{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T15:27:30Z","timestamp":1726068450411},"publisher-location":"Cham","reference-count":39,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030412982"},{"type":"electronic","value":"9783030412999"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":[[2020]]},"DOI":"10.1007\/978-3-030-41299-9_3","type":"book-chapter","created":{"date-parts":[[2020,2,22]],"date-time":"2020-02-22T04:02:51Z","timestamp":1582344171000},"page":"27-40","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Action Recognition in Untrimmed Videos with Composite Self-attention Two-Stream Framework"],"prefix":"10.1007","author":[{"given":"Dong","family":"Cao","sequence":"first","affiliation":[]},{"given":"Lisha","family":"Xu","sequence":"additional","affiliation":[]},{"given":"HaiBo","family":"Chen","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,2,23]]},"reference":[{"key":"3_CR1","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? A new model and the kinetics dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"3_CR2","doi-asserted-by":"crossref","unstructured":"Dosovitskiy, A., et al.: Flownet: learning optical flow with convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, ICCV (2015)","DOI":"10.1109\/ICCV.2015.316"},{"key":"3_CR3","doi-asserted-by":"crossref","unstructured":"Fan, L., Huang, W., Chuang G., Ermon, S., Gong, B., Huang, J.: End-to-end learning of motion representation for video understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR (2018)","DOI":"10.1109\/CVPR.2018.00630"},{"key":"3_CR4","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Pinz, A., Zisserman, A.: Convolutional two-stream network fusion for video action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR (2016)","DOI":"10.1109\/CVPR.2016.213"},{"key":"3_CR5","doi-asserted-by":"crossref","unstructured":"Gao, J., Zhu, T., Xu, C.: I know the relationships: zero-shot action recognition via two-stream graph convolutional networks and knowledge graphs. In: AAAI (2019)","DOI":"10.1609\/aaai.v33i01.33018303"},{"key":"3_CR6","unstructured":"Ng, J.Y.-H., Hausknecht, M., Vijayanarasimhan, S., Vinyals, O., Monga, R., Toderici, G.: Beyond short snippets: deepnetworks for video classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR (2015)"},{"key":"3_CR7","doi-asserted-by":"crossref","unstructured":"Jain, M., Gemert, J.C., Snoek, C.G.M: What do 15000 object categories tell us about classifying and localizing actions? In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298599"},{"issue":"1","key":"3_CR8","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1109\/TPAMI.2012.59","volume":"35","author":"S Ji","year":"2013","unstructured":"Ji, S., Xu, W., Yang, M., Yu, K.: 3D convolutional neural networks for human action recognition. IEEE Trans. Pattern Anal. Mach. Intell. 35(1), 221\u2013231 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3_CR9","doi-asserted-by":"crossref","unstructured":"Mishra, A., Verma, V.K., Reddy, M.S.K., Arulkumar, S., Rai, P., Mittal, A.: A generative approach to zero-shot and few-shot action recognition. In: WACV (2018)","DOI":"10.1109\/WACV.2018.00047"},{"key":"3_CR10","unstructured":"Norouzi, M., et al.: Zero-shot learning by convex combination of semantic embeddings. In: ICLR (2014)"},{"key":"3_CR11","unstructured":"Simonyan, K., Zisserman A.: Two-stream convolutional networks for action recognition in videos. In: Advances in Neural Information Processing Systems (NIPS), pp. 568\u2013576 (2014)"},{"key":"3_CR12","doi-asserted-by":"crossref","unstructured":"Song, J., Shen, C., Yang, Y., Liu, Y., Song, M.: Transductive unbiased embedding for zero-shot learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR (2018)","DOI":"10.1109\/CVPR.2018.00113"},{"key":"3_CR13","doi-asserted-by":"crossref","unstructured":"Sun, S., Kuang, Z., Sheng, L., Ouyang, W., Zhang, W.: Optical flow guided feature: a fast and robust motion representation for video action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR (2018)","DOI":"10.1109\/CVPR.2018.00151"},{"key":"3_CR14","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3D convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"3_CR15","doi-asserted-by":"crossref","unstructured":"Tran, D., Wang, H., Torresani, L., Ray, J., LeCun, Y., Paluri, M.: A closer look at spatiotemporal convolutions for action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR (2018)","DOI":"10.1109\/CVPR.2018.00675"},{"key":"3_CR16","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":"3_CR17","doi-asserted-by":"crossref","unstructured":"Wang, L., Xiong, Y., Lin, D., Gool, L.: UntrimmedNets for weakly supervised action recognition and detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR (2017)","DOI":"10.1109\/CVPR.2017.678"},{"key":"3_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1007\/978-3-319-46484-8_2","volume-title":"Computer Vision \u2013 ECCV 2016","author":"L Wang","year":"2016","unstructured":"Wang, L., et al.: Temporal segment networks: towards good practices for deep action recognition. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 20\u201336. Springer, Cham (2016). \nhttps:\/\/doi.org\/10.1007\/978-3-319-46484-8_2"},{"key":"3_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"343","DOI":"10.1007\/978-3-319-46475-6_22","volume-title":"Computer Vision \u2013 ECCV 2016","author":"X Xu","year":"2016","unstructured":"Xu, X., Hospedales, T.M., Gong, S.: Multi-task zero-shot action recognition with prioritised data augmentation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 343\u2013359. Springer, Cham (2016). \nhttps:\/\/doi.org\/10.1007\/978-3-319-46475-6_22"},{"key":"3_CR20","doi-asserted-by":"crossref","unstructured":"Zhu, W., Hu, J., Sun, G., Cao, X., Qiao, Y.: A key volume mining deep framework for action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR (2016)","DOI":"10.1109\/CVPR.2016.219"},{"key":"3_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"668","DOI":"10.1007\/978-3-319-46604-0_47","volume-title":"Computer Vision \u2013 ECCV 2016 Workshops","author":"Y Zhu","year":"2016","unstructured":"Zhu, Y., Newsam, S.: Depth2Action: exploring embedded depth for large-scale action recognition. In: Hua, G., J\u00e9gou, H. (eds.) ECCV 2016. LNCS, vol. 9913, pp. 668\u2013684. Springer, Cham (2016). \nhttps:\/\/doi.org\/10.1007\/978-3-319-46604-0_47"},{"key":"3_CR22","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Long, Y., Guan, Y., Newsam, S., Shao, L.: Towards universal representation for unseen action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR (2018)","DOI":"10.1109\/CVPR.2018.00983"},{"key":"3_CR23","doi-asserted-by":"crossref","unstructured":"Farhadi, A., Endres, I., Hoiem, D., Forsyth, D.: Describing objects by their attributes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR (2009)","DOI":"10.1109\/CVPR.2009.5206772"},{"key":"3_CR24","doi-asserted-by":"crossref","unstructured":"Lampert, C.H., Nickisch, H., Harmeling, S.: Learning to detect unseen object classes by between-class attribute transfer. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR (2009)","DOI":"10.1109\/CVPR.2009.5206594"},{"key":"3_CR25","doi-asserted-by":"crossref","unstructured":"Akata, Z., Perronnin, F., Harchaoui, Z., Schmid, C.: Label embedding for attribute-based classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR (2013)","DOI":"10.1109\/CVPR.2013.111"},{"key":"3_CR26","doi-asserted-by":"crossref","unstructured":"Morgado, P., Vasconcelos, N.: Semantically consistent regularization for zero-shot recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR (2017)","DOI":"10.1109\/CVPR.2017.220"},{"key":"3_CR27","doi-asserted-by":"crossref","unstructured":"Xian, Y., Lampert, C.H., Schiele, B., Akata, Z.: Zero-shot learning-a comprehensive evaluation of the good, the bad and the ugly. In: IEEE Transactions on Pattern Analysis and Machine Intelligence (2017)","DOI":"10.1109\/CVPR.2017.328"},{"key":"3_CR28","unstructured":"Frome, A., Corrado, G.S., Shlens, J., Bengio, S., Dean, J., Mikolov, T., et al.: Devise: a deep visual-semantic embedding model. In: Advances in Neural Information Processing Systems, pp. 2121\u20132129 (2013)"},{"key":"3_CR29","doi-asserted-by":"crossref","unstructured":"Reed, S., Akata, Z., Lee, H., Schiele, B.: Learning deep representations of fine-grained visual descriptions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR (2016)","DOI":"10.1109\/CVPR.2016.13"},{"key":"3_CR30","doi-asserted-by":"crossref","unstructured":"Zhang, L., Xiang, T., Gong, S.: Learning a deep embedding model for zero-shot learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR (2017)","DOI":"10.1109\/CVPR.2017.321"},{"key":"3_CR31","doi-asserted-by":"crossref","unstructured":"Qin, J., et al.: Zero-shot action recognition with error-correcting output codes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR (2017)","DOI":"10.1109\/CVPR.2017.117"},{"key":"3_CR32","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). \nhttps:\/\/doi.org\/10.1007\/978-3-642-15552-9_29"},{"issue":"10","key":"3_CR33","doi-asserted-by":"publisher","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","volume":"22","author":"SJ Pan","year":"2010","unstructured":"Pan, S.J., Yang, Q.: A survey on transfer learning. IEEE Trans. Knowl. Data Eng. 22(10), 1345\u20131359 (2010)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"3_CR34","unstructured":"Ganin, Y., Lempitsky, V.: Unsupervised domain adaptation by backpropagation. In: International Conference on Machine Learning (2015)"},{"key":"3_CR35","unstructured":"Long, M., Cao, Y., Wang, J., Jordan, M.I.: Learning transferable features with deep adaptation networks. In: International Conference on Machine Learning (2015)"},{"key":"3_CR36","first-page":"723","volume":"13","author":"A Gretton","year":"2012","unstructured":"Gretton, A., Borgwardt, K.M., Rasch, M.J., Scholkopf, B., Smola, A.J.: A kernel two-sample test. JMLR 13, 723\u2013773 (2012)","journal-title":"JMLR"},{"key":"3_CR37","doi-asserted-by":"crossref","unstructured":"Tzeng, E., Hoffman, J., Saenko, K., Darrell, T.: Adversarial discriminative domain adaptation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR (2017)","DOI":"10.1109\/CVPR.2017.316"},{"key":"3_CR38","doi-asserted-by":"crossref","unstructured":"Zhang, X., Shi, H., Li, C., Zheng, K., Zhu, X., Duan, L.: Learning transferable self-attentive representations for action recognition in untrimmed videos with weak supervision. In: AAAI (2019)","DOI":"10.1609\/aaai.v33i01.33019227"},{"issue":"3","key":"3_CR39","doi-asserted-by":"publisher","first-page":"309","DOI":"10.1007\/s11263-016-0983-5","volume":"123","author":"X Xu","year":"2017","unstructured":"Xu, X., Hospedales, T., Gong, S.: Transductive zero-shot action recognition by word-vector embedding. Int. J. Comput. Vis. 123(3), 309\u2013333 (2017)","journal-title":"Int. J. Comput. Vis."}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-41299-9_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,2,22]],"date-time":"2020-02-22T04:04:56Z","timestamp":1582344296000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-41299-9_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030412982","9783030412999"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-41299-9_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"23 February 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Auckland","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"New Zealand","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 November 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 November 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"acpr2019a","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.acpr2019.org\/","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":"easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"214","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":"125","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":"58% - 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","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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"for ACPR 2019 Workshops volume accepted 17 full papers and 6 short papers","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}