{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T08:49:11Z","timestamp":1765356551289,"version":"3.40.3"},"publisher-location":"Cham","reference-count":42,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030208691"},{"type":"electronic","value":"9783030208707"}],"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\/978-3-030-20870-7_45","type":"book-chapter","created":{"date-parts":[[2019,5,24]],"date-time":"2019-05-24T16:14:21Z","timestamp":1558714461000},"page":"729-745","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Global Regularizer and Temporal-Aware Cross-Entropy for Skeleton-Based Early Action Recognition"],"prefix":"10.1007","author":[{"given":"Qiuhong","family":"Ke","sequence":"first","affiliation":[]},{"given":"Jun","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Mohammed","family":"Bennamoun","sequence":"additional","affiliation":[]},{"given":"Hossein","family":"Rahmani","sequence":"additional","affiliation":[]},{"given":"Senjian","family":"An","sequence":"additional","affiliation":[]},{"given":"Ferdous","family":"Sohel","sequence":"additional","affiliation":[]},{"given":"Farid","family":"Boussaid","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,5,25]]},"reference":[{"key":"45_CR1","doi-asserted-by":"crossref","unstructured":"Ryoo, M.S.: Human activity prediction: early recognition of ongoing activities from streaming videos. In: ICCV, pp. 1036\u20131043. IEEE (2011)","DOI":"10.1109\/ICCV.2011.6126349"},{"key":"45_CR2","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":"45_CR3","doi-asserted-by":"crossref","unstructured":"Ma, Q., Shen, L., Chen, E., Tian, S., Wang, J., Cottrell, G.W.: WALKING WALKing walking: action recognition from action echoes. In: IJCAI, pp. 2457\u20132463. AAAI Press (2017)","DOI":"10.24963\/ijcai.2017\/342"},{"key":"45_CR4","unstructured":"Wang, J., Liu, Z., Wu, Y., Yuan, J.: Mining actionlet ensemble for action recognition with depth cameras. In: CVPR, pp. 1290\u20131297. IEEE (2012)"},{"key":"45_CR5","doi-asserted-by":"crossref","unstructured":"Vemulapalli, R., Arrate, F., Chellappa, R.: Human action recognition by representing 3D skeletons as points in a lie group. In: CVPR, pp. 588\u2013595. IEEE (2014)","DOI":"10.1109\/CVPR.2014.82"},{"key":"45_CR6","unstructured":"Du, Y., Wang, W., Wang, L.: Hierarchical recurrent neural network for skeleton based action recognition. In: CVPR, pp. 1110\u20131118. IEEE (2015)"},{"key":"45_CR7","doi-asserted-by":"crossref","unstructured":"Shahroudy, A., Liu, J., Ng, T.T., Wang, G.: NTU RGB+D: a large scale dataset for 3D human activity analysis. In: CVPR. IEEE (2016)","DOI":"10.1109\/CVPR.2016.115"},{"key":"45_CR8","doi-asserted-by":"crossref","unstructured":"Zhu, W., et al.: Co-occurrence feature learning for skeleton based action recognition using regularized deep LSTM networks. In: AAAI, vol. 2, p. 8. AAAI Press (2016)","DOI":"10.1609\/aaai.v30i1.10451"},{"key":"45_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"816","DOI":"10.1007\/978-3-319-46487-9_50","volume-title":"Computer Vision \u2013 ECCV 2016","author":"J Liu","year":"2016","unstructured":"Liu, J., Shahroudy, A., Xu, D., Wang, G.: Spatio-temporal LSTM with trust gates for 3D human action recognition. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9907, pp. 816\u2013833. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46487-9_50"},{"key":"45_CR10","doi-asserted-by":"crossref","unstructured":"Ke, Q., Bennamoun, M., An, S., Boussaid, F., Sohel, F.: A new representation of skeleton sequences for 3D action recognition. In: CVPR. IEEE (2017)","DOI":"10.1109\/CVPR.2017.486"},{"key":"45_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"392","DOI":"10.1007\/978-3-642-15552-9_29","volume-title":"Computer Vision \u2013 ECCV 2010","author":"JC Niebles","year":"2010","unstructured":"Niebles, J.C., Chen, C.-W., Fei-Fei, L.: Modeling temporal structure of decomposable motion segments for activity classification. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6312, pp. 392\u2013405. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-15552-9_29"},{"key":"45_CR12","doi-asserted-by":"publisher","first-page":"810","DOI":"10.1109\/TIP.2013.2295753","volume":"23","author":"L Wang","year":"2014","unstructured":"Wang, L., Qiao, Y., Tang, X.: Latent hierarchical model of temporal structure for complex activity classification. IEEE Transa. Image Process. 23, 810\u2013822 (2014)","journal-title":"IEEE Transa. Image Process."