{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T18:22:12Z","timestamp":1759774932199,"version":"3.41.2"},"reference-count":71,"publisher":"American Association for the Advancement of Science (AAAS)","content-domain":{"domain":["spj.science.org"],"crossmark-restriction":true},"short-container-title":["Intell Comput"],"published-print":{"date-parts":[[2023,1]]},"abstract":"<jats:p>In this study, we compare interlaced and multiscale sampling of smooth manifolds for snapshot compressive imaging. With a particular focus on spectral, spatial, and temporal focal photographic imaging systems, we show that structured transformer networks enable the efficient integration of multiscale manifolds. In the applications considered here, transformer networks enable simpler and more target-specific sampling strategies for compressive tomography.<\/jats:p>","DOI":"10.34133\/icomputing.0038","type":"journal-article","created":{"date-parts":[[2023,6,13]],"date-time":"2023-06-13T18:10:56Z","timestamp":1686679856000},"update-policy":"https:\/\/doi.org\/10.34133\/aaas_crossmark_01","source":"Crossref","is-referenced-by-count":5,"title":["Sampling for Snapshot Compressive Imaging"],"prefix":"10.34133","volume":"2","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2222-6823","authenticated-orcid":false,"given":"Minghao","family":"Hu","sequence":"first","affiliation":[{"name":"Wyant College of Optical Sciences, University of Arizona, Tucson, AZ 85721, USA."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0750-0246","authenticated-orcid":false,"given":"Zongliang","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Engineering, Westlake University, Hangzhou, Zhejiang 310030, China."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7240-3085","authenticated-orcid":false,"given":"Qian","family":"Huang","sequence":"additional","affiliation":[{"name":"Wyant College of Optical Sciences, University of Arizona, Tucson, AZ 85721, USA."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8311-7524","authenticated-orcid":false,"given":"Xin","family":"Yuan","sequence":"additional","affiliation":[{"name":"School of Engineering, Westlake University, Hangzhou, Zhejiang 310030, China."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5655-2478","authenticated-orcid":true,"given":"David","family":"Brady","sequence":"additional","affiliation":[{"name":"Wyant College of Optical Sciences, University of Arizona, Tucson, AZ 85721, USA."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"221","published-online":{"date-parts":[[2023,8,16]]},"reference":[{"key":"e_1_3_3_2_2","doi-asserted-by":"publisher","DOI":"10.1364\/AOP.7.000756"},{"issue":"7","key":"e_1_3_3_3_2","doi-asserted-by":"crossref","first-page":"1140","DOI":"10.1364\/JOSAA.21.001140","article-title":"Reference structure tomography","volume":"21","author":"Brady DJ","year":"2004","unstructured":"Brady DJ, Pitsianis NP, Sun X. Reference structure tomography. J Opt Soc Am A Opt Image Sci Vis. 2004;21(7):1140\u20131147.","journal-title":"J Opt Soc Am A Opt Image Sci Vis"},{"issue":"2","key":"e_1_3_3_4_2","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1109\/MSP.2020.3023869","article-title":"Snapshot compressive imaging: Theory, algorithms, and applications","volume":"38","author":"Yuan X","year":"2021","unstructured":"Yuan X, Brady DJ, Katsaggelos AK. Snapshot compressive imaging: Theory, algorithms, and applications. IEEE Signal Process Mag. 2021;38(2):65\u201388.","journal-title":"IEEE Signal Process Mag"},{"issue":"21","key":"e_1_3_3_5_2","first-page":"13","article-title":"Single-shot compressive spectral imaging with a dual-disperser architecture","volume":"15","author":"Gehm ME","year":"2007","unstructured":"Gehm ME, John R, Brady DJ, Willett RM, Schulz TJ. Single-shot compressive spectral imaging with a dual-disperser architecture. Opt Express. 