{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:35:41Z","timestamp":1742913341282,"version":"3.40.3"},"publisher-location":"Cham","reference-count":92,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031730030"},{"type":"electronic","value":"9783031730047"}],"license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-73004-7_15","type":"book-chapter","created":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T17:05:21Z","timestamp":1730394321000},"page":"249-267","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Pre-trained Visual Dynamics Representations for\u00a0Efficient Policy Learning"],"prefix":"10.1007","author":[{"given":"Hao","family":"Luo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bohan","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zongqing","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,1]]},"reference":[{"key":"15_CR1","unstructured":"Akan, A.K., Safadoust, S., G\u00fcney, F.: Stochastic video prediction with structure and motion. arXiv preprint arXiv:2203.10528 (2022)"},{"key":"15_CR2","unstructured":"Andrychowicz, M., et al.: Hindsight experience replay. In: Neural Information Processing Systems (2017)"},{"key":"15_CR3","doi-asserted-by":"publisher","first-page":"174","DOI":"10.1016\/0022-247X(65)90154-X","volume":"10","author":"KJ \u00c5str\u00f6m","year":"1965","unstructured":"\u00c5str\u00f6m, K.J.: Optimal control of markov processes with incomplete state information i. J. Math. Anal. Appl. 10, 174\u2013205 (1965)","journal-title":"J. Math. Anal. Appl."},{"key":"15_CR4","doi-asserted-by":"crossref","unstructured":"Bahl, S., Gupta, A., Pathak, D.: Human-to-robot imitation in the wild. arXiv preprint arXiv:2207.09450 (2022)","DOI":"10.15607\/RSS.2022.XVIII.026"},{"key":"15_CR5","doi-asserted-by":"crossref","unstructured":"Bahl, S., Mendonca, R., Chen, L., Jain, U., Pathak, D.: Affordances from human videos as a versatile representation for robotics. In: Computer Vision and Pattern Recognition (2023)","DOI":"10.1109\/CVPR52729.2023.01324"},{"key":"15_CR6","unstructured":"Baker, B., et al.: Video pretraining (VPT): learning to act by watching unlabeled online videos. In: Neural Information Processing Systems (2022)"},{"key":"15_CR7","doi-asserted-by":"crossref","unstructured":"Bhateja, C., et al.: Robotic offline RL from internet videos via value-function pre-training. arXiv preprint arXiv:2309.13041 (2023)","DOI":"10.1109\/ICRA57147.2024.10611575"},{"key":"15_CR8","doi-asserted-by":"crossref","unstructured":"Blattmann, A., et al.: Align your latents: high-resolution video synthesis with latent diffusion models. In: Computer Vision and Pattern Recognition (2023)","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"15_CR9","unstructured":"Bobrin, M., Buzun, N., Krylov, D., Dylov, D.V.: Align your intents: offline imitation learning via optimal transport. arXiv preprint arXiv:2402.13037 (2024)"},{"key":"15_CR10","unstructured":"Bojarski, M., et\u00a0al.: End to end learning for self-driving cars. arXiv preprint arXiv:1604.07316 (2016)"},{"key":"15_CR11","unstructured":"Brown, T., et\u00a0al.: Language models are few-shot learners. In: Neural Information Processing Systems (2020)"},{"key":"15_CR12","unstructured":"Bruce, J., Anand, A., Mazoure, B., Fergus, R.: Learning about progress from experts. In: International Conference on Learning Representations (2023)"},{"key":"15_CR13","unstructured":"Bruce, J., et\u00a0al.: Genie: generative interactive environments. arXiv preprint arXiv:2402.15391 (2024)"},{"key":"15_CR14","unstructured":"Chang, M., Gupta, A., Gupta, S.: Learning value functions from undirected state-only experience. In: International Conference on Learning Representations (2022)"},{"key":"15_CR15","doi-asserted-by":"crossref","unstructured":"Chen, A.S., Nair, S., Finn, C.: Learning generalizable robotic reward functions from \u201cin-the-wild\u201d human videos. In: Robotics: Science and Systems (2022)","DOI":"10.15607\/RSS.2021.XVII.012"},{"key":"15_CR16","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International