{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T16:36:26Z","timestamp":1778085386269,"version":"3.51.4"},"publisher-location":"Cham","reference-count":44,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319464923","type":"print"},{"value":"9783319464930","type":"electronic"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"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":[[2016]]},"DOI":"10.1007\/978-3-319-46493-0_45","type":"book-chapter","created":{"date-parts":[[2016,9,16]],"date-time":"2016-09-16T14:59:53Z","timestamp":1474037993000},"page":"744-759","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":203,"title":["Multi-region Two-Stream R-CNN for Action Detection"],"prefix":"10.1007","author":[{"given":"Xiaojiang","family":"Peng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cordelia","family":"Schmid","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,9,17]]},"reference":[{"key":"45_CR1","doi-asserted-by":"crossref","unstructured":"Wang, H., Schmid, C.: Action recognition with improved trajectories. In: ICCV, pp. 3551\u20133558 (2013)","DOI":"10.1109\/ICCV.2013.441"},{"key":"45_CR2","doi-asserted-by":"crossref","unstructured":"Jain, A., Gupta, A., Rodriguez, M., Davis, L.: Representing videos using mid-level discriminative patches. In: CVPR, pp. 2571\u20132578 (2013)","DOI":"10.1109\/CVPR.2013.332"},{"key":"45_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"581","DOI":"10.1007\/978-3-319-10602-1_38","volume-title":"Computer Vision \u2013 ECCV 2014","author":"X Peng","year":"2014","unstructured":"Peng, X., Zou, C., Qiao, Y., Peng, Q.: Action recognition with stacked fisher vectors. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014, Part V. LNCS, vol. 8693, pp. 581\u2013595. Springer, Heidelberg (2014)"},{"key":"45_CR4","doi-asserted-by":"crossref","unstructured":"Wang, L., Qiao, Y., Tang, X.: Action recognition with trajectory-pooled deep-convolutional descriptors. In: CVPR, pp. 4305\u20134314 (2015)","DOI":"10.1109\/CVPR.2015.7299059"},{"key":"45_CR5","doi-asserted-by":"crossref","unstructured":"Tian, Y., Sukthankar, R., Shah, M.: Spatiotemporal deformable part models for action detection. In: CVPR, pp. 2642\u20132649 (2013)","DOI":"10.1109\/CVPR.2013.341"},{"key":"45_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"565","DOI":"10.1007\/978-3-319-10602-1_37","volume-title":"Computer Vision \u2013 ECCV 2014","author":"L Wang","year":"2014","unstructured":"Wang, L., Qiao, Y., Tang, X.: Video action detection with relational dynamic-poselets. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014, Part V. LNCS, vol. 8693, pp. 565\u2013580. Springer, Heidelberg (2014)"},{"key":"45_CR7","doi-asserted-by":"crossref","unstructured":"Gkioxari, G., Malik, J.: Finding action tubes. In: CVPR, pp. 759\u2013768 (2015)","DOI":"10.1109\/CVPR.2015.7298676"},{"key":"45_CR8","doi-asserted-by":"crossref","unstructured":"Weinzaepfel, P., Harchaoui, Z., Schmid, C.: Learning to track for spatio-temporal action localization. In: ICCV, pp. 3164\u20133172 (2015)","DOI":"10.1109\/ICCV.2015.362"},{"issue":"11","key":"45_CR9","doi-asserted-by":"publisher","first-page":"2782","DOI":"10.1109\/TPAMI.2013.65","volume":"35","author":"A Gaidon","year":"2013","unstructured":"Gaidon, A., Harchaoui, Z., Schmid, C.: Temporal localization of actions with actoms. PAMI 35(11), 2782\u20132795 (2013)","journal-title":"PAMI"},{"key":"45_CR10","doi-asserted-by":"crossref","unstructured":"Oneata, D., Verbeek, J., Schmid, C.: Efficient action localization with approximately normalized Fisher vectors. In: CVPR, pp. 2545\u20132552 (2014)","DOI":"10.1109\/CVPR.2014.326"},{"key":"45_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"459","DOI":"10.1007\/978-3-319-16178-5_32","volume-title":"Computer Vision - ECCV 2014 Workshops","author":"S Escalera","year":"2015","unstructured":"Escalera, S., et al.: ChaLearn looking at people challenge 2014: dataset and results. In: Agapito, L., Bronstein, M.M., Rother, C. (eds.) ECCV 2014. LNCS, vol. 8925, pp. 459\u2013473. Springer, Heidelberg (2015). doi: 10.1007\/978-3-319-16178-5_32"},{"key":"45_CR12","doi-asserted-by":"crossref","unstructured":"Felzenszwalb, P., McAllester, D., Ramanan, D.: A discriminatively trained, multiscale, deformable part model. In: CVPR, pp. 1\u20138 (2008)","DOI":"10.1109\/CVPR.2008.4587597"},{"key":"45_CR13","doi-asserted-by":"crossref","unstructured":"Bourdev, L., Malik, J.: Poselets: body part detectors trained using 3D human pose annotations. In: ICCV, pp. 1365\u20131372 (2009)","DOI":"10.1109\/ICCV.2009.5459303"},{"key":"45_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"391","DOI":"10.1007\/978-3-319-10602-1_26","volume-title":"Computer Vision \u2013 ECCV 2014","author":"CL Zitnick","year":"2014","unstructured":"Zitnick, C.L., Doll\u00e1r, P.: Edge boxes: locating object proposals from edges. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014, Part V. LNCS, vol. 8693, pp. 391\u2013405. Springer, Heidelberg (2014)"},{"key":"45_CR15","doi-asserted-by":"crossref","unstructured":"Gkioxari, G., Girshick, R., Malik, J.: Contextual action recognition with R*CNN. In: ICCV, pp. 1080\u20131088 (2015)","DOI":"10.1109\/ICCV.2015.129"},{"key":"45_CR16","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: CVPR, pp. 580\u2013587 (2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"45_CR17","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NIPS, pp. 91\u201399 (2015)"},{"key":"45_CR18","doi-asserted-by":"crossref","unstructured":"Gidaris, S., Komodakis, N.: Object detection via a multi-region and semantic segmentation-aware CNN model. In: ICCV, pp. 1134\u20131142 (2015)","DOI":"10.1109\/ICCV.2015.135"},{"issue":"2","key":"45_CR19","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1007\/s11263-013-0620-5","volume":"104","author":"JR Uijlings","year":"2013","unstructured":"Uijlings, J.R., van de Sande, K.E., Gevers, T., Smeulders, A.W.: Selective search for object recognition. IJCV 104(2), 154\u2013171 (2013)","journal-title":"IJCV"},{"key":"45_CR20","doi-asserted-by":"crossref","unstructured":"Jhuang, H., Gall, J., Zuffi, S., Schmid, C., Black, M.: Towards understanding action recognition. In: ICCV, pp. 3192\u20133199 (2013)","DOI":"10.1109\/ICCV.2013.396"},{"key":"45_CR21","doi-asserted-by":"crossref","unstructured":"Ch\u00e9ron, G., Laptev, I., Schmid, C.: P-CNN: pose-based CNN features for action recognition. In: ICCV, pp. 3218\u20133226 (2015)","DOI":"10.1109\/ICCV.2015.368"},{"key":"45_CR22","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: NIPS, pp. 568\u2013576 (2014)"},{"issue":"3","key":"45_CR23","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1145\/1922649.1922653","volume":"43","author":"JK Aggarwal","year":"2011","unstructured":"Aggarwal, J.K., Ryoo, M.S.: Human activity analysis: a review. ACM Comput. Surv. (CSUR) 43(3), 16 (2011)","journal-title":"ACM Comput. Surv. (CSUR)"},{"issue":"7553","key":"45_CR24","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436\u2013444 (2015)","journal-title":"Nature"},{"key":"45_CR25","doi-asserted-by":"crossref","unstructured":"Sivic, J., Zisserman, A.: Video Google: a text retrieval approach to object matching in videos. In: ICCV, pp. 1470\u20131477 (2003)","DOI":"10.1109\/ICCV.2003.1238663"},{"key":"45_CR26","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., Fei-Fei, L.: Large-scale video classification with convolutional neural networks. In: CVPR, pp. 1725\u20131732 (2014)","DOI":"10.1109\/CVPR.2014.223"},{"key":"45_CR27","doi-asserted-by":"crossref","unstructured":"Sun, L., Jia, K., Chan, T.H., Fang, Y., Wang, G., Yan, S.: DL-SFA: deeply-learned slow feature analysis for action recognition. In: CVPR, pp. 2625\u20132632 (2014)","DOI":"10.1109\/CVPR.2014.336"},{"key":"45_CR28","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1007\/978-3-642-15561-1_11","volume-title":"Computer Vision \u2013 ECCV 2010","author":"F Perronnin","year":"2010","unstructured":"Perronnin, F., S\u00e1nchez, J., Mensink, T.: Improving the fisher kernel for large-scale image classification. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part IV. LNCS, vol. 6314, pp. 143\u2013156. Springer, Heidelberg (2010)"},{"key":"45_CR29","doi-asserted-by":"crossref","unstructured":"Laptev, I., P\u00e9rez, P.: Retrieving actions in movies. In: ICCV 2007, pp. 1\u20138 (2007)","DOI":"10.1109\/ICCV.2007.4409105"},{"key":"45_CR30","doi-asserted-by":"crossref","unstructured":"Yuan, J., Liu, Z., Wu, Y.: Discriminative subvolume search for efficient action detection. In: CVPR, pp. 2442\u20132449 (2009)","DOI":"10.1109\/CVPR.2009.5206671"},{"key":"45_CR31","doi-asserted-by":"crossref","unstructured":"Rodriguez, M.D., Ahmed, J., Shah, M.: Action MACH a spatio-temporal maximum average