25","DOI":"10.1007\/978-3-031-73235-5_25"},{"key":"17_CR21","doi-asserted-by":"publisher","unstructured":"Hinojosa, C., Liu, S., Ghanem, B.: ColorMAE: exploring data-independent masking strategies in Masked AutoEncoders. In: European Conference on Computer Vision, pp. 432\u2013449. Springer, Heidelberg (2024). https:\/\/doi.org\/10.1007\/978-3-031-72661-3_25","DOI":"10.1007\/978-3-031-72661-3_25"},{"key":"17_CR22","doi-asserted-by":"crossref","unstructured":"Huang, B., Zhao, Z., Zhang, G., Qiao, Y., Wang, L.: Mgmae: motion guided masking for video masked autoencoding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13493\u201313504 (2023)","DOI":"10.1109\/ICCV51070.2023.01241"},{"key":"17_CR23","doi-asserted-by":"crossref","unstructured":"Huang, P.Y.,, et al.: Mavil: masked audio-video learners. Adv. Neural. Inf. Process. Syst. 36, 20371\u201320393 (2023)","DOI":"10.52202\/075280-0894"},{"key":"17_CR24","doi-asserted-by":"crossref","unstructured":"Huang, P.Y., et al.: Masked autoencoders that listen. Adv. Neural. Inf. Process. Syst. 35, 28708\u201328720 (2022)","DOI":"10.52202\/068431-2081"},{"key":"17_CR25","doi-asserted-by":"crossref","unstructured":"Kara, D., et al.: Phymask: an adaptive masking paradigm for efficient self-supervised learning in iot. In: Proceedings of the 22nd ACM Conference on Embedded Networked Sensor Systems, pp. 97\u2013111 (2024)","DOI":"10.1145\/3666025.3699325"},{"key":"17_CR26","unstructured":"Kay, W., et al.: The kinetics human action video dataset. arXiv preprint arXiv:1705.06950 (2017)"},{"issue":"1\u20132","key":"17_CR27","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1002\/nav.3800020109","volume":"2","author":"HW Kuhn","year":"1955","unstructured":"Kuhn, H.W.: The hungarian method for the assignment problem. Naval Res. Logist. Q. 2(1\u20132), 83\u201397 (1955)","journal-title":"Naval Res. Logist. Q."},{"issue":"4","key":"17_CR28","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1109\/MSP.2003.1215229","volume":"20","author":"DL Lau","year":"2003","unstructured":"Lau, D.L., Ulichney, R., Arce, G.R.: Blue and green noise halftoning models. IEEE Signal Process. Mag. 20(4), 28\u201338 (2003)","journal-title":"IEEE Signal Process. Mag."},{"key":"17_CR29","doi-asserted-by":"crossref","unstructured":"Li, F., et al.: Mask dino: towards a unified transformer-based framework for object detection and segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3041\u20133050 (2023)","DOI":"10.1109\/CVPR52729.2023.00297"},{"key":"17_CR30","doi-asserted-by":"publisher","first-page":"14290","DOI":"10.52202\/068431-1039","volume":"35","author":"G Li","year":"2022","unstructured":"Li, G., Zheng, H., Liu, D., Wang, C., Su, B., Zheng, C.: Semmae: semantic-guided masking for learning masked autoencoders. Adv. Neural. Inf. Process. Syst. 35, 14290\u201314302 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"17_CR31","first-page":"13165","volume":"34","author":"Z Li","year":"2021","unstructured":"Li, Z., et al.: Mst: masked self-supervised transformer for visual representation. Adv. Neural. Inf. Process. Syst. 34, 13165\u201313176 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"17_CR32","unstructured":"Liu, R., et al.: Frequency-aware masked autoencoders for multimodal pretraining on biosignals. In: ICLR 2024 Workshop on Learning from Time Series For Health (2024)"},{"key":"17_CR33","unstructured":"Lu, C., Jin, X., Huang, Z., Hou, Q., Cheng, M., Feng, J.: CMAE-V: contrastive masked autoencoders for video action recognition. CoRR arxiv:2301.06018 (2023)"},{"key":"17_CR34","doi-asserted-by":"crossref","unstructured":"Madan, N., Ristea, N.C., Nasrollahi, K., Moeslund, T.B., Ionescu, R.T.: Cl-mae: curriculum-learned masked autoencoders. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 2492\u20132502 (2024)","DOI":"10.1109\/WACV57701.2024.00248"},{"key":"17_CR35","doi-asserted-by":"crossref","unstructured":"Park, D.S., et al.: Specaugment: a simple data augmentation method for automatic speech recognition. arXiv preprint arXiv:1904.08779 (2019)","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"17_CR36","doi-asserted-by":"crossref","unstructured":"Piczak, K.J.: Esc: dataset for environmental sound classification. In: Proceedings of the 23rd ACM International Conference on Multimedia, pp. 1015\u20131018 (2015)","DOI":"10.1145\/2733373.2806390"},{"key":"17_CR37","unstructured":"Pont-Tuset, J., Perazzi, F., Caelles, S., Arbel\u00e1ez, P., Sorkine-Hornung, A., Van\u00a0Gool, L.: The 2017 davis challenge on video object segmentation. arXiv preprint arXiv:1704.00675 (2017)"},{"issue":"1","key":"17_CR38","first-page":"92","volume":"9","author":"H Rauhut","year":"2010","unstructured":"Rauhut, H.: Compressive sensing and structured random matrices. Theor. Found. Numer. Methods Sparse Rec. 9(1), 92 (2010)","journal-title":"Theor. Found. Numer. Methods Sparse Rec."