Conference on Machine Learning (2020)"},{"key":"15_CR17","unstructured":"Clark, A., Donahue, J., Simonyan, K.: Adversarial video generation on complex datasets. arXiv preprint arXiv:1907.06571 (2019)"},{"key":"15_CR18","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (2021)"},{"key":"15_CR19","unstructured":"Ebert, F., Finn, C., Lee, A.X., Levine, S.: Self-supervised visual planning with temporal skip connections. Conf. Robot Learn. (2017)"},{"key":"15_CR20","unstructured":"Edwards, A., Sahni, H., Schroecker, Y., Isbell, C.: Imitating latent policies from observation. In: International Conference on Machine Learning (2019)"},{"key":"15_CR21","unstructured":"Escontrela, A., et al.: Video prediction models as rewards for reinforcement learning. In: Neural Information Processing Systems (2023)"},{"key":"15_CR22","doi-asserted-by":"crossref","unstructured":"Esser, P., Rombach, R., Ommer, B.: Taming transformers for high-resolution image synthesis. In: Computer Vision and Pattern Recognition (2021)","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"15_CR23","unstructured":"Ghosh, D., Bhateja, C.A., Levine, S.: Reinforcement learning from passive data via latent intentions. In: International Conference on Machine Learning (2023)"},{"key":"15_CR24","unstructured":"Gupta, A., et al.: Maskvit: masked visual pre-training for video prediction. In: International Conference on Learning Representations (2022)"},{"key":"15_CR25","unstructured":"Hafner, D., Lillicrap, T.P., Norouzi, M., Ba, J.: Mastering atari with discrete world models. In: International Conference on Learning Representations (2021)"},{"key":"15_CR26","unstructured":"He, H., Bai, C., Pan, L., Zhang, W., Zhao, B., Li, X.: Large-scale actionless video pre-training via discrete diffusion for efficient policy learning. arXiv preprint arXiv:2402.14407 (2024)"},{"key":"15_CR27","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: Computer Vision and Pattern Recognition (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"15_CR28","unstructured":"Ho, J., Salimans, T., Gritsenko, A., Chan, W., Norouzi, M., Fleet, D.J.: Video diffusion models. arXiv preprint arXiv:2204.03458 (2021)"},{"issue":"2","key":"15_CR29","doi-asserted-by":"publisher","first-page":"3019","DOI":"10.1109\/LRA.2020.2974707","volume":"5","author":"S James","year":"2020","unstructured":"James, S., Ma, Z., Arrojo, D.R., Davison, A.J.: Rlbench: the robot learning benchmark & learning environment. Robot. Autom. Lett. 5(2), 3019\u20133026 (2020)","journal-title":"Robot. Autom. Lett."},{"issue":"1\u20132","key":"15_CR30","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1016\/S0004-3702(98)00023-X","volume":"101","author":"LP Kaelbling","year":"1998","unstructured":"Kaelbling, L.P., Littman, M.L., Cassandra, A.R.: Planning and acting in partially observable stochastic domains. Artif. Intell. 101(1\u20132), 99\u2013134 (1998)","journal-title":"Artif. Intell."},{"key":"15_CR31","doi-asserted-by":"crossref","unstructured":"Karamcheti, S., et al.: Language-driven representation learning for robotics. arXiv preprint arXiv:2302.12766 (2023)","DOI":"10.15607\/RSS.2023.XIX.032"},{"key":"15_CR32","unstructured":"Kumar, A., Zhou, A., Tucker, G., Levine, S.: Conservative q-learning for offline reinforcement learning. In: Neural Information Processing Systems (2020)"},{"key":"15_CR33","unstructured":"Li, S., Han, S., Zhao, Y., Liang, B., Liu, P.: Auxiliary reward generation with transition distance representation learning. arXiv preprint arXiv:2402.07412 (2024)"},{"key":"15_CR34","unstructured":"Luc, P., et al.: Transformation-based adversarial video prediction on large-scale data. arXiv preprint arXiv:2003.04035 (2020)"},{"key":"15_CR35","unstructured":"Ma, Y.J., Sodhani, S., Jayaraman, D., Bastani, O., Kumar, V., Zhang, A.: Vip: towards universal visual reward and representation via value-implicit pre-training. arXiv preprint arXiv:2210.00030 (2022)"},{"key":"15_CR36","doi-asserted-by":"crossref","unstructured":"Mei, K., Patel, V.: VIDM: video implicit diffusion models. In: Association