{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,12]],"date-time":"2025-07-12T01:05:28Z","timestamp":1752282328358,"version":"3.40.3"},"publisher-location":"Cham","reference-count":44,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030129385"},{"type":"electronic","value":"9783030129392"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","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":[[2019]]},"DOI":"10.1007\/978-3-030-12939-2_21","type":"book-chapter","created":{"date-parts":[[2019,2,14]],"date-time":"2019-02-14T19:03:20Z","timestamp":1550171000000},"page":"298-314","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Context-driven Multi-stream LSTM (M-LSTM) for Recognizing Fine-Grained Activity of Drivers"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0276-9000","authenticated-orcid":false,"given":"Ardhendu","family":"Behera","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2804-602X","authenticated-orcid":false,"given":"Alexander","family":"Keidel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2026-8632","authenticated-orcid":false,"given":"Bappaditya","family":"Debnath","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,2,14]]},"reference":[{"unstructured":"Abouelnaga, Y., Eraqi, H.M., Moustafa, M.N.: Real-time distracted driver posture classification. arXiv preprint \n                      arXiv:1706.09498\n                      \n                     (2017)","key":"21_CR1"},{"issue":"3","key":"21_CR2","doi-asserted-by":"publisher","first-page":"16:1","DOI":"10.1145\/1922649.1922653","volume":"43","author":"J Aggarwal","year":"2011","unstructured":"Aggarwal, J., Ryoo, M.: Human activity analysis: a review. ACM Comput. Surv. 43(3), 16:1\u201316:43 (2011)","journal-title":"ACM Comput. Surv."},{"key":"21_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"519","DOI":"10.1007\/978-3-642-37431-9_40","volume-title":"Computer Vision \u2013 ACCV 2012","author":"A Behera","year":"2013","unstructured":"Behera, A., Hogg, D.C., Cohn, A.G.: Egocentric activity monitoring and recovery. In: Lee, K.M., Matsushita, Y., Rehg, J.M., Hu, Z. (eds.) ACCV 2012. LNCS, vol. 7726, pp. 519\u2013532. Springer, Heidelberg (2013). \n                      https:\/\/doi.org\/10.1007\/978-3-642-37431-9_40"},{"doi-asserted-by":"crossref","unstructured":"Blank, M., Gorelick, L., Shechtman, E., Irani, M., Basri, R.: Actions as space-time shapes. In: ICCV, pp. 1395\u20131402 (2005)","key":"21_CR4","DOI":"10.1109\/ICCV.2005.28"},{"doi-asserted-by":"crossref","unstructured":"Cao, Z., Simon, T., Wei, S.E., Sheikh, Y.: Realtime multi-person 2D pose estimation using part affinity fields. In: IEEE CVPR (2017)","key":"21_CR5","DOI":"10.1109\/CVPR.2017.143"},{"key":"21_CR6","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1007\/978-1-84628-618-6_6","volume-title":"Modelling Driver Behaviour in Automotive Environments","author":"O Carsten","year":"2007","unstructured":"Carsten, O.: From driver models to modelling the driver: what do we really need to know about the driver? In: Cacciabue, P.C. (ed.) Modelling Driver Behaviour in Automotive Environments, pp. 105\u2013120. Springer, London (2007). \n                      https:\/\/doi.org\/10.1007\/978-1-84628-618-6_6"},{"unstructured":"State Farm Corporate: State farm distracted driver detection (2016). \n                      https:\/\/www.kaggle.com\/c\/state-farm-distracted-driver-detection","key":"21_CR7"},{"issue":"4","key":"21_CR8","doi-asserted-by":"publisher","first-page":"677","DOI":"10.1109\/TPAMI.2016.2599174","volume":"39","author":"J Donahue","year":"2017","unstructured":"Donahue, J., et al.: Long-term recurrent convolutional networks for visual recognition and description. IEEE Trans. PAMI 39(4), 677\u2013691 (2017)","journal-title":"IEEE