{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T15:42:07Z","timestamp":1781797327359,"version":"3.54.5"},"publisher-location":"Cham","reference-count":34,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030695347","type":"print"},{"value":"9783030695354","type":"electronic"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-69535-4_40","type":"book-chapter","created":{"date-parts":[[2021,2,24]],"date-time":"2021-02-24T15:13:11Z","timestamp":1614179591000},"page":"654-669","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Multi-task Learning with Future States for Vision-Based Autonomous Driving"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1426-108X","authenticated-orcid":false,"given":"Inhan","family":"Kim","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1899-7211","authenticated-orcid":false,"given":"Hyemin","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3217-2168","authenticated-orcid":false,"given":"Joonyeong","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6027-2863","authenticated-orcid":false,"given":"Eunseop","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8046-8521","authenticated-orcid":false,"given":"Daijin","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,2,25]]},"reference":[{"key":"40_CR1","doi-asserted-by":"publisher","first-page":"1231","DOI":"10.1177\/0278364913491297","volume":"32","author":"A Geiger","year":"2013","unstructured":"Geiger, A., Lenz, P., Stiller, C., Urtasun, R.: Vision meets robotics: the Kitti dataset. Int. J. Robot. Res. 32, 1231\u20131237 (2013)","journal-title":"Int. J. Robot. Res."},{"key":"40_CR2","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":"40_CR3","unstructured":"Bojarski, M., et al.: End to end learning for self-driving cars. arXiv preprint arXiv:1604.07316 (2016)"},{"key":"40_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"449","DOI":"10.1007\/978-3-030-01234-2_27","volume-title":"Computer Vision \u2013 ECCV 2018","author":"S Hecker","year":"2018","unstructured":"Hecker, S., Dai, D., Van Gool, L.: End-to-end learning of driving models with surround-view cameras and route planners. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018, Part VII. LNCS, vol. 11211, pp. 449\u2013468. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01234-2_27"},{"key":"40_CR5","doi-asserted-by":"crossref","unstructured":"Huang, Z., Zhang, J., Tian, R., Zhang, Y.: End-to-end autonomous driving decision based on deep reinforcement learning. In: 2019 5th International Conference on Control, Automation and Robotics (ICCAR), pp. 658\u2013662. IEEE (2019)","DOI":"10.1109\/ICCAR.2019.8813431"},{"key":"40_CR6","doi-asserted-by":"crossref","unstructured":"Codevilla, F., Miiller, 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. 1\u20139. IEEE (2018)","DOI":"10.1109\/ICRA.2018.8460487"},{"key":"40_CR7","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 International Conference on Computer Vision, pp. 9329\u20139338 (2019)","DOI":"10.1109\/ICCV.2019.00942"},{"key":"40_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"604","DOI":"10.1007\/978-3-030-01234-2_36","volume-title":"Computer Vision \u2013 ECCV 2018","author":"X Liang","year":"2018","unstructured":"Liang, X., Wang, T., Yang, L., Xing, E.: CIRL: controllable imitative reinforcement learning for vision-based self-driving. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018, Part VII. LNCS, vol. 11211, pp. 604\u2013620. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01234-2_36"},{"key":"40_CR9","unstructured":"Sauer, A., Savinov, N., Geiger, A.: Conditional affordance learning for driving in urban environments. arXiv preprint arXiv:1806.06498 (2018)"},{"key":"40_CR10","doi-asserted-by":"crossref","unstructured":"Wang, Q., Chen, L., Tian, B., Tian, W., Li, L., Cao, D.: End-to-end autonomous driving: An angle branched network approach. IEEE Trans. Veh. Technol.(2019)","DOI":"10.1109\/TVT.2019.2921918"},{"key":"40_CR11","unstructured":"Chen, D., Zhou, B., Koltun, V., Kr\u00e4henb\u00fchl, P.: Learning by cheating. arXiv preprint arXiv:1912.12294 (2019)"},{"key":"40_CR12","unstructured":"Li, Z., Motoyoshi, T., Sasaki, K., Ogata, T., Sugano, S.: Rethinking self-driving: Multi-task knowledge for better generalization and accident explanation ability. arXiv preprint arXiv:1809.11100 (2018)"},{"key":"40_CR13","doi-asserted-by":"crossref","unstructured":"Chowdhuri, S., Pankaj, T., Zipser, K.: Multinet: Multi-modal multi-task learning for autonomous driving. In: 2019 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 1496\u20131504. IEEE (2019)","DOI":"10.1109\/WACV.2019.00164"},{"key":"40_CR14","unstructured":"Lotter, W., Kreiman, G., Cox, D.: Deep predictive coding networks for video prediction and unsupervised learning. arXiv preprint arXiv:1605.08104 (2016)"},{"key":"40_CR15","doi-asserted-by":"crossref","unstructured":"Kong, J., Pfeiffer, M., Schildbach, G., Borrelli, F.: Kinematic and dynamic vehicle models for autonomous driving control design. In: 2015 IEEE Intelligent Vehicles Symposium (IV), pp. 1094\u20131099. IEEE (2015)","DOI":"10.1109\/IVS.2015.7225830"},{"key":"40_CR16","unstructured":"Zhang, Y., Yang, Q.: A survey on multi-task learning. arXiv preprint arXiv:1707.08114 (2017)"},{"key":"40_CR17","doi-asserted-by":"crossref","unstructured":"Xu, H., Gao, Y., Yu, F., Darrell, T.: End-to-end learning of driving models from large-scale video datasets. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2174\u20132182 (2017)","DOI":"10.1109\/CVPR.2017.376"},{"key":"40_CR18","doi-asserted-by":"crossref","unstructured":"Chi, L., Mu, Y.: Deep steering: Learning end-to-end driving model from spatial and temporal visual cues. arXiv preprint arXiv:1708.03798 (2017)","DOI":"10.1145\/3132734.3132737"},{"key":"40_CR19","doi-asserted-by":"crossref","unstructured":"Ohn-Bar, E., Prakash, A., Behl, A., Chitta, K., Geiger, A.: Learning situational driving. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11296\u201311305 (2020)","DOI":"10.1109\/CVPR42600.2020.01131"},{"key":"40_CR20","unstructured":"Yu, A., Palefsky-Smith, R., Bedi, R.: Deep reinforcement learning for simulated autonomous vehicle control, pp. 1\u20137. Course Project Reports, Winter (2016)"},{"key":"40_CR21","doi-asserted-by":"crossref","unstructured":"Toromanoff, M., Wirbel, E., Moutarde, F.: End-to-end model-free reinforcement learning for urban driving using implicit affordances. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7153\u20137162 (2020)","DOI":"10.1109\/CVPR42600.2020.00718"},{"key":"40_CR22","doi-asserted-by":"crossref","unstructured":"Tai, L., Yun, P., Chen, Y., Liu, C., Ye, H., Liu, M.: Visual-based autonomous driving deployment from a stochastic and uncertainty-aware perspective. arXiv preprint arXiv:1903.00821 (2019)","DOI":"10.1109\/IROS40897.2019.8968307"},{"key":"40_CR23","doi-asserted-by":"crossref","unstructured":"Yang, Z., Zhang, Y., Yu, J., Cai, J., Luo, J.: End-to-end multi-modal multi-task vehicle control for self-driving cars with visual perceptions. In: 2018 24th International Conference on Pattern Recognition (ICPR), pp. 2289\u20132294. IEEE (2018)","DOI":"10.1109\/ICPR.2018.8546189"},{"key":"40_CR24","unstructured":"Mathieu, M., Couprie, C., LeCun, Y.: Deep multi-scale video prediction beyond mean square error. arXiv preprint arXiv:1511.05440 (2015)"},{"key":"40_CR25","unstructured":"Srivastava, N., Mansimov, E., Salakhudinov, R.: Unsupervised learning of video representations using LSTMs. In: International Conference on Machine Learning, pp. 843\u2013852 (2015)"},{"key":"40_CR26","doi-asserted-by":"crossref","unstructured":"Liang, X., Lee, L., Dai, W., Xing, E.P.: Dual motion GAN for future-flow embedded video prediction. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1744\u20131752 (2017)","DOI":"10.1109\/ICCV.2017.194"},{"key":"40_CR27","unstructured":"Wei, H., Yin, X., Lin, P.: Novel video prediction for large-scale scene using optical flow. arXiv preprint arXiv:1805.12243 (2018)"},{"key":"40_CR28","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1109\/TPAMI.2017.2781233","volume":"41","author":"R Ranjan","year":"2017","unstructured":"Ranjan, R., Patel, V.M., Chellappa, R.: Hyperface: a deep multi-task learning framework for face detection, landmark localization, pose estimation, and gender recognition. IEEE Trans. Pattern Anal. Mach. Intell. 41, 121\u2013135 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"40_CR29","doi-asserted-by":"crossref","unstructured":"Du, L., Zhao, Z., Su, F., Wang, L., An, C.: Jointly predicting future sequence and steering angles for dynamic driving scenes. In: ICASSP 2019\u20132019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4070\u20134074. IEEE (2019)","DOI":"10.1109\/ICASSP.2019.8682300"},{"key":"40_CR30","unstructured":"Jin, X., et al.: Predicting scene parsing and motion dynamics in the future. In: Advances in Neural Information Processing Systems, pp. 6915\u20136924 (2017)"},{"key":"40_CR31","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778. (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"40_CR32","unstructured":"Song, G., Chai, W.: Collaborative learning for deep neural networks. In: Advances in Neural Information Processing Systems, pp. 1832\u20131841 (2018)"},{"key":"40_CR33","unstructured":"Dosovitskiy, A., Ros, G., Codevilla, F., Lopez, A., Koltun, V.: Carla: An open urban driving simulator. arXiv preprint arXiv:1711.03938 (2017)"},{"key":"40_CR34","unstructured":"felipecode: Carla 0.8.4 data collector (2018). https:\/\/github.com\/carla-simulator\/data-collector"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2020"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-69535-4_40","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,2,24]],"date-time":"2021-02-24T16:14:58Z","timestamp":1614183298000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-69535-4_40"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030695347","9783030695354"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-69535-4_40","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"25 February 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kyoto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 November 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 December 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/accv2020.kyoto\/","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":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"768","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":"254","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":"33% - 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","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","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)"}},{"value":"The conference was held virtually.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}