{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,17]],"date-time":"2026-01-17T22:28:20Z","timestamp":1768688900368,"version":"3.49.0"},"publisher-location":"Cham","reference-count":51,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030012519","type":"print"},{"value":"9783030012526","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"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":[[2018]]},"DOI":"10.1007\/978-3-030-01252-6_10","type":"book-chapter","created":{"date-parts":[[2018,10,5]],"date-time":"2018-10-05T13:48:05Z","timestamp":1538747285000},"page":"162-180","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":77,"title":["CAR-Net: Clairvoyant Attentive Recurrent Network"],"prefix":"10.1007","author":[{"given":"Amir","family":"Sadeghian","sequence":"first","affiliation":[]},{"given":"Ferdinand","family":"Legros","sequence":"additional","affiliation":[]},{"given":"Maxime","family":"Voisin","sequence":"additional","affiliation":[]},{"given":"Ricky","family":"Vesel","sequence":"additional","affiliation":[]},{"given":"Alexandre","family":"Alahi","sequence":"additional","affiliation":[]},{"given":"Silvio","family":"Savarese","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,10,6]]},"reference":[{"key":"10_CR1","doi-asserted-by":"crossref","unstructured":"Walker, J., Gupta, A., Hebert, M.: Patch to the future: unsupervised visual prediction. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3302\u20133309 (2014)","DOI":"10.1109\/CVPR.2014.416"},{"key":"10_CR2","doi-asserted-by":"crossref","unstructured":"Trautman, P., Krause, A.: Unfreezing the robot: navigation in dense, interacting crowds. In: 2010 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 797\u2013803. IEEE (2010)","DOI":"10.1109\/IROS.2010.5654369"},{"key":"10_CR3","doi-asserted-by":"crossref","unstructured":"Karasev, V., Ayvaci, A., Heisele, B., Soatto, S.: Intent-aware long-term prediction of pedestrian motion. In: 2016 IEEE International Conference on Robotics and Automation (ICRA), pp. 2543\u20132549. IEEE (2016)","DOI":"10.1109\/ICRA.2016.7487409"},{"key":"10_CR4","unstructured":"Hirose, N., et al.: To go or not to go? A near unsupervised learning approach for robot navigation. arXiv preprint arXiv:1709.05439 (2017)"},{"key":"10_CR5","doi-asserted-by":"crossref","unstructured":"Sadeghian, A., Alahi, A., Savarese, S.: Tracking the untrackable: learning to track multiple cues with long-term dependencies. arXiv preprint arXiv:1701.01909 (2017)","DOI":"10.1109\/ICCV.2017.41"},{"key":"10_CR6","unstructured":"Oh, S., et al.: A large-scale benchmark dataset for event recognition in surveillance video. In: 2011 IEEE conference on Computer vision and pattern recognition (CVPR), pp. 3153\u20133160. IEEE (2011)"},{"issue":"8","key":"10_CR7","doi-asserted-by":"publisher","first-page":"1114","DOI":"10.1109\/TCSVT.2008.927109","volume":"18","author":"BT Morris","year":"2008","unstructured":"Morris, B.T., Trivedi, M.M.: A survey of vision-based trajectory learning and analysis for surveillance. IEEE Trans. Circuits Syst. Video Technol. 18(8), 1114\u20131127 (2008)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10_CR8","doi-asserted-by":"publisher","first-page":"1639","DOI":"10.1109\/TPAMI.2017.2728788","volume":"40","author":"D Xie","year":"2017","unstructured":"Xie, D., Shu, T., Todorovic, S., Zhu, S.C.: Learning and inferring \u201cdark matter\u201d and predicting human intents and trajectories in videos. IEEE Trans. Pattern Anal. Mach. Intell. 