2007;15(21):13\u201327.","journal-title":"Opt Express"},{"issue":"10","key":"e_1_3_3_6_2","doi-asserted-by":"crossref","first-page":"B44","DOI":"10.1364\/AO.47.000B44","article-title":"Single disperser design for coded aperture snapshot spectral imaging","volume":"47","author":"Wagadarikar A","year":"2008","unstructured":"Wagadarikar A, John R, Willett R, Brady D. Single disperser design for coded aperture snapshot spectral imaging. Appl Opt. 2008;47(10):B44\u2013B51.","journal-title":"Appl Opt"},{"issue":"6","key":"e_1_3_3_7_2","doi-asserted-by":"crossref","first-page":"964","DOI":"10.1109\/JSTSP.2015.2411575","article-title":"Compressive hyperspectral imaging with side information","volume":"9","author":"Yuan X","year":"2015","unstructured":"Yuan X, Tsai T, Zhu R, Llull P, Brady D, Carin L. Compressive hyperspectral imaging with side information. IEEE J Sel Top Signal Process. 2015;9(6):964\u2013976.","journal-title":"IEEE J Sel Top Signal Process"},{"issue":"6","key":"e_1_3_3_8_2","doi-asserted-by":"crossref","DOI":"10.1038\/srep25718","article-title":"Spectral camera based on ghost imaging via sparsity constraints","volume":"2016","author":"Liu Z","year":"2016","unstructured":"Liu Z, Tan S, Wu J, Li E, Shen X, Han S. Spectral camera based on ghost imaging via sparsity constraints. Sci Rep. 2016;2016(6):Article 25718.","journal-title":"Sci Rep"},{"issue":"20","key":"e_1_3_3_9_2","doi-asserted-by":"crossref","DOI":"10.1063\/1.4935941","article-title":"Dynamic metamaterial aperture for microwave imaging","volume":"107","author":"Sleasman T","year":"2015","unstructured":"Sleasman T, Imani MF, Gollub JN, Smith DR. Dynamic metamaterial aperture for microwave imaging. Appl Phys Lett. 2015;107(20):Article 204104.","journal-title":"Appl Phys Lett"},{"issue":"2","key":"e_1_3_3_10_2","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1109\/MSP.2007.914731","article-title":"An introduction to compressive sampling","volume":"25","author":"Cand\u00e8s EJ","year":"2008","unstructured":"Cand\u00e8s EJ, Wakin MB. An introduction to compressive sampling. IEEE Signal Process Mag. 2008;25(2):21\u201330.","journal-title":"IEEE Signal Process Mag"},{"issue":"9","key":"e_1_3_3_11_2","doi-asserted-by":"crossref","first-page":"526","DOI":"10.1364\/OE.21.010526","article-title":"Coded aperture compressive temporal imaging","volume":"21","author":"Llull P","year":"2013","unstructured":"Llull P, Liao X, Yuan X, Yang J, Kittle D, Carin L, Sapiro G, Brady DJ. Coded aperture compressive temporal imaging. Opt Express. 2013;21(9):526\u2013545.","journal-title":"Opt Express"},{"issue":"3","key":"e_1_3_3_12_2","doi-asserted-by":"crossref","DOI":"10.1063\/1.5140721","article-title":"Deep learning for video compressive sensing","volume":"5","author":"Qiao M","year":"2020","unstructured":"Qiao M, Meng Z, Ma J, Yuan X. Deep learning for video compressive sensing. APL Photonics. 2020;5(3):Article 030801.","journal-title":"APL Photonics"},{"issue":"4","key":"e_1_3_3_13_2","doi-asserted-by":"crossref","first-page":"1260","DOI":"10.1109\/TCE.2005.1561853","article-title":"Color filter arrays: Design and performance analysis","volume":"51","author":"Lukac R","year":"2005","unstructured":"Lukac R, Plataniotis KN. Color filter arrays: Design and performance analysis. IEEE Trans Consum Electron. 2005;51(4):1260\u20131267.","journal-title":"IEEE Trans Consum Electron"},{"key":"e_1_3_3_14_2","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1109\/34.121783","article-title":"Single lens stereo with a plenoptic camera","volume":"14","author":"Adelson EH","year":"1992","unstructured":"Adelson EH, Wang JYA. Single lens stereo with a plenoptic camera. IEEE Trans Pattern Anal Mach Intell. 1992;14:99\u2013106.","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"3","key":"e_1_3_3_15_2","doi-asserted-by":"crossref","first-page":"483","DOI":"10.1364\/OPEX.12.000483","article-title":"Three-dimensional volumetric object reconstruction using computational integral imaging","volume":"12","author":"Hong S-H","year":"2004","unstructured":"Hong S-H, Jang J-S, Javidi B. Three-dimensional volumetric object reconstruction using computational integral imaging. Opt Express. 