{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T05:09:28Z","timestamp":1789621768569,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":87,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726903","type":"print"},{"value":"9783031726910","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-72691-0_17","type":"book-chapter","created":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T18:04:40Z","timestamp":1730570680000},"page":"293-312","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["SIGMA: Sinkhorn-Guided Masked Video Modeling"],"prefix":"10.1007","author":[{"given":"Mohammadreza","family":"Salehi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Dorkenwald","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fida Mohammad","family":"Thoker","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Efstratios","family":"Gavves","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cees G. M.","family":"Snoek","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuki M.","family":"Asano","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,11,3]]},"reference":[{"key":"17_CR1","doi-asserted-by":"crossref","unstructured":"Arnab, A., Dehghani, M., Heigold, G., Sun, C., Lu\u010di\u0107, M., Schmid, C.: ViViT: a video vision transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"17_CR2","unstructured":"Asano, Y., Patrick, M., Rupprecht, C., Vedaldi, A.: Labelling unlabelled videos from scratch with multi-modal self-supervision. In: Advances in Neural Information Processing Systems (2020)"},{"key":"17_CR3","unstructured":"Asano, Y.M., Rupprecht, C., Vedaldi, A.: Self-labelling via simultaneous clustering and representation learning. In: ICLR (2020)"},{"key":"17_CR4","doi-asserted-by":"crossref","unstructured":"Assran, M., et al.: Self-supervised learning from images with a joint-embedding predictive architecture. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15619\u201315629 (2023)","DOI":"10.1109\/CVPR52729.2023.01499"},{"key":"17_CR5","unstructured":"Bardes, A., Ponce, J., LeCun, Y.: MC-JEPA: a joint-embedding predictive architecture for self-supervised learning of motion and content features (2023)"},{"key":"17_CR6","doi-asserted-by":"crossref","unstructured":"Benaim, S., et al.: SpeedNet: learning the speediness in videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9922\u20139931 (2020)","DOI":"10.1109\/CVPR42600.2020.00994"},{"key":"17_CR7","unstructured":"Bertasius, G., Wang, H., Torresani, L.: Is space-time attention all you need for video understanding? ArXiv abs\/2102.05095 (2021)"},{"key":"17_CR8","doi-asserted-by":"crossref","unstructured":"Caron, M., Bojanowski, P., Joulin, A., Douze, M.: Deep clustering for unsupervised learning of visual features. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 132\u2013149 (2018)","DOI":"10.1007\/978-3-030-01264-9_9"},{"key":"17_CR9","unstructured":"Caron, M., Misra, I., Mairal, J., Goyal, P., Bojanowski, P., Joulin, A.: Unsupervised learning of visual features by contrasting cluster assignments (2020)"},{"key":"17_CR10","doi-asserted-by":"crossref","unstructured":"Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9650\u20139660 (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"17_CR11","doi-asserted-by":"crossref","unstructured":"Chen, L., Wu, P., Chitta, K., Jaeger, B., Geiger, A., Li, H.: End-to-end autonomous driving: challenges and frontiers. arXiv preprint arXiv:2306.16927 (2023)","DOI":"10.1109\/TPAMI.2024.3435937"},{"key":"17_CR12","doi-asserted-by":"crossref","unstructured":"Chen, P., et al.: RSPNet: relative speed perception for unsupervised video representation learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a035, pp. 1045\u20131053 (2021)","DOI":"10.1609\/aaai.v35i2.16189"},{"key":"17_CR13","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International Conference on Machine Learning, pp. 1597\u20131607. PMLR (2020)"},{"key":"17_CR14","unstructured":"Cuturi, M.: Sinkhorn distances: lightspeed computation of optimal transportation distances (2013)"},{"key":"17_CR15","doi-asserted-by":"publisher","first-page":"103406","DOI":"10.1016\/j.cviu.2022.103406","volume":"219","author":"I Dave","year":"2022","unstructured":"Dave, I., Gupta, R., Rizve, M.N., Shah, M.: TCLR: temporal contrastive learning for video representation. Comput. Vis. Image Underst. 