{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T17:00:17Z","timestamp":1777568417862,"version":"3.51.4"},"publisher-location":"Cham","reference-count":48,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031198083","type":"print"},{"value":"9783031198090","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-19809-0_7","type":"book-chapter","created":{"date-parts":[[2022,10,31]],"date-time":"2022-10-31T07:03:04Z","timestamp":1667199784000},"page":"111-128","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":19,"title":["Learning to Drive by Watching YouTube Videos: Action-Conditioned Contrastive Policy Pretraining"],"prefix":"10.1007","author":[{"given":"Qihang","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Zhenghao","family":"Peng","sequence":"additional","affiliation":[]},{"given":"Bolei","family":"Zhou","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,11,1]]},"reference":[{"key":"7_CR1","unstructured":"Agrawal, P., Nair, A.V., Abbeel, P., Malik, J., Levine, S.: Learning to poke by poking: Experiential learning of intuitive physics. Adv. Neural Inf. Process. Syst. 29, 5074\u20135082 (2016)"},{"issue":"1","key":"7_CR2","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1177\/0278364919887447","volume":"39","author":"OM Andrychowicz","year":"2020","unstructured":"Andrychowicz, O.M., et al.: Learning dexterous in-hand manipulation. Int. J. Robot. Res. 39(1), 3\u201320 (2020)","journal-title":"Int. J. Robot. Res."},{"key":"7_CR3","unstructured":"Baker, B., et al.: Video pretraining (VPT): learning to act by watching unlabeled online videos. arXiv preprint arXiv:2206.11795 (2022)"},{"key":"7_CR4","doi-asserted-by":"crossref","unstructured":"Caesar, H., et al.: nuScenes: a multimodal dataset for autonomous driving. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 11621\u201311631 (2020)","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"7_CR5","unstructured":"Chen, D., Zhou, B., Koltun, V., Kr\u00e4henb\u00fchl, P.: Learning by cheating. In: Conference on Robot Learning, pp. 66\u201375. PMLR (2020)"},{"key":"7_CR6","unstructured":"Chen, T., Xu, J., Agrawal, P.: A system for general in-hand object re-orientation. In: Conference on Robot Learning, pp. 297\u2013307. PMLR (2022)"},{"key":"7_CR7","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International Conference on Machine Learning, pp. 1597\u20131607. PMLR (2020)"},{"key":"7_CR8","unstructured":"Chen, X., Fan, H., Girshick, R., He, K.: Improved baselines with momentum contrastive learning. arXiv preprint arXiv:2003.04297 (2020)"},{"key":"7_CR9","doi-asserted-by":"crossref","unstructured":"Codevilla, F., M\u00fcller, M., L\u00f3pez, A., Koltun, V., Dosovitskiy, A.: End-to-end driving via conditional imitation learning. In: 2018 IEEE International Conference on Robotics and Automation (ICRA), pp. 4693\u20134700. IEEE (2018)","DOI":"10.1109\/ICRA.2018.8460487"},{"key":"7_CR10","doi-asserted-by":"crossref","unstructured":"Codevilla, F., Santana, E., L\u00f3pez, A.M., Gaidon, A.: Exploring the limitations of behavior cloning for autonomous driving. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9329\u20139338 (2019)","DOI":"10.1109\/ICCV.2019.00942"},{"key":"7_CR11","unstructured":"Dosovitskiy, A., Ros, G., Codevilla, F., L\u00f3pez, A.M., Koltun, V.: CARLA: an open urban driving simulator. CoRR abs\/1711.03938 (2017), arxiv.org\/abs\/1711.03938"},{"key":"7_CR12","unstructured":"Finn, C., Tan, X.Y., Duan, Y., Darrell, T., Levine, S., Abbeel, P.: Learning visual feature spaces for robotic manipulation with deep spatial autoencoders. arXiv preprint arXiv:1509.06113 25 (2015)"},{"key":"7_CR13","first-page":"21271","volume":"33","author":"JB Grill","year":"2020","unstructured":"Grill, J.B., et al.: Bootstrap your own latent-a new approach to self-supervised learning. Adv. Neural Inf. Process. Syst. 33, 21271\u201321284 (2020)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"7_CR14","unstructured":"Ha, D., Schmidhuber, J.: World models. arXiv preprint arXiv:1803.10122 (2018)"},{"key":"7_CR15","unstructured":"Hafner, D., Lillicrap, T., Fischer, I., Villegas, R., Ha, D., Lee, H., Davidson, J.: Learning latent dynamics for planning from pixels. In: International Conference on Machine Learning, pp. 2555\u20132565. PMLR (2019)"},{"key":"7_CR16","unstructured":"Hansen, N., et al.: Self-supervised policy adaptation during deployment. arXiv preprint arXiv:2007.04309 (2020)"},{"key":"7_CR17","doi-asserted-by":"crossref","unstructured":"Hansen, N., Wang, X.: Generalization in reinforcement learning by soft data augmentation. In: 2021 IEEE International Conference on Robotics and Automation (ICRA), pp. 13611\u201313617. IEEE (2021)","DOI":"10.1109\/ICRA48506.2021.9561103"},{"key":"7_CR18","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9729\u20139738 (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"7_CR19","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on ImageNet classification. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1026\u20131034 (2015)","DOI":"10.1109\/ICCV.2015.123"},{"key":"7_CR20","unstructured":"Kalashnikov, D., et al.: Scalable deep reinforcement learning for vision-based robotic manipulation. In: Conference on Robot Learning, pp. 651\u2013673. PMLR (2018)"},{"key":"7_CR21","unstructured":"Kumar, A., Gupta, S., Malik, J.: Learning navigation subroutines by watching videos. corr abs\/1905.12612 (2019) (1905)"},{"key":"7_CR22","doi-asserted-by":"crossref","unstructured":"Lange, S., Riedmiller, M., Voigtl\u00e4nder, A.: Autonomous reinforcement learning on raw visual input data in a real world application. In: The 2012 International Joint Conference on Neural Networks (IJCNN), pp. 1\u20138. IEEE (2012)","DOI":"10.1109\/IJCNN.2012.6252823"},{"key":"7_CR23","unstructured":"Laskin, M., Srinivas, A., Abbeel, P.: Curl: contrastive unsupervised representations for reinforcement learning. In: International Conference on Machine Learning, pp. 5639\u20135650. PMLR (2020)"},{"key":"7_CR24","first-page":"741","volume":"33","author":"AX Lee","year":"2020","unstructured":"Lee, A.X., Nagabandi, A., Abbeel, P., Levine, S.: Stochastic latent actor-critic: deep reinforcement learning with a latent variable model. Adv. Neural Inf. Process. Syst. 33, 741\u2013752 (2020)","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"1","key":"7_CR25","first-page":"1334","volume":"17","author":"S Levine","year":"2016","unstructured":"Levine, S., Finn, C., Darrell, T., Abbeel, P.: End-to-end training of deep visuomotor policies. J. Mach. Learn. Res. 17(1), 1334\u20131373 (2016)","journal-title":"J. Mach. Learn. Res."},{"issue":"11","key":"7_CR26","first-page":"2579","volume":"9","author":"L Van der Maaten","year":"2008","unstructured":"Van der Maaten, L., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9(11), 2579\u20132605 (2008)","journal-title":"J. Mach. Learn. Res."},{"key":"7_CR27","doi-asserted-by":"crossref","unstructured":"Pan, X., Shi, J., Luo, P., Wang, X., Tang, X.: Spatial as deep: Spatial CNN for traffic scene understanding. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32 (2018)","DOI":"10.1609\/aaai.v32i1.12301"},{"key":"7_CR28","doi-asserted-by":"crossref","unstructured":"Peng, X.B., Andrychowicz, M., Zaremba, W., Abbeel, P.: Sim-to-real transfer of robotic control with dynamics randomization. In: 2018 IEEE International Conference on Robotics and Automation (ICRA), pp. 3803\u20133810. IEEE (2018)","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"7_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-319-46475-6_1","volume-title":"Computer Vision","author":"L Pinto","year":"2016","unstructured":"Pinto, L., Gandhi, D., Han, Y., Park, Y.-L., Gupta, A.: The curious robot: learning visual representations via physical interactions. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 3\u201318. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46475-6_1"},{"key":"7_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"276","DOI":"10.1007\/978-3-030-58586-0_17","volume-title":"Computer Vision","author":"Z Qin","year":"2020","unstructured":"Qin, Z., Wang, H., Li, X.: Ultra fast structure-aware deep lane detection. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12369, pp. 276\u2013291. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58586-0_17"},{"key":"7_CR31","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"7_CR32","unstructured":"Shah, R., Kumar, V.: RRL: Resnet as representation for reinforcement learning. arXiv preprint arXiv:2107.03380 (2021)"},{"key":"7_CR33","unstructured":"Stooke, A., Lee, K., Abbeel, P., Laskin, M.: Decoupling representation learning from reinforcement learning. In: International Conference on Machine Learning, pp. 9870\u20139879. PMLR (2021)"},{"key":"7_CR34","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"402","DOI":"10.1007\/978-3-030-58536-5_24","volume-title":"Computer Vision","author":"Z Teed","year":"2020","unstructured":"Teed, Z., Deng, J.: RAFT: recurrent all-pairs field transforms for optical flow. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12347, pp. 402\u2013419. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58536-5_24"},{"key":"7_CR35","doi-asserted-by":"crossref","unstructured":"Tobin, J., Fong, R., Ray, A., Schneider, J., Zaremba, W., Abbeel, P.: Domain randomization for transferring deep neural networks from simulation to the real world. In: 2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 23\u201330. IEEE (2017)","DOI":"10.1109\/IROS.2017.8202133"},{"key":"7_CR36","doi-asserted-by":"crossref","unstructured":"Torabi, F., Warnell, G., Stone, P.: Behavioral cloning from observation. In: IJCAI (2018)","DOI":"10.24963\/ijcai.2018\/687"},{"key":"7_CR37","unstructured":"Wang, C., Luo, X., Ross, K., Li, D.: Vrl3: a data-driven framework for visual deep reinforcement learning. arXiv preprint arXiv:2202.10324 (2022)"},{"key":"7_CR38","unstructured":"Wu, B., Nair, S., Fei-Fei, L., Finn, C.: Example-driven model-based reinforcement learning for solving long-horizon visuomotor tasks. arXiv preprint arXiv:2109.10312 (2021)"},{"key":"7_CR39","doi-asserted-by":"crossref","unstructured":"Wu, Z., Xiong, Y., Yu, S.X., Lin, D.: Unsupervised feature learning via non-parametric instance discrimination. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3733\u20133742 (2018)","DOI":"10.1109\/CVPR.2018.00393"},{"key":"7_CR40","unstructured":"Xiao, T., Radosavovic, I., Darrell, T., Malik, J.: Masked visual pre-training for motor control. arXiv preprint arXiv:2203.06173 (2022)"},{"key":"7_CR41","unstructured":"Yan, W., Vangipuram, A., Abbeel, P., Pinto, L.: Learning predictive representations for deformable objects using contrastive estimation. arXiv preprint arXiv:2003.05436 (2020)"},{"key":"7_CR42","doi-asserted-by":"crossref","unstructured":"Yang, C., Wu, Z., Zhou, B., Lin, S.: Instance localization for self-supervised detection pretraining. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3987\u20133996 (2021)","DOI":"10.1109\/CVPR46437.2021.00398"},{"key":"7_CR43","unstructured":"Yarats, D., Kostrikov, I., Fergus, R.: Image augmentation is all you need: regularizing deep reinforcement learning from pixels. In: International Conference on Learning Representations (2020)"},{"key":"7_CR44","unstructured":"Yarats, D., Zhang, A., Kostrikov, I., Amos, B., Pineau, J., Fergus, R.: Improving sample efficiency in model-free reinforcement learning from images. arXiv preprint arXiv:1910.01741 (2019)"},{"key":"7_CR45","unstructured":"Zhan, A., Zhao, P., Pinto, L., Abbeel, P., Laskin, M.: A framework for efficient robotic manipulation. arXiv preprint arXiv:2012.07975 (2020)"},{"key":"7_CR46","unstructured":"Zhang, A., McAllister, R., Calandra, R., Gal, Y., Levine, S.: Learning invariant representations for reinforcement learning without reconstruction. arXiv preprint arXiv:2006.10742 (2020)"},{"key":"7_CR47","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Liniger, A., Dai, D., Yu, F., Van Gool, L.: End-to-end urban driving by imitating a reinforcement learning coach. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.01494"},{"key":"7_CR48","doi-asserted-by":"crossref","unstructured":"Zheng, T., et al.: Resa: Recurrent feature-shift aggregator for lane detection (2020)","DOI":"10.1609\/aaai.v35i4.16469"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-19809-0_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T00:08:25Z","timestamp":1667434105000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19809-0_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031198083","9783031198090"],"references-count":48,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19809-0_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"1 November 2022","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":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1645","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"28% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.21","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.91","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}