2004;12(3):483\u2013491.","journal-title":"Opt Express"},{"issue":"8","key":"e_1_3_3_16_2","doi-asserted-by":"crossref","first-page":"1888","DOI":"10.1364\/OL.420139","article-title":"Snapshot temporal compressive microscopy using an iterative algorithm with untrained neural networks","volume":"46","author":"Qiao M","year":"2021","unstructured":"Qiao M, Liu X, Yuan X. Snapshot temporal compressive microscopy using an iterative algorithm with untrained neural networks. Opt Lett. 2021;46(8):1888\u20131891.","journal-title":"Opt Lett"},{"key":"e_1_3_3_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCI.2021.3089828"},{"key":"e_1_3_3_18_2","doi-asserted-by":"crossref","unstructured":"Meng Z Ma J Yuan X. End-to-end low cost compressive spectral imaging with spatial-spectral self-attention. European Conference on Computer Vision (ECCV). Cham: Springer; 2020.","DOI":"10.1007\/978-3-030-58592-1_12"},{"issue":"14","key":"e_1_3_3_19_2","doi-asserted-by":"crossref","first-page":"3897","DOI":"10.1364\/OL.393213","article-title":"Snapshot multispectral endomicroscopy","volume":"45","author":"Meng Z","year":"2020","unstructured":"Meng Z, Qiao M, Ma J, Yu Z, Xu K, Yuan X. Snapshot multispectral endomicroscopy. Opt Lett. 2020;45(14):3897\u20133900.","journal-title":"Opt Lett"},{"issue":"25","key":"e_1_3_3_20_2","doi-asserted-by":"crossref","DOI":"10.1088\/1361-6463\/acc7b4","article-title":"Grating based coded aperture compressive spectral imaging to reconstruct over 190 spectral bands from a snapshot measurement","volume":"56","author":"Luo T","year":"2023","unstructured":"Luo T, Wang L, Yuan X. Grating based coded aperture compressive spectral imaging to reconstruct over 190 spectral bands from a snapshot measurement. J Phys D Appl Phys. 2023;56(25):Article 254004.","journal-title":"J Phys D Appl Phys"},{"issue":"17","key":"e_1_3_3_21_2","doi-asserted-by":"crossref","first-page":"4054","DOI":"10.1364\/OL.40.004054","article-title":"Spectral-temporal compressive imaging","volume":"40","author":"Tsai T-H","year":"2015","unstructured":"Tsai T-H, Llull P, Yuan X, Brady DJ, Carin L. Spectral-temporal compressive imaging. Opt Lett. 2015;40(17):4054\u20134057.","journal-title":"Opt Lett"},{"key":"e_1_3_3_22_2","article-title":"Recent advances of deep learning for spectral snapshot compressive imaging","volume":"12317","author":"Suo J","year":"2023","unstructured":"Suo J, Wu Z, Li Z, Yuan X. Recent advances of deep learning for spectral snapshot compressive imaging. Optoelectron. Imaging Multimedia Technol. IX. 2023;12317:Article 1231702.","journal-title":"Optoelectron. Imaging Multimedia Technol. IX"},{"key":"e_1_3_3_23_2","first-page":"1","article-title":"Adaptive deep pnp algorithm for video snapshot compressive imaging","author":"Wu Z","year":"2023","unstructured":"Wu Z, Yang C, Su X, Yuan X. Adaptive deep pnp algorithm for video snapshot compressive imaging. Int J Comput Vis. 2023;1\u201318.","journal-title":"Int J Comput Vis"},{"issue":"2","key":"e_1_3_3_24_2","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1364\/OPTICA.5.000127","article-title":"Parallel cameras","volume":"5","author":"Brady DJ","year":"2018","unstructured":"Brady DJ, Pang W, Li H, Ma Z, Tao Y, Cao X. Parallel cameras. Optica. 2018;5(2):127\u2013137.","journal-title":"Optica"},{"issue":"3","key":"e_1_3_3_25_2","doi-asserted-by":"crossref","first-page":"765","DOI":"10.1145\/1073204.1073259","article-title":"High performance imaging using large camera arrays","volume":"24","author":"Wilburn B","year":"2005","unstructured":"Wilburn B, Joshi N, Vaish V, Talvala E-V, Antunez E, Barth A, Adams A, Horowitz M, Levoy M. High performance imaging using large camera arrays. ACM Trans Graphics. 