{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T15:27:16Z","timestamp":1787758036988,"version":"build-2784847793"},"publisher-location":"Cham","reference-count":49,"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_30","type":"book-chapter","created":{"date-parts":[[2020,11,8]],"date-time":"2020-11-08T16:02:34Z","timestamp":1604851354000},"page":"505-521","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Localizing the Common Action Among a Few Videos"],"prefix":"10.1007","author":[{"given":"Pengwan","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vincent Tao","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pascal","family":"Mettes","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cees G. M.","family":"Snoek","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,11,9]]},"reference":[{"key":"30_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"628","DOI":"10.1007\/978-3-319-10602-1_41","volume-title":"Computer Vision \u2013 ECCV 2014","author":"P Bojanowski","year":"2014","unstructured":"Bojanowski, P., et al.: Weakly supervised action labeling in videos under ordering constraints. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, Tinne (eds.) ECCV 2014. LNCS, vol. 8693, pp. 628\u2013643. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_41"},{"key":"30_CR2","doi-asserted-by":"crossref","unstructured":"Buch, S., Escorcia, V., Shen, C., Ghanem, B., Carlos Niebles, J.: Sst: single-stream temporal action proposals. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.675"},{"key":"30_CR3","doi-asserted-by":"crossref","unstructured":"Caba Heilbron, F., Escorcia, V., Ghanem, B., Car-los Niebles, J.: Activitynet: a large-scale video benchmark for human activity understanding. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"30_CR4","unstructured":"Chen, D.L., Dolan, W.B.: Collecting highly parallel data for paraphrase evaluation. In: ACL (2011)"},{"key":"30_CR5","doi-asserted-by":"crossref","unstructured":"Dai, X., Singh, B., Zhang, G., Davis, L.S., Chen, Y.Q: Temporal context network for activity localization in videos. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.610"},{"key":"30_CR6","doi-asserted-by":"crossref","unstructured":"Damen, D.: Scaling egocentric vision: the epic-kitchens dataset. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01225-0_44"},{"issue":"7","key":"30_CR7","doi-asserted-by":"publisher","first-page":"1641","DOI":"10.1109\/TPAMI.2018.2844853","volume":"41","author":"X Dong","year":"2018","unstructured":"Dong, X., Zheng, L., Ma, F., Yang, Y., Meng, D.: Few-example object detection with model communication. PAMI 41(7), 1641\u20131654 (2018)","journal-title":"PAMI"},{"key":"30_CR8","doi-asserted-by":"crossref","unstructured":"Duchenne, O., Laptev, I., Sivic, J., Bach, F., Ponce, J.: Automatic annotation of human actions in video. In ICCV (2009)","DOI":"10.1109\/ICCV.2009.5459279"},{"key":"30_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"768","DOI":"10.1007\/978-3-319-46487-9_47","volume-title":"Computer Vision \u2013 ECCV 2016","author":"V Escorcia","year":"2016","unstructured":"Escorcia, V., Caba Heilbron, F., Niebles, J.C., Ghanem, B.: DAPs: deep action proposals for action understanding. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9907, pp. 768\u2013784. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46487-9_47"},{"key":"30_CR10","doi-asserted-by":"crossref","unstructured":"Feng, Y., Ma, L., Liu, W., Zhang, T., Luo, J.: Video re-localization. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01264-9_4"},{"key":"30_CR11","doi-asserted-by":"crossref","unstructured":"Gao, J., Chen, K., Nevatia, R.: Ctap: Complementary temporal action proposal generation. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01216-8_5"},{"key":"30_CR12","doi-asserted-by":"crossref","unstructured":"Gao, J., Yang, Z., Sun, C., Chen, K., Nevatia, R.: Turn tap: temporal unit regression network for temporal action proposals. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.392"},{"key":"30_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"505","DOI":"10.1007\/978-3-319-10584-0_33","volume-title":"Computer Vision \u2013 ECCV 2014","author":"M Gygli","year":"2014","unstructured":"Gygli, M., Grabner, H., Riemenschneider, H., Van Gool, L.: Creating summaries from user videos. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, Tinne (eds.) ECCV 2014. LNCS, vol. 8695, pp. 505\u2013520. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10584-0_33"},{"key":"30_CR14","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"30_CR15","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"30_CR16","doi-asserted-by":"crossref","unstructured":"Hu, T., Mettes, P., Huang, J.-H., Snoek, C.G.M.: SILCO: show a few images, localize the common object. In: ICCV(2019)","DOI":"10.1109\/ICCV.2019.00517"},{"key":"30_CR17","doi-asserted-by":"crossref","unstructured":"Idrees, H., et al.: The THUMOS challenge on action recognition for videos \u201cin the wild\u201d. In: CVIU (2017)","DOI":"10.1016\/j.cviu.2016.10.018"},{"key":"30_CR18","doi-asserted-by":"crossref","unstructured":"Jain, M., Ghodrati, A., Snoek, C.G.M.: ActionBytes: learning from trimmed videos to localize actions. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00125"},{"key":"30_CR19","doi-asserted-by":"crossref","unstructured":"Jain, M., van Gemert, J.C., Mensink, T., Snoek, C.G.M.: Objects2action: classifying and localizing actions without any video example. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.521"},{"key":"30_CR20","doi-asserted-by":"crossref","unstructured":"Kalogeiton, V., Weinzaepfel, P., Ferrari, V., Schmid, C.: Joint learning of object and action detectors. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.219"},{"key":"30_CR21","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., Fei-Fei, L.: Large-scale video classification with convolutional neural networks. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.223"},{"key":"30_CR22","unstructured":"Kay, W., et al.: The kinetics human action video dataset. arXiv (2017)"},{"key":"30_CR23","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv (2014)"},{"key":"30_CR24","doi-asserted-by":"crossref","unstructured":"Kuehne, H., Richard, A., Gall, J.: A hybrid RNN-HMM approach for weakly supervised temporal action segmentation. arXiv (2019)","DOI":"10.1109\/TPAMI.2018.2884469"},{"key":"30_CR25","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 (2017)","DOI":"10.1109\/ICCV.2017.381"},{"key":"30_CR26","doi-asserted-by":"crossref","unstructured":"Lin, T., Zhao, X., Su, H., Wang, C., Yang, M.: BSN: boundary sensitive network for temporal action proposal generation. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01225-0_1"},{"key":"30_CR27","doi-asserted-by":"crossref","unstructured":"Ma, S., Sigal, L., Sclaroff, S.: Learning activity progression in LSTMS for activity detection and early detection. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.214"},{"key":"30_CR28","first-page":"2579","volume":"9","author":"L van der Maaten","year":"2008","unstructured":"van der Maaten, L., Hinton, G.: Visualizing data using t-SNE. JMLR 9, 2579\u20132605 (2008)","journal-title":"Visualizing data using t-SNE. JMLR"},{"key":"30_CR29","doi-asserted-by":"crossref","unstructured":"Mettes, P., Snoek, C.G.M.: Spatial-aware object embeddings for zero-shot localization and classification of actions. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.476"},{"key":"30_CR30","doi-asserted-by":"crossref","unstructured":"Nguyen, P., Liu, T., Prasad, G., Han, G.: Weakly supervised action localization by sparse temporal pooling network. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00706"},{"key":"30_CR31","doi-asserted-by":"crossref","unstructured":"Nguyen, P.X., Ramanan, D., Charless C.F.: Weakly-supervised action localization with background modeling. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00560"},{"key":"30_CR32","doi-asserted-by":"crossref","unstructured":"Oneata, D., Verbeek, J., Cordelia, S.: Action and event recognition with fisher vectors on a compact feature set. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.228"},{"key":"30_CR33","unstructured":"Pasze, A., et al.: Automatic differentiation in pytorch. In: NeurIPS (2017)"},{"key":"30_CR34","doi-asserted-by":"crossref","unstructured":"Paul, S., Roy, S., Roy-Chowdhury, A.K.: W-talc: Weakly-supervised temporal activity localization and classification. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01225-0_35"},{"key":"30_CR35","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1007\/978-3-030-12939-2_13","volume-title":"Pattern Recognition","author":"J Sawatzky","year":"2019","unstructured":"Sawatzky, J., Garbade, M., Gall, J.: Ex paucis plura: learning affordance segmentation from very few examples. In: Brox, T., Bruhn, A., Fritz, M. (eds.) GCPR 2018. LNCS, vol. 11269, pp. 169\u2013184. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-12939-2_13"},{"key":"30_CR36","doi-asserted-by":"crossref","unstructured":"Shaban, A., Rahimi, A., Gould, S., Boots, B., Hartley, R.: Learning to find common objects across image collections. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00522"},{"key":"30_CR37","doi-asserted-by":"crossref","unstructured":"Shou, Z., Wang, D., Chang, S.-F.: Temporal action localization in untrimmed videos via multi-stage CNNS. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.119"},{"key":"30_CR38","doi-asserted-by":"crossref","unstructured":"Singh, B., Marks, T.K., Jones, M., Tuzel, O., Shao, M.: A multi-stream bi-directional recurrent neural network for fine-grained action detection. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.216"},{"key":"30_CR39","doi-asserted-by":"crossref","unstructured":"Soomro, K., Shah, M.: Unsupervised action discovery and localization in videos. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.82"},{"key":"30_CR40","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3D convolutional networks. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"30_CR41","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS (2017)"},{"key":"30_CR42","unstructured":"Wang, L., Qiao, Y., Tang, X.: Action recognition and detection by combining motion and appearance features. THUMOS14 Action Recogn. Challenge, 1(2), 2 (2014)"},{"key":"30_CR43","doi-asserted-by":"crossref","unstructured":"Wang, L., Xiong, Y., Lin, D., Van Gool, L.: Untrimmednets for weakly supervised action recognition and detection. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.678"},{"key":"30_CR44","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00813"},{"key":"30_CR45","doi-asserted-by":"crossref","unstructured":"Xu, H., Das, A., Saenko, K.: R-C3D: Region convolutional 3D network for temporal activity detection. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.617"},{"key":"30_CR46","doi-asserted-by":"crossref","unstructured":"Yang, H., He, X., Porikli, F.: One-shot action localization by learning sequence matching network. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00157"},{"key":"30_CR47","doi-asserted-by":"crossref","unstructured":"Yang, J., Yuan, J.: Common action discovery and localization in unconstrained videos. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.237"},{"key":"30_CR48","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 (2016)","DOI":"10.1109\/CVPR.2016.293"},{"key":"30_CR49","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Zhao, Z., Lin, Z., Song, J., Cai, D.: Localizing unseen activities in video via image query. In: IJCAI (2019)","DOI":"10.24963\/ijcai.2019\/610"}],"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_30","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,8]],"date-time":"2024-11-08T00:10:31Z","timestamp":1731024631000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58571-6_30"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585709","9783030585716"],"references-count":49,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58571-6_30","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)"}}]}}