for the Advancement of Artificial Intelligence (2023)","DOI":"10.1609\/aaai.v37i8.26094"},{"key":"15_CR37","doi-asserted-by":"crossref","unstructured":"Menapace, W., Lathuiliere, S., Tulyakov, S., Siarohin, A., Ricci, E.: Playable video generation. In: Conference on Computer Vision and Pattern Recognition (2021)","DOI":"10.1109\/CVPR46437.2021.00993"},{"key":"15_CR38","doi-asserted-by":"crossref","unstructured":"Mendonca, R., Bahl, S., Pathak, D.: Structured world models from human videos. In: Robotics: Science and Systems (2023)","DOI":"10.15607\/RSS.2023.XIX.012"},{"key":"15_CR39","unstructured":"Mendonca, R., Rybkin, O., Daniilidis, K., Hafner, D., Pathak, D.: Discovering and achieving goals via world models. In: Neural Information Processing Systems (2021)"},{"key":"15_CR40","unstructured":"Nair, A., Bahl, S., Khazatsky, A., Pong, V., Berseth, G., Levine, S.: Contextual imagined goals for self-supervised robotic learning. In: Conference on Robot Learning (2020)"},{"key":"15_CR41","unstructured":"Nair, A.V., Pong, V., Dalal, M., Bahl, S., Lin, S., Levine, S.: Visual reinforcement learning with imagined goals. In: Neural Information Processing Systems (2018)"},{"key":"15_CR42","unstructured":"Nair, S., Finn, C.: Hierarchical foresight: self-supervised learning of long-horizon tasks via visual subgoal generation. In: International Conference on Learning Representations (2020)"},{"key":"15_CR43","unstructured":"Nair, S., Rajeswaran, A., Kumar, V., Finn, C., Gupta, A.: R3m: a universal visual representation for robot manipulation. In: Conference on Robot Learning (2023)"},{"key":"15_CR44","unstructured":"Nair, S., Savarese, S., Finn, C.: Goal-aware prediction: learning to model what matters. In: International Conference on Machine Learning (2020)"},{"key":"15_CR45","unstructured":"Padalkar, A., et al.: Open x-embodiment: robotic learning datasets and rt-x models. arXiv preprint arXiv:2310.08864 (2023)"},{"key":"15_CR46","unstructured":"Paszke, A., et\u00a0al.: PyTorch: an imperative style, high-performance deep learning library. In: Neural Information Processing Systems (2019)"},{"key":"15_CR47","doi-asserted-by":"crossref","unstructured":"Pathak, D., et al.: Zero-shot visual imitation. In: Computer Vision and Pattern Recognition Workshops (2018)","DOI":"10.1109\/CVPRW.2018.00278"},{"issue":"6","key":"15_CR48","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3272127.3275014","volume":"37","author":"XB Peng","year":"2018","unstructured":"Peng, X.B., Kanazawa, A., Malik, J., Abbeel, P., Levine, S.: Sfv: reinforcement learning of physical skills from videos. ACM Trans. Graph. 37(6), 1\u201314 (2018)","journal-title":"ACM Trans. Graph."},{"key":"15_CR49","unstructured":"Pong, V., Dalal, M., Lin, S., Nair, A., Bahl, S., Levine, S.: Skew-fit: state-covering self-supervised reinforcement learning. In: International Conference on Machine Learning (2020)"},{"key":"15_CR50","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning (2021)"},{"key":"15_CR51","unstructured":"Radosavovic, I., Xiao, T., James, S., Abbeel, P., Malik, J., Darrell, T.: Real-world robot learning with masked visual pre-training. In: Conference on Robot Learning (2023)"},{"key":"15_CR52","unstructured":"Ranzato, M., Szlam, A., Bruna, J., Mathieu, M., Collobert, R., Chopra, S.: Video (language) modeling: a baseline for generative models of natural videos. arXiv preprint arXiv:1412.6604 (2014)"},{"key":"15_CR53","unstructured":"Schaul, T., Horgan, D., Gregor, K., Silver, D.: Universal value function approximators. In: International Conference on Machine Learning (2015)"},{"key":"15_CR54","unstructured":"Schmeckpeper, K., Rybkin, O., Daniilidis, K., Levine, S., Finn, C.: Reinforcement learning with videos: combining offline observations with interaction. In: Conference on Robot Learning (2021)"},{"key":"15_CR55","unstructured":"Schmidt, D., Jiang, M.: Learning to act without actions. In: International Conference on Learning Representations (2024)"},{"key":"15_CR56","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"15_CR57","unstructured":"Sekar, R., Rybkin, O., Daniilidis, K., Abbeel, P., Hafner, D., Pathak, D.: Planning to explore via self-supervised world models. In: International Conference on Machine Learning (2020)"},{"key":"15_CR58","unstructured":"Seo, Y., Lee, K., James, S.L., Abbeel, P.: Reinforcement learning with action-free pre-training from videos. In: International Conference on Machine Learning (2022)"},{"key":"15_CR59","doi-asserted-by":"crossref","unstructured":"Sermanet, P., et al.: Time-contrastive networks: self-supervised learning from video. In: International Conference on Robotics and Automation (2018)","DOI":"10.1109\/ICRA.2018.8462891"},{"issue":"12\u201314","key":"15_CR60","doi-asserted-by":"publisher","first-page":"1419","DOI":"10.1177\/02783649211046285","volume":"40","author":"L Shao","year":"2021","unstructured":"Shao, L., Migimatsu, T., Zhang, Q., Yang, K., Bohg, J.: Concept2robot: learning manipulation concepts from instructions and human demonstrations. Int. J. Robot. Res. 40(12\u201314), 1419\u20131434 (2021)","journal-title":"Int. J. Robot. Res."},{"key":"15_CR61","unstructured":"Sharma, P., Pathak, D., Gupta, A.: Third-person visual imitation learning via decoupled hierarchical controller. In: Neural Information Processing Systems (2019)"},{"key":"15_CR62","unstructured":"Shridhar, M., Manuelli, L., Fox, D.: Perceiver-actor: a multi-task transformer for robotic manipulation. In: Conference on Robot Learning (2023)"},{"key":"15_CR63","unstructured":"Singer, U., et al.: Make-a-video: text-to-video generation without text-video data. In: International Conference on Learning Representations (2023)"},{"key":"15_CR64","unstructured":"Sohn, K., Lee, H., Yan, X.: Learning structured output representation using deep conditional generative models. In: Neural Information Processing Systems (2015)"},{"key":"15_CR65","doi-asserted-by":"crossref","unstructured":"Torabi, F., Warnell, G., Stone, P.: Behavioral cloning from observation. In: International Joint Conference on Artificial Intelligence (2018)","DOI":"10.24963\/ijcai.2018\/687"},{"key":"15_CR66","unstructured":"Torabi, F., Warnell, G., Stone, P.: Generative adversarial imitation from observation. arXiv preprint arXiv:1807.06158 (2018)"},{"key":"15_CR67","doi-asserted-by":"crossref","unstructured":"Torabi, F., Warnell, G., Stone, P.: Imitation learning from video by leveraging proprioception. In: International Joint Conference on Artificial Intelligence (2019)","DOI":"10.24963\/ijcai.2019\/497"},{"key":"15_CR68","unstructured":"Trott, A., Zheng, S., Xiong, C., Socher, R.: Keeping your distance: solving sparse reward tasks using self-balancing shaped rewards. In: Neural Information Processing Systems (2019)"},{"key":"15_CR69","unstructured":"Van Den\u00a0Oord, A., Vinyals, O., , Kavukcuoglu, K.: Neural discrete representation learning. In: Neural Information Processing Systems (2017)"},{"key":"15_CR70","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Neural Information Processing Systems (2017)"},{"key":"15_CR71","unstructured":"Villegas, R., et al.: Phenaki: variable length video generation from open domain textual descriptions. In: International Conference on Learning Representations (2023)"},{"key":"15_CR72","unstructured":"Villegas, R., Pathak, A., Kannan, H., Erhan, D., Le, Q.V., Lee, H.: High fidelity video prediction with large stochastic recurrent neural networks. In: Neural Information Processing Systems (2019)"},{"key":"15_CR73","unstructured":"Walker, J., Razavi, A., Oord, A.V.D.: Predicting video with vqvae. arXiv preprint arXiv:2103.01950 (2021)"},{"key":"15_CR74","unstructured":"Wang, X., Zhu, Z., Huang, G., Wang, B., Chen, X., Lu, J.: Worlddreamer: towards general world models for video generation via predicting masked tokens. arXiv preprint arXiv:2401.09985 (2024)"},{"key":"15_CR75","unstructured":"Wu, H., et al.: Unleashing large-scale video generative pre-training for visual robot manipulation. arXiv preprint arXiv:2312.13139 (2023)"},{"key":"15_CR76","unstructured":"Wu, J., Ma, H., Deng, C., Long, M.: Pre-training contextualized