Trans. PAMI"},{"doi-asserted-by":"crossref","unstructured":"Fathi, A., Farhadi, A., Rehg, J.M.: Understanding egocentric activities. In: ICCV (2011)","key":"21_CR9","DOI":"10.1109\/ICCV.2011.6126269"},{"doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Pinz, A., Zisserman, A.: Convolutional two-stream network fusion for video action recognition. In: IEEE CVPR, pp. 1933\u20131941 (2016)","key":"21_CR10","DOI":"10.1109\/CVPR.2016.213"},{"unstructured":"Girdhar, R., Ramanan, D.: Attentional pooling for action recognition. In: Advances in NIPS, pp. 33\u201344 (2017)","key":"21_CR11"},{"doi-asserted-by":"crossref","unstructured":"Gkioxari, G., Girshick, R., Malik, J.: Contextual action recognition with R*CNN. In: ICCV, pp. 1080\u20131088 (2015)","key":"21_CR12","DOI":"10.1109\/ICCV.2015.129"},{"doi-asserted-by":"crossref","unstructured":"Gupta, A., Davis, L.S.: Objects in action: an approach for combining action understanding and object perception. In: CVPR (2007)","key":"21_CR13","DOI":"10.1109\/CVPR.2007.383331"},{"issue":"2","key":"21_CR14","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1016\/j.arcontrol.2006.09.005","volume":"30","author":"A Heide","year":"2006","unstructured":"Heide, A., Henning, K.: The \u201ccognitive car\u201d: a roadmap for research issues in the automotive sector. Ann. Rev. Control 30(2), 197\u2013203 (2006)","journal-title":"Ann. Rev. Control"},{"key":"21_CR15","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1016\/j.imavis.2017.01.010","volume":"60","author":"S Herath","year":"2017","unstructured":"Herath, S., Harandi, M., Porikli, F.: Going deeper into action recognition: a survey. Image Vis. Comput. 60, 4\u201321 (2017)","journal-title":"Image Vis. Comput."},{"key":"21_CR16","doi-asserted-by":"publisher","first-page":"20","DOI":"10.2352\/ISSN.2470-1173.2017.10.IMAWM-162","volume":"10","author":"M Hssayeni","year":"2017","unstructured":"Hssayeni, M., Saxena, S., Ptucha, R., Savakis, A.: Distracted driver detection: deep learning vs handcrafted features. Electron. Imaging 10, 20\u201326 (2017)","journal-title":"Electron. Imaging"},{"doi-asserted-by":"crossref","unstructured":"Huang, J., et al.: Speed\/accuracy trade-offs for modern convolutional object detectors. In: IEEE CVPR, pp. 3296\u20133297 (2017)","key":"21_CR17","DOI":"10.1109\/CVPR.2017.351"},{"unstructured":"Jozefowicz, R., Zaremba, W., Sutskever, I.: An empirical exploration of recurrent network architectures. In: ICML, pp. 2342\u20132350 (2015)","key":"21_CR18"},{"issue":"6","key":"21_CR19","doi-asserted-by":"publisher","first-page":"3017","DOI":"10.1109\/TITS.2015.2462084","volume":"16","author":"S Kaplan","year":"2015","unstructured":"Kaplan, S., Guvensan, M.A., Yavuz, A.G., Karalurt, Y.: Driver behavior analysis for safe driving: a survey. IEEE Trans. Int. Transp. Syst. 16(6), 3017\u20133032 (2015). \n                      https:\/\/doi.org\/10.1109\/TITS.2015.2462084","journal-title":"IEEE Trans. Int. Transp. Syst."},{"issue":"5","key":"21_CR20","doi-asserted-by":"publisher","first-page":"735","DOI":"10.1109\/THMS.2017.2674998","volume":"47","author":"HJ Kim","year":"2017","unstructured":"Kim, H.J., Yang, J.H.: Takeover requests in simulated partially autonomous vehicles considering human factors. IEEE Trans. Hum.-Mach. Syst. 47(5), 735\u2013740 (2017). \n                      https:\/\/doi.org\/10.1109\/THMS.2017.2674998","journal-title":"IEEE Trans. Hum.-Mach. Syst."