2005;24(3):765\u2013776.","journal-title":"ACM Trans Graphics"},{"issue":"13","key":"e_1_3_3_26_2","doi-asserted-by":"crossref","first-page":"2871","DOI":"10.1364\/AO.45.002871","article-title":"Multiaperture imaging","volume":"45","author":"Shankar PM","year":"2006","unstructured":"Shankar PM, Hasenplaugh WC, Morrison RL, Stack RA, Neifeld MA. Multiaperture imaging. Appl Opt. 2006;45(13):2871\u20132883.","journal-title":"Appl Opt"},{"key":"e_1_3_3_27_2","doi-asserted-by":"crossref","unstructured":"Cull EC Kowalski DP Burchett JB Feller SD Brady DJ. Three-dimensional imaging with the Argus sensor array in Three-dimensional TV video and display . Boston (MA): SPIE the Convergence of Information Technologies and Communications; 2002; vol. 4864 p. 211\u2013222.","DOI":"10.1117\/12.454932"},{"issue":"13","key":"e_1_3_3_28_2","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1364\/OE.25.014008","article-title":"Heterogeneous camera array for multispectral light field imaging","volume":"25","author":"Zhao Y","year":"2017","unstructured":"Zhao Y, Yue T, Chen L, Wang H, Ma Z, Brady DJ, Cao X. Heterogeneous camera array for multispectral light field imaging. Opt Express. 2017;25(13):8\u201322.","journal-title":"Opt Express"},{"issue":"3","key":"e_1_3_3_29_2","doi-asserted-by":"crossref","first-page":"546","DOI":"10.1137\/0143035","article-title":"An inversion formula for cone-beam reconstruction","volume":"43","author":"Tuy HK","year":"1983","unstructured":"Tuy HK. An inversion formula for cone-beam reconstruction. SIAM J Appl Math. 1983;43(3):546\u2013552.","journal-title":"SIAM J Appl Math"},{"key":"e_1_3_3_30_2","unstructured":"Brady DJ. Optical imaging and spectroscopy . Hoboken (NJ): John Wiley & Sons; 2009."},{"issue":"20","key":"e_1_3_3_31_2","doi-asserted-by":"crossref","first-page":"22048","DOI":"10.1364\/OE.20.022048","article-title":"Development of a scalable image formation pipeline for multiscale gigapixel photography","volume":"20","author":"Golish D","year":"2012","unstructured":"Golish D, Vera E, Kelly K, Gong Q, Jansen P, Hughes J, Kittle D, Brady D, Gehm M. Development of a scalable image formation pipeline for multiscale gigapixel photography. Opt Express. 2012;20(20):22048\u201322062.","journal-title":"Opt Express"},{"issue":"1","key":"e_1_3_3_32_2","doi-asserted-by":"crossref","DOI":"10.1063\/5.0076022","article-title":"Intelligent meta-imagers: From compressed to learned sensing","volume":"9","author":"Saigre-Tardif C","year":"2022","unstructured":"Saigre-Tardif C, Faqiri R, Zhao H, Li L, del, Hougne P. Intelligent meta-imagers: From compressed to learned sensing. Appl Phys Rev. 2022;9(1):Article 011314.","journal-title":"Appl Phys Rev"},{"key":"e_1_3_3_33_2","doi-asserted-by":"crossref","unstructured":"He K Zhang X Ren S Sun J. Deep residual learning for image recognition. Paper presented at: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition; 27\u201330 Jun 2016; Las Vegas NV USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_3_34_2","doi-asserted-by":"crossref","unstructured":"Zhu X Lyu S Wang X Zhao Q. Tph-yolov5: Improved yolov5 based on transformer prediction head for object detection on drone-captured scenarios. Paper presented at: Proceedings of the IEEE\/CVF International Conference on Computer Vision; 11\u201317 Oct 2021; Montreal BC Canada.","DOI":"10.1109\/ICCVW54120.2021.00312"},{"issue":"12","key":"e_1_3_3_35_2","doi-asserted-by":"crossref","first-page":"2481","DOI":"10.1109\/TPAMI.2016.2644615","article-title":"Segnet: A deep convolutional encoder-decoder architecture for image segmentation","volume":"39","author":"Badrinarayanan V","year":"2017","unstructured":"Badrinarayanan V, Kendall A, Cipolla R. Segnet: A deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans Pattern Anal Mach Intell. 