world models with in-the-wild videos for reinforcement learning. arXiv preprint arXiv:2305.18499 (2023)"},{"key":"15_CR77","unstructured":"Wu, Y., Tucker, G., Nachum, O.: The laplacian in RL: learning representations with efficient approximations. In: International Conference on Learning Representations (2018)"},{"key":"15_CR78","unstructured":"Xiao, T., Radosavovic, I., Darrell, T., Malik, J.: Masked visual pre-training for motor control. arXiv preprint arXiv:2203.06173 (2022)"},{"key":"15_CR79","unstructured":"Xu, M., et al.: Spatial-temporal transformer networks for traffic flow forecasting. arXiv preprint arXiv:2001.02908 (2020)"},{"key":"15_CR80","unstructured":"Yan, W., Hafner, D., James, S., Abbeel, P.: Temporally consistent transformers for video generation. In: International Conference on Machine Learning (2023)"},{"key":"15_CR81","unstructured":"Yan, W., Zhang, Y., Abbeel, P., Srinivas, A.: Videogpt: video generation using VQ-VAE and transformers. arXiv preprint arXiv:2104.10157 (2021)"},{"key":"15_CR82","unstructured":"Yang, C., et al.: Imitation learning from observations by minimizing inverse dynamics disagreement. In: Neural Information Processing Systems (2019)"},{"key":"15_CR83","unstructured":"Yang, J., Liu, B., Fu, J., Pan, B., Wu, G., Wang, L.: Spatiotemporal predictive pre-training for robotic motor control. arXiv preprint arXiv:2403.05304 (2024)"},{"key":"15_CR84","unstructured":"Yang, M., Nachum, O.: Representation matters: offline pretraining for sequential decision making. In: International Conference on Machine Learning (2021)"},{"key":"15_CR85","unstructured":"Ye, W., Zhang, Y., Abbeel, P., Gao, Y.: Become a proficient player with limited data through watching pure videos. In: International Conference on Learning Representations (2022)"},{"key":"15_CR86","doi-asserted-by":"crossref","unstructured":"Yu, L., et\u00a0al.: Magvit: masked generative video transformer. In: Computer Vision and Pattern Recognition (2023)","DOI":"10.1109\/CVPR52729.2023.01008"},{"key":"15_CR87","unstructured":"Yu, T., Kumar, A., Chebotar, Y., Hausman, K., Finn, C., Levine, S.: How to leverage unlabeled data in offline reinforcement learning. In: International Conference on Machine Learning (2022)"},{"key":"15_CR88","unstructured":"Yu, T., et al.: Meta-world: a benchmark and evaluation for multi-task and meta reinforcement learning. In: Conference on Robot Learning (2020)"},{"key":"15_CR89","unstructured":"Yu, X., Lyu, Y., Tsang, I.: Intrinsic reward driven imitation learning via generative model. In: International Conference on Machine Learning (2020)"},{"key":"15_CR90","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1007\/978-3-031-19809-0_7","volume-title":"ECCV 2022","author":"Q Zhang","year":"2022","unstructured":"Zhang, Q., Peng, Z., Zhou, B.: Learning to drive by watching YouTube videos: action-conditioned contrastive policy pretraining. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13686, pp. 111\u2013128. Springer, Cham. (2022). https:\/\/doi.org\/10.1007\/978-3-031-19809-0_7"},{"key":"15_CR91","unstructured":"Zheng, Q., Henaff, M., Amos, B., Grover, A.: Semi-supervised offline reinforcement learning with action-free trajectories. In: International Conference on Machine Learning (2023)"},{"key":"15_CR92","unstructured":"Zhou, B., Li, K., Jiang, J., Lu, Z.: Learning from visual observation via offline pretrained state-to-go transformer. In: Neural Information Processing Systems (2023)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73004-7_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T17:08:02Z","timestamp":1730394482000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73004-7_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,1]]},"ISBN":["9783031730030","9783031730047"],"references-count":92,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73004-7_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,1]]},"assertion":[{"value":"1 November 2024","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":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}