219, 103406 (2022)","journal-title":"Comput. Vis. Image Underst."},{"key":"17_CR16","unstructured":"Dehghani, M., et\u00a0al.: Scaling vision transformers to 22 billion parameters. In: International Conference on Machine Learning, pp. 7480\u20137512. PMLR (2023)"},{"key":"17_CR17","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: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"17_CR18","doi-asserted-by":"crossref","unstructured":"Dorkenwald, M., Xiao, F., Brattoli, B., Tighe, J., Modolo, D.: SCVRL: shuffled contrastive video representation learning (2022)","DOI":"10.1109\/CVPRW56347.2022.00458"},{"key":"17_CR19","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"17_CR20","doi-asserted-by":"crossref","unstructured":"Duan, H., Zhao, N., Chen, K., Lin, D.: TransRank: self-supervised video representation learning via ranking-based transformation recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3000\u20133010 (2022)","DOI":"10.1109\/CVPR52688.2022.00301"},{"issue":"2","key":"17_CR21","doi-asserted-by":"publisher","first-page":"230","DOI":"10.1109\/TETCI.2022.3141105","volume":"6","author":"J Duan","year":"2022","unstructured":"Duan, J., Yu, S., Tan, H.L., Zhu, H., Tan, C.: A survey of embodied AI: From simulators to research tasks. IEEE Trans. Emerg. Top. Comput. Intell. 6(2), 230\u2013244 (2022)","journal-title":"IEEE Trans. Emerg. Top. Comput. Intell."},{"key":"17_CR22","doi-asserted-by":"crossref","unstructured":"Fan, D., et al.: Motion-guided masking for spatiotemporal representation learning. In: ICCV, pp. 5596\u20135606. IEEE (2023)","DOI":"10.1109\/ICCV51070.2023.00517"},{"key":"17_CR23","doi-asserted-by":"crossref","unstructured":"Fan, H., et al.: Multiscale vision transformers. In: ICCV, pp. 6804\u20136815. IEEE (2021)","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"17_CR24","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., Malik, J., He, K.: Slowfast networks for video recognition. In: ICCV (2018)","DOI":"10.1109\/ICCV.2019.00630"},{"key":"17_CR25","first-page":"35946","volume":"35","author":"C Feichtenhofer","year":"2022","unstructured":"Feichtenhofer, C., Li, Y., He, K., et al.: Masked autoencoders as spatiotemporal learners. Adv. Neural. Inf. Process. Syst. 35, 35946\u201335958 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"17_CR26","doi-asserted-by":"crossref","unstructured":"Fernando, B., Bilen, H., Gavves, E., Gould, S.: Self-supervised video representation learning with odd-one-out networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3636\u20133645 (2017)","DOI":"10.1109\/CVPR.2017.607"},{"key":"17_CR27","doi-asserted-by":"crossref","unstructured":"Finn, C., Levine, S.: Deep visual foresight for planning robot motion. In: 2017 IEEE International Conference on Robotics and Automation (ICRA), pp. 2786\u20132793. IEEE (2017)","DOI":"10.1109\/ICRA.2017.7989324"},{"key":"17_CR28","unstructured":"Gidaris, S., Singh, P., Komodakis, N.: Unsupervised representation learning by predicting image rotations. arXiv preprint arXiv:1803.07728 (2018)"},{"key":"17_CR29","doi-asserted-by":"crossref","unstructured":"Girdhar, R., El-Nouby, A., Singh, M., Alwala, K.V., Joulin, A., Misra, I.: OmniMAE: single model masked pretraining on images and videos (2023)","DOI":"10.1109\/CVPR52729.2023.01003"},{"key":"17_CR30","doi-asserted-by":"crossref","unstructured":"Goyal, R., et\u00a0al.: 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":"17_CR31","unstructured":"Ha, D., Schmidhuber, J.: World models. arXiv preprint arXiv:1803.10122 (2018)"},{"key":"17_CR32","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16000\u201316009 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"17_CR33","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9729\u20139738 (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"17_CR34","doi-asserted-by":"crossref","unstructured":"Huang, B., Zhao, Z., Zhang, G., Qiao, Y., Wang, L.: MGMAE: motion guided masking for video masked autoencoding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13493\u201313504 (2023)","DOI":"10.1109\/ICCV51070.2023.01241"},{"key":"17_CR35","doi-asserted-by":"crossref","unstructured":"Huang, B., Zhao, Z., Zhang, G., Qiao, Y., Wang, L.: MGMAE: motion guided masking for video masked autoencoding. In: ICCV, pp. 13447\u201313458. IEEE (2023)","DOI":"10.1109\/ICCV51070.2023.01241"},{"key":"17_CR36","doi-asserted-by":"crossref","unstructured":"Janai, J., G\u00fcney, F., Behl, A., Geiger, A., et\u00a0al.: Computer vision for autonomous vehicles: Problems, datasets and state of the art. Found. Trends\u00ae Comput. Graph. Vision 12(1\u20133), 1\u2013308 (2020)","DOI":"10.1561\/0600000079"},{"key":"17_CR37","doi-asserted-by":"crossref","unstructured":"Kim, D., Cho, D., Kweon, I.S.: Self-supervised video representation learning with space-time cubic puzzles. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a033, pp. 8545\u20138552 (2019)","DOI":"10.1609\/aaai.v33i01.33018545"},{"key":"17_CR38","unstructured":"Krizhevsky, A., Hinton, G., et\u00a0al.: Learning multiple layers of features from tiny images (2009)"},{"key":"17_CR39","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"},{"issue":"1\u20132","key":"17_CR40","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1002\/nav.3800020109","volume":"2","author":"HW Kuhn","year":"1955","unstructured":"Kuhn, H.W.: The Hungarian method for the assignment problem. Naval Res. Logist. Q. 2(1\u20132), 83\u201397 (1955)","journal-title":"Naval Res. Logist. Q."},{"issue":"2","key":"17_CR41","doi-asserted-by":"publisher","first-page":"712","DOI":"10.1109\/TITS.2019.2962338","volume":"22","author":"S Kuutti","year":"2020","unstructured":"Kuutti, S., Bowden, R., Jin, Y., Barber, P., Fallah, S.: A survey of deep learning applications to autonomous vehicle control. IEEE Trans. Intell. Transp. Syst. 22(2), 712\u2013733 (2020)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"17_CR42","doi-asserted-by":"crossref","unstructured":"Lee, H.Y., Huang, J.B., Singh, M., Yang, M.H.: Unsupervised representation learning by sorting sequences. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 667\u2013676 (2017)","DOI":"10.1109\/ICCV.2017.79"},{"key":"17_CR43","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Video swin transformer. In: CVPR, pp. 3192\u20133201. IEEE (2022)","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"17_CR44","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization (2019)"},{"key":"17_CR45","unstructured":"Lu, C., Jin, X., Huang, Z., Hou, Q., Cheng, M., Feng, J.: CMAE-V: contrastive masked autoencoders for video action recognition. CoRR abs\/2301.06018 (2023)"},{"key":"17_CR46","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1016\/j.neunet.2022.03.037","volume":"152","author":"Y Matsuo","year":"2022","unstructured":"Matsuo, Y., et al.: Deep learning, reinforcement learning, and world models. Neural Netw. 152, 267\u2013275 (2022)","journal-title":"Neural Netw."},{"key":"17_CR47","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, Part I. LNCS, vol. 9905, pp. 527\u2013544. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_32"},{"key":"17_CR48","unstructured":"Nguyen, D.K., et al.: R-MAE: regions meet masked autoencoders. In: ICLR (2024)"},{"key":"17_CR49","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":"17_CR50","unstructured":"Oord, A.V.D., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)"},{"key":"17_CR51","doi-asserted-by":"crossref","unstructured":"Pathak, D., Krahenbuhl, P., Donahue, J., Darrell, T., Efros, A.A.: Context encoders: feature learning by inpainting. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2536\u20132544 (2016)","DOI":"10.1109\/CVPR.2016.278"},{"key":"17_CR52","unstructured":"Patrick, M., et al.: Multi-modal self-supervision from generalized data transformations (2020)"},{"key":"17_CR53","unstructured":"Photutorial.com: Key YouTube video statistics in 2024 (2024)"},{"key":"17_CR54","unstructured":"Pont-Tuset, J., Perazzi, F., Caelles, S., Arbel\u00e1ez, P., Sorkine-Hornung, A., Van\u00a0Gool, L.: The 2017 DAVIS challenge on video object segmentation. arXiv preprint arXiv:1704.00675 (2017)"},{"key":"17_CR55","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":"17_CR56","doi-asserted-by":"crossref","unstructured":"Ranasinghe, K., Naseer, M., Khan, S., Khan, F.S., Ryoo, M.S.: Self-supervised video transformer. In: CVPR, pp. 2864\u20132874. IEEE (2022)","DOI":"10.1109\/CVPR52688.2022.00289"},{"key":"17_CR57","doi-asserted-by":"publisher","DOI":"10.1002\/0470847832","volume-title":"Video Codec Design: Developing Image and Video Compression Systems","author":"IE Richardson","year":"2002","unstructured":"Richardson, I.E.: Video Codec Design: Developing Image and Video Compression Systems. Wiley, Hoboken (2002)"},{"key":"17_CR58","doi-asserted-by":"crossref","unstructured":"Salehi, M., Gavves, E., Snoek, C.G., Asano, Y.M.: Time does tell: self-supervised time-tuning of dense image representations. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 16536\u201316547 (2023)","DOI":"10.1109\/ICCV51070.2023.01516"},{"key":"17_CR59","doi-asserted-by":"crossref","unstructured":"Shao, D., Zhao, Y., Dai, B., Lin, D.: FineGym: a hierarchical video dataset for fine-grained action understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2616\u20132625 (2020)","DOI":"10.1109\/CVPR42600.2020.00269"},{"key":"17_CR60","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"510","DOI":"10.1007\/978-3-319-46448-0_31","volume-title":"Computer Vision \u2013 ECCV 2016","author":"GA Sigurdsson","year":"2016","unstructured":"Sigurdsson, G.A., Varol, G., Wang, X., Farhadi, A., Laptev, I., Gupta, A.: Hollywood in homes: crowdsourcing data collection for activity understanding. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016, Part I. LNCS, vol. 9905, pp. 510\u2013526. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_31"},{"key":"17_CR61","doi-asserted-by":"crossref","unstructured":"Singh, M., et al.: The effectiveness of MAE pre-pretraining for billion-scale pretraining. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00505"},{"key":"17_CR62","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":"17_CR63","doi-asserted-by":"crossref","unstructured":"Sun, X., et al.: Masked motion encoding for self-supervised video representation learning. In: CVPR, pp. 2235\u20132245. IEEE (2023)","DOI":"10.1109\/CVPR52729.2023.00222"},{"key":"17_CR64","doi-asserted-by":"crossref","unstructured":"Tao, L., Wang, X., Yamasaki, T.: Self-supervised video representation learning using inter-intra contrastive framework. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 2193\u20132201 (2020)","DOI":"10.1145\/3394171.3413694"},{"key":"17_CR65","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"632","DOI":"10.1007\/978-3-031-19830-4_36","volume-title":"Computer Vision \u2013 ECCV 2022","author":"FM Thoker","year":"2022","unstructured":"Thoker, F.M., Doughty, H., Bagad, P., Snoek, C.G.M.: How severe is benchmark-sensitivity in video self-supervised learning? In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13694, pp. 632\u2013652. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19830-4_36"},{"key":"17_CR66","doi-asserted-by":"crossref","unstructured":"Thoker, F.M., Doughty, H., Snoek, C.: Tubelet-contrastive self-supervision for video-efficient generalization (2023)","DOI":"10.1109\/ICCV51070.2023.01270"},{"key":"17_CR67","doi-asserted-by":"crossref","unstructured":"Thoker, F.M., Doughty, H., Snoek, C.G.M.: Tubelet-contrastive self-supervision for video-efficient generalization. In: ICCV, pp. 13766\u201313777. IEEE (2023)","DOI":"10.1109\/ICCV51070.2023.01270"},{"key":"17_CR68","unstructured":"Tong, Z., Song, Y., Wang, J., Wang, L.: VideoMAE: masked autoencoders are data-efficient learners for self-supervised video pre-training. In: NeurIPS (2022)"},{"key":"17_CR69","first-page":"10078","volume":"35","author":"Z Tong","year":"2022","unstructured":"Tong, Z., Song, Y., Wang, J., Wang, L.: VideoMAE: masked autoencoders are data-efficient learners for self-supervised video pre-training. Adv. Neural. Inf. Process. Syst. 35, 10078\u201310093 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"17_CR70","unstructured":"Touvron, H., et al.: LLaMA 2: open foundation and fine-tuned chat models. CoRR abs\/2307.09288 (2023)"},{"key":"17_CR71","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":"17_CR72","doi-asserted-by":"crossref","unstructured":"Wang, J., et al.: Enhancing unsupervised video representation learning by decoupling the scene and the motion. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a035, pp. 10129\u201310137 (2021)","DOI":"10.1609\/aaai.v35i11.17215"},{"key":"17_CR73","doi-asserted-by":"crossref","unstructured":"Wang, L., et al.: VideoMAE v2: scaling video masked autoencoders with dual masking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 14549\u201314560 (2023)","DOI":"10.1109\/CVPR52729.2023.01398"},{"key":"17_CR74","doi-asserted-by":"crossref","unstructured":"Wang, R., et al.: BEVT: BERT pretraining of video transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14733\u201314743 (2022)","DOI":"10.1109\/CVPR52688.2022.01432"},{"key":"17_CR75","doi-asserted-by":"crossref","unstructured":"Wang, R., et al.: Masked video distillation: rethinking masked feature modeling for self-supervised video representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6312\u20136322 (2023)","DOI":"10.1109\/CVPR52729.2023.00611"},{"key":"17_CR76","doi-asserted-by":"crossref","unstructured":"Wang, R., et al.: Masked video distillation: Rethinking masked feature modeling for self-supervised video representation learning. In: CVPR, pp. 6312\u20136322. IEEE (2023)","DOI":"10.1109\/CVPR52729.2023.00611"},{"key":"17_CR77","doi-asserted-by":"crossref","unstructured":"Wei, C., Fan, H., Xie, S., Wu, C.Y., Yuille, A., Feichtenhofer, C.: Masked feature prediction for self-supervised visual pre-training. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14668\u201314678 (2022)","DOI":"10.1109\/CVPR52688.2022.01426"},{"issue":"2","key":"17_CR78","doi-asserted-by":"publisher","first-page":"1509","DOI":"10.1109\/LRA.2019.2895390","volume":"4","author":"L Wellhausen","year":"2019","unstructured":"Wellhausen, L., Dosovitskiy, A., Ranftl, R., Walas, K., Cadena, C., Hutter, M.: Where should i walk? Predicting terrain properties from images via self-supervised learning. IEEE Robot. Autom. Lett. 4(2), 1509\u20131516 (2019)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"17_CR79","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":"17_CR80","doi-asserted-by":"crossref","unstructured":"Xie, Z., et al.: SimMIM: a simple framework for masked image modeling. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9653\u20139663 (2022)","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"17_CR81","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10334\u201310343 (2019)","DOI":"10.1109\/CVPR.2019.01058"},{"key":"17_CR82","unstructured":"Xu, N., et al.: YouTube-VOS: a large-scale video object segmentation benchmark. arXiv preprint arXiv:1809.03327 (2018)"},{"key":"17_CR83","unstructured":"Yang, H., et al.: Self-supervised video representation learning with motion-aware masked autoencoders. arXiv preprint arXiv:2210.04154 (2022)"},{"key":"17_CR84","doi-asserted-by":"crossref","unstructured":"Yao, T., Zhang, Y., Qiu, Z., Pan, Y., Mei, T.: SeCo: exploring sequence supervision for unsupervised representation learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a035, pp. 10656\u201310664 (2021)","DOI":"10.1609\/aaai.v35i12.17274"},{"key":"17_CR85","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6548\u20136557 (2020)","DOI":"10.1109\/CVPR42600.2020.00658"},{"key":"17_CR86","doi-asserted-by":"crossref","unstructured":"Zhang, H., Xu, X., Han, G., He, S.: Context-aware and scale-insensitive temporal repetition counting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00075"},{"key":"17_CR87","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.A.: Colorful image colorization. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016, Part III. LNCS, vol. 9907, pp. 649\u2013666. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46487-9_40"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72691-0_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T18:08:10Z","timestamp":1730570890000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72691-0_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,3]]},"ISBN":["9783031726903","9783031726910"],"references-count":87,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72691-0_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,3]]},"assertion":[{"value":"3 November 2024","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":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}