2017;39(12):2481\u20132495.","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"e_1_3_3_36_2","doi-asserted-by":"crossref","unstructured":"Lefkimmiatis S. Non-local color image denoising with convolutional neural networks. Paper presented at: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition; 21\u201326 Jul 2017; Honolulu HI USA.","DOI":"10.1109\/CVPR.2017.623"},{"key":"e_1_3_3_37_2","doi-asserted-by":"crossref","unstructured":"Dong C Loy CC Tang X. Accelerating the super-resolution convolutional neural network. European Conference on Computer Vision. Cham: Springer; 2016.","DOI":"10.1007\/978-3-319-46475-6_25"},{"key":"e_1_3_3_38_2","doi-asserted-by":"crossref","unstructured":"Yu J Lin Z Yang J Shen X Lu X Huang TS. Generative image inpainting with contextual attention. Paper presented at: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition; 18\u201323 Jun 2018 Salt Lake City UT USA.","DOI":"10.1109\/CVPR.2018.00577"},{"key":"e_1_3_3_39_2","first-page":"525","article-title":"Handwritten digit recognition with a back-propagation network","volume":"2","author":"LeCun Y","year":"1989","unstructured":"LeCun Y, Boser B, Denker J, Henderson D, Howard R, Hubbard W, Jackel L. Handwritten digit recognition with a back-propagation network. Adv Neural Inf Proces Syst. 1989;2:525\u2013532.","journal-title":"Adv Neural Inf Proces Syst"},{"issue":"143","key":"e_1_3_3_40_2","first-page":"18","article-title":"Generalization and network design strategies","volume":"19","author":"LeCun Y","year":"1989","unstructured":"LeCun Y. Generalization and network design strategies. Conn perspective. 1989;19(143-155):18.","journal-title":"Conn perspective"},{"key":"e_1_3_3_41_2","doi-asserted-by":"crossref","unstructured":"Wang L Sun C Fu Y Kim MH Huang H. Hyperspectral image reconstruction using a deep spatial-spectral prior. Paper presented at: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR); 15\u201320 Jun 2019; Long Beach CA USA.","DOI":"10.1109\/CVPR.2019.00822"},{"key":"e_1_3_3_42_2","unstructured":"Meng Z Jalali S Yuan X. Gap-net for snapshot compressive imaging. ArXiv. 2020. https:\/\/doi.org\/10.48550\/arXiv.2012.08364"},{"key":"e_1_3_3_43_2","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1016\/j.dsp.2017.09.010","article-title":"Deep fully-connected networks for video compressive sensing","volume":"72","author":"Iliadis M","year":"2018","unstructured":"Iliadis M, Spinoulas L, Katsaggelos AK. Deep fully-connected networks for video compressive sensing. Digit Signal Process. 2018;72:9\u201318.","journal-title":"Digit Signal Process"},{"key":"e_1_3_3_44_2","doi-asserted-by":"crossref","unstructured":"Zhao E Deshler N Monakhova Waller L. Multi-sensor lensless imaging: Synthetic large-format sensing with a disjoint sensor array. In: Computational optical sensing and imaging . Washington (DC): Optical Society of America; 2020.","DOI":"10.1364\/COSI.2020.CF2C.6"},{"issue":"1","key":"e_1_3_3_45_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41377-020-00403-7","article-title":"Miniscope3d: Optimized single-shot miniature 3d fluorescence microscopy","volume":"9","author":"Yanny K","year":"2020","unstructured":"Yanny K, Antipa N, Liberti W, Dehaeck S, Monakhova K, Liu FL, Shen K, Ng R, Waller L. Miniscope3d: Optimized single-shot miniature 3d fluorescence microscopy. Light: Sci Appl. 2020;9(1):1\u201313.","journal-title":"Light: Sci Appl"},{"key":"e_1_3_3_46_2","article-title":"Attention is all you need","volume":"30","author":"Vaswani A","year":"2017","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser\u00a0\u0141, Polosukhin I. Attention is all you need. Adv Neural Inf Proces Syst. 2017;30.","journal-title":"Adv Neural Inf Proces Syst"},{"key":"e_1_3_3_47_2","unstructured":"Devlin J Chang M-W Lee K Toutanova K. Bert: Pre-training of deep bidirectional transformers for language understanding. ArXiv. 2018. https:\/\/doi.org\/10.48550\/arXiv.1810.04805"},{"key":"e_1_3_3_48_2","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown T","year":"2020","unstructured":"Brown T, Mann B, Ryder N, Subbiah M, Kaplan JD, Dhariwal P, Neelakantan A, Shyam P, Sastry G, Askell A, et al. Language models are few-shot learners. Adv Neural Inf Proces Syst. 2020;33:1877\u20131901.","journal-title":"Adv Neural Inf Proces Syst"},{"key":"e_1_3_3_49_2","unstructured":"Dosovitskiy A Beyer L Kolesnikov A Weissenborn D Zhai X Unterthiner T Dehghani M Minderer M Heigold G Gelly S et\u00a0al. An image is worth 16x16 words: Transformers for image recognition at scale. ArXiv. 