},{"doi-asserted-by":"crossref","unstructured":"Kovashka, A., Grauman, K.: Learning a hierarchy of discriminative space-time neighborhood features for human action recognition. In: IEEE CVPR (2010)","key":"21_CR21","DOI":"10.1109\/CVPR.2010.5539881"},{"doi-asserted-by":"crossref","unstructured":"Laptev, I., Lindeberg, T.: Space-time interest points. In: ICCV, pp. 432\u2013439 (2003)","key":"21_CR22","DOI":"10.1109\/ICCV.2003.1238378"},{"doi-asserted-by":"crossref","unstructured":"Laptev, I., Marszalek, M., Schmid, C., Rozenfeld, B.: Learning realistic human actions from movies. In: CVPR (2008)","key":"21_CR23","DOI":"10.1109\/CVPR.2008.4587756"},{"doi-asserted-by":"crossref","unstructured":"Liu, J., Luo, J., Shah, M.: Recognizing realistic actions from videos \u201cin the wild\u201d. In: IEEE CVPR, pp. 1996\u20132003 (2009)","key":"21_CR24","DOI":"10.1109\/CVPR.2009.5206744"},{"doi-asserted-by":"crossref","unstructured":"Luo, Z., Peng, B., Huang, D.A., Alahi, A., Fei-Fei, L.: Unsupervised learning of long-term motion dynamics for videos. arXiv preprint \n                      arXiv:1701.01821\n                      \n                    , vol. 2 (2017)","key":"21_CR25","DOI":"10.1109\/CVPR.2017.751"},{"key":"21_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"414","DOI":"10.1007\/978-3-319-46448-0_25","volume-title":"Computer Vision \u2013 ECCV 2016","author":"A Mallya","year":"2016","unstructured":"Mallya, A., Lazebnik, S.: Learning models for actions and person-object interactions with transfer to question answering. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 414\u2013428. Springer, Cham (2016). \n                      https:\/\/doi.org\/10.1007\/978-3-319-46448-0_25"},{"unstructured":"Ng, J.Y.H., Hausknecht, M., Vijayanarasimhan, S., Vinyals, O., Monga, R., Toderici, G.: Beyond short snippets: deep networks for video classification. In: CVPR (2015)","key":"21_CR27"},{"issue":"1","key":"21_CR28","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1109\/TIV.2016.2551553","volume":"1","author":"B Ranft","year":"2016","unstructured":"Ranft, B., Stiller, C.: The role of machine vision for intelligent vehicles. IEEE Trans. Int. Veh. 1(1), 8\u201319 (2016). \n                      https:\/\/doi.org\/10.1109\/TIV.2016.2551553","journal-title":"IEEE Trans. Int. Veh."},{"doi-asserted-by":"crossref","unstructured":"Razavian, A.S., Azizpour, H., Sullivan, J., Carlsson, S.: CNN features off-the-shelf: an astounding baseline for recognition. In: IEEE CVPRW, pp. 512\u2013519 (2014)","key":"21_CR29","DOI":"10.1109\/CVPRW.2014.131"},{"doi-asserted-by":"crossref","unstructured":"Rohrbach, M., Amin, S., Andriluka, M., Schiele, B.: A database for fine grained activity detection of cooking activities. In: IEEE CVPR, pp. 1194\u20131201, June 2012","key":"21_CR30","DOI":"10.1109\/CVPR.2012.6247801"},{"issue":"3","key":"21_CR31","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. IJCV 115(3), 211\u2013252 (2015)","journal-title":"IJCV"},{"doi-asserted-by":"crossref","unstructured":"Ryoo, M.S., Aggarwal, J.K.: Spatio-temporal relationship match: video structure comparison for recognition of complex human activities. In: ICCV (2009)","key":"21_CR32","DOI":"10.1109\/ICCV.2009.5459361"},{"doi-asserted-by":"crossref","unstructured":"Ryoo, M.S., Rothrock, B., Matthies, L.H.: Pooled motion features for first-person videos. In: IEEE CVPR (2014)","key":"21_CR33","DOI":"10.1109\/CVPR.2015.7298691"},{"unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint \n                      arXiv:1409.1556\n                      \n                     (2014)","key":"21_CR34"},{"doi-asserted-by":"crossref","unstructured":"Singh, B., Marks, T.K., Jones, M., Tuzel, O., Shao, M.: A multi-stream bi-directional recurrent neural network for fine-grained action detection. In: IEEE CVPR, pp. 1961\u20131970 (2016)","key":"21_CR35","DOI":"10.1109\/CVPR.2016.216"},{"unstructured":"Singh, D.: Using convolutional neural networks to perform classification on state farm insurance driver images. Technical report. Stanford University, Stanford, CA (2016)","key":"21_CR36"},{"issue":"2","key":"21_CR37","first-page":"26","volume":"4","author":"T Tieleman","year":"2012","unstructured":"Tieleman, T., Hinton, G.: Lecture 65-rmsprop: divide the gradient by a running average of its recent magnitude. COURSERA: Neural Networks for Mach. Learn. 