{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T19:46:17Z","timestamp":1775245577775,"version":"3.50.1"},"publisher-location":"Cham","reference-count":47,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030012182","type":"print"},{"value":"9783030012199","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\/978-3-030-01219-9_26","type":"book-chapter","created":{"date-parts":[[2018,10,6]],"date-time":"2018-10-06T10:23:51Z","timestamp":1538821431000},"page":"435-451","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":37,"title":["Part-Activated Deep Reinforcement Learning for Action Prediction"],"prefix":"10.1007","author":[{"given":"Lei","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiwen","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhanjie","family":"Song","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,10,7]]},"reference":[{"key":"26_CR1","doi-asserted-by":"crossref","unstructured":"Caicedo, J.C., Lazebnik, S.: Active object localization with deep reinforcement learning. In: ICCV, pp. 2488\u20132496 (2015)","DOI":"10.1109\/ICCV.2015.286"},{"key":"26_CR2","doi-asserted-by":"crossref","unstructured":"Cao, Y., et al.: Recognize human activities from partially observed videos. In: CVPR, pp. 2658\u20132665 (2013)","DOI":"10.1109\/CVPR.2013.343"},{"key":"26_CR3","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: CVPR, pp. 7291\u20137299 (2017)","DOI":"10.1109\/CVPR.2017.143"},{"key":"26_CR4","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo Vadis, action recognition? A new model and the kinetics dataset. In: CVPR, pp. 6299\u20136308 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"26_CR5","doi-asserted-by":"crossref","unstructured":"Du, Y., Wang, W., Wang, L.: Hierarchical recurrent neural network for skeleton based action recognition. In: CVPR, pp. 1110\u20131118 (2015)","DOI":"10.1109\/CVPR.2015.7298714"},{"key":"26_CR6","doi-asserted-by":"crossref","unstructured":"Goodrich, B., Arel, I.: Reinforcement learning based visual attention with application to face detection. In: CVPRW, pp. 19\u201324 (2012)","DOI":"10.1109\/CVPRW.2012.6239177"},{"key":"26_CR7","doi-asserted-by":"crossref","unstructured":"Hinami, R., Mei, T., Satoh, S.: Joint detection and recounting of abnormal events by learning deep generic knowledge. In: ICCV, pp. 3619\u20133627 (2017)","DOI":"10.1109\/ICCV.2017.391"},{"key":"26_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"280","DOI":"10.1007\/978-3-319-46448-0_17","volume-title":"Computer Vision \u2013 ECCV 2016","author":"J-F Hu","year":"2016","unstructured":"Hu, J.-F., Zheng, W.-S., Ma, L., Wang, G., Lai, J.: Real-time RGB-D activity prediction by soft regression. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 280\u2013296. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_17"},{"key":"26_CR9","doi-asserted-by":"crossref","unstructured":"Huang, C., Lucey, S., Ramanan, D.: Learning policies for adaptive tracking with deep feature cascades. In: ICCV, pp. 105\u2013114 (2017)","DOI":"10.1109\/ICCV.2017.21"},{"key":"26_CR10","unstructured":"Jie, Z., Liang, X., Feng, J., Jin, X., Lu, W., Yan, S.: Tree-structured reinforcement learning for sequential object localization. In: NIPS, pp. 127\u2013135 (2016)"},{"key":"26_CR11","unstructured":"Karayev, S., Baumgartner, T., Fritz, M., Darrell, T.: Timely object recognition. In: NIPS, pp. 890\u2013898 (2012)"},{"key":"26_CR12","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2015)"},{"key":"26_CR13","doi-asserted-by":"crossref","unstructured":"Kong, X., Xin, B., Wang, Y., Hua, G.: Collaborative deep reinforcement learning for joint object search. In: CVPR, pp. 1695\u20131704 (2017)","DOI":"10.1109\/CVPR.2017.748"},{"issue":"9","key":"26_CR14","doi-asserted-by":"publisher","first-page":"1844","DOI":"10.1109\/TPAMI.2015.2491928","volume":"38","author":"Y Kong","year":"2016","unstructured":"Kong, Y., Fu, Y.: Max-margin action prediction machine. TPAMI 38(9), 1844\u20131858 (2016)","journal-title":"TPAMI"},{"key":"26_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"300","DOI":"10.1007\/978-3-642-33718-5_22","volume-title":"Computer Vision \u2013 ECCV 2012","author":"Y Kong","year":"2012","unstructured":"Kong, Y., Jia, Y., Fu, Y.: Learning human interaction by interactive phrases. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7572, pp. 300\u2013313. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33718-5_22"},{"key":"26_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"596","DOI":"10.1007\/978-3-319-10602-1_39","volume-title":"Computer Vision \u2013 ECCV 2014","author":"Y Kong","year":"2014","unstructured":"Kong, Y., Kit, D., Fu, Y.: A discriminative model with multiple temporal scales for action prediction. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 596\u2013611. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_39"},{"key":"26_CR17","doi-asserted-by":"crossref","unstructured":"Kong, Y., Tao, Z., Fu, Y.: Deep sequential context networks for action prediction. In: CVPR, pp. 1473\u20131481 (2017)","DOI":"10.1109\/CVPR.2017.390"},{"key":"26_CR18","doi-asserted-by":"crossref","unstructured":"Krull, A., Brachmann, E., Nowozin, S., Michel, F., Shotton, J., Rother, C.: Poseagent: budget-constrained 6D object pose estimation via reinforcement learning. In: CVPR, pp. 6702\u20136710 (2017)","DOI":"10.1109\/CVPR.2017.275"},{"key":"26_CR19","first-page":"2272","volume":"27","author":"S Lai","year":"2017","unstructured":"Lai, S., Zheng, W.S., Hu, J.F., Zhang, J.: Global-local temporal saliency action prediction. TIP 27, 2272\u20132285 (2017)","journal-title":"TIP"},{"key":"26_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"689","DOI":"10.1007\/978-3-319-10578-9_45","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T Lan","year":"2014","unstructured":"Lan, T., Chen, T.-C., Savarese, S.: A hierarchical representation for future action prediction. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8691, pp. 689\u2013704. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10578-9_45"},{"key":"26_CR21","doi-asserted-by":"crossref","unstructured":"Liang, X., Lee, L., Dai, W., Xing, E.P.: Dual motion GAN for future-flow embedded video prediction. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.194"},{"key":"26_CR22","doi-asserted-by":"crossref","unstructured":"Liang, X., Lee, L., Xing, E.P.: Deep variation-structured reinforcement learning for visual relationship and attribute detection. In: CVPR, pp. 848\u2013857 (2017)","DOI":"10.1109\/CVPR.2017.469"},{"issue":"7553","key":"26_CR23","doi-asserted-by":"publisher","first-page":"445","DOI":"10.1038\/nature14540","volume":"521","author":"ML Littman","year":"2015","unstructured":"Littman, M.L.: Reinforcement learning improves behaviour from evaluative feedback. Nature 521(7553), 445\u2013451 (2015)","journal-title":"Nature"},{"key":"26_CR24","doi-asserted-by":"crossref","unstructured":"Ma, S., Sigal, L., Sclaroff, S.: Learning activity progression in LSTMs for activity detection and early detection. In: CVPR, pp. 1942\u20131950 (2016)","DOI":"10.1109\/CVPR.2016.214"},{"key":"26_CR25","doi-asserted-by":"crossref","unstructured":"Mahmud, T., Hasan, M., Roy-Chowdhury, A.K.: Joint prediction of activity labels and starting times in untrimmed videos. In: ICCV, pp. 5773\u20135782 (2017)","DOI":"10.1109\/ICCV.2017.616"},{"key":"26_CR26","doi-asserted-by":"crossref","unstructured":"Martinez, J., Black, M.J., Romero, J.: On human motion prediction using recurrent neural networks. In: CVPR, pp. 2891\u20132900 (2017)","DOI":"10.1109\/CVPR.2017.497"},{"key":"26_CR27","doi-asserted-by":"crossref","unstructured":"Mathe, S., Pirinen, A., Sminchisescu, C.: Reinforcement learning for visual object detection. In: CVPR, pp. 2894\u20132902 (2016)","DOI":"10.1109\/CVPR.2016.316"},{"issue":"7540","key":"26_CR28","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529\u2013533 (2015)","journal-title":"Nature"},{"key":"26_CR29","doi-asserted-by":"crossref","unstructured":"Qi, S., Huang, S., Wei, P., Zhu, S.C.: Predicting human activities using stochastic grammar. In: ICCV, pp. 1164\u20131172 (2017)","DOI":"10.1109\/ICCV.2017.132"},{"key":"26_CR30","doi-asserted-by":"crossref","unstructured":"Ren, Z., Wang, X., Zhang, N., Lv, X., Li, L.J.: Deep reinforcement learning-based image captioning with embedding reward. In: CVPR, pp. 290\u2013298 (2017)","DOI":"10.1109\/CVPR.2017.128"},{"key":"26_CR31","doi-asserted-by":"crossref","unstructured":"Ryoo, M.S.: Human activity prediction: early recognition of ongoing activities from streaming videos. In: ICCV, pp. 1036\u20131043 (2011)","DOI":"10.1109\/ICCV.2011.6126349"},{"key":"26_CR32","unstructured":"Ryoo, M.S., Aggarwal, J.: UT-interaction dataset, ICPR contest on semantic description of human activities (SDHA). In: ICPR, vol. 2, p. 4 (2010)"},{"key":"26_CR33","doi-asserted-by":"crossref","unstructured":"Ryoo, M.S., Matthies, L.: First-person activity recognition: what are they doing to me? In: CVPR, pp. 2730\u20132737 (2013)","DOI":"10.1109\/CVPR.2013.352"},{"issue":"1","key":"26_CR34","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1007\/s11263-010-0384-0","volume":"93","author":"Q Shi","year":"2011","unstructured":"Shi, Q., Cheng, L., Wang, L., Smola, A.: Human action segmentation and recognition using discriminative semi-markov models. IJCV 93(1), 22\u201332 (2011)","journal-title":"IJCV"},{"key":"26_CR35","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: NIPS, pp. 568\u2013576 (2014)"},{"key":"26_CR36","doi-asserted-by":"crossref","unstructured":"Singh, G., Saha, S., Sapienza, M., Torr, P.H.S., Cuzzolin, F.: Online real-time multiple spatiotemporal action localisation and prediction. In: ICCV, pp. 3637\u20133646 (2017)","DOI":"10.1109\/ICCV.2017.393"},{"key":"26_CR37","unstructured":"Soomro, K., Zamir, A.R., Shah, M.: UCF101: a dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:1212.0402 (2012)"},{"key":"26_CR38","doi-asserted-by":"crossref","unstructured":"Supancic III, J.S., Ramanan, D.: Tracking as online decision-making: learning a policy from streaming videos with reinforcement learning. In: ICCV, pp. 322\u2013331 (2017)","DOI":"10.1109\/ICCV.2017.43"},{"key":"26_CR39","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3D convolutional networks. In: ICCV, pp. 4489\u20134497 (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"26_CR40","doi-asserted-by":"crossref","unstructured":"Tudor Ionescu, R., Smeureanu, S., Alexe, B., Popescu, M.: Unmasking the abnormal events in video. In: ICCV, pp. 2895\u20132903 (2017)","DOI":"10.1109\/ICCV.2017.315"},{"key":"26_CR41","doi-asserted-by":"crossref","unstructured":"Wang, J., Liu, Z., Wu, Y., Yuan, J.: Mining actionlet ensemble for action recognition with depth cameras. In: CVPR, pp. 1290\u20131297 (2012)","DOI":"10.1109\/CVPR.2012.6247813"},{"key":"26_CR42","doi-asserted-by":"crossref","unstructured":"Wang, L., Xiong, Y., Lin, D., Van Gool, L.: Untrimmednets for weakly supervised action recognition and detection. In: CVPR, pp. 4325\u20134334 (2017)","DOI":"10.1109\/CVPR.2017.678"},{"key":"26_CR43","doi-asserted-by":"crossref","unstructured":"Wei, S.E., Ramakrishna, V., Kanade, T., Sheikh, Y.: Convolutional pose machines. In: CVPR, pp. 4724\u20134732 (2016)","DOI":"10.1109\/CVPR.2016.511"},{"key":"26_CR44","doi-asserted-by":"crossref","unstructured":"Xu, Z., Qing, L., Miao, J.: Activity auto-completion: predicting human activities from partial videos. In: ICCV, pp. 3191\u20133199 (2015)","DOI":"10.1109\/ICCV.2015.365"},{"key":"26_CR45","unstructured":"Yoo, Y., Yun, S., Choi, J., Yun, K., Choi, J.Y.: Action-decision networks for visual tracking with deep reinforcement learning. In: CVPR, pp. 2711\u20132720 (2017)"},{"key":"26_CR46","doi-asserted-by":"crossref","unstructured":"Zaki, H.F.M., Shafait, F., Mian, A.: Modeling sub-event dynamics in first-person action recognition. In: CVPR, pp. 7253\u20137262 (2017)","DOI":"10.1109\/CVPR.2017.176"},{"key":"26_CR47","doi-asserted-by":"crossref","unstructured":"Zhuang, B., Liu, L., Shen, C., Reid, I.: Towards context-aware interaction recognition for visual relationship detection. In: ICCV, pp. 589\u2013598 (2017)","DOI":"10.1109\/ICCV.2017.71"}],"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\/978-3-030-01219-9_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T18:47:20Z","timestamp":1775242040000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01219-9_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012182","9783030012199"],"references-count":47,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01219-9_26","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":"7 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"}]}}