{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T18:17:08Z","timestamp":1782152228110,"version":"3.54.5"},"publisher-location":"Cham","reference-count":62,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031730030","type":"print"},{"value":"9783031730047","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"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\/978-3-031-73004-7_7","type":"book-chapter","created":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T17:02:14Z","timestamp":1730394134000},"page":"104-122","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Hierarchical Separable Video Transformer for\u00a0Snapshot Compressive Imaging"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-2746-5102","authenticated-orcid":false,"given":"Ping","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2288-5079","authenticated-orcid":false,"given":"Yulun","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3245-9265","authenticated-orcid":false,"given":"Lishun","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8311-7524","authenticated-orcid":false,"given":"Xin","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,11,1]]},"reference":[{"key":"7_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: International Conference on Computer Vision, pp. 6836\u20136846 (2021)","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"7_CR2","unstructured":"Bertasius, G., Wang, H., Torresani, L.: Is space-time attention all you need for video understanding? In: International Conference on Machine Learning, vol.\u00a02, p.\u00a04 (2021)"},{"key":"7_CR3","unstructured":"Boyd, S., Parikh, N., Chu, E., Peleato, B., Eckstein, J., et\u00a0al.: Distributed optimization and statistical learning via the alternating direction method of multipliers. Found. Trends\u00ae Mach. Learn. 3(1), 1\u2013122 (2011)"},{"key":"7_CR4","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., et al.: Language models are few-shot learners. Adv. Neural Inform. Process. Syst. 33, 1877\u20131901 (2020)","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"7_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":"7_CR6","doi-asserted-by":"crossref","unstructured":"Chan, K.C., Zhou, S., Xu, X., Loy, C.C.: Investigating tradeoffs in real-world video super-resolution. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 5962\u20135971 (2022)","DOI":"10.1109\/CVPR52688.2022.00587"},{"key":"7_CR7","doi-asserted-by":"crossref","unstructured":"Chen, H., et al.: Pre-trained image processing transformer. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 12299\u201312310 (2021)","DOI":"10.1109\/CVPR46437.2021.01212"},{"key":"7_CR8","doi-asserted-by":"crossref","unstructured":"Chen, Z., Zhang, Y., Gu, J., Kong, L., Yang, X.: Recursive generalization transformer for image super-resolution. In: International Conference on Learning Representation (2024)","DOI":"10.1109\/ICCV51070.2023.01131"},{"key":"7_CR9","doi-asserted-by":"crossref","unstructured":"Chen, Z., Zhang, Y., Gu, J., Kong, L., Yang, X., Yu, F.: Dual aggregation transformer for image super-resolution. In: International Conference on Computer Vision, pp. 12312\u201312321 (2023)","DOI":"10.1109\/ICCV51070.2023.01131"},{"key":"7_CR10","first-page":"25478","volume":"35","author":"Z Chen","year":"2022","unstructured":"Chen, Z., Zhang, Y., Gu, J., Kong, L., Yuan, X., et al.: Cross aggregation transformer for image restoration. Adv. Neural Inform. Process. Syst. 35, 25478\u201325490 (2022)","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"7_CR11","doi-asserted-by":"crossref","unstructured":"Cheng, Z., et al.: Memory-efficient network for large-scale video compressive sensing. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 16246\u201316255 (2021)","DOI":"10.1109\/CVPR46437.2021.01598"},{"issue":"2","key":"7_CR12","doi-asserted-by":"publisher","first-page":"2264","DOI":"10.1109\/TPAMI.2022.3161934","volume":"45","author":"Z Cheng","year":"2022","unstructured":"Cheng, Z., et al.: Recurrent neural networks for snapshot compressive imaging. IEEE Trans. Pattern Anal. Mach. Intell. 45(2), 2264\u20132281 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"7_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"258","DOI":"10.1007\/978-3-030-58586-0_16","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Z Cheng","year":"2020","unstructured":"Cheng, Z., et al.: BIRNAT: bidirectional recurrent neural networks with adversarial training for video snapshot compressive imaging. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12369, pp. 258\u2013275. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58586-0_16"},{"key":"7_CR14","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: Transformers for image recognition at scale. In: International Conference on Learning Representation (2020)"},{"issue":"2","key":"7_CR15","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1109\/MSP.2007.914730","volume":"25","author":"MF Duarte","year":"2008","unstructured":"Duarte, M.F., et al.: Single-pixel imaging via compressive sampling. IEEE Sign. Process. Mag. 25(2), 83\u201391 (2008)","journal-title":"IEEE Sign. Process. Mag."},{"issue":"7529","key":"7_CR16","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1038\/nature14005","volume":"516","author":"L Gao","year":"2014","unstructured":"Gao, L., Liang, J., Li, C., Wang, L.V.: Single-shot compressed ultrafast photography at one hundred billion frames per second. Nature 516(7529), 74\u201377 (2014)","journal-title":"Nature"},{"key":"7_CR17","doi-asserted-by":"crossref","unstructured":"Hitomi, Y., Gu, J., Gupta, M., Mitsunaga, T., Nayar, S.K.: Video from a single coded exposure photograph using a learned over-complete dictionary. In: International Conference on Computer Vision, pp. 287\u2013294 (2011)","DOI":"10.1109\/ICCV.2011.6126254"},{"key":"7_CR18","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 7132\u20137141 (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"7_CR19","unstructured":"Kenton, J.D.M.W.C., Toutanova, L.K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of NAACL-HLT, pp. 4171\u20134186 (2019)"},{"issue":"12","key":"7_CR20","doi-asserted-by":"publisher","first-page":"15992","DOI":"10.1364\/OE.23.015992","volume":"23","author":"R Koller","year":"2015","unstructured":"Koller, R., et al.: High spatio-temporal resolution video with compressed sensing. Opt. Express 23(12), 15992\u201316007 (2015)","journal-title":"Opt. Express"},{"key":"7_CR21","doi-asserted-by":"crossref","unstructured":"Lai, Z., Yan, C., Fu, Y.: Hybrid spectral denoising transformer with guided attention. In: International Conference on Computer Vision, pp. 13065\u201313075 (2023)","DOI":"10.1109\/ICCV51070.2023.01201"},{"key":"7_CR22","doi-asserted-by":"crossref","unstructured":"Liang, J., et al.: VRT: a video restoration transformer. IEEE Trans. Image Process. 33, 2171\u20132182 (2024)","DOI":"10.1109\/TIP.2024.3372454"},{"key":"7_CR23","doi-asserted-by":"crossref","unstructured":"Liang, J., Cao, J., Sun, G., Zhang, K., Van\u00a0Gool, L., Timofte, R.: Swinir: Image restoration using swin transformer. In: International Conference on Computer Vision Workshop, pp. 1833\u20131844 (2021)","DOI":"10.1109\/ICCVW54120.2021.00210"},{"key":"7_CR24","first-page":"378","volume":"35","author":"J Liang","year":"2022","unstructured":"Liang, J., et al.: Recurrent video restoration transformer with guided deformable attention. Adv. Neural Inform. Process. Syst. 35, 378\u2013393 (2022)","journal-title":"Adv. Neural Inform. Process. Syst."},{"issue":"2","key":"7_CR25","doi-asserted-by":"publisher","first-page":"797","DOI":"10.1137\/130936658","volume":"7","author":"X Liao","year":"2014","unstructured":"Liao, X., Li, H., Carin, L.: Generalized alternating projection for weighted-2,1 minimization with applications to model-based compressive sensing. SIAM J. Imag. Sci. 7(2), 797\u2013823 (2014)","journal-title":"SIAM J. Imag. Sci."},{"issue":"12","key":"7_CR26","doi-asserted-by":"publisher","first-page":"2990","DOI":"10.1109\/TPAMI.2018.2873587","volume":"41","author":"Y Liu","year":"2019","unstructured":"Liu, Y., Yuan, X., Suo, J., Brady, D.J., Dai, Q.: Rank minimization for snapshot compressive imaging. IEEE Trans. Pattern Anal. Mach. Intell. 41(12), 2990\u20133006 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"7_CR27","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"7_CR28","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Video swin transformer. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3202\u20133211 (2022)","DOI":"10.1109\/CVPR52688.2022.00320"},{"issue":"9","key":"7_CR29","doi-asserted-by":"publisher","first-page":"10526","DOI":"10.1364\/OE.21.010526","volume":"21","author":"P Llull","year":"2013","unstructured":"Llull, P., et al.: Coded aperture compressive temporal imaging. Opt. Express 21(9), 10526\u201310545 (2013)","journal-title":"Opt. Express"},{"key":"7_CR30","unstructured":"Lu, J., et al.: Soft: softmax-free transformer with linear complexity. Adv. Neural Inform. Process. Syst. 34, 21297\u201321309 (2021)"},{"key":"7_CR31","doi-asserted-by":"crossref","unstructured":"Ma, J., Liu, X.Y., Shou, Z., Yuan, X.: Deep tensor admm-net for snapshot compressive imaging. In: International Conference on Computer Vision, pp. 10223\u201310232 (2019)","DOI":"10.1109\/ICCV.2019.01032"},{"issue":"7","key":"7_CR32","doi-asserted-by":"publisher","first-page":"1642","DOI":"10.1109\/TPAMI.2020.2986944","volume":"42","author":"JN Martel","year":"2020","unstructured":"Martel, J.N., Mueller, L.K., Carey, S.J., Dudek, P., Wetzstein, G.: Neural sensors: Learning pixel exposures for HDR imaging and video compressive sensing with programmable sensors. IEEE Trans. Pattern Anal. Mach. Intell. 