{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T17:56:12Z","timestamp":1742925372108,"version":"3.40.3"},"publisher-location":"Cham","reference-count":48,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031250682"},{"type":"electronic","value":"9783031250699"}],"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\/978-3-031-25069-9_2","type":"book-chapter","created":{"date-parts":[[2023,2,14]],"date-time":"2023-02-14T00:15:46Z","timestamp":1676333746000},"page":"20-38","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["MoQuad: Motion-focused Quadruple Construction for\u00a0Video Contrastive Learning"],"prefix":"10.1007","author":[{"given":"Yuan","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiacheng","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,2,14]]},"reference":[{"key":"2_CR1","doi-asserted-by":"crossref","unstructured":"Agrawal, P., Carreira, J., Malik, J.: Learning to see by moving. In: 2015 IEEE International Conference on Computer Vision (ICCV), pp. 37\u201345 (2015)","DOI":"10.1109\/ICCV.2015.13"},{"key":"2_CR2","doi-asserted-by":"crossref","unstructured":"Benaim, S., et al.: SpeedNet: Learning the speediness in videos. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9919\u20139928 (2020)","DOI":"10.1109\/CVPR42600.2020.00994"},{"key":"2_CR3","unstructured":"Cai, T.T., Frankle, J., Schwab, D.J., Morcos, A.S.: Are all negatives created equal in contrastive instance discrimination? (2020) arXiv preprint arXiv:2010.06682"},{"key":"2_CR4","doi-asserted-by":"crossref","unstructured":"Caron, M., Bojanowski, P., Mairal, J., Joulin, A.: Unsupervised pre-training of image features on non-curated data. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 2959\u20132968 (2019)","DOI":"10.1109\/ICCV.2019.00305"},{"key":"2_CR5","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? a new model and the kinetics dataset. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4724\u20134733 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"2_CR6","doi-asserted-by":"crossref","unstructured":"Chen, P., Huang, D., He, D., Long, X., Zeng, R., Wen, S., Tan, M., Gan, C.: RSPNet: Relative speed perception for unsupervised video representation learning. In: AAAI (2021)","DOI":"10.1609\/aaai.v35i2.16189"},{"key":"2_CR7","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: III, H.D., Singh, A. (eds.) In: Proceedings of the 37th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 119, pp. 1597\u20131607. PMLR (13\u201318 Jul 2020), https:\/\/proceedings.mlr.press\/v119\/chen20j.html"},{"key":"2_CR8","doi-asserted-by":"crossref","unstructured":"Chen, X., He, K.: Exploring simple siamese representation learning. (2020) ArXiv abs\/2011.10566","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"2_CR9","doi-asserted-by":"crossref","unstructured":"Diba, A., Sharma, V., Gool, L., Stiefelhagen, R.: Dynamonet: dynamic action and motion network. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 6191\u20136200 (2019)","DOI":"10.1109\/ICCV.2019.00629"},{"key":"2_CR10","doi-asserted-by":"crossref","unstructured":"Epstein, D., Chen, B., Vondrick, C.: Oops! predicting unintentional action in video. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 916\u2013926 (2020)","DOI":"10.1109\/CVPR42600.2020.00100"},{"key":"2_CR11","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., Malik, J., He, K.: SlowFast networks for video recognition. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 6201\u20136210 (2019)","DOI":"10.1109\/ICCV.2019.00630"},{"key":"2_CR12","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., Xiong, B., Girshick, R.B., He, K.: A large-scale study on unsupervised spatiotemporal representation learning. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3298\u20133308 (2021)","DOI":"10.1109\/CVPR46437.2021.00331"},{"key":"2_CR13","unstructured":"Gidaris, S., Singh, P., Komodakis, N.: Unsupervised representation learning by predicting image rotations. (2018) arXiv preprint arXiv:1803.07728"},{"key":"2_CR14","doi-asserted-by":"crossref","unstructured":"Goyal, R., Kahou, S.E., Michalski, V., Materzynska, J., Westphal, S., Kim, H., Haenel, V., Fr\u00fcnd, I., Yianilos, P.N., Mueller-Freitag, M., Hoppe, F., Thurau, C., Bax, I., Memisevic, R.: The \"something something\" video database for learning and evaluating visual common sense. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 5843\u20135851 (2017)","DOI":"10.1109\/ICCV.2017.622"},{"key":"2_CR15","unstructured":"Grill, J.B., et al.: Bootstrap your own latent: a new approach to self-supervised learning. (2020) ArXiv abs\/2006.07733"},{"key":"2_CR16","doi-asserted-by":"crossref","unstructured":"Han, T., Xie, W., Zisserman, A.: Video representation learning by dense predictive coding. In: 2019 IEEE\/CVF International Conference on Computer Vision Workshop (ICCVW), pp. 1483\u20131492 (2019)","DOI":"10.1109\/ICCVW.2019.00186"},{"key":"2_CR17","doi-asserted-by":"crossref","unstructured":"Han, T., Xie, W., Zisserman, A.: Memory-augmented dense predictive coding for video representation learning. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58580-8_19"},{"key":"2_CR18","unstructured":"Han, T., Xie, W., Zisserman, A.: Self-supervised co-training for video representation learning. (2020) ArXiv abs\/2010.09709"},{"key":"2_CR19","doi-asserted-by":"crossref","unstructured":"Hara, K., Kataoka, H., Satoh, Y.: Can spatiotemporal 3d CNNs retrace the history of 2d CNNs and imagenet? In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6546\u20136555 (2018)","DOI":"10.1109\/CVPR.2018.00685"},{"key":"2_CR20","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.B.: Momentum contrast for unsupervised visual representation learning. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9726\u20139735 (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"2_CR21","doi-asserted-by":"crossref","unstructured":"He, T., Zhang, Z., Zhang, H., Zhang, Z., Xie, J., Li, M.: Bag of tricks for image classification with convolutional neural networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 558\u2013567 (2019)","DOI":"10.1109\/CVPR.2019.00065"},{"key":"2_CR22","doi-asserted-by":"crossref","unstructured":"Hu, K., Shao, J., Liu, Y., Raj, B., Savvides, M., Shen, Z.: Contrast and order representations for video self-supervised learning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 7939\u20137949 October 2021","DOI":"10.1109\/ICCV48922.2021.00784"},{"key":"2_CR23","doi-asserted-by":"crossref","unstructured":"Huang, D., et al.: ASCNet: Self-supervised video representation learning with appearance-speed consistency. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 8096\u20138105 October 2021","DOI":"10.1109\/ICCV48922.2021.00799"},{"key":"2_CR24","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 (2021)","DOI":"10.1109\/CVPR46437.2021.01367"},{"key":"2_CR25","unstructured":"Isola, P., Zoran, D., Krishnan, D., Adelson, E.: Learning visual groups from co-occurrences in space and time. (2015) ArXiv abs\/1511.06811"},{"key":"2_CR26","doi-asserted-by":"crossref","unstructured":"Jayaraman, D., Grauman, K.: Learning image representations tied to ego-motion. In: 2015 IEEE International Conference on Computer Vision (ICCV), pp. 1413\u20131421 (2015)","DOI":"10.1109\/ICCV.2015.166"},{"key":"2_CR27","doi-asserted-by":"crossref","unstructured":"Jenni, S., Meishvili, G., Favaro, P.: Video representation learning by recognizing temporal transformations. (2020) ArXiv abs\/2007.10730","DOI":"10.1007\/978-3-030-58604-1_26"},{"key":"2_CR28","doi-asserted-by":"crossref","unstructured":"Jenni, S., Jin, H.: Time-equivariant contrastive video representation learning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 9970\u20139980 October 2021","DOI":"10.1109\/ICCV48922.2021.00982"},{"key":"2_CR29","doi-asserted-by":"crossref","unstructured":"Kolouri, S., Martin, C.E., Hoffmann, H.: Explaining distributed neural activations via unsupervised learning. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 1670\u20131678 (2017)","DOI":"10.1109\/CVPRW.2017.213"},{"key":"2_CR30","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: 2011 International conference on computer vision, pp. 2556\u20132563. IEEE (2011)","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"2_CR31","doi-asserted-by":"crossref","unstructured":"Lai, Z., Lu, E., Xie, W.: Mast: A memory-augmented self-supervised tracker. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6478\u20136487 (2020)","DOI":"10.1109\/CVPR42600.2020.00651"},{"key":"2_CR32","unstructured":"Luo, D., et al.: Video cloze procedure for self-supervised spatio-temporal learning. (2020) ArXiv abs\/2001.00294"},{"key":"2_CR33","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"527","DOI":"10.1007\/978-3-319-46448-0_32","volume-title":"Computer Vision \u2013 ECCV 2016","author":"I Misra","year":"2016","unstructured":"Misra, I., Zitnick, C.L., Hebert, M.: Shuffle and Learn: Unsupervised Learning Using Temporal Order Verification. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 527\u2013544. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_32"},{"key":"2_CR34","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1007\/978-3-319-46466-4_5","volume-title":"Computer Vision \u2013 ECCV 2016","author":"M Noroozi","year":"2016","unstructured":"Noroozi, M., Favaro, P.: Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9910, pp. 69\u201384. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46466-4_5"},{"key":"2_CR35","unstructured":"van den Oord, A., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. (2018) ArXiv abs\/1807.03748"},{"key":"2_CR36","doi-asserted-by":"crossref","unstructured":"Pan, T., Song, Y., Yang, T., Jiang, W., Liu, W.: VideoMoCo: Contrastive video representation learning with temporally adversarial examples. (2021) ArXiv abs\/2103.05905","DOI":"10.1109\/CVPR46437.2021.01105"},{"key":"2_CR37","doi-asserted-by":"crossref","unstructured":"Qian, R., et al.: Enhancing self-supervised video representation learning via multi-level feature optimization. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 7990\u20138001 October 2021","DOI":"10.1109\/ICCV48922.2021.00789"},{"key":"2_CR38","doi-asserted-by":"crossref","unstructured":"Qian, R., et al.: Spatiotemporal contrastive video representation learning. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00689"},{"key":"2_CR39","unstructured":"Soomro, K., Zamir, A.R., Shah, M.: A dataset of 101 human action classes from videos in the wild. Center for Research in Computer Vision 2 (11) (2012)"},{"key":"2_CR40","doi-asserted-by":"crossref","unstructured":"Wang, J., Jiao, J., hui Liu, Y.: Self-supervised video representation learning by pace prediction. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58520-4_30"},{"key":"2_CR41","doi-asserted-by":"crossref","unstructured":"Wang, J., Gao, Y., Li, K., Lin, Y., Ma, A.J., Sun, X.: Removing the background by adding the background: towards background robust self-supervised video representation learning. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01163"},{"key":"2_CR42","doi-asserted-by":"crossref","unstructured":"Wu, Z., Xiong, Y., Yu, S.X., Lin, D.: Unsupervised feature learning via non-parametric instance discrimination. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3733\u20133742 (2018)","DOI":"10.1109\/CVPR.2018.00393"},{"key":"2_CR43","doi-asserted-by":"crossref","unstructured":"Xie, S., Sun, C., Huang, J., Tu, Z., Murphy, K.P.: Rethinking spatiotemporal feature learning: speed-accuracy trade-offs in video classification. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"2_CR44","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: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10326\u201310335 (2019)","DOI":"10.1109\/CVPR.2019.01058"},{"key":"2_CR45","unstructured":"YM., A., C., R., A., V.: Self-labelling via simultaneous clustering and representation learning. In: International Conference on Learning Representations (2020). https:\/\/openreview.net\/forum?id=Hyx-jyBFPr"},{"key":"2_CR46","unstructured":"You, Y., Gitman, I., Ginsburg, B.: Large batch training of convolutional networks. (2017) arXiv preprint arXiv:1708.03888"},{"key":"2_CR47","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"649","DOI":"10.1007\/978-3-319-46487-9_40","volume-title":"Computer Vision \u2013 ECCV 2016","author":"R Zhang","year":"2016","unstructured":"Zhang, R., Isola, P., Efros, A.: Colorful Image Colorization. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9907, pp. 649\u2013666. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46487-9_40"},{"key":"2_CR48","doi-asserted-by":"crossref","unstructured":"Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., Torralba, A.: Learning deep features for discriminative localization. In: Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.319"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-25069-9_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T17:14:56Z","timestamp":1709831696000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-25069-9_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031250682","9783031250699"],"references-count":48,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-25069-9_2","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":"14 February 2023","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":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","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":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","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":"5804","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":"1645","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":"28% - 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":"3.21","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":"3.91","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":"From the workshops, 367 reviewed full papers have been selected for publication","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)"}}]}}