{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T21:11:29Z","timestamp":1743023489123,"version":"3.40.3"},"publisher-location":"Cham","reference-count":39,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030316532"},{"type":"electronic","value":"9783030316549"}],"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\/978-3-030-31654-9_18","type":"book-chapter","created":{"date-parts":[[2019,10,31]],"date-time":"2019-10-31T00:05:31Z","timestamp":1572480331000},"page":"205-216","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Weakly-Supervised Action Recognition and Localization via Knowledge Transfer"],"prefix":"10.1007","author":[{"given":"Haichao","family":"Shi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoyu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Changsheng","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,10,31]]},"reference":[{"key":"18_CR1","unstructured":"Alwassel, H., Heilbron, F.C., Ghanem, B.: Action search: learning to search for human activities in untrimmed videos. CoRR abs\/1706.04269 (2017)"},{"key":"18_CR2","doi-asserted-by":"crossref","unstructured":"Chao, Y., Vijayanarasimhan, S., Seybold, B., Ross, D.A., Deng, J., Sukthankar, R.: Rethinking the faster R-CNN architecture for temporal action localization. CoRR abs\/1804.07667 (2018)","DOI":"10.1109\/CVPR.2018.00124"},{"key":"18_CR3","doi-asserted-by":"crossref","unstructured":"Girshick, R.B.: Fast R-CNN. In: ICCV, pp. 1440\u20131448 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"18_CR4","doi-asserted-by":"crossref","unstructured":"Huang, X., Belongie, S.: Arbitrary style transfer in real-time with adaptive instance normalization. In: ICLR, pp. 1510\u20131519 (2017)","DOI":"10.1109\/ICCV.2017.167"},{"key":"18_CR5","doi-asserted-by":"crossref","unstructured":"Jain, M., van Gemert, J.C., Snoek, C.G.M.: What do 15, 000 object categories tell us about classifying and localizing actions? In: CVPR, pp. 46\u201355 (2015)","DOI":"10.1109\/CVPR.2015.7298599"},{"key":"18_CR6","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., Li, F.: Large-scale video classification with convolutional neural networks. In: CVPR, pp. 1725\u20131732 (2014)","DOI":"10.1109\/CVPR.2014.223"},{"key":"18_CR7","unstructured":"Li, X., Liu, S., Kautz, J., Yang, M.: Learning linear transformations for fast arbitrary style transfer. CoRR abs\/1808.04537 (2018)"},{"key":"18_CR8","doi-asserted-by":"crossref","unstructured":"Li, Y., Yang, F., Liu, Y., Yeh, Y., Du, X., Wang, Y.F.: Adaptation and re-identification network: an unsupervised deep transfer learning approach to person reidentification. CoRR abs\/1804.09347 (2018)","DOI":"10.1109\/CVPRW.2018.00054"},{"key":"18_CR9","unstructured":"Long, M., Cao, Y., Wang, J., Jordan, M.I.: Learning transferable features with deep adaptation networks. In: ICML, pp. 97\u2013105 (2015)"},{"key":"18_CR10","unstructured":"Long, M., Zhu, H., Wang, J., Jordan, M.I.: Deep transfer learning with joint adaptation networks. In: ICML, pp. 2208\u20132217 (2017)"},{"key":"18_CR11","doi-asserted-by":"crossref","unstructured":"Nguyen, P., Liu, T., Prasad, G., Han, B.: Weakly supervised action localization by sparse temporal pooling network. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00706"},{"key":"18_CR12","unstructured":"Ren, S., He, K., Girshick, R.B., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NIPS, pp. 91\u201399 (2015)"},{"issue":"10","key":"18_CR13","doi-asserted-by":"publisher","first-page":"5677","DOI":"10.1109\/TGRS.2015.2427791","volume":"53","author":"Q Shi","year":"2015","unstructured":"Shi, Q., Du, B., Zhang, L.: Domain adaptation for remote sensing image classification: a low-rank reconstruction and instance weighting label propagation inspired algorithm. IEEE Trans. Geosci. Remote Sens. 53(10), 5677\u20135689 (2015)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"18_CR14","doi-asserted-by":"crossref","unstructured":"Shou, Z., Wang, D., Chang, S.: Temporal action localization in untrimmed videos via multi-stage CNNs. In: CVPR, pp. 1049\u20131058 (2016)","DOI":"10.1109\/CVPR.2016.119"},{"key":"18_CR15","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: NIPS, pp. 568\u2013576 (2014)"},{"key":"18_CR16","doi-asserted-by":"crossref","unstructured":"Singh, K.K., Lee, Y.J.: Hide-and-seek: forcing a network to be meticulous for weakly-supervised object and action localization. In: ICCV, pp. 3544\u20133553 (2017)","DOI":"10.1109\/ICCV.2017.381"},{"key":"18_CR17","doi-asserted-by":"crossref","unstructured":"Sultani, W., Saleemi, I.: Human action recognition across datasets by foreground-weighted histogram decomposition. In: CVPR, pp. 764\u2013771 (2014)","DOI":"10.1109\/CVPR.2014.103"},{"key":"18_CR18","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L.D., 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"},{"issue":"6","key":"18_CR19","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1109\/MSP.2017.2740460","volume":"34","author":"H Venkateswara","year":"2017","unstructured":"Venkateswara, H., Chakraborty, S., Panchanathan, S.: Deep learning systems for domain adaptation in computer vision: learning transferable feature representations. IEEE Signal Process. Mag. 34(6), 117\u2013129 (2017)","journal-title":"IEEE Signal Process. Mag."},{"key":"18_CR20","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":"18_CR21","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). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_2"},{"key":"18_CR22","doi-asserted-by":"crossref","unstructured":"Wang, L., Xiong, Y., Lin, D., Gool, L.V.: Untrimmednets for weakly supervised action recognition and detection. In: CVPR, pp. 6402\u20136411 (2017)","DOI":"10.1109\/CVPR.2017.678"},{"key":"18_CR23","doi-asserted-by":"crossref","unstructured":"Xu, H., Das, A., Saenko, K.: R-C3D: region convolutional 3D network for temporal activity detection. In: ICCV, pp. 5794\u20135803 (2017)","DOI":"10.1109\/ICCV.2017.617"},{"key":"18_CR24","doi-asserted-by":"crossref","unstructured":"Yeung, S., Russakovsky, O., Mori, G., Fei-Fei, L.: End-to-end learning of action detection from frame glimpses in videos. In: CVPR, pp. 2678\u20132687 (2016)","DOI":"10.1109\/CVPR.2016.293"},{"key":"18_CR25","doi-asserted-by":"crossref","unstructured":"Yuan, J., Ni, B., Yang, X., Kassim, A.A.: Temporal action localization with pyramid of score distribution features. In: CVPR, pp. 3093\u20133102 (2016)","DOI":"10.1109\/CVPR.2016.337"},{"key":"18_CR26","doi-asserted-by":"crossref","unstructured":"Zhang, B., Wang, L., Wang, Z., Qiao, Y., Wang, H.: Real-time action recognition with enhanced motion vector CNNs. In: CVPR, pp. 2718\u20132726 (2016)","DOI":"10.1109\/CVPR.2016.297"},{"key":"18_CR27","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Xiong, Y., Wang, L., Wu, Z., Tang, X., Lin, D.: Temporal action detection with structured segment networks. In: ICCV, pp. 2933\u20132942 (2017)","DOI":"10.1109\/ICCV.2017.317"},{"key":"18_CR28","doi-asserted-by":"crossref","unstructured":"Zhong, Z., Zheng, L., Zheng, Z., Li, S., Yang, Y.: Camera style adaptation for person re-identification. CoRR abs\/1711.10295 (2017)","DOI":"10.1109\/CVPR.2018.00541"},{"key":"18_CR29","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1016\/j.neucom.2019.01.083","volume":"345","author":"X Zhang","year":"2019","unstructured":"Zhang, X., Shi, H., Zhu, X., Li, P.: Active semi-supervised learning based on self-expressive correlation with generative adversarial networks. Neurocomputing 345, 103\u2013113 (2019). https:\/\/doi.org\/10.1016\/j.neucom.2019.01.083","journal-title":"Neurocomputing"},{"key":"18_CR30","doi-asserted-by":"publisher","first-page":"455","DOI":"10.1016\/j.neucom.2016.03.062","volume":"205","author":"X Zhang","year":"2016","unstructured":"Zhang, X.: Simultaneous optimization for robust correlation estimation in partially observed social network. Neurocomputing 205, 455\u2013462 (2016)","journal-title":"Neurocomputing"},{"issue":"12","key":"18_CR31","doi-asserted-by":"publisher","first-page":"3034","DOI":"10.1109\/TNNLS.2015.2401595","volume":"26","author":"X Zhang","year":"2015","unstructured":"Zhang, X., Wang, S., Yun, X.: Bidirectional active learning: a two-way exploration into unlabeled and labeled dataset. IEEE Trans. Neural Netw. Learn. Syst. 