},{"key":"45_CR13","doi-asserted-by":"crossref","unstructured":"Donahue, J., et al.: Long-term recurrent convolutional networks for visual recognition and description. In: CVPR, pp. 2625\u20132634. IEEE (2015)","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"45_CR14","unstructured":"Kong, Y., Fu, Y.: Human action recognition and prediction: a survey. arXiv preprint arXiv:1806.11230 (2018)"},{"key":"45_CR15","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. 5784\u20135793. IEEE (2017)","DOI":"10.1109\/ICCV.2017.616"},{"key":"45_CR16","doi-asserted-by":"crossref","unstructured":"B\u00fctepage, J., Black, M.J., Kragic, D., Kjellstr\u00f6m, H.: Deep representation learning for human motion prediction and classification. In: CVPR 2017. IEEE (2017)","DOI":"10.1109\/CVPR.2017.173"},{"key":"45_CR17","doi-asserted-by":"crossref","unstructured":"Ke, Q., Liu, J., Bennamoun, M., An, S., Sohel, F., Boussaid, F.: Chapter 5 - computer vision for human-machine interaction. In: Leo, M., Farinella, G.M., (eds.) Computer Vision for Assistive Healthcare, pp. 127\u2013145. Academic Press (2018)","DOI":"10.1016\/B978-0-12-813445-0.00005-8"},{"key":"45_CR18","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1016\/j.ins.2018.08.003","volume":"467","author":"C Tang","year":"2018","unstructured":"Tang, C., Li, W., Wang, P., Wang, L.: Online human action recognition based on incremental learning of weighted covariance descriptors. Inf. Sci. 467, 219\u2013237 (2018)","journal-title":"Inf. Sci."},{"key":"45_CR19","doi-asserted-by":"publisher","first-page":"2430","DOI":"10.1109\/TPAMI.2016.2533389","volume":"38","author":"H Rahmani","year":"2016","unstructured":"Rahmani, H., Mahmood, A., Huynh, D., Mian, A.: Histogram of oriented principal components for cross-view action recognition. PAMI 38, 2430\u20132443 (2016)","journal-title":"PAMI"},{"issue":"3","key":"45_CR20","doi-asserted-by":"publisher","first-page":"667","DOI":"10.1109\/TPAMI.2017.2691768","volume":"40","author":"H Rahmani","year":"2018","unstructured":"Rahmani, H., Mian, A., Shah, M.: Learning a deep model for human action recognition from novel viewpoints. PAMI 40(3), 667\u2013681 (2018)","journal-title":"PAMI"},{"key":"45_CR21","doi-asserted-by":"crossref","unstructured":"Rahmani, H., Bennamoun, M.: Learning action recognition model from depth and skeleton videos. In: ICCV. IEEE (2017)","DOI":"10.1109\/ICCV.2017.621"},{"key":"45_CR22","doi-asserted-by":"crossref","unstructured":"Rahmani, H., Mian, A.: 3D action recognition from novel viewpoints. In: CVPR, pp. 1506\u20131515. IEEE (2016)","DOI":"10.1109\/CVPR.2016.167"},{"key":"45_CR23","doi-asserted-by":"publisher","first-page":"118","DOI":"10.1016\/j.cviu.2018.04.007","volume":"171","author":"P Wang","year":"2018","unstructured":"Wang, P., Li, W., Ogunbona, P., Wan, J., Escalera, S.: RGB-D-based human motion recognition with deep learning: a survey. Comput. Vis. Image Underst. 171, 118\u2013139 (2018)","journal-title":"Comput. Vis. Image Underst."},{"key":"45_CR24","doi-asserted-by":"publisher","first-page":"731","DOI":"10.1109\/LSP.2017.2690339","volume":"24","author":"Q Ke","year":"2017","unstructured":"Ke, Q., An, S., Bennamoun, M., Sohel, F., Boussaid, F.: Skeletonnet: mining deep part features for 3-D action recognition. IEEE Sig. Process. Lett. 24, 731\u2013735 (2017)","journal-title":"IEEE Sig. Process. Lett."},{"key":"45_CR25","doi-asserted-by":"publisher","first-page":"2842","DOI":"10.1109\/TIP.2018.2812099","volume":"27","author":"Q Ke","year":"2018","unstructured":"Ke, Q., Bennamoun, M., An, S., Sohel, F., Boussaid, F.: Learning clip representations for skeleton-based 3D action recognition. IEEE Trans. Image Process. 27, 2842\u20132855 (2018)","journal-title":"IEEE Trans. Image Process."},{"key":"45_CR26","doi-asserted-by":"crossref","unstructured":"Liu, J., Wang, G., Hu, P., Duan, L.Y., Kot, A.C.: Global context-aware attention LSTM networks for 3D action recognition. In: CVPR, vol. 7. IEEE (2017)","DOI":"10.1109\/CVPR.2017.391"},{"key":"45_CR27","doi-asserted-by":"crossref","unstructured":"Ryoo, M.: Human activity prediction: early recognition of ongoing activities from streaming videos. In: ICCV, pp. 1036\u20131043. IEEE (2011)","DOI":"10.1109\/ICCV.2011.6126349"},{"key":"45_CR28","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":"45_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"403","DOI":"10.1007\/978-3-319-48881-3_28","volume-title":"Computer Vision \u2013 ECCV 2016 Workshops","author":"Q Ke","year":"2016","unstructured":"Ke, Q., Bennamoun, M., An, S., Boussaid, F., Sohel, F.: Human interaction prediction using deep temporal features. In: Hua, G., J\u00e9gou, H. (eds.) ECCV 2016. LNCS, vol. 9914, pp. 403\u2013414. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-48881-3_28"},{"key":"45_CR30","doi-asserted-by":"publisher","first-page":"1712","DOI":"10.1109\/TMM.2017.2778559","volume":"20","author":"Q Ke","year":"2017","unstructured":"Ke, Q., Bennamoun, M., An, S., Sohel, F., Boussaid, F.: Leveraging structural context models and ranking score fusion forhuman interaction prediction. IEEE Trans. Multimed. 20, 1712\u20131723 (2017)","journal-title":"IEEE Trans. Multimed."},{"key":"45_CR31","doi-asserted-by":"crossref","unstructured":"Jain, A., Singh, A., Koppula, H.S., Soh, S., Saxena, A.: Recurrent neural networks for driver activity anticipation via sensory-fusion architecture. In: ICRA, pp. 3118\u20133125. IEEE (2016)","DOI":"10.1109\/ICRA.2016.7487478"},{"key":"45_CR32","doi-asserted-by":"crossref","unstructured":"Aliakbarian, M.S., Saleh, F., Salzmann, M., Fernando, B., Petersson, L., Andersson, L.: Encouraging LSTMs to anticipate actions very early. In: ICCV. IEEE (2017)","DOI":"10.1109\/ICCV.2017.39"},{"key":"45_CR33","doi-asserted-by":"crossref","unstructured":"Farha, Y.A., Richard, A., Gall, J.: When will you do what? Anticipating temporal occurrences of activities. arXiv preprint arXiv:1804.00892 (2018)","DOI":"10.1109\/CVPR.2018.00560"},{"key":"45_CR34","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":"45_CR35","doi-asserted-by":"crossref","unstructured":"Liu, J., Shahroudy, A., Wang, G., Duan, L.Y., Kot, A.C.: SSNet: scale selection network for online 3D action prediction. In: CVPR, pp. 8349\u20138358. IEEE (2018)","DOI":"10.1109\/CVPR.2018.00871"},{"key":"45_CR36","doi-asserted-by":"crossref","unstructured":"Herath, S., Harandi, M., Porikli, F.: Learning an invariant hilbert space for domain adaptation. arXiv preprint arXiv:1611.08350 (2016)","DOI":"10.1109\/CVPR.2017.421"},{"key":"45_CR37","doi-asserted-by":"crossref","unstructured":"Hubert Tsai, Y.H., Yeh, Y.R., Frank Wang, Y.C.: Learning cross-domain landmarks for heterogeneous domain adaptation. In: CVPR, pp. 5081\u20135090. IEEE (2016)","DOI":"10.1109\/CVPR.2016.549"},{"key":"45_CR38","first-page":"3760","volume":"17","author":"M Baktashmotlagh","year":"2016","unstructured":"Baktashmotlagh, M., Harandi, M., Salzmann, M.: Distribution-matching embedding for visual domain adaptation. J. Mach. Learn. Res. 17, 3760\u20133789 (2016)","journal-title":"J. Mach. Learn. Res."},{"key":"45_CR39","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1109\/TNN.2010.2091281","volume":"22","author":"SJ Pan","year":"2011","unstructured":"Pan, S.J., Tsang, I.W., Kwok, J.T., Yang, Q.: Domain adaptation via transfer component analysis. IEEE Trans. Neural Netw. 22, 199\u2013210 (2011)","journal-title":"IEEE Trans. Neural Netw."},{"key":"45_CR40","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: NIPS, pp. 1097\u20131105 (2012)"},{"key":"45_CR41","unstructured":"CMU: CMU graphics lab motion capture database (2013). http:\/\/mocap.cs.cmu.edu\/"},{"key":"45_CR42","doi-asserted-by":"crossref","unstructured":"Hu, J.F., Zheng, W.S., Lai, J., Zhang, J.: Jointly learning heterogeneous features for RGB-D activity recognition. In: CVPR, pp. 5344\u20135352. IEEE (2015)","DOI":"10.1109\/CVPR.2015.7299172"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2018"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-20870-7_45","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,18]],"date-time":"2022-09-18T16:21:37Z","timestamp":1663518097000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-20870-7_45"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030208691","9783030208707"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-20870-7_45","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":"25 May 2019","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":"Perth, WA","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","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":"2 December 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 December 2018","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":"accv2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/accv2018.net\/","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":"979","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":"274","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":"28% - 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":"2.7","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}