40, 1639\u20131652 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10_CR9","doi-asserted-by":"crossref","unstructured":"Hirose, N., et al.: Gonet: a semi-supervised deep learning approach for traversability estimation. arXiv preprint arXiv:1803.03254 (2018)","DOI":"10.1109\/IROS.2018.8594031"},{"key":"10_CR10","unstructured":"Hirose, N., et al.: Gonet++: Traversability estimation via dynamic scene view synthesis. arXiv preprint arXiv:1806.08864 (2018)"},{"key":"10_CR11","unstructured":"Gong, H., Sim, J., Likhachev, M., Shi, J.: Multi-hypothesis motion planning for visual object tracking. In: 2011 IEEE International Conference on Computer Vision (ICCV), pp. 619\u2013626. IEEE (2011)"},{"issue":"3","key":"10_CR12","doi-asserted-by":"publisher","first-page":"397","DOI":"10.1109\/TSMCB.2005.846652","volume":"35","author":"D Makris","year":"2005","unstructured":"Makris, D., Ellis, T.: Learning semantic scene models from observing activity in visual surveillance. IEEE Trans. Syst. Man Cybern. Part B (Cybern.) 35(3), 397\u2013408 (2005)","journal-title":"IEEE Trans. Syst. Man Cybern. Part B (Cybern.)"},{"key":"10_CR13","doi-asserted-by":"crossref","unstructured":"Kretzschmar, H., Kuderer, M., Burgard, W.: Learning to predict trajectories of cooperatively navigating agents. In: 2014 IEEE International Conference on Robotics and Automation (ICRA), pp. 4015\u20134020. IEEE (2014)","DOI":"10.1109\/ICRA.2014.6907442"},{"key":"10_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"201","DOI":"10.1007\/978-3-642-33765-9_15","volume-title":"Computer Vision \u2013 ECCV 2012","author":"KM Kitani","year":"2012","unstructured":"Kitani, K.M., Ziebart, B.D., Bagnell, J.A., Hebert, M.: Activity forecasting. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7575, pp. 201\u2013214. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33765-9_15"},{"key":"10_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"697","DOI":"10.1007\/978-3-319-46448-0_42","volume-title":"Computer Vision \u2013 ECCV 2016","author":"L Ballan","year":"2016","unstructured":"Ballan, L., Castaldo, F., Alahi, A., Palmieri, F., Savarese, S.: Knowledge transfer for scene-specific motion prediction. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 697\u2013713. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_42"},{"key":"10_CR16","doi-asserted-by":"crossref","unstructured":"Lee, N., Choi, W., Vernaza, P., Choy, C.B., Torr, P.H., Chandraker, M.: Desire: distant future prediction in dynamic scenes with interacting agents. arXiv preprint arXiv:1704.04394 (2017)","DOI":"10.1109\/CVPR.2017.233"},{"key":"10_CR17","unstructured":"Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: International Conference on Machine Learning, pp. 2048\u20132057 (2015)"},{"key":"10_CR18","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014)"},{"key":"10_CR19","unstructured":"Sadeghian, A., Rodriguez, M., Wang, D.Z., Colas, A.: Temporal reasoning over event knowledge graphs (2016)"},{"key":"10_CR20","unstructured":"Sadeghian, A., Sundaram, L., Wang, D., Hamilton, W., Branting, K., Pfeifer, C.: Semantic edge labeling over legal citation graphs (2016)"},{"key":"10_CR21","unstructured":"Mnih, V., Heess, N., Graves, A., et al.: Recurrent models of visual attention. In: Advances in neural information processing systems, pp. 2204\u20132212 (2014)"},{"key":"10_CR22","unstructured":"Ba, J., Mnih, V., Kavukcuoglu, K.: Multiple object recognition with visual attention. arXiv preprint arXiv:1412.7755 (2014)"},{"key":"10_CR23","unstructured":"Gregor, K., Danihelka, I., Graves, A., Rezende, D.J., Wierstra, D.: Draw: a recurrent neural network for image generation. arXiv preprint arXiv:1502.04623 (2015)"},{"key":"10_CR24","doi-asserted-by":"crossref","unstructured":"Caba Heilbron, F., Escorcia, V., Ghanem, B., Carlos Niebles, J.: Activitynet: a large-scale video benchmark for human activity understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 961\u2013970 (2015)","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"10_CR25","doi-asserted-by":"crossref","unstructured":"Bagautdinov, T., Alahi, A., Fleuret, F., Fua, P., Savarese, S.: Social scene understanding: end-to-end multi-person action localization and collective activity recognition. arXiv preprint arXiv:1611.09078 (2016)","DOI":"10.1109\/CVPR.2017.365"},{"issue":"2\u20133","key":"10_CR26","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1145\/2815474.2815476","volume":"7","author":"R Vesel","year":"2015","unstructured":"Vesel, R.: Racing line optimization@ race optimal. ACM SIGEVOlution 7(2\u20133), 12\u201320 (2015)","journal-title":"ACM SIGEVOlution"},{"issue":"1","key":"10_CR27","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1115\/1.3662552","volume":"82","author":"RE Kalman","year":"1960","unstructured":"Kalman, R.E.: A new approach to linear filtering and prediction problems. J. Basic Eng. 82(1), 35\u201345 (1960)","journal-title":"J. Basic Eng."