{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T12:26:14Z","timestamp":1782390374267,"version":"3.54.5"},"publisher-location":"Cham","reference-count":34,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030585709","type":"print"},{"value":"9783030585716","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-58571-6_22","type":"book-chapter","created":{"date-parts":[[2020,11,8]],"date-time":"2020-11-08T16:02:34Z","timestamp":1604851354000},"page":"363-378","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":24,"title":["Temporal Distinct Representation Learning for Action Recognition"],"prefix":"10.1007","author":[{"given":"Junwu","family":"Weng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Donghao","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yabiao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ying","family":"Tai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chengjie","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jilin","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feiyue","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xudong","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junsong","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,11,9]]},"reference":[{"key":"22_CR1","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":"22_CR2","unstructured":"Choi, J., Gao, C., Messou, J.C., Huang, J.B.: Why can\u2019t i dance in the mall, learning to mitigate scene bias in action recognition. In: NeurIPS, pp. 853\u2013865 (2019)"},{"key":"22_CR3","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: CVPR, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"22_CR4","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., Malik, J., He, K.: Slowfast networks for video recognition. In: ICCV, pp. 6202\u20136211 (2019)","DOI":"10.1109\/ICCV.2019.00630"},{"key":"22_CR5","doi-asserted-by":"crossref","unstructured":"Goyal, R., et al.: The \u201csomething something\u201d video database for learning and evaluating visual common sense. In: ICCV, vol. 1, p. 5 (2017)","DOI":"10.1109\/ICCV.2017.622"},{"key":"22_CR6","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"22_CR7","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: CVPR, pp. 7132\u20137141 (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"22_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"425","DOI":"10.1007\/978-3-642-33715-4_31","volume-title":"Computer Vision \u2013 ECCV 2012","author":"Y-G Jiang","year":"2012","unstructured":"Jiang, Y.-G., Dai, Q., Xue, X., Liu, W., Ngo, C.-W.: Trajectory-based modeling of human actions with motion reference points. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7576, pp. 425\u2013438. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33715-4_31"},{"key":"22_CR9","doi-asserted-by":"crossref","unstructured":"Li, Y., Song, S., Li, Y., Liu, J.: Temporal bilinear networks for video action recognition. In: AAAI, vol. 33, pp. 8674\u20138681 (2019)","DOI":"10.1609\/aaai.v33i01.33018674"},{"key":"22_CR10","doi-asserted-by":"crossref","unstructured":"Lin, J., Gan, C., Han, S.: Tsm: Temporal shift module for efficient video understanding. In: ICCV, pp. 7083\u20137093 (2019)","DOI":"10.1109\/ICCV.2019.00718"},{"key":"22_CR11","unstructured":"Liu, Z., et al.: Teinet: towards an efficient architecture for video recognition. In: AAAI, vol. 2, p. 8 (2020)"},{"key":"22_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"369","DOI":"10.1007\/978-3-030-01264-9_22","volume-title":"Computer Vision \u2013 ECCV 2018","author":"X Lu","year":"2018","unstructured":"Lu, X., Ma, C., Ni, B., Yang, X., Reid, I., Yang, M.-H.: Deep regression tracking with shrinkage loss. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer Vision \u2013 ECCV 2018. LNCS, vol. 11218, pp. 369\u2013386. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01264-9_22"},{"key":"22_CR13","doi-asserted-by":"crossref","unstructured":"Lu, X., Wang, W., Ma, C., Shen, J., Shao, L., Porikli, F.: See more, know more: Unsupervised video object segmentation with co-attention siamese networks. In: CVPR, pp. 3623\u20133632 (2019)","DOI":"10.1109\/CVPR.2019.00374"},{"key":"22_CR14","doi-asserted-by":"crossref","unstructured":"Lu, X., Wang, W., Shen, J., Tai, Y.W., Crandall, D.J., Hoi, S.C.: Learning video object segmentation from unlabeled videos. In: CVPR, pp. 8960\u20138970 (2020)","DOI":"10.1109\/CVPR42600.2020.00898"},{"key":"22_CR15","doi-asserted-by":"crossref","unstructured":"Luo, C., Yuille, A.L.: Grouped spatial-temporal aggregation for efficient action recognition. In: ICCV, pp. 5512\u20135521 (2019)","DOI":"10.1109\/ICCV.2019.00561"},{"key":"22_CR16","unstructured":"Mahdisoltani, F., Berger, G., Gharbieh, W., Fleet, D., Memisevic, R.: On the effectiveness of task granularity for transfer learning. arXiv:1804.09235 (2018)"},{"key":"22_CR17","doi-asserted-by":"crossref","unstructured":"Qiu, Z., Yao, T., Ngo, C.W., Tian, X., Mei, T.: Learning spatio-temporal representation with local and global diffusion. In: CVPR, pp. 12056\u201312065 (2019)","DOI":"10.1109\/CVPR.2019.01233"},{"key":"22_CR18","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: ICLR (2014)"},{"key":"22_CR19","doi-asserted-by":"crossref","unstructured":"Szegedy, C., et