4(2), 26\u201331 (2012)","journal-title":"COURSERA: Neural Networks for Mach. Learn."},{"issue":"1","key":"21_CR38","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1109\/TITS.2006.889442","volume":"8","author":"MM Trivedi","year":"2007","unstructured":"Trivedi, M.M., Gandhi, T., McCall, J.: Looking-in and looking-out of a vehicle: computer-vision-based enhanced vehicle safety. IEEE Trans. Int. Transp. Syst. 8(1), 108\u2013120 (2007). \n                      https:\/\/doi.org\/10.1109\/TITS.2006.889442","journal-title":"IEEE Trans. Int. Transp. Syst."},{"issue":"1","key":"21_CR39","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1007\/s11263-012-0594-8","volume":"103","author":"H Wang","year":"2013","unstructured":"Wang, H., Kl\u00e4ser, A., Schmid, C., Liu, C.L.: Dense trajectories and motion boundary descriptors for action recognition. IJCV 103(1), 60\u201379 (2013)","journal-title":"IJCV"},{"doi-asserted-by":"crossref","unstructured":"Wang, L., Qiao, Y., Tang, X.: Action recognition with trajectory-pooled deep-convolutional descriptors. In: IEEE CVPR (2015)","key":"21_CR40","DOI":"10.1109\/CVPR.2015.7299059"},{"unstructured":"Wu, Z., Jiang, Y.G., Wang, X., Ye, H., Xue, X., Wang, J.: Fusing multi-stream deep networks for video classification. arXiv preprint \n                      arXiv:1509.06086\n                      \n                     (2015)","key":"21_CR41"},{"unstructured":"Xingjian, S., Chen, Z., Wang, H., Yeung, D.Y., Wong, W.K., Woo, W.C.: Convolutional LSTM network: a machine learning approach for precipitation nowcasting. In: Advances in NIPS, pp. 802\u2013810 (2015)","key":"21_CR42"},{"unstructured":"Yosinski, J., Clune, J., Bengio, Y., Lipson, H.: How transferable are features in deep neural networks? In: NIPS, pp. 3320\u20133328 (2014)","key":"21_CR43"},{"doi-asserted-by":"crossref","unstructured":"Yue-Hei Ng, J., Hausknecht, M., Vijayanarasimhan, S., Vinyals, O., Monga, R., Toderici, G.: Beyond short snippets: deep networks for video classification. In: IEEE CVPR, pp. 4694\u20134702 (2015)","key":"21_CR44","DOI":"10.1109\/CVPR.2015.7299101"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-12939-2_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,20]],"date-time":"2019-05-20T07:01:33Z","timestamp":1558335693000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-12939-2_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030129385","9783030129392"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-12939-2_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"14 February 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"GCPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"German Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Stuttgart","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":"9 October 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 October 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"40","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"dagm2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/gcprvmv2018.vis.uni-stuttgart.de\/","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"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"118","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"48","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"41% - 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"}},{"value":"2.92","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"6.27","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}}]}}