},{"issue":"3","key":"10_CR28","doi-asserted-by":"publisher","first-page":"285","DOI":"10.1016\/0377-2217(84)90282-0","volume":"16","author":"P McCullagh","year":"1984","unstructured":"McCullagh, P.: Generalized linear models. Eur. J. Oper. Res. 16(3), 285\u2013292 (1984)","journal-title":"Eur. J. Oper. Res."},{"key":"10_CR29","series-title":"NATO ASI series D Behavioural and Social Sciences","doi-asserted-by":"publisher","first-page":"599","DOI":"10.1007\/978-94-011-5014-9_23","volume-title":"Learning in Graphical Models","author":"CK Williams","year":"1998","unstructured":"Williams, C.K.: Prediction with gaussian processes: from linear regression to linear prediction and beyond. In: Jordan, M.I. (ed.) Learning in Graphical Models. NATO ASI series D Behavioural and Social Sciences, vol. 89, pp. 599\u2013621. Springer, Dordrecht (1998). https:\/\/doi.org\/10.1007\/978-94-011-5014-9_23"},{"key":"10_CR30","first-page":"1939","volume":"6","author":"J Qui\u00f1onero-Candela","year":"2005","unstructured":"Qui\u00f1onero-Candela, J., Rasmussen, C.E.: A unifying view of sparse approximate Gaussian process regression. J. Mach. Learn. Res. 6, 1939\u20131959 (2005)","journal-title":"J. Mach. Learn. Res."},{"issue":"2","key":"10_CR31","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1109\/TPAMI.2007.1167","volume":"30","author":"JM Wang","year":"2008","unstructured":"Wang, J.M., Fleet, D.J., Hertzmann, A.: Gaussian process dynamical models for human motion. IEEE Trans. Pattern Anal. Mach. Intell. 30(2), 283\u2013298 (2008)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10_CR32","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"452","DOI":"10.1007\/978-3-642-15549-9_33","volume-title":"Computer Vision \u2013 ECCV 2010","author":"S Pellegrini","year":"2010","unstructured":"Pellegrini, S., Ess, A., Van Gool, L.: Improving data association by joint modeling of pedestrian trajectories and groupings. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6311, pp. 452\u2013465. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-15549-9_33"},{"issue":"1","key":"10_CR33","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1109\/TPAMI.2015.2430335","volume":"38","author":"HS Koppula","year":"2016","unstructured":"Koppula, H.S., Saxena, A.: Anticipating human activities using object affordances for reactive robotic response. IEEE Trans. Pattern Anal. Mach. Intell. 38(1), 14\u201329 (2016)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"5","key":"10_CR34","doi-asserted-by":"publisher","first-page":"4282","DOI":"10.1103\/PhysRevE.51.4282","volume":"51","author":"D Helbing","year":"1995","unstructured":"Helbing, D., Molnar, P.: Social force model for pedestrian dynamics. Phys. Rev. E 51(5), 4282 (1995)","journal-title":"Phys. Rev. E"},{"key":"10_CR35","doi-asserted-by":"crossref","unstructured":"Alahi, A., Goel, K., Ramanathan, V., Robicquet, A., Fei-Fei, L., Savarese, S.: Social LSTM: human trajectory prediction in crowded spaces. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 961\u2013971 (2016)","DOI":"10.1109\/CVPR.2016.110"},{"key":"10_CR36","doi-asserted-by":"crossref","unstructured":"Alahi, A., et al.: Learning to predict human behavior in crowded scenes. In: Group and Crowd Behavior for Computer Vision, pp. 183\u2013207. Elsevier (2017)","DOI":"10.1016\/B978-0-12-809276-7.00011-4"},{"key":"10_CR37","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"549","DOI":"10.1007\/978-3-319-46484-8_33","volume-title":"Computer Vision \u2013 ECCV 2016","author":"A Robicquet","year":"2016","unstructured":"Robicquet, A., Sadeghian, A., Alahi, A., Savarese, S.: Learning social etiquette: human trajectory understanding in crowded scenes. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 549\u2013565. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_33"},{"key":"10_CR38","unstructured":"Robicquet, A., et al.: Forecasting social navigation in crowded complex scenes. arXiv preprint arXiv:1601.00998 (2016)"},{"key":"10_CR39","doi-asserted-by":"crossref","unstructured":"Haque, A., Alahi, A., Fei-Fei, L.: Recurrent attention models for depth-based person identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1229\u20131238 (2016)","DOI":"10.1109\/CVPR.2016.138"},{"key":"10_CR40","doi-asserted-by":"crossref","unstructured":"Sadeghian, A., Kosaraju, V., Sadeghian, A., Hirose, N., Savarese, S.: SoPhie: an attentive GAN for predicting paths compliant to social and physical constraints. arXiv preprint arXiv:1806.01482 (2018)","DOI":"10.1109\/CVPR.2019.00144"},{"issue":"6","key":"10_CR41","doi-asserted-by":"publisher","first-page":"1245","DOI":"10.1109\/TMM.2017.2648498","volume":"19","author":"B Zhao","year":"2017","unstructured":"Zhao, B., Wu, X., Feng, J., Peng, Q., Yan, S.: Diversified visual attention networks for fine-grained object classification. IEEE Trans. Multimed. 19(6), 1245\u20131256 (2017)","journal-title":"IEEE Trans. Multimed."},{"key":"10_CR42","doi-asserted-by":"crossref","unstructured":"You, Q., Jin, H., Wang, Z., Fang, C., Luo, J.: Image captioning with semantic attention. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4651\u20134659 (2016)","DOI":"10.1109\/CVPR.2016.503"},{"key":"10_CR43","unstructured":"Sharma, S., Kiros, R., Salakhutdinov, R.: Action recognition using visual attention. arXiv preprint arXiv:1511.04119 (2015)"},{"issue":"8","key":"10_CR44","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"10_CR45","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"issue":"3","key":"10_CR46","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., et al.: Imagenet large scale visual recognition challenge. Int. J. Comput. Vis. (IJCV) 115(3), 211\u2013252 (2015)","journal-title":"Int. J. Comput. Vis. (IJCV)"},{"key":"10_CR47","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431\u20133440 (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"10_CR48","unstructured":"Kingma, D., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"10_CR49","unstructured":"OpenAI gym, published. https:\/\/gym.openai.com\/envs\/carracing-v0\/. Accessed 01 Jan 2017"},{"issue":"1","key":"10_CR50","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1002\/j.1538-7305.1983.tb04381.x","volume":"62","author":"N Graham","year":"1983","unstructured":"Graham, N.: Smoothing with periodic cubic splines. Bell Labs Tech. J. 62(1), 101\u2013110 (1983)","journal-title":"Bell Labs Tech. J."},{"key":"10_CR51","doi-asserted-by":"crossref","unstructured":"Yamaguchi, K., Berg, A.C., Ortiz, L.E., Berg, T.L.: Who are you with and where are you going? In: 2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1345\u20131352. IEEE (2011)","DOI":"10.1109\/CVPR.2011.5995468"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2018"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-01252-6_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,5]],"date-time":"2022-10-05T01:05:42Z","timestamp":1664931942000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01252-6_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012519","9783030012526"],"references-count":51,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01252-6_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"6 October 2018","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":"Munich","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 September 2018","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":"eccv2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2018.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}