{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T14:38:11Z","timestamp":1743086291745,"version":"3.40.3"},"publisher-location":"Cham","reference-count":47,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031262838"},{"type":"electronic","value":"9783031262845"}],"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\/978-3-031-26284-5_32","type":"book-chapter","created":{"date-parts":[[2023,2,22]],"date-time":"2023-02-22T08:02:59Z","timestamp":1677052979000},"page":"526-542","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["TCVM: Temporal Contrasting Video Montage Framework for\u00a0Self-supervised Video Representation Learning"],"prefix":"10.1007","author":[{"given":"Fengrui","family":"Tian","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiawei","family":"Fan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xie","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shaoyi","family":"Du","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meina","family":"Song","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,2,23]]},"reference":[{"key":"32_CR1","doi-asserted-by":"publisher","unstructured":"Ahsan, U., Madhok, R., Essa, I.: Video Jigsaw: unsupervised learning of spatiotemporal context for video action recognition. In: 2019 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 179\u2013189 (2019). https:\/\/doi.org\/10.1109\/WACV.2019.00025","DOI":"10.1109\/WACV.2019.00025"},{"key":"32_CR2","unstructured":"Alwassel, H., Mahajan, D., Korbar, B., Torresani, L., Ghanem, B., Tran, D.: Self-supervised learning by cross-modal audio-video clustering. In: NeurIPS (2020)"},{"key":"32_CR3","doi-asserted-by":"crossref","unstructured":"Benaim, S., et al.: SpeedNet: learning the speediness in videos. In: CVPR, pp. 9922\u20139931 (2020)","DOI":"10.1109\/CVPR42600.2020.00994"},{"key":"32_CR4","doi-asserted-by":"publisher","first-page":"932","DOI":"10.1080\/10447318.2018.1561792","volume":"35","author":"FN Biondi","year":"2019","unstructured":"Biondi, F.N., Alvarez, I.J., Jeong, K.A.: Human-vehicle cooperation in automated driving: a multidisciplinary review and appraisal. Int. J. Hum.-Comput. Interact. 35, 932\u2013946 (2019)","journal-title":"Int. J. Hum.-Comput. Interact."},{"key":"32_CR5","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":"32_CR6","doi-asserted-by":"crossref","unstructured":"Chen, P., et al.: RSPNet: relative speed perception for unsupervised video representation learning. In: AAAI, vol. 1 (2021)","DOI":"10.1609\/aaai.v35i2.16189"},{"key":"32_CR7","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: ICML, pp. 1597\u20131607. PMLR (2020)"},{"key":"32_CR8","unstructured":"Chen, X., Fan, H., Girshick, R., He, K.: Improved baselines with momentum contrastive learning. arXiv preprint arXiv:2003.04297 (2020)"},{"key":"32_CR9","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. arXiv preprint arXiv:1912.05534 (2019)"},{"key":"32_CR10","doi-asserted-by":"crossref","unstructured":"Dave, I., Gupta, R., Rizve, M.N., Shah, M.: TCLR: temporal contrastive learning for video representation. arXiv preprint arXiv:2101.07974 (2021)","DOI":"10.1016\/j.cviu.2022.103406"},{"key":"32_CR11","doi-asserted-by":"crossref","unstructured":"Ding, S., et al.: Motion-aware self-supervised video representation learning via foreground-background merging. arXiv preprint arXiv:2109.15130 (2021)","DOI":"10.1109\/CVPR52688.2022.00949"},{"key":"32_CR12","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":"32_CR13","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., Xiong, B., Girshick, R., He, K.: A large-scale study on unsupervised spatiotemporal representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3299\u20133309 (2021)","DOI":"10.1109\/CVPR46437.2021.00331"},{"key":"32_CR14","doi-asserted-by":"crossref","unstructured":"Fernando, B., Bilen, H., Gavves, E., Gould, S.: Self-supervised video representation learning with odd-one-out networks. In: CVPR, pp. 3636\u20133645 (2017)","DOI":"10.1109\/CVPR.2017.607"},{"key":"32_CR15","doi-asserted-by":"crossref","unstructured":"Goyal, R., et al.: The \u201csomething something\u201d video database for learning and evaluating visual common sense. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5842\u20135850 (2017)","DOI":"10.1109\/ICCV.2017.622"},{"key":"32_CR16","unstructured":"Grill, J.B., et al.: Bootstrap your own latent: a new approach to self-supervised learning. arXiv preprint arXiv:2006.07733 (2020)"},{"key":"32_CR17","doi-asserted-by":"crossref","unstructured":"Han, T., Xie, W., Zisserman, A.: Video representation learning by dense predictive coding. In: ICCV Workshops (2019)","DOI":"10.1109\/ICCVW.2019.00186"},{"key":"32_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"312","DOI":"10.1007\/978-3-030-58580-8_19","volume-title":"Computer Vision \u2013 ECCV 2020","author":"T Han","year":"2020","unstructured":"Han, T., Xie, W., Zisserman, A.: Memory-augmented dense predictive coding for video representation learning. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12348, pp. 312\u2013329. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58580-8_19"},{"key":"32_CR19","unstructured":"Han, T., Xie, W., Zisserman, A.: Self-supervised co-training for video representation learning. In: NeurIPS (2020)"},{"key":"32_CR20","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: CVPR, pp. 9729\u20139738 (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"32_CR21","doi-asserted-by":"crossref","unstructured":"Huang, D.A., et al.: What makes a video a video: analyzing temporal information in video understanding models and datasets. In: CVPR, pp. 7366\u20137375 (2018)","DOI":"10.1109\/CVPR.2018.00769"},{"key":"32_CR22","doi-asserted-by":"crossref","unstructured":"Huang, L., Liu, Y., Wang, B., Pan, P., Xu, Y., Jin, R.: Self-supervised video representation learning by context and motion decoupling. In: CVPR, pp. 13886\u201313895 (2021)","DOI":"10.1109\/CVPR46437.2021.01367"},{"key":"32_CR23","doi-asserted-by":"crossref","unstructured":"Huang, Z., Zhang, S., Jiang, J., Tang, M., Jin, R., Ang, M.H.: Self-supervised motion learning from static images. In: CVPR, pp. 1276\u20131285 (2021)","DOI":"10.1109\/CVPR46437.2021.00133"},{"key":"32_CR24","doi-asserted-by":"publisher","unstructured":"Huo, Y., et al.: Self-supervised video representation learning with constrained spatiotemporal jigsaw. In: IJCAI, pp. 751\u2013757 (2021). https:\/\/doi.org\/10.24963\/ijcai.2021\/104","DOI":"10.24963\/ijcai.2021\/104"},{"key":"32_CR25","unstructured":"Jing, L., Yang, X., Liu, J., Tian, Y.: Self-supervised spatiotemporal feature learning via video rotation prediction. arXiv preprint arXiv:1811.11387 (2018)"},{"key":"32_CR26","unstructured":"Khosla, P., et al.: Supervised contrastive learning. In: NeurIPS, vol. 33, pp. 18661\u201318673 (2020)"},{"key":"32_CR27","doi-asserted-by":"publisher","unstructured":"Kim, D., Cho, D., Kweon, I.S.: Self-supervised video representation learning with space-time cubic puzzles. In: AAAI, vol. 33, pp. 8545\u20138552 (2019). https:\/\/doi.org\/10.1609\/aaai.v33i01.33018545","DOI":"10.1609\/aaai.v33i01.33018545"},{"key":"32_CR28","doi-asserted-by":"crossref","unstructured":"Kuehne, H., Jhuang, H., Garrote, E., Poggio, T., Serre, T.: HMDB: a large video database for human motion recognition. In: ICCV, pp. 2556\u20132563. IEEE (2011)","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"32_CR29","doi-asserted-by":"crossref","unstructured":"Lee, H.Y., Huang, J.B., Singh, M., Yang, M.H.: Unsupervised representation learning by sorting sequences. In: ICCV, pp. 667\u2013676 (2017)","DOI":"10.1109\/ICCV.2017.79"},{"key":"32_CR30","doi-asserted-by":"publisher","unstructured":"Li, Y., et al.: MPC-based switched driving model for human vehicle co-piloting considering human factors. Transp. Res. Part C Emerg. Technol. 115, 102612 (2020). https:\/\/doi.org\/10.1016\/j.trc.2020.102612. https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0968090X18308179","DOI":"10.1016\/j.trc.2020.102612"},{"key":"32_CR31","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":"32_CR32","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-030-01225-0_1","volume-title":"Computer Vision \u2013 ECCV 2018","author":"T Lin","year":"2018","unstructured":"Lin, T., Zhao, X., Su, H., Wang, C., Yang, M.: BSN: boundary sensitive network for temporal action proposal generation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11208, pp. 3\u201321. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01225-0_1"},{"key":"32_CR33","doi-asserted-by":"crossref","unstructured":"Misra, I., van der Maaten, L.: Self-supervised learning of pretext-invariant representations. In: CVPR, pp. 6707\u20136717 (2020)","DOI":"10.1109\/CVPR42600.2020.00674"},{"key":"32_CR34","doi-asserted-by":"crossref","unstructured":"Pan, T., Song, Y., Yang, T., Jiang, W., Liu, W.: VideoMoCo: contrastive video representation learning with temporally adversarial examples. In: CVPR, pp. 11205\u201311214 (2021)","DOI":"10.1109\/CVPR46437.2021.01105"},{"key":"32_CR35","doi-asserted-by":"crossref","unstructured":"Patrick, M., et al.: Space-time crop & attend: improving cross-modal video representation learning. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01039"},{"key":"32_CR36","doi-asserted-by":"crossref","unstructured":"Qian, R., et al.: Spatiotemporal contrastive video representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6964\u20136974 (2021)","DOI":"10.1109\/CVPR46437.2021.00689"},{"key":"32_CR37","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-CAM: visual explanations from deep networks via gradient-based localization. In: ICCV, pp. 618\u2013626 (2017)","DOI":"10.1109\/ICCV.2017.74"},{"key":"32_CR38","unstructured":"Soomro, K., Zamir, A.R., Shah, M.: UCF101: a dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:1212.0402 (2012)"},{"key":"32_CR39","doi-asserted-by":"crossref","unstructured":"Sun, C., Myers, A., Vondrick, C., Murphy, K., Schmid, C.: VideoBERT: a joint model for video and language representation learning. In: ICCV, pp. 7464\u20137473 (2019)","DOI":"10.1109\/ICCV.2019.00756"},{"key":"32_CR40","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"590","DOI":"10.1007\/978-3-030-11012-3_45","volume-title":"Computer Vision \u2013 ECCV 2018 Workshops","author":"T Suzuki","year":"2019","unstructured":"Suzuki, T., Itazuri, T., Hara, K., Kataoka, H.: Learning spatiotemporal 3D convolution with video order self-supervision. In: Leal-Taix\u00e9, L., Roth, S. (eds.) ECCV 2018. LNCS, vol. 11130, pp. 590\u2013598. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-11012-3_45"},{"key":"32_CR41","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"402","DOI":"10.1007\/978-3-030-01261-8_24","volume-title":"Computer Vision \u2013 ECCV 2018","author":"C Vondrick","year":"2018","unstructured":"Vondrick, C., Shrivastava, A., Fathi, A., Guadarrama, S., Murphy, K.: Tracking emerges by colorizing videos. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11217, pp. 402\u2013419. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01261-8_24"},{"key":"32_CR42","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1007\/978-3-030-58520-4_30","volume-title":"Computer Vision \u2013 ECCV 2020","author":"J Wang","year":"2020","unstructured":"Wang, J., Jiao, J., Liu, Y.-H.: Self-supervised video representation learning by pace prediction. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12362, pp. 504\u2013521. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58520-4_30"},{"key":"32_CR43","doi-asserted-by":"crossref","unstructured":"Wang, J., et al.: Removing the background by adding the background: towards background robust self-supervised video representation learning. In: CVPR, pp. 11804\u201311813 (2021)","DOI":"10.1109\/CVPR46437.2021.01163"},{"issue":"11","key":"32_CR44","doi-asserted-by":"publisher","first-page":"2740","DOI":"10.1109\/TPAMI.2018.2868668","volume":"41","author":"L Wang","year":"2018","unstructured":"Wang, L., et al.: Temporal segment networks for action recognition in videos. IEEE Trans. Pattern Anal. Mach. Intell. 41(11), 2740\u20132755 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"32_CR45","unstructured":"Xiao, F., Tighe, J., Modolo, D.: MoDist: motion distillation for self-supervised video representation learning. arXiv preprint arXiv:2106.09703 (2021)"},{"key":"32_CR46","doi-asserted-by":"crossref","unstructured":"Xu, D., Xiao, J., Zhao, Z., Shao, J., Xie, D., Zhuang, Y.: Self-supervised spatiotemporal learning via video clip order prediction. In: CVPR, pp. 10334\u201310343 (2019)","DOI":"10.1109\/CVPR.2019.01058"},{"key":"32_CR47","doi-asserted-by":"crossref","unstructured":"Yao, Y., Liu, C., Luo, D., Zhou, Y., Ye, Q.: Video playback rate perception for self-supervised spatio-temporal representation learning. In: CVPR, pp. 6548\u20136557 (2020)","DOI":"10.1109\/CVPR42600.2020.00658"}],"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\/978-3-031-26284-5_32","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,22]],"date-time":"2023-02-22T08:19:43Z","timestamp":1677053983000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-26284-5_32"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031262838","9783031262845"],"references-count":47,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-26284-5_32","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":"23 February 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)"}}]}}