{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,23]],"date-time":"2025-04-23T23:27:44Z","timestamp":1745450864296,"version":"3.40.3"},"publisher-location":"Cham","reference-count":35,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031263156"},{"type":"electronic","value":"9783031263163"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-26316-3_14","type":"book-chapter","created":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T08:02:32Z","timestamp":1677657752000},"page":"223-238","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["SCOAD: Single-Frame Click Supervision for\u00a0Online Action Detection"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5985-2281","authenticated-orcid":false,"given":"Na","family":"Ye","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9112-4070","authenticated-orcid":false,"given":"Xing","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5202-0255","authenticated-orcid":false,"given":"Dawei","family":"Yan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0263-3584","authenticated-orcid":false,"given":"Wei","family":"Dong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1010-3540","authenticated-orcid":false,"given":"Qingsen","family":"Yan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,3,2]]},"reference":[{"key":"14_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"549","DOI":"10.1007\/978-3-319-46478-7_34","volume-title":"Computer Vision \u2013 ECCV 2016","author":"A Bearman","year":"2016","unstructured":"Bearman, A., Russakovsky, O., Ferrari, V., Fei-Fei, L.: What\u2019s the point: semantic segmentation with point supervision. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9911, pp. 549\u2013565. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46478-7_34"},{"key":"14_CR2","doi-asserted-by":"crossref","unstructured":"Caba Heilbron, F., Escorcia, V., Ghanem, B., Carlos Niebles, J.: ActivityNet: a large-scale video benchmark for human activity understanding. In: CVPR, pp. 961\u2013970 (2015)","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"14_CR3","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":"14_CR4","doi-asserted-by":"crossref","unstructured":"Cho, K., et al.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. In: EMNLP, pp. 1724\u20131734, October 2014","DOI":"10.3115\/v1\/D14-1179"},{"key":"14_CR5","doi-asserted-by":"crossref","unstructured":"Eun, H., Moon, J., Park, J., Jung, C., Kim, C.: Learning to discriminate information for online action detection. In: CVPR, pp. 809\u2013818 (2020)","DOI":"10.1109\/CVPR42600.2020.00089"},{"key":"14_CR6","doi-asserted-by":"crossref","unstructured":"Gao, J., Yang, Z., Nevatia, R.: RED: reinforced encoder-decoder networks for action anticipation. In: BMVC (2017)","DOI":"10.5244\/C.31.92"},{"key":"14_CR7","doi-asserted-by":"crossref","unstructured":"Gao, M., Xu, M., Davis, L.S., Socher, R., Xiong, C.: StartNet: online detection of action start in untrimmed videos. In: ICCV, pp. 5542\u20135551 (2019)","DOI":"10.1109\/ICCV.2019.00564"},{"key":"14_CR8","doi-asserted-by":"crossref","unstructured":"Gao, M., Zhou, Y., Xu, R., Socher, R., Xiong, C.: WOAD: weakly supervised online action detection in untrimmed videos. In: CVPR, pp. 1915\u20131923 (2021)","DOI":"10.1109\/CVPR46437.2021.00195"},{"key":"14_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"269","DOI":"10.1007\/978-3-319-46454-1_17","volume-title":"Computer Vision \u2013 ECCV 2016","author":"R De Geest","year":"2016","unstructured":"De Geest, R., Gavves, E., Ghodrati, A., Li, Z., Snoek, C., Tuytelaars, T.: Online action detection. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9909, pp. 269\u2013284. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46454-1_17"},{"key":"14_CR10","doi-asserted-by":"crossref","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. In: Neural Computation, pp. 1735\u20131780, November 1997","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"14_CR11","unstructured":"Jiang, Y.G., et al.: THUMOS challenge: action recognition with a large number of classes (2014). http:\/\/crcv.ucf.edu\/THUMOS14\/"},{"key":"14_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"339","DOI":"10.1007\/978-3-030-58595-2_21","volume-title":"Computer Vision \u2013 ECCV 2020","author":"H-U Kim","year":"2020","unstructured":"Kim, H.