al.: Going deeper with convolutions. In: CVPR, pp. 1\u20139 (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"22_CR20","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":"22_CR21","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: CVPR, pp. 6450\u20136459 (2018)","DOI":"10.1109\/CVPR.2018.00675"},{"key":"22_CR22","doi-asserted-by":"crossref","unstructured":"Wang, L., Li, W., Li, W., Van Gool, L.: Appearance-and-relation networks for video classification. In: CVPR, pp. 1430\u20131439 (2018)","DOI":"10.1109\/CVPR.2018.00155"},{"key":"22_CR23","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., Xiong, Y., Wang, Z., Qiao, Yu., Lin, D., Tang, X., Van Gool, L.: 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":"22_CR24","doi-asserted-by":"crossref","unstructured":"Wang, X., Farhadi, A., Gupta, A.: Actions transformations. In: CVPR, pp. 2658\u20132667 (2016)","DOI":"10.1109\/CVPR.2016.291"},{"key":"22_CR25","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: CVPR, pp. 7794\u20137803 (2018)","DOI":"10.1109\/CVPR.2018.00813"},{"key":"22_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"413","DOI":"10.1007\/978-3-030-01228-1_25","volume-title":"Computer Vision \u2013 ECCV 2018","author":"X Wang","year":"2018","unstructured":"Wang, X., Gupta, A.: Videos as space-time region graphs. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11209, pp. 413\u2013431. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01228-1_25"},{"key":"22_CR27","doi-asserted-by":"crossref","unstructured":"Wang, Y., Hoai, M.: Pulling actions out of context, explicit separation for effective combination. In: CVPR, pp. 7044\u20137053 (2018)","DOI":"10.1109\/CVPR.2018.00736"},{"key":"22_CR28","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"318","DOI":"10.1007\/978-3-030-01267-0_19","volume-title":"Computer Vision \u2013 ECCV 2018","author":"S Xie","year":"2018","unstructured":"Xie, S., Sun, C., Huang, J., Tu, Z., Murphy, K.: Rethinking spatiotemporal feature learning: speed-accuracy trade-offs in video classification. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11219, pp. 318\u2013335. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01267-0_19"},{"key":"22_CR29","unstructured":"Xingjian, S., Chen, Z., Wang, H., Yeung, D.Y., Wong, W.K., Woo, W.c.: Convolutional LSTM network: a machine learning approach for precipitation nowcasting. In: NeurIPS, pp. 802\u2013810 (2015)"},{"key":"22_CR30","doi-asserted-by":"crossref","unstructured":"Zhang, P., Lan, C., Xing, J., Zeng, W., Xue, J., Zheng, N.: View adaptive recurrent neural networks for high performance human action recognition from skeleton data. In: ICCV, pp. 2117\u20132126 (2017)","DOI":"10.1109\/ICCV.2017.233"},{"issue":"6","key":"22_CR31","first-page":"1245","volume":"19","author":"B Zhao","year":"2017","unstructured":"Zhao, B., Wu, X., Feng, J., Peng, Q., Yan, S.: Diversified visual attention networks for fine-grained object classification. T-MM 19(6), 1245\u20131256 (2017)","journal-title":"T-MM"},{"key":"22_CR32","doi-asserted-by":"crossref","unstructured":"Zheng, H., Fu, J., Mei, T., Luo, J.: Learning multi-attention convolutional neural network for fine-grained image recognition. In: CVPR, pp. 5209\u20135217 (2017)","DOI":"10.1109\/ICCV.2017.557"},{"key":"22_CR33","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"831","DOI":"10.1007\/978-3-030-01246-5_49","volume-title":"Computer Vision \u2013 ECCV 2018","author":"B Zhou","year":"2018","unstructured":"Zhou, B., Andonian, A., Oliva, A., Torralba, A.: Temporal relational reasoning in videos. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11205, pp. 831\u2013846. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01246-5_49"},{"key":"22_CR34","doi-asserted-by":"crossref","unstructured":"Zhu, X., Xu, C., Hui, L., Lu, C., Tao, D.: Approximated bilinear modules for temporal modeling. In: ICCV, pp. 3494\u20133503 (2019)","DOI":"10.1109\/ICCV.2019.00359"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2020"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-58571-6_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,8]],"date-time":"2024-11-08T00:07:35Z","timestamp":1731024455000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58571-6_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585709","9783030585716"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58571-6_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"9 November 2020","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":"Glasgow","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 August 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2020.eu\/","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":"OpenReview","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5025","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":"1360","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":"27% - 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":"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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"The conference was held virtually due to the COVID-19 pandemic.","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)"}}]}}