{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T15:34:03Z","timestamp":1792596843855,"version":"4.5.0"},"publisher-location":"Cham","reference-count":79,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032373687","type":"print"},{"value":"9783032373694","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\/978-3-032-37369-4_36","type":"book-chapter","created":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T05:42:40Z","timestamp":1788932560000},"page":"671-689","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["V-JEPA 2.1: Unlocking Dense Features in\u00a0Video Self-Supervised Learning"],"prefix":"10.1007","author":[{"given":"Lorenzo","family":"Mur-Labadia","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthew","family":"Muckley","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Amir","family":"Bar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mido","family":"Assran","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Koustuv","family":"Sinha","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mike","family":"Rabbat","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yann","family":"LeCun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nicolas","family":"Ballas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,10]]},"reference":[{"key":"36_CR1","doi-asserted-by":"crossref","unstructured":"Arnab, A., Dehghani, M., Heigold, G., Sun, C., Lucic, M., Schmid, C.: ViViT: a video vision transformer. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"36_CR2","doi-asserted-by":"crossref","unstructured":"Assran, M., et al.: Self-supervised learning from images with a joint-embedding predictive architecture. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15619\u201315629 (2023)","DOI":"10.1109\/CVPR52729.2023.01499"},{"key":"36_CR3","unstructured":"Assran, M., et al.: V-JEPA 2: self-supervised video models enable understanding, prediction and planning. arXiv preprint: arXiv:2506.09985 (2025)"},{"key":"36_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. arXiv preprint: arXiv:2202.03555 (2022)"},{"key":"36_CR5","unstructured":"Balestriero, R., LeCun, Y.: LeJEPA: provable and scalable self-supervised learning without the heuristics. arXiv preprint: arXiv:2511.08544 (2025)"},{"key":"36_CR6","unstructured":"Bao, H., Dong, L., Wei, F.: BEiT: BERT pre-training of image transformers. arXiv preprint: arXiv:2106.08254 (2021)"},{"key":"36_CR7","doi-asserted-by":"crossref","unstructured":"Bar, A., Zhou, G., Tran, D., Darrell, T., LeCun, Y.: Navigation world models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 15791\u201315801 (2025)","DOI":"10.1109\/CVPR52734.2025.01472"},{"key":"36_CR8","unstructured":"Bardes, A., et al.: Revisiting feature prediction for learning visual representations from video. arXiv preprint: arXiv:2404.08471 (2024)"},{"key":"36_CR9","unstructured":"Bardes, A., Ponce, J., LeCun, Y.: VICReg: variance-invariance-covariance regularization for self-supervised learning. arXiv preprint: arXiv:2105.04906 (2021)"},{"key":"36_CR10","doi-asserted-by":"crossref","unstructured":"Bardes, A., Ponce, J., LeCun, Y.: VICRegL: self-supervised learning of local visual features. In: NeurIPS (2022)","DOI":"10.52202\/068431-0640"},{"key":"36_CR11","unstructured":"Bertasius, G., Wang, H., Torresani, L.: Is space-time attention all you need for video understanding? In: ICML (2021)"},{"key":"36_CR12","unstructured":"Baldassarre, F., et al.: Back to the features: Dino as a foundation for video world models. arXiv preprint: arXiv:2507.19468 (2025)"},{"key":"36_CR13","unstructured":"Bolya, D., et al.: Perception encoder: the best visual embeddings are not at the output of the network. arXiv preprint: arXiv:2504.13181 (2025)"},{"key":"36_CR14","unstructured":"Caron, M., Misra, I., Mairal, J., Goyal, P., Bojanowski, P., Joulin, A.: Unsupervised learning of visual features by contrasting cluster assignments. In: NeurIPS (2020)"},{"key":"36_CR15","doi-asserted-by":"crossref","unstructured":"Caron, M., Touvron, H., Misra, I., Jegou, H., Joulin, J.M.P.B.A.: Emerging properties in self-supervised vision transformers. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"36_CR16","unstructured":"Carreira, J., et al.: Scaling 4D representations. arXiv preprint: arXiv:2412.15212 (2024)"},{"key":"36_CR17","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo Vadis, action recognition? A new model and the kinetics dataset. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"36_CR18","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.E.: A simple framework for contrastive learning of visual representations. In: ICML (2020)"},{"key":"36_CR19","doi-asserted-by":"crossref","unstructured":"Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3213\u20133223 (2016)","DOI":"10.1109\/CVPR.2016.350"},{"key":"36_CR20","doi-asserted-by":"crossref","unstructured":"Damen, D., et al.: Rescaling egocentric vision: collection, pipeline and challenges for epic-kitchens-100. Int. J. Comput. Vis. (IJCV) (2022)","DOI":"10.1007\/s11263-021-01531-2"},{"key":"36_CR21","unstructured":"Darcet, T., Oquab, M., Mairal, J., Bojanowski, P.: Vision transformers need registers. arXiv preprint: arXiv:2309.16588 (2023)"},{"key":"36_CR22","doi-asserted-by":"crossref","unstructured":"Doersch, C., Gupta, A., Efros, A.A.: Unsupervised visual representation learning by context. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.167"},{"key":"36_CR23","unstructured":"Dosovitskiy, A.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint: arXiv:2010.11929 (2020)"},{"issue":"1","key":"36_CR24","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1007\/s11263-014-0733-5","volume":"111","author":"M Everingham","year":"2015","unstructured":"Everingham, M., Eslami, S.A., Van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The pascal visual object classes challenge: a retrospective. Int. J. Comput. Vision 111(1), 98\u2013136 (2015)","journal-title":"Int. J. Comput. Vision"},{"key":"36_CR25","unstructured":"Fan, D., et al.: Scaling language-free visual representation learning. arXiv preprint: arXiv:2504.01017 (2025)"},{"key":"36_CR26","doi-asserted-by":"crossref","unstructured":"Fan, H., Xiong, B., Mangalam, K., Li, Y., Yan, Z., Malik, J.: Multiscale vision transformers. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"36_CR27","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., Li, Y., He, K.: Masked autoencoders as spatiotemporal learners. In: NeurIPS (2022)","DOI":"10.52202\/068431-2605"},{"key":"36_CR28","unstructured":"Garrido, Q., et al.: Intuitive physics understanding emerges from self-supervised pretraining on natural videos. arXiv preprint: arXiv:2502.11831 (2025)"},{"key":"36_CR29","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., Stiller, C., Urtasun, R.: Vision meets robotics: the KITTI dataset. Int. J. Robot. Res. (2013)","DOI":"10.1177\/0278364913491297"},{"key":"36_CR30","unstructured":"Gidaris, S., Singh, P., Komodakis, N.: Unsupervised representation learning by predicting image rotations. In: ICLR (2018)"},{"key":"36_CR31","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_CR32","unstructured":"Grill, J.B., et al.: Bootstrap your own latent-a new approach to self-supervised learning. In: Advances in Neural Information Processing Systems, vol. 33, pp. 21271\u201321284 (2020)"},{"key":"36_CR33","unstructured":"Grill, J.B., et al.: Bootstrap your own latent: a new approach to self-supervised learning. In: NeurIPS (2020)"},{"key":"36_CR34","unstructured":"Ha, D., Schmidhuber, J.: World models 2(3). arXiv preprint: arXiv:1803.10122 (2018)"},{"key":"36_CR35","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"36_CR36","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint: arXiv:1503.02531 (2015)"},{"key":"36_CR37","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: Advances in Neural Information Processing Systems, vol. 33, pp. 6840\u20136851 (2020)"},{"key":"36_CR38","doi-asserted-by":"crossref","unstructured":"H\u00e9naff, O.J., Koppula, S., Alayrac, J.B., van\u00a0den Oord, A., Vinyals, O., Carreira, J.: Efficient visual pretraining with contrastive detection. arXiv preprint: arXiv:2103.10957 (2021)","DOI":"10.1109\/ICCV48922.2021.00993"},{"key":"36_CR39","unstructured":"Jabri, A., Owens, A., Efros, A.: Space-time correspondence as a contrastive random walk. In: Advances in Neural Information Processing Systems, vol. 33, pp. 19545\u201319560 (2020)"},{"key":"36_CR40","doi-asserted-by":"crossref","unstructured":"Jayaraman, D., Grauman, K.: Learning image representations tied to ego-motion. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.166"},{"key":"36_CR41","doi-asserted-by":"crossref","unstructured":"Karypidis, E., Kakogeorgiou, I., Gidaris, S., Komodakis, N.: DINO-foresight: looking into the future with DINO. arXiv preprint: arXiv:2412.11673 (2024)","DOI":"10.52202\/085713-5466"},{"key":"36_CR42","unstructured":"Khazatsky, A., et al.: DROID: a large-scale in-the-wild robot manipulation dataset. arXiv preprint: arXiv:2403.12945 (2024)"},{"key":"36_CR43","unstructured":"LeCun, Y.: A path towards autonomous machine intelligence version 0.9. 2, 2022-06-27. Open Rev. 62(1), 1\u201362 (2022)"},{"key":"36_CR44","unstructured":"Li, T., He, K.: Back to basics: let denoising generative models denoise. arXiv preprint: arXiv:2511.13720 (2025)"},{"key":"36_CR45","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"36_CR46","doi-asserted-by":"crossref","unstructured":"Misra, I., Zitnick, C.L., Hebert, M.: Shuffle and learn: unsupervised learning using temporal order verification. In: ECCV (2016)","DOI":"10.1007\/978-3-319-46448-0_32"},{"key":"36_CR47","doi-asserted-by":"crossref","unstructured":"Mittal, H., Agarwal, N., Lo, S.Y., Lee, K.: Can\u2019t make an omelette without breaking some eggs: plausible action anticipation using large video-language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18580\u201318590 (2024)","DOI":"10.1109\/CVPR52733.2024.01758"},{"key":"36_CR48","doi-asserted-by":"crossref","unstructured":"Mo, S., Tong, S.: Connecting joint-embedding predictive architecture with contrastive self-supervised learning. In: Advances in Neural Information Processing Systems, vol. 37, pp. 2348\u20132377 (2024)","DOI":"10.52202\/079017-0077"},{"key":"36_CR49","doi-asserted-by":"crossref","unstructured":"Mur-Labadia, L., Martinez-Cantin, R., Guerrero, J.J., Farinella, G.M., Furnari, A.: AFF-ttention! affordances and attention models for short-term object interaction anticipation. In: European Conference on Computer Vision, pp. 167\u2013184. Springer (2024)","DOI":"10.1007\/978-3-031-73337-6_10"},{"key":"36_CR50","doi-asserted-by":"crossref","unstructured":"Noroozi, M., Favaro, P.: Unsupervised learning of visual representations by solving jigsaw puzzles. In: ECCV (2016)","DOI":"10.1007\/978-3-319-46466-4_5"},{"key":"36_CR51","unstructured":"Oquab, M., et al.: DINOv2: Learning robust visual features without supervision. arXiv preprint: arXiv:2304.07193 (2023)"},{"key":"36_CR52","doi-asserted-by":"crossref","unstructured":"Pathak, D., Krahenbuhl, P., Donahue, J., Darrell, T., Efros, A.A.: Context encoders: feature learning by inpainting. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.278"},{"key":"36_CR53","doi-asserted-by":"crossref","unstructured":"Perazzi, F., Pont-Tuset, J., McWilliams, B., Van\u00a0Gool, L., Gross, M., Sorkine-Hornung, A.: A benchmark dataset and evaluation methodology for video object segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 724\u2013732 (2016)","DOI":"10.1109\/CVPR.2016.85"},{"key":"36_CR54","unstructured":"Pont-Tuset, J., et al.: The 2017 DAVIS challenge on video object segmentation. arXiv preprint: arXiv:1704.00675 (2017)"},{"key":"36_CR55","doi-asserted-by":"crossref","unstructured":"Ragusa, F., Farinella, G.M., Furnari, A.: StillFast: an end-to-end approach for short-term object interaction anticipation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops (2023)","DOI":"10.1109\/CVPRW59228.2023.00371"},{"key":"36_CR56","doi-asserted-by":"crossref","unstructured":"Ranftl, R., Bochkovskiy, A., Koltun, V.: Vision transformers for dense prediction. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"36_CR57","doi-asserted-by":"crossref","unstructured":"Ranzinger, M., Heinrich, G., Kautz, J., Molchanov, P.: AM-RADIO: agglomerative vision foundation model reduce all domains into one. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01187"},{"key":"36_CR58","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"36_CR59","doi-asserted-by":"crossref","unstructured":"Roy, D., Rajendiran, R., Fernando, B.: Interaction region visual transformer for egocentric action anticipation. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 6740\u20136750 (2024)","DOI":"10.1109\/WACV57701.2024.00660"},{"key":"36_CR60","doi-asserted-by":"crossref","unstructured":"Silberman, N., Hoiem, D., Kohli, P., Fergus, R.: Indoor segmentation and support inference from RGBD images. In: ECCV (2012)","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"36_CR61","unstructured":"Sim\u00e9oni, O., et\u00a0al.: DINOv3. arXiv preprint: arXiv:2508.10104 (2025)"},{"key":"36_CR62","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. arXiv preprint: arXiv:2010.02502 (2020)"},{"issue":"3","key":"36_CR63","first-page":"217","volume":"4","author":"RS Sutton","year":"1981","unstructured":"Sutton, R.S.: An adaptive network that constructs and uses and internal model of its world. Cogn. Brain Theory 4(3), 217\u2013246 (1981)","journal-title":"Cogn. Brain Theory"},{"key":"36_CR64","doi-asserted-by":"crossref","unstructured":"Tong, Z., Song, Y., Wang, J., Wang, L.: VideoMAE: masked autoencoders are data-efficient learners for self-supervised video pre-training. In: Advances in Neural Information Processing Systems, vol. 35, pp. 10078\u201310093 (2022)","DOI":"10.52202\/068431-0732"},{"key":"36_CR65","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3d convolutional networks. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"36_CR66","doi-asserted-by":"crossref","unstructured":"Tran, D., Wang, H., Torresani, L., Ray, J., LeCun, Y., Paluri, M.: Look at spatiotemporal convolutions for action recognition. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00675"},{"key":"36_CR67","unstructured":"Tschannen, M., et al.: SigLIP 2: multilingual vision-language encoders with improved semantic understanding, localization, and dense features. arXiv preprint: arXiv:2502.14786 (2025)"},{"key":"36_CR68","doi-asserted-by":"crossref","unstructured":"Wang, L., et al.: VideoMAE V2: scaling video masked autoencoders with dual masking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14549\u201314560 (2023)","DOI":"10.1109\/CVPR52729.2023.01398"},{"key":"36_CR69","doi-asserted-by":"crossref","unstructured":"Wang, X., Gupta, A.: Unsupervised learning of visual representations using videos. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.320"},{"key":"36_CR70","doi-asserted-by":"crossref","unstructured":"Wang, Y., et\u00a0al.: InternVideo2: scaling foundation models for multimodal video understanding. In: European Conference on Computer Vision, pp. 396\u2013416. Springer (2024)","DOI":"10.1007\/978-3-031-73013-9_23"},{"key":"36_CR71","unstructured":"Xie, J., Zhan, X., Liu, Z., Ong, Y.S., Loy, C.C.: Unsupervised object-level representation learning from scene images. In: NeurIPS (2021)"},{"key":"36_CR72","doi-asserted-by":"crossref","unstructured":"Xie, Z., et al.: SimMIM: a simple framework for masked image modeling. arXiv preprint: arXiv:2111.09886 (2021)","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"36_CR73","doi-asserted-by":"crossref","unstructured":"Xu, N., et al.: YouTube-VOS: sequence-to-sequence video object segmentation. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 585\u2013601 (2018)","DOI":"10.1007\/978-3-030-01228-1_36"},{"key":"36_CR74","doi-asserted-by":"crossref","unstructured":"Yang, L., Kang, B., Huang, Z., Xu, X., Feng, J., Zhao, H.: Depth anything: unleashing the power of large-scale unlabeled data. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"36_CR75","doi-asserted-by":"crossref","unstructured":"Zellers, R., et al.: MERLOT reserve: neural script knowledge through vision and language and sound. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16375\u201316387 (2022)","DOI":"10.1109\/CVPR52688.2022.01589"},{"key":"36_CR76","doi-asserted-by":"crossref","unstructured":"Zhang, H., Li, X., Bing, L.: Video-LLaMA: an instruction-tuned audio-visual language model for video understanding. arXiv preprint: arXiv:2306.02858 (2023)","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"36_CR77","unstructured":"Zhao, L., et\u00a0al.: VideoPrism: a foundational visual encoder for video understanding. arXiv preprint: arXiv:2402.13217 (2024)"},{"key":"36_CR78","doi-asserted-by":"crossref","unstructured":"Zhou, B., Xavier Puig, H.Z., Fidler, S., Barriuso, A., Torralba, A.: Scene parsing through ADE20K dataset. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.544"},{"key":"36_CR79","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\/978-3-032-37369-4_36","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T05:42:50Z","timestamp":1788932570000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37369-4_36"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032373687","9783032373694"],"references-count":79,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37369-4_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":"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"}}]}}