{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T15:19:26Z","timestamp":1783610366701,"version":"3.55.0"},"publisher-location":"Cham","reference-count":58,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031734137","type":"print"},{"value":"9783031734144","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T00:00:00Z","timestamp":1729814400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T00:00:00Z","timestamp":1729814400000},"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\/978-3-031-73414-4_5","type":"book-chapter","created":{"date-parts":[[2024,10,24]],"date-time":"2024-10-24T17:02:54Z","timestamp":1729789374000},"page":"75-92","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":64,"title":["Mamba-ND: Selective State Space Modeling for\u00a0Multi-dimensional Data"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-0393-6581","authenticated-orcid":false,"given":"Shufan","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-3600-3641","authenticated-orcid":false,"given":"Harkanwar","family":"Singh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4217-6624","authenticated-orcid":false,"given":"Aditya","family":"Grover","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,25]]},"reference":[{"key":"5_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":"5_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":"5_CR3","unstructured":"Baron, E., Zimerman, I., Wolf, L.: 2-D SSM: a general spatial layer for visual transformers. arXiv preprint arXiv:2306.06635 (2023)"},{"key":"5_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":"5_CR5","unstructured":"Bi, K., Xie, L., Zhang, H., Chen, X., Gu, X., Tian, Q.: Pangu-Weather: a 3D high-resolution model for fast and accurate global weather forecast. arXiv preprint arXiv:2211.02556 (2022)"},{"key":"5_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":"5_CR7","doi-asserted-by":"crossref","unstructured":"Chen, L., et al.: SCA-CNN: spatial and channel-wise attention in convolutional networks for image captioning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5659\u20135667 (2017)","DOI":"10.1109\/CVPR.2017.667"},{"key":"5_CR8","unstructured":"Christoph, R., Pinz, F.A.: Spatiotemporal residual networks for video action recognition. Adv. Neural Inf. Process. Syst. 2 (2016)"},{"key":"5_CR9","first-page":"3965","volume":"34","author":"Z Dai","year":"2021","unstructured":"Dai, Z., Liu, H., Le, Q.V., Tan, M.: CoATNET: marrying convolution and attention for all data sizes. Adv. Neural. Inf. Process. Syst. 34, 3965\u20133977 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"5_CR10","doi-asserted-by":"publisher","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). https:\/\/doi.org\/10.1109\/CVPR.2009.5206848","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"5_CR11","doi-asserted-by":"publisher","unstructured":"Ding, M., Xiao, B., Codella, N., Luo, P., Wang, J., Yuan, L.: DaViT: dual attention vision transformers. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022. ECCV 2022. LNCS, vol. 13684, pp. 74\u201392. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20053-3_5","DOI":"10.1007\/978-3-031-20053-3_5"},{"key":"5_CR12","doi-asserted-by":"crossref","unstructured":"Dong, X., et al.: CSWin transformer: a general vision transformer backbone with cross-shaped windows. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12124\u201312134 (2022)","DOI":"10.1109\/CVPR52688.2022.01181"},{"key":"5_CR13","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"5_CR14","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":"5_CR15","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Pinz, A., Zisserman, A.: Convolutional two-stream network fusion for video action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1933\u20131941 (2016)","DOI":"10.1109\/CVPR.2016.213"},{"key":"5_CR16","unstructured":"Gu, A., Dao, T.: Mamba: linear-time sequence modeling with selective state spaces. arXiv preprint arXiv:2312.00752 (2023)"},{"key":"5_CR17","unstructured":"Gu, A., Goel, K., R\u00e9, C.: Efficiently modeling long sequences with structured state spaces. In: The International Conference on Learning Representations (ICLR) (2022)"},{"key":"5_CR18","doi-asserted-by":"publisher","first-page":"272","DOI":"10.1007\/978-3-031-08999-2_22","volume-title":"Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries","author":"A Hatamizadeh","year":"2022","unstructured":"Hatamizadeh, A., Nath, V., Tang, Y., Yang, D., Roth, H.R., Xu, D.: Swin UNETR: Swin transformers for\u00a0semantic segmentation of\u00a0brain tumors in\u00a0MRI images. In: Crimi, A., Bakas, S. (eds.) Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries, pp. 272\u2013284. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-08999-2_22"},{"key":"5_CR19","doi-asserted-by":"crossref","unstructured":"Hatamizadeh, A., Tang, Y., Nath, V., Yang, D., Myronenko, A., Landman, B., Roth, H.R., Xu, D.: UNETR: transformers for 3D medical image segmentation. In: Proceedings of the IEEE\/CVF winter Conference on Applications of Computer Vision, pp. 574\u2013584 (2022)","DOI":"10.1109\/WACV51458.2022.00181"},{"key":"5_CR20","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"5_CR21","doi-asserted-by":"publisher","unstructured":"Hersbach, H., et\u00a0al.: ERA5 hourly data on single levels from 1979 to present. In: Copernicus Climate Change Service (C3S) Climate Data Store (CDS) (2018). https:\/\/doi.org\/10.24381\/cds.adbb2d47","DOI":"10.24381\/cds.adbb2d47"},{"key":"5_CR22","unstructured":"Ho, J., Kalchbrenner, N., Weissenborn, D., Salimans, T.: Axial attention in multidimensional transformers. arXiv preprint arXiv:1912.12180 (2019)"},{"key":"5_CR23","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der\u00a0Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4700\u20134708 (2017)","DOI":"10.1109\/CVPR.2017.243"},{"key":"5_CR24","doi-asserted-by":"crossref","unstructured":"Islam, M.M., Bertasius, G.: Long movie clip classification with state-space video models. arXiv preprint arXiv:2204.01692 (2022)","DOI":"10.1007\/978-3-031-19833-5_6"},{"key":"5_CR25","doi-asserted-by":"crossref","unstructured":"Islam, M.M., Hasan, M., Athrey, K.S., Braskich, T., Bertasius, G.: Efficient movie scene detection using state-space transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18749\u201318758 (2023)","DOI":"10.1109\/CVPR52729.2023.01798"},{"key":"5_CR26","unstructured":"Kay, W., et\u00a0al.: The kinetics human action video dataset. arXiv preprint arXiv:1705.06950 (2017)"},{"key":"5_CR27","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. Adv. Neural Inf. Process. Syst. 25 (2012)"},{"key":"5_CR28","doi-asserted-by":"crossref","unstructured":"Kuehne, H., Arslan, A., Serre, T.: The language of actions: recovering the syntax and semantics of goal-directed human activities. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 780\u2013787 (2014)","DOI":"10.1109\/CVPR.2014.105"},{"key":"5_CR29","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":"5_CR30","unstructured":"Landman, B., Xu, Z., Igelsias, J., Styner, M., Langerak, T., Klein, A.: MICCAI multi-atlas labeling beyond the cranial vault\u2013workshop and challenge. In: Proceedings of the MICCAI Multi-Atlas Labeling Beyond Cranial Vault-Workshop Challenge, vol.\u00a05, p.\u00a012 (2015)"},{"key":"5_CR31","unstructured":"LeCun, Y., et al.: Handwritten Digit Recognition with a Back-Propagation Network. In: Advances in Neural Information Processing Systems, vol.\u00a02. Morgan-Kaufmann (1989)"},{"key":"5_CR32","doi-asserted-by":"publisher","first-page":"340","DOI":"10.1016\/j.neucom.2020.06.014","volume":"411","author":"J Li","year":"2020","unstructured":"Li, J., Jin, K., Zhou, D., Kubota, N., Ju, Z.: Attention mechanism-based CNN for facial expression recognition. Neurocomputing 411, 340\u2013350 (2020)","journal-title":"Neurocomputing"},{"key":"5_CR33","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: MViTv2: improved multiscale vision transformers for classification and detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4804\u20134814 (2022)","DOI":"10.1109\/CVPR52688.2022.00476"},{"key":"5_CR34","doi-asserted-by":"crossref","unstructured":"Lin, X., Petroni, F., Bertasius, G., Rohrbach, M., Chang, S.F., Torresani, L.: Learning to recognize procedural activities with distant supervision. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13853\u201313863 (2022)","DOI":"10.1109\/CVPR52688.2022.01348"},{"key":"5_CR35","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin Transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"5_CR36","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":"5_CR37","doi-asserted-by":"crossref","unstructured":"Liu, Z., Mao, H., Wu, C.Y., Feichtenhofer, C., Darrell, T., Xie, S.: A convnet for the 2020s. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11976\u201311986 (2022)","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"5_CR38","first-page":"19160","volume":"34","author":"J Lu","year":"2021","unstructured":"Lu, J., Mottaghi, R., Kembhavi, A., et al.: Container: context aggregation networks. Adv. Neural. Inf. Process. Syst. 34, 19160\u201319171 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"5_CR39","doi-asserted-by":"crossref","unstructured":"Mangalam, K., et al.: Reversible vision transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10830\u201310840 (2022)","DOI":"10.1109\/CVPR52688.2022.01056"},{"key":"5_CR40","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":"5_CR41","unstructured":"Nguyen, E., et al.: S4ND: modeling images and videos as multidimensional signals using state spaces. Adv. Neural Inf. Process. Syst. 35 (2022)"},{"key":"5_CR42","unstructured":"Nguyen, T., Brandstetter, J., Kapoor, A., Gupta, J.K., Grover, A.: ClimaX: a foundation model for weather and climate. arXiv preprint arXiv:2301.10343 (2023)"},{"key":"5_CR43","unstructured":"Nguyen, T., Jewik, J., Bansal, H., Sharma, P., Grover, A.: ClimateLearn: benchmarking machine learning for weather and climate modeling. arXiv preprint arXiv:2307.01909 (2023)"},{"key":"5_CR44","unstructured":"Nguyen, T., et al.: Scaling transformer neural networks for skillful and reliable medium-range weather forecasting. arXiv preprint arXiv:2312.03876 (2023)"},{"key":"5_CR45","unstructured":"Poli, M., et al.: Hyena hierarchy: towards larger convolutional language models. arXiv preprint arXiv:2302.10866 (2023)"},{"key":"5_CR46","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"5_CR47","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":"5_CR48","doi-asserted-by":"crossref","unstructured":"Szegedy, C., et al.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.\u00a01\u20139 (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"5_CR49","doi-asserted-by":"crossref","unstructured":"Tian, Y., et al.: Integrally pre-trained transformer pyramid networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18610\u201318620 (2023)","DOI":"10.1109\/CVPR52729.2023.01785"},{"key":"5_CR50","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":"5_CR51","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":"5_CR52","unstructured":"Van Den\u00a0Oord, A., Kalchbrenner, N., Kavukcuoglu, K.: Pixel recurrent neural networks. In: International Conference on Machine Learning, pp. 1747\u20131756. PMLR (2016)"},{"key":"5_CR53","unstructured":"Vaswani, A., et al.: Attention is All You Need. In: Advances of the Neural Information Processing Systems, vol. 30. Curran Associates, Inc. (2017)"},{"key":"5_CR54","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":"5_CR55","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":"5_CR56","doi-asserted-by":"crossref","unstructured":"Zhang, B., Wang, L., Wang, Z., Qiao, Y., Wang, H.: Real-time action recognition with enhanced motion vector CNNs. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2718\u20132726 (2016)","DOI":"10.1109\/CVPR.2016.297"},{"issue":"5","key":"5_CR57","doi-asserted-by":"publisher","first-page":"2326","DOI":"10.1109\/TIP.2018.2791180","volume":"27","author":"B Zhang","year":"2018","unstructured":"Zhang, B., Wang, L., Wang, Z., Qiao, Y., Wang, H.: Real-time action recognition with deeply transferred motion vector CNNs. IEEE Trans. Image Process. 27(5), 2326\u20132339 (2018)","journal-title":"IEEE Trans. Image Process."},{"key":"5_CR58","unstructured":"Zhang, X., et al.: HiViT: a simpler and more efficient design of hierarchical vision transformer. In: The Eleventh International Conference on Learning Representations (2022)"}],"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\/978-3-031-73414-4_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,24]],"date-time":"2024-10-24T17:05:58Z","timestamp":1729789558000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73414-4_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,25]]},"ISBN":["9783031734137","9783031734144"],"references-count":58,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73414-4_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,25]]},"assertion":[{"value":"25 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"}}]}}