42(7), 1642\u20131653 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"7_CR33","doi-asserted-by":"crossref","unstructured":"Mei, Y., et al.: Pyramid attention network for image restoration. Int. J. Comput. Vis. 131(12), 3207\u20133225 (2023)","DOI":"10.1007\/s11263-023-01843-5"},{"issue":"11","key":"7_CR34","doi-asserted-by":"publisher","first-page":"2933","DOI":"10.1007\/s11263-023-01844-4","volume":"131","author":"Z Meng","year":"2023","unstructured":"Meng, Z., Yuan, X., Jalali, S.: Deep unfolding for snapshot compressive imaging. Int. J. Comput. Vis. 131(11), 2933\u20132958 (2023)","journal-title":"Int. J. Comput. Vis."},{"key":"7_CR35","unstructured":"Park, N., Kim, S.: How do vision transformers work? In: International Conference on Learning Representation (2022)"},{"key":"7_CR36","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":"7_CR37","doi-asserted-by":"crossref","unstructured":"Qiao, M., Meng, Z., Ma, J., Yuan, X.: Deep learning for video compressive sensing. APL Photon. 5(3) (2020)","DOI":"10.1063\/1.5140721"},{"key":"7_CR38","doi-asserted-by":"crossref","unstructured":"Qu, G., Wang, P., Yuan, X.: Dual-scale transformer for large-scale single-pixel imaging. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 25327\u201325337 (2024)","DOI":"10.1109\/CVPR52733.2024.02393"},{"key":"7_CR39","doi-asserted-by":"crossref","unstructured":"Reddy, D., Veeraraghavan, A., Chellappa, R.: P2C2: programmable pixel compressive camera for high speed imaging. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 329\u2013336 (2011)","DOI":"10.1109\/CVPR.2011.5995542"},{"key":"7_CR40","first-page":"10","volume":"29","author":"J Sun","year":"2016","unstructured":"Sun, J., Li, H., Xu, Z., et al.: Deep ADMM-net for compressive sensing MRI. Adv. Neural Inform. Process. Syst. 29, 10\u201318 (2016)","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"7_CR41","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inform. Process. Syst. 30 (2017)"},{"issue":"5","key":"7_CR42","doi-asserted-by":"publisher","first-page":"957","DOI":"10.1063\/1.1138645","volume":"57","author":"E Voigtman","year":"1986","unstructured":"Voigtman, E., Winefordner, J.D.: Low-pass filters for signal averaging. Rev. Sci. Instrum. 57(5), 957\u2013966 (1986)","journal-title":"Rev. Sci. Instrum."},{"key":"7_CR43","doi-asserted-by":"crossref","unstructured":"Wang, L., Cao, M., Yuan, X.: EfficientSci: densely connected network with space-time factorization for large-scale video snapshot compressive imaging. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 18477\u201318486 (2023)","DOI":"10.1109\/CVPR52729.2023.01772"},{"issue":"7","key":"7_CR44","first-page":"9072","volume":"45","author":"L Wang","year":"2022","unstructured":"Wang, L., Cao, M., Zhong, Y., Yuan, X.: Spatial-temporal transformer for video snapshot compressive imaging. IEEE Trans. Pattern Anal. Mach. Intell. 45(7), 9072\u20139089 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"7_CR45","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"285","DOI":"10.1007\/978-3-031-20053-3_17","volume-title":"Computer Vision \u2013 ECCV 2022","author":"P Wang","year":"2022","unstructured":"Wang, P., et al.: KVT: k-NN attention for boosting vision transformers. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13684, pp. 285\u2013302. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20053-3_17"},{"issue":"18","key":"7_CR46","doi-asserted-by":"publisher","first-page":"4813","DOI":"10.1364\/OL.499735","volume":"48","author":"P Wang","year":"2023","unstructured":"Wang, P., Wang, L., Qiao, M., Yuan, X.: Full-resolution and full-dynamic-range coded aperture compressive temporal imaging. Opt. Lett. 48(18), 4813\u20134816 (2023)","journal-title":"Opt. Lett."},{"key":"7_CR47","doi-asserted-by":"crossref","unstructured":"Wang, P., Wang, L., Yuan, X.: Deep optics for video snapshot compressive imaging. In: International Conference on Computer Vision, pp. 10646\u201310656 (2023)","DOI":"10.1109\/ICCV51070.2023.00977"},{"key":"7_CR48","doi-asserted-by":"crossref","unstructured":"Wang, P., Yuan, X.: SaUNet: spatial-attention unfolding network for image compressive sensing. In: ACM International Conference on Multimedia, pp. 5099\u20135108 (2023)","DOI":"10.1145\/3581783.3612242"},{"key":"7_CR49","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: Pyramid vision transformer: a versatile backbone for dense prediction without convolutions. In: International Conference on Computer Vision, pp. 568\u2013578 (2021)","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"7_CR50","doi-asserted-by":"crossref","unstructured":"Wang, Z., Cun, X., Bao, J., Zhou, W., Liu, J., Li, H.: UFormer: a general U-shaped transformer for image restoration. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 17683\u201317693 (2022)","DOI":"10.1109\/CVPR52688.2022.01716"},{"key":"7_CR51","doi-asserted-by":"crossref","unstructured":"Wang, Z., Zhang, H., Cheng, Z., Chen, B., Yuan, X.: MetaSci: scalable and adaptive reconstruction for video compressive sensing. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2083\u20132092 (2021)","DOI":"10.1109\/CVPR46437.2021.00212"},{"key":"7_CR52","unstructured":"Wu, Z., Zhang, J., Mou, C.: Dense deep unfolding network with 3D-CNN prior for snapshot compressive imaging. In: International Conference on Computer Vision, pp. 4892\u20134901 (2021)"},{"key":"7_CR53","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1007\/978-3-031-20050-2_35","volume-title":"Computer Vision \u2013 ECCV 2022","author":"C Yang","year":"2022","unstructured":"Yang, C., Zhang, S., Yuan, X.: Ensemble learning priors driven deep unfolding for scalable video snapshot compressive imaging. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13683, pp. 600\u2013618. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20050-2_35"},{"key":"7_CR54","doi-asserted-by":"crossref","unstructured":"Yuan, X.: Generalized alternating projection based total variation minimization for compressive sensing. In: IEEE International Conference on Image Processing, pp. 2539\u20132543 (2016)","DOI":"10.1109\/ICIP.2016.7532817"},{"key":"7_CR55","doi-asserted-by":"crossref","unstructured":"Yuan, X., Liu, Y., Suo, J., Dai, Q.: Plug-and-play algorithms for large-scale snapshot compressive imaging. In: IEEE Conference on Computer Vision and Pattern Recognition (2020)","DOI":"10.1109\/CVPR42600.2020.00152"},{"issue":"2","key":"7_CR56","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1109\/MSP.2020.3023869","volume":"38","author":"X Yuan","year":"2021","unstructured":"Yuan, X., Brady, D.J., Katsaggelos, A.K.: Snapshot compressive imaging: theory, algorithms, and applications. IEEE Sign. Process. Mag. 38(2), 65\u201388 (2021)","journal-title":"IEEE Sign. Process. Mag."},{"issue":"10","key":"7_CR57","doi-asserted-by":"publisher","first-page":"7093","DOI":"10.1109\/TPAMI.2021.3099035","volume":"44","author":"X Yuan","year":"2021","unstructured":"Yuan, X., Liu, Y., Suo, J., Durand, F., Dai, Q.: Plug-and-play algorithms for video snapshot compressive imaging. IEEE Trans. Pattern Anal. Mach. Intell. 44(10), 7093\u20137111 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"7_CR58","doi-asserted-by":"crossref","unstructured":"Yuan, X., et al.: Low-cost compressive sensing for color video and depth. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3318\u20133325 (2014)","DOI":"10.1109\/CVPR.2014.424"},{"key":"7_CR59","doi-asserted-by":"crossref","unstructured":"Zamir, S.W., Arora, A., Khan, S., Hayat, M., Khan, F.S., Yang, M.H.: Restormer: Efficient transformer for high-resolution image restoration. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 5728\u20135739 (2022)","DOI":"10.1109\/CVPR52688.2022.00564"},{"key":"7_CR60","unstructured":"Zhang, J., Zhang, Y., Gu, J., Zhang, Y., Kong, L., Yuan, X.: Accurate image restoration with attention retractable transformer. In: International Conference on Learning Representation (2023)"},{"key":"7_CR61","doi-asserted-by":"crossref","unstructured":"Zheng, S., Yuan, X.: Unfolding framework with prior of convolution-transformer mixture and uncertainty estimation for video snapshot compressive imaging. In: International Conference on Computer Vision, pp. 12738\u201312749 (2023)","DOI":"10.1109\/ICCV51070.2023.01170"},{"key":"7_CR62","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable DETR: deformable transformers for end-to-end object detection. In: International Conference on Learning Representation (2021)"}],"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\/978-3-031-73004-7_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T17:04:30Z","timestamp":1730394270000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73004-7_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,1]]},"ISBN":["9783031730030","9783031730047"],"references-count":62,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73004-7_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,1]]},"assertion":[{"value":"1 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"}}]}}