{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T16:35:34Z","timestamp":1783701334491,"version":"3.55.0"},"publisher-location":"Cham","reference-count":56,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726972","type":"print"},{"value":"9783031726989","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T00:00:00Z","timestamp":1729900800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T00:00:00Z","timestamp":1729900800000},"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\/978-3-031-72698-9_1","type":"book-chapter","created":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T04:45:57Z","timestamp":1729831557000},"page":"1-18","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":21,"title":["VideoMamba: Spatio-Temporal Selective State Space Model"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7129-2141","authenticated-orcid":false,"given":"Jinyoung","family":"Park","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-4006-6112","authenticated-orcid":false,"given":"Hee-Seon","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5101-9751","authenticated-orcid":false,"given":"Kangwook","family":"Ko","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0300-0988","authenticated-orcid":false,"given":"Minbeom","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9323-8488","authenticated-orcid":false,"given":"Changick","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,26]]},"reference":[{"key":"1_CR1","first-page":"24206","volume":"34","author":"H Akbari","year":"2021","unstructured":"Akbari, H., et al.: Vatt: transformers for multimodal self-supervised learning from raw video, audio and text. Adv. Neural. Inf. Process. Syst. 34, 24206\u201324221 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"1_CR2","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, pp. 6836\u20136846 (2021)","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"1_CR3","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":"1_CR4","unstructured":"Bertasius, G., Wang, H., Torresani, L.: Is space-time attention all you need for video understanding? In: ICML, vol.\u00a02, p.\u00a04 (2021)"},{"key":"1_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-End object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"1_CR6","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? a new model and the kinetics dataset. In: proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6299\u20136308 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"1_CR7","doi-asserted-by":"crossref","unstructured":"Chen, H., et al.: Pre-trained image processing transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12299\u201312310 (2021)","DOI":"10.1109\/CVPR46437.2021.01212"},{"key":"1_CR8","doi-asserted-by":"crossref","unstructured":"Cubuk, E.D., Zoph, B., Shlens, J., Le, Q.V.: Randaugment: practical automated data augmentation with a reduced search space. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 702\u2013703 (2020)","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"1_CR9","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (2020)"},{"key":"1_CR10","doi-asserted-by":"crossref","unstructured":"Fan, H., et al.: Multiscale vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6824\u20136835 (2021)","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"1_CR11","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., Malik, J., He, K.: Slowfast networks for video recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6202\u20136211 (2019)","DOI":"10.1109\/ICCV.2019.00630"},{"key":"1_CR12","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":"1_CR13","doi-asserted-by":"crossref","unstructured":"Gavrilyuk, K., Sanford, R., Javan, M., Snoek, C.G.: Actor-transformers for group activity recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 839\u2013848 (2020)","DOI":"10.1109\/CVPR42600.2020.00092"},{"key":"1_CR14","doi-asserted-by":"crossref","unstructured":"Goyal, R., et\u00a0al.: The \u201csomething something\" 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":"1_CR15","unstructured":"Gu, A., Dao, T.: Mamba: linear-time sequence modeling with selective state spaces. arXiv preprint arXiv:2312.00752 (2023)"},{"key":"1_CR16","unstructured":"Gu, A., Goel, K., Re, C.: Efficiently modeling long sequences with structured state spaces. In: International Conference on Learning Representations (2021)"},{"key":"1_CR17","first-page":"572","volume":"34","author":"A Gu","year":"2021","unstructured":"Gu, A., et al.: Combining recurrent, convolutional, and continuous-time models with linear state space layers. Adv. Neural. Inf. Process. Syst. 34, 572\u2013585 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"1_CR18","first-page":"22982","volume":"35","author":"A