},{"key":"17_CR39","doi-asserted-by":"publisher","unstructured":"Salehi, M., Dorkenwald, M., Thoker, F.M., Gavves, E., Snoek, C.G., Asano, Y.M.: Sigma: Sinkhorn-guided masked video modeling. In: European Conference on Computer Vision, pp. 293\u2013312. Springer, Heidelberg (2024). https:\/\/doi.org\/10.1007\/978-3-031-72691-0_17","DOI":"10.1007\/978-3-031-72691-0_17"},{"key":"17_CR40","doi-asserted-by":"crossref","unstructured":"Salehi, M., Gavves, E., Snoek, C.G.M., Asano, Y.M.: Time does tell: self-supervised time-tuning of dense image representations. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 16536\u201316547 (2023)","DOI":"10.1109\/ICCV51070.2023.01516"},{"key":"17_CR41","doi-asserted-by":"crossref","unstructured":"Schneider, S., Baevski, A., Collobert, R., Auli, M.: wav2vec: unsupervised pre-training for speech recognition. arXiv preprint arXiv:1904.05862 (2019)","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"17_CR42","doi-asserted-by":"crossref","unstructured":"Shao, D., Zhao, Y., Dai, B., Lin, D.: Finegym: a hierarchical video dataset for fine-grained action understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00269"},{"key":"17_CR43","doi-asserted-by":"crossref","unstructured":"Sick, L., Engel, D., Hermosilla, P., Ropinski, T.: Attention-guided masked autoencoders for learning image representations. In: 2025 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 836\u2013846. IEEE (2025)","DOI":"10.1109\/WACV61041.2025.00091"},{"key":"17_CR44","doi-asserted-by":"crossref","unstructured":"Sigurdsson, G.A., Varol, G., Wang, X., Farhadi, A., Laptev, I., Gupta, A.: Hollywood in homes: crowdsourcing data collection for activity understanding. In: European Conference on Computer Vision (ECCV) (2016)","DOI":"10.1007\/978-3-319-46448-0_31"},{"key":"17_CR45","doi-asserted-by":"crossref","unstructured":"Sun, X., Chen, P., Chen, L., Li, C., Li, T.H., Tan, M., Gan, C.: Masked motion encoding for self-supervised video representation learning. In: CVPR, pp. 2235\u20132245. IEEE (2023)","DOI":"10.1109\/CVPR52729.2023.00222"},{"key":"17_CR46","doi-asserted-by":"crossref","unstructured":"Thoker, F.M., Doughty, H., Bagad, P., Snoek, C.G.: How severe is benchmark-sensitivity in video self-supervised learning? In: European Conference on Computer Vision (ECCV) (2022)","DOI":"10.1007\/978-3-031-19830-4_36"},{"key":"17_CR47","doi-asserted-by":"crossref","unstructured":"Thoker, F.M., Doughty, H., Snoek, C.G.M.: Tubelet-contrastive self-supervision for video-efficient generalization. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2023)","DOI":"10.1109\/ICCV51070.2023.01270"},{"key":"17_CR48","doi-asserted-by":"crossref","unstructured":"Thoker, F.M., Jiang, L., Zhao, C., Ghanem, B.: Smile: infusing spatial and motion semantics in masked video learning. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 8438\u20138449 (2025)","DOI":"10.1109\/CVPR52734.2025.00790"},{"key":"17_CR49","doi-asserted-by":"publisher","first-page":"10078","DOI":"10.52202\/068431-0732","volume":"35","author":"Z Tong","year":"2022","unstructured":"Tong, Z., Song, Y., Wang, J., Wang, L.: Videomae: masked autoencoders are data-efficient learners for self-supervised video pre-training. Adv. Neural. Inf. Process. Syst. 35, 10078\u201310093 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"17_CR50","unstructured":"Warden, P.: Speech commands: a dataset for limited-vocabulary speech recognition. arXiv preprint arXiv:1804.03209 (2018)"},{"key":"17_CR51","unstructured":"Wolfe, A., Morrical, N., Akenine-M\u00f6ller, T., Ramamoorthi, R., Ghosh, A., Wei, L.: Spatiotemporal blue noise masks. In: EGSR (ST), pp. 117\u2013126 (2022)"},{"key":"17_CR52","unstructured":"Xie, J., Li, W., Zhan, X., Liu, Z., Ong, Y.S., Loy, C.C.: Masked frequency modeling for self-supervised visual pre-training. arXiv preprint arXiv:2206.07706 (2022)"},{"key":"17_CR53","doi-asserted-by":"crossref","unstructured":"Xie, Z., et al.: Simmim: a simple framework for masked image modeling. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9653\u20139663 (2022)","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"17_CR54","unstructured":"Xu, N., et al.: Youtube-vos: a large-scale video object segmentation benchmark. arXiv preprint arXiv:1809.03327 (2018)"},{"key":"17_CR55","doi-asserted-by":"crossref","unstructured":"Zhang, H., Xu, X., Han, G., He, S.: Context-aware and scale-insensitive temporal repetition counting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00075"},{"key":"17_CR56","unstructured":"Zhou, J., et al.: ibot: image bert pre-training with online tokenizer. arXiv preprint arXiv:2111.07832 (2021)"}],"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\/978-3-032-37517-9_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T16:42:59Z","timestamp":1789576979000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37517-9_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032375162","9783032375179"],"references-count":56,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37517-9_17","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":"17 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"}}]}}