-U., Koh, Y.J., Kim, C.-S.: Global and local enhancement networks for paired and unpaired image enhancement. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12370, pp. 339\u2013354. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58595-2_21"},{"key":"14_CR13","doi-asserted-by":"crossref","unstructured":"Kim, J., Misu, T., Chen, Y.T., Tawari, A., Canny, J.: Grounding human-to-vehicle advice for self-driving vehicles. In: CVPR, pp. 10591\u201310599 (2019)","DOI":"10.1109\/CVPR.2019.01084"},{"key":"14_CR14","doi-asserted-by":"publisher","first-page":"226","DOI":"10.1016\/j.engappai.2017.10.001","volume":"67","author":"KE Ko","year":"2018","unstructured":"Ko, K.E., Sim, K.B.: Deep convolutional framework for abnormal behavior detection in a smart surveillance system. Eng. Appl. Artif. Intell. 67, 226\u2013234 (2018)","journal-title":"Eng. Appl. Artif. Intell."},{"key":"14_CR15","doi-asserted-by":"crossref","unstructured":"Lee, P., Byun, H.: Learning action completeness from points for weakly-supervised temporal action localization. In: ICCV, pp. 13648\u201313657 (2021)","DOI":"10.1109\/ICCV48922.2021.01339"},{"key":"14_CR16","doi-asserted-by":"crossref","unstructured":"Li, J., Han, K., Wang, P., Liu, Y., Yuan, X.: Anisotropic convolutional networks for 3D semantic scene completion. In: CVPR, pp. 3351\u20133359 (2020)","DOI":"10.1109\/CVPR42600.2020.00341"},{"key":"14_CR17","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: ICCV, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"14_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"420","DOI":"10.1007\/978-3-030-58548-8_25","volume-title":"Computer Vision \u2013 ECCV 2020","author":"F Ma","year":"2020","unstructured":"Ma, F., et al.: SF-Net: single-frame supervision for temporal action localization. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12349, pp. 420\u2013437. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58548-8_25"},{"key":"14_CR19","doi-asserted-by":"crossref","unstructured":"Moran, S., Marza, P., McDonagh, S., Parisot, S., Slabaugh, G.: DeepLPF: deep local parametric filters for image enhancement. In: CVPR, pp. 12826\u201312835 (2020)","DOI":"10.1109\/CVPR42600.2020.01284"},{"key":"14_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"588","DOI":"10.1007\/978-3-030-01225-0_35","volume-title":"Computer Vision \u2013 ECCV 2018","author":"S Paul","year":"2018","unstructured":"Paul, S., Roy, S., Roy-Chowdhury, A.K.: W-TALC: weakly-supervised temporal activity localization and classification. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11208, pp. 588\u2013607. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01225-0_35"},{"key":"14_CR21","unstructured":"Shu, T., Xie, D., Rothrock, B., Todorovic, S., Chun Zhu, S.: Joint inference of groups, events and human roles in aerial videos. In: CVPR, pp. 4576\u20134584 (2015)"},{"key":"14_CR22","doi-asserted-by":"crossref","unstructured":"Wang, L., Xiong, Y., Lin, D., Van Gool, L.: UntrimmedNets for weakly supervised action recognition and detection. In: CVPR, pp. 4325\u20134334 (2017)","DOI":"10.1109\/CVPR.2017.678"},{"key":"14_CR23","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1016\/j.patcog.2019.03.002","volume":"91","author":"P Wang","year":"2019","unstructured":"Wang, P., Liu, L., Shen, C., Shen, H.T.: Order-aware convolutional pooling for video based action recognition. Pattern Recogn. 91, 357\u2013365 (2019)","journal-title":"Pattern Recogn."},{"key":"14_CR24","doi-asserted-by":"crossref","unstructured":"Wang, X., et al.: OadTR: online action detection with transformers. In: ICCV, pp. 7565\u20137575 (2021)","DOI":"10.1109\/ICCV48922.2021.00747"},{"key":"14_CR25","doi-asserted-by":"crossref","unstructured":"Xu, M., Gao, M., Chen, Y.T., Davis, L.S., Crandall, D.J.: Temporal recurrent networks for online action detection. In: ICCV, pp. 5532\u20135541 (2019)","DOI":"10.1109\/ICCV.2019.00563"},{"key":"14_CR26","doi-asserted-by":"crossref","unstructured":"Yan, Q., Gong, D., Liu, Y., van den Hengel, A., Shi, J.Q.: Learning Bayesian sparse networks with full experience replay for continual learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 109\u2013118 (2022)","DOI":"10.1109\/CVPR52688.2022.00021"},{"key":"14_CR27","doi-asserted-by":"publisher","first-page":"108342","DOI":"10.1016\/j.patcog.2021.108342","volume":"122","author":"Q Yan","year":"2022","unstructured":"Yan, Q., et al.: High dynamic range imaging via gradient-aware context aggregation network. Pattern Recogn. 