26(12), 3034\u20133044 (2015)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"18_CR32","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1016\/j.neucom.2015.03.056","volume":"162","author":"X Zhang","year":"2015","unstructured":"Zhang, X., Wang, S., Zhu, X., Yun, X., Wu, G., Wang, Y.: Update vs. upgrade: modeling with indeterminate multi-class active learning. Neurocomputing 162, 163\u2013170 (2015)","journal-title":"Neurocomputing"},{"key":"18_CR33","doi-asserted-by":"publisher","first-page":"200","DOI":"10.1016\/j.neucom.2013.08.013","volume":"127","author":"X Zhang","year":"2014","unstructured":"Zhang, X.: Interactive patent classification based on multi-classifier fusion and active learning. Neurocomputing 127, 200\u2013205 (2014)","journal-title":"Neurocomputing"},{"key":"18_CR34","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: Proceedings of the 33rd AAAI Conference on Artificial Intelligence, pp. 1\u20138 (2019)","DOI":"10.1609\/aaai.v33i01.33019227"},{"key":"18_CR35","doi-asserted-by":"publisher","first-page":"182","DOI":"10.1016\/j.neucom.2017.06.008","volume":"267","author":"Y Liu","year":"2017","unstructured":"Liu, Y., Zhang, X., Zhu, X., Guan, Q., Zhao, X.: ListNet-based object proposals ranking. Neurocomputing 267, 182\u2013194 (2017)","journal-title":"Neurocomputing"},{"key":"18_CR36","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"534","DOI":"10.1007\/978-3-319-77380-3_51","volume-title":"Advances in Multimedia Information Processing \u2013 PCM 2017","author":"H Shi","year":"2018","unstructured":"Shi, H., Dong, J., Wang, W., Qian, Y., Zhang, X.: SSGAN: secure steganography based on generative adversarial networks. In: Zeng, B., Huang, Q., El Saddik, A., Li, H., Jiang, S., Fan, X. (eds.) PCM 2017. LNCS, vol. 10735, pp. 534\u2013544. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-319-77380-3_51"},{"key":"18_CR37","doi-asserted-by":"publisher","first-page":"532","DOI":"10.1016\/j.jvcir.2018.11.020","volume":"58","author":"X Zhu","year":"2019","unstructured":"Zhu, X., Zhang, X., Zhang, X., Xue, Z., Wang, L.: A novel framework for semantic segmentation with generative adversarial network. J. Vis. Commun. Image Represent. (JVCI) 58, 532\u2013543 (2019)","journal-title":"J. Vis. Commun. Image Represent. (JVCI)"},{"issue":"2","key":"18_CR38","doi-asserted-by":"publisher","first-page":"272","DOI":"10.1109\/TMM.2008.2009689","volume":"11","author":"X Zhang","year":"2009","unstructured":"Zhang, X., Xu, C., Cheng, J., Lu, H., Ma, S.: Effective annotation and search for video blogs with integration of context and content analysis. IEEE Trans. Multimedia (TMM) 11(2), 272\u2013285 (2009)","journal-title":"IEEE Trans. Multimedia (TMM)"},{"key":"18_CR39","doi-asserted-by":"crossref","unstructured":"Zhu, X., Li, Z., Zhang, X., Li, C., Liu, Y., Xue, Z.: Residual invertible spatio-temporal network for video super-resolution. In: Proceedings of the 33rd AAAI Conference on Artificial Intelligence, pp. 1\u20138 (2019)","DOI":"10.1609\/aaai.v33i01.33015981"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-31654-9_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:07:26Z","timestamp":1730333246000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-31654-9_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030316532","9783030316549"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-31654-9_18","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":"31 October 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Xi'an","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"8 November 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 November 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.prcv2019.com\/en\/index.html","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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"412","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":"165","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":"40% - 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":"4","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":"4","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)"}}]}}