2020. https:\/\/doi.org\/10.48550\/arXiv.2010.11929"},{"key":"e_1_3_3_50_2","unstructured":"Bahdanau D Cho K Bengio Y. Neural machine translation by jointly learning to align and translate. ArXiv. 2014. https:\/\/doi.org\/10.48550\/arXiv.1409.0473"},{"key":"e_1_3_3_51_2","doi-asserted-by":"crossref","unstructured":"Parikh AP T\u00e4ckstr\u00f6m O Das D Uszkoreit J. A decomposable attention model for natural language inference. ArXiv 2016. https:\/\/doi.org\/10.48550\/arXiv.1606.01933","DOI":"10.18653\/v1\/D16-1244"},{"key":"e_1_3_3_52_2","unstructured":"Chen M Radford A Child R Wu J Jun H Luan D Sutskever I. Generative pretraining from pixels. Paper presented at: International Conference on Machine Learning. PMLR; 13\u201318 Jul 2020."},{"key":"e_1_3_3_53_2","doi-asserted-by":"crossref","unstructured":"Wu H Xiao B Codella N Liu M Dai X Yuan L Zhang L. Cvt: Introducing convolutions to vision transformers. Paper presented at: Proceedings of the IEEE\/CVF International Conference on Computer Vision; 10\u201317 Oct 2021; Montreal Canada.","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"e_1_3_3_54_2","unstructured":"Hassani A Walton S Shah N Abuduweili A Li J Shi H. Escaping the big data paradigm with compact transformers. ArXiv 2021. https:\/\/doi.org\/10.48550\/arXiv.2104.05704"},{"key":"e_1_3_3_55_2","doi-asserted-by":"crossref","unstructured":"Carion N Massa F Synnaeve G Usunier N Kirillov A Zagoruyko S. End-to-end object detection with transformers. European Conference on Computer Vision. Cham: Springer; 2020.","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"e_1_3_3_56_2","unstructured":"Zhu X Su W Lu L Li B Wang X Dai J. Deformable detr: Deformable transformers for end-to-end object detection. ArXiv 2020. https:\/\/doi.org\/10.48550\/arXiv.2010.04159"},{"key":"e_1_3_3_57_2","doi-asserted-by":"crossref","unstructured":"Zheng S Lu J Zhao H Zhu X Luo Z Wang Y Fu Y Feng J Xiang T Torr PH et\u00a0al. Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers. Paper presented at: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition; June 2021.","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"e_1_3_3_58_2","doi-asserted-by":"crossref","unstructured":"Chen H Wang Y Guo T Xu C Deng Y Liu Z Ma S Xu C Xu C Gao W. Pre-trained image processing transformer. Paper presented at: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition; June 2021.","DOI":"10.1109\/CVPR46437.2021.01212"},{"key":"e_1_3_3_59_2","doi-asserted-by":"crossref","unstructured":"Zhou L Zhou Y Corso JJ Socher R Xiong C. End-to-end dense video captioning with masked transformer. Paper presented at: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition; 18\u201323 Jun 2018; Salt Lake City UT USA.","DOI":"10.1109\/CVPR.2018.00911"},{"key":"e_1_3_3_60_2","doi-asserted-by":"crossref","unstructured":"Liu Z Lin Y Cao Y Hu H Wei Y Zhang Z Lin S Guo B. Swin transformer: Hierarchical vision transformer using shifted windows. Paper presented at: Proceedings of the IEEE\/CVF International Conference on Computer Vision; October 2021.","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_3_61_2","doi-asserted-by":"crossref","unstructured":"Liang J Cao J Sun G Zhang K Van Gool L Timofte R. Swinir: Image restoration using swin transformer. Paper presented at: Proceedings of the IEEE\/CVF International Conference on Computer Vision; October 2021.","DOI":"10.1109\/ICCVW54120.2021.00210"},{"issue":"8","key":"e_1_3_3_62_2","doi-asserted-by":"crossref","first-page":"1848","DOI":"10.1364\/PRJ.458231","article-title":"Snapshot spectral compressive imaging reconstruction using convolution and contextual transformer","volume":"10","author":"Wang L","year":"2022","unstructured":"Wang L, Wu Z, Zhong Y, Yuan X. Snapshot spectral compressive imaging reconstruction using convolution and contextual transformer. Photonics Res. 2022;10(8):1848\u20131858.","journal-title":"Photonics Res"},{"key":"e_1_3_3_63_2","article-title":"Spatial-temporal transformer for video snapshot compressive imaging","author":"Wang L","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. 