122, 108342 (2022)","journal-title":"Pattern Recogn."},{"key":"14_CR28","doi-asserted-by":"crossref","unstructured":"Yan, Q., et al.: Attention-guided network for ghost-free high dynamic range imaging. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1751\u20131760 (2019)","DOI":"10.1109\/CVPR.2019.00185"},{"issue":"5","key":"14_CR29","doi-asserted-by":"publisher","first-page":"2200","DOI":"10.1109\/TIP.2018.2883741","volume":"28","author":"Q Yan","year":"2018","unstructured":"Yan, Q., Gong, D., Zhang, Y.: Two-stream convolutional networks for blind image quality assessment. IEEE Trans. Image Process. 28(5), 2200\u20132211 (2018)","journal-title":"IEEE Trans. Image Process."},{"key":"14_CR30","doi-asserted-by":"publisher","first-page":"4308","DOI":"10.1109\/TIP.2020.2971346","volume":"29","author":"Q Yan","year":"2020","unstructured":"Yan, Q., et al.: Deep HDR imaging via a non-local network. IEEE Trans. Image Process. 29, 4308\u20134322 (2020)","journal-title":"IEEE Trans. Image Process."},{"key":"14_CR31","doi-asserted-by":"crossref","unstructured":"Yang, L., Han, J., Zhang, D.: Colar: effective and efficient online action detection by consulting exemplars. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00316"},{"issue":"12","key":"14_CR32","doi-asserted-by":"publisher","first-page":"9814","DOI":"10.1109\/TPAMI.2021.3132058","volume":"44","author":"L Yang","year":"2021","unstructured":"Yang, L., et al.: Background-click supervision for temporal action localization. IEEE Trans. Pattern Anal. Mach. Intell. 44(12), 9814\u20139829 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"12","key":"14_CR33","doi-asserted-by":"publisher","first-page":"5689","DOI":"10.1109\/TIP.2016.2614136","volume":"25","author":"L Yu","year":"2016","unstructured":"Yu, L., Yang, Y., Huang, Z., Wang, P., Song, J., Shen, H.T.: Web video event recognition by semantic analysis from ubiquitous documents. IEEE Trans. Image Process. 25(12), 5689\u20135701 (2016)","journal-title":"IEEE Trans. Image Process."},{"key":"14_CR34","unstructured":"Yuan, Y., Lyu, Y., Shen, X., Tsang, I., Yeung, D.Y.: Marginalized average attentional network for weakly-supervised learning. In: ICLR (2019)"},{"key":"14_CR35","doi-asserted-by":"crossref","unstructured":"Zhang, C., Cao, M., Yang, D., Chen, J., Zou, Y.: Cola: weakly-supervised temporal action localization with snippet contrastive learning. In: CVPR, pp. 16010\u201316019 (2021)","DOI":"10.1109\/CVPR46437.2021.01575"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-26316-3_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T08:24:27Z","timestamp":1677659067000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-26316-3_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031263156","9783031263163"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-26316-3_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"2 March 2023","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":"Macao","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":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 December 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 December 2022","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":"accv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.accv2022.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":"CMT Microsoft","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"836","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":"277","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":"33% - 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":"3.3","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":"2.6","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 the ACCV 2022 workshops 25 papers have been accepted from 40 submissions","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)"}}]}}