correlation height filter for action recognition. In: CVPR, pp. 1\u20138 (2008)","DOI":"10.1109\/CVPR.2008.4587727"},{"key":"45_CR32","doi-asserted-by":"crossref","unstructured":"Derpanis, K.G., Sizintsev, M., Cannons, K., Wildes, R.P.: Efficient action spotting based on a spacetime oriented structure representation. In: CVPR, pp. 1990\u20131997 (2010)","DOI":"10.1109\/CVPR.2010.5539874"},{"issue":"2","key":"45_CR33","doi-asserted-by":"publisher","first-page":"404","DOI":"10.1109\/TPAMI.2013.137","volume":"36","author":"D Tran","year":"2014","unstructured":"Tran, D., Yuan, J., Forsyth, D.: Video event detection: from subvolume localization to spatiotemporal path search. PAMI 36(2), 404\u2013416 (2014)","journal-title":"PAMI"},{"key":"45_CR34","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: NIPS, pp. 1097\u20131105 (2012)"},{"issue":"9","key":"45_CR35","doi-asserted-by":"publisher","first-page":"1904","DOI":"10.1109\/TPAMI.2015.2389824","volume":"37","author":"K He","year":"2015","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Spatial pyramid pooling in deep convolutional networks for visual recognition. PAMI 37(9), 1904\u20131916 (2015)","journal-title":"PAMI"},{"key":"45_CR36","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: ICCV, pp. 1440\u20131448 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"issue":"2","key":"45_CR37","doi-asserted-by":"publisher","first-page":"260","DOI":"10.1109\/TIT.1967.1054010","volume":"13","author":"AJ Viterbi","year":"1967","unstructured":"Viterbi, A.J.: Error bounds for convolutional codes and an asymptotically optimum decoding algorithm. Inf. Theory 13(2), 260\u2013269 (1967)","journal-title":"Inf. Theory"},{"key":"45_CR38","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556 (2014)"},{"issue":"3","key":"45_CR39","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al.: ImageNet large scale visual recognition challenge. IJCV 115(3), 211\u2013252 (2015)","journal-title":"IJCV"},{"key":"45_CR40","doi-asserted-by":"crossref","unstructured":"Dai, J., He, K., Sun, J.: Convolutional feature masking for joint object and stuff segmentation. In: CVPR, pp. 3992\u20134000 (2015)","DOI":"10.1109\/CVPR.2015.7299025"},{"issue":"9","key":"45_CR41","doi-asserted-by":"publisher","first-page":"865","DOI":"10.1145\/358234.381162","volume":"27","author":"J Bentley","year":"1984","unstructured":"Bentley, J.: Programming pearls: algorithm design techniques. Commun. ACM 27(9), 865\u2013873 (1984)","journal-title":"Commun. ACM"},{"key":"45_CR42","unstructured":"Soomro, K., Zamir, A.R., Shah, M.: UCF101: a dataset of 101 human actions classes from videos in the wild. arXiv:1212.0402 (2012)"},{"key":"45_CR43","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1007\/978-3-540-24673-2_3","volume-title":"Computer Vision - ECCV 2004","author":"T Brox","year":"2004","unstructured":"Brox, T., Bruhn, A., Papenberg, N., Weickert, J.: High accuracy optical flow estimation based on a theory for warping. In: Pajdla, T., Matas, J.G. (eds.) ECCV 2004. LNCS, vol. 3024, pp. 25\u201336. Springer, Heidelberg (2004)"},{"key":"45_CR44","doi-asserted-by":"crossref","unstructured":"Yu, G., Yuan, J.: Fast action proposals for human action detection and search. In: CVPR, pp. 1302\u20131311 (2015)","DOI":"10.1109\/CVPR.2015.7298735"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2016"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-46493-0_45","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,10]],"date-time":"2025-06-10T19:21:37Z","timestamp":1749583297000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-46493-0_45"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319464923","9783319464930"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-46493-0_45","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016]]},"assertion":[{"value":"17 September 2016","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":"Amsterdam","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"The Netherlands","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2016","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 October 2016","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 October 2016","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2016","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.eccv2016.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"}]}}