2022;Article 3225382.","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"e_1_3_3_64_2","unstructured":"Huang Q Hu M Brady DJ. Array camera image fusion using physics-aware transformers. ArXiv 2022. https:\/\/doi.org\/10.48550\/arXiv.2207.02250"},{"issue":"4","key":"e_1_3_3_65_2","doi-asserted-by":"crossref","first-page":"600","DOI":"10.1109\/TIP.2003.819861","article-title":"Image quality assessment: From error visibility to structural similarity","volume":"13","author":"Wang Z","year":"2004","unstructured":"Wang Z, Bovik AC, Sheikh HR, Simoncelli EP, et al. Image quality assessment: From error visibility to structural similarity. IEEE Trans Image Process. 2004;13(4):600\u2013612.","journal-title":"IEEE Trans Image Process"},{"key":"e_1_3_3_66_2","doi-asserted-by":"crossref","unstructured":"Janai J G\u00fcney F Wulff J Black M Geiger A. Slow flow: Exploiting high-speed cameras for accurate and diverse optical flow reference data. Paper presented at: Conference on Computer Vision and Pattern Recognition (CVPR); 21\u201326 Jul 2017; Honolulu HI USA.","DOI":"10.1109\/CVPR.2017.154"},{"key":"e_1_3_3_67_2","doi-asserted-by":"crossref","unstructured":"Yuan X Liu Y Suo J Dai Q. Plug-and-play algorithms for large-scale snapshot compressive imaging. Paper presented at: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR); 13\u201319 Jun 2020; Seattle WA USA.","DOI":"10.1109\/CVPR42600.2020.00152"},{"key":"e_1_3_3_68_2","unstructured":"Pont-Tuset J Perazzi F Caelles S Arbel\u00e1ez P Sorkine-Hornung A Van Gool L. The 2017 davis challenge on video object segmentation. ArXiv 2017. https:\/\/doi.org\/10.48550\/arXiv.1704.00675"},{"issue":"2","key":"e_1_3_3_69_2","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","article-title":"Distinctive image features from scale-invariant keypoints","volume":"60","author":"Lowe DG","year":"2004","unstructured":"Lowe DG. Distinctive image features from scale-invariant keypoints. Int J Comput Vis. 2004;60(2):91\u2013110.","journal-title":"Int J Comput Vis"},{"key":"e_1_3_3_70_2","doi-asserted-by":"crossref","unstructured":"Yuan X. Generalized alternating projection based total variation minimization for compressive sensing. Paper presented at: 2016 IEEE International Conference on Image Processing (ICIP); 25\u201328 Sep 2016; Phoenix USA.","DOI":"10.1109\/ICIP.2016.7532817"},{"issue":"10","key":"e_1_3_3_71_2","doi-asserted-by":"crossref","DOI":"10.1109\/TPAMI.2021.3099035","article-title":"Plug-and-play algorithms for video snapshot compressive imaging","volume":"44","author":"Yuan X","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. 2021;44(10):7093\u20137111.","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"e_1_3_3_72_2","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. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR); 2023; p. 18477\u201318486.","DOI":"10.1109\/CVPR52729.2023.01772"}],"container-title":["Intelligent Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/spj.science.org\/doi\/pdf\/10.34133\/icomputing.0038","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T06:31:30Z","timestamp":1729578690000},"score":1,"resource":{"primary":{"URL":"https:\/\/spj.science.org\/doi\/10.34133\/icomputing.0038"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1]]},"references-count":71,"alternative-id":["10.34133\/icomputing.0038"],"URL":"https:\/\/doi.org\/10.34133\/icomputing.0038","relation":{},"ISSN":["2771-5892"],"issn-type":[{"type":"electronic","value":"2771-5892"}],"subject":[],"published":{"date-parts":[[2023,1]]},"assertion":[{"value":"2022-09-27","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-05-16","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-08-16","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"0038"}}