Gupta","year":"2022","unstructured":"Gupta, A., Gu, A., Berant, J.: Diagonal state spaces are as effective as structured state spaces. Adv. Neural. Inf. Process. Syst. 35, 22982\u201322994 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"1_CR19","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":"1_CR20","doi-asserted-by":"crossref","unstructured":"Hara, K., Kataoka, H., Satoh, Y.: Learning spatio-temporal features with 3d residual networks for action recognition. In: Proceedings of the IEEE International Conference on Computer Vision Workshops, pp. 3154\u20133160 (2017)","DOI":"10.1109\/ICCVW.2017.373"},{"key":"1_CR21","doi-asserted-by":"crossref","unstructured":"Hu, V.T., et al.: Zigma: a dit-style zigzag mamba diffusion model. arXiv preprint arXiv:2403.13802 (2024)","DOI":"10.1007\/978-3-031-72664-4_9"},{"key":"1_CR22","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1007\/978-3-031-19833-5_6","volume-title":"European Conference on Computer Vision","author":"MM Islam","year":"2022","unstructured":"Islam, M.M., Bertasius, G.: Long movie clip classification with state-space video models. In: Avidan, S., Brostow, G., Cisse, M., Farinella, G.M., Hassner, T. (eds.) European Conference on Computer Vision, pp. 87\u2013104. Springer, Heidelberg (2022). https:\/\/doi.org\/10.1007\/978-3-031-19833-5_6"},{"issue":"1","key":"1_CR23","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1109\/TPAMI.2012.59","volume":"35","author":"S Ji","year":"2012","unstructured":"Ji, S., Xu, W., Yang, M., Yu, K.: 3d convolutional neural networks for human action recognition. IEEE Trans. Pattern Anal. Mach. Intell. 35(1), 221\u2013231 (2012)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1_CR24","doi-asserted-by":"crossref","unstructured":"Kalman, R.E.: A new approach to linear filtering and prediction problems. J. Basic Eng. (1960)","DOI":"10.1115\/1.3662552"},{"key":"1_CR25","unstructured":"Kay, W., et\u00a0al.: The kinetics human action video dataset. arXiv preprint arXiv:1705.06950 (2017)"},{"key":"1_CR26","doi-asserted-by":"crossref","unstructured":"Kondratyuk, D., et al.: Movinets: mobile video networks for efficient video recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16020\u201316030 (2021)","DOI":"10.1109\/CVPR46437.2021.01576"},{"key":"1_CR27","doi-asserted-by":"crossref","unstructured":"Kozlov, A., Andronov, V., Gritsenko, Y.: Lightweight network architecture for real-time action recognition. In: Proceedings of the 35th Annual ACM Symposium on Applied Computing, pp. 2074\u20132080 (2020)","DOI":"10.1145\/3341105.3373906"},{"key":"1_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: 2011 International Conference on Computer Vision, pp. 2556\u20132563. IEEE (2011)","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"1_CR29","doi-asserted-by":"crossref","unstructured":"Li, S., Singh, H., Grover, A.: Mamba-nd: selective state space modeling for multi-dimensional data. arXiv preprint arXiv:2402.05892 (2024)","DOI":"10.1007\/978-3-031-73414-4_5"},{"key":"1_CR30","unstructured":"Liang, D., et al.: Pointmamba: a simple state space model for point cloud analysis. arXiv preprint arXiv:2402.10739 (2024)"},{"key":"1_CR31","doi-asserted-by":"crossref","unstructured":"Lin, J., Gan, C., Han, S.: Tsm: temporal shift module for efficient video understanding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7083\u20137093 (2019)","DOI":"10.1109\/ICCV.2019.00718"},{"key":"1_CR32","unstructured":"Liu, Y., et al.: Vmamba: visual state space model. arXiv preprint arXiv:2401.10166 (2024)"},{"key":"1_CR33","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Video swin transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3202\u20133211 (2022)","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"1_CR34","doi-asserted-by":"crossref","unstructured":"Neimark, D., Bar, O., Zohar, M., Asselmann, D.: Video transformer network. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3163\u20133172 (2021)","DOI":"10.1109\/ICCVW54120.2021.00355"},{"key":"1_CR35","first-page":"2846","volume":"35","author":"E Nguyen","year":"2022","unstructured":"Nguyen, E., et al.: S4nd: modeling images and videos as multidimensional signals with state spaces. Adv. Neural. Inf. Process. Syst. 35, 2846\u20132861 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"1_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":"1_CR37","doi-asserted-by":"crossref","unstructured":"Qiu, Z., Yao, T., Mei, T.: Learning spatio-temporal representation with pseudo-3d residual networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5533\u20135541 (2017)","DOI":"10.1109\/ICCV.2017.590"},{"key":"1_CR38","unstructured":"Smith, J.T., Warrington, A., Linderman, S.W.: Simplified state space layers for sequence modeling. arXiv preprint arXiv:2208.04933 (2022)"},{"key":"1_CR39","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818\u20132826 (2016)","DOI":"10.1109\/CVPR.2016.308"},{"key":"1_CR40","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":"1_CR41","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3d convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4489\u20134497 (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"1_CR42","doi-asserted-by":"crossref","unstructured":"Tran, D., Wang, H., Torresani, L., Ray, J., LeCun, Y., Paluri, M.: A closer look at spatiotemporal convolutions for action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6450\u20136459 (2018)","DOI":"10.1109\/CVPR.2018.00675"},{"key":"1_CR43","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"1_CR44","doi-asserted-by":"crossref","unstructured":"Wang, J., et al.: Selective structured state-spaces for long-form video understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6387\u20136397 (2023)","DOI":"10.1109\/CVPR52729.2023.00618"},{"key":"1_CR45","doi-asserted-by":"crossref","unstructured":"Wang, L., et al.: Videomae v2: scaling video masked autoencoders with dual masking (2023)","DOI":"10.1109\/CVPR52729.2023.01398"},{"key":"1_CR46","doi-asserted-by":"crossref","unstructured":"Wang, N., Zhou, W., Wang, J., Li, H.: Transformer meets tracker: exploiting temporal context for robust visual tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1571\u20131580 (2021)","DOI":"10.1109\/CVPR46437.2021.00162"},{"key":"1_CR47","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: Pyramid vision transformer: a versatile backbone for dense prediction without convolutions. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 568\u2013578 (2021)","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"1_CR48","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7794\u20137803 (2018)","DOI":"10.1109\/CVPR.2018.00813"},{"key":"1_CR49","doi-asserted-by":"crossref","unstructured":"Wu, C.Y., Feichtenhofer, C., Fan, H., He, K., Krahenbuhl, P., Girshick, R.: Long-term feature banks for detailed video understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 284\u2013293 (2019)","DOI":"10.1109\/CVPR.2019.00037"},{"key":"1_CR50","doi-asserted-by":"crossref","unstructured":"Wu, C.Y., Krahenbuhl, P.: Towards long-form video understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1884\u20131894 (2021)","DOI":"10.1109\/CVPR46437.2021.00192"},{"key":"1_CR51","doi-asserted-by":"crossref","unstructured":"Xie, S., Sun, C., Huang, J., Tu, Z., Murphy, K.: Rethinking spatiotemporal feature learning: speed-accuracy trade-offs in video classification. In: Proceedings of the European Conference on computer Vision (ECCV), pp. 305\u2013321 (2018)","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"1_CR52","unstructured":"Yang, C., Xu, Y., Dai, B., Zhou, B.: Video representation learning with visual tempo consistency. arXiv preprint arXiv:2006.15489 (2020)"},{"key":"1_CR53","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"191","DOI":"10.1007\/978-3-030-58555-6_12","volume-title":"Computer Vision \u2013 ECCV 2020","author":"M Yin","year":"2020","unstructured":"Yin, M., et al.: Disentangled non-local neural networks. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12360, pp. 191\u2013207. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58555-6_12"},{"key":"1_CR54","doi-asserted-by":"crossref","unstructured":"Zheng, S., et\u00a0al.: Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6881\u20136890 (2021)","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"1_CR55","doi-asserted-by":"crossref","unstructured":"Zhong, Z., Zheng, L., Kang, G., Li, S., Yang, Y.: Random erasing data augmentation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a034, pp. 13001\u201313008 (2020)","DOI":"10.1609\/aaai.v34i07.7000"},{"key":"1_CR56","unstructured":"Zhu, L., Liao, B., Zhang, Q., Wang, X., Liu, W., Wang, X.: Vision mamba: efficient visual representation learning with bidirectional state space model. arXiv preprint arXiv:2401.09417 (2024)"}],"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\/978-3-031-72698-9_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,30]],"date-time":"2024-11-30T07:20:42Z","timestamp":1732951242000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72698-9_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,26]]},"ISBN":["9783031726972","9783031726989"],"references-count":56,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72698-9_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,26]]},"assertion":[{"value":"26 October 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"}}]}}