{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T15:47:40Z","timestamp":1784908060758,"version":"3.55.0"},"publisher-location":"Cham","reference-count":48,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031250811","type":"print"},{"value":"9783031250828","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-25082-8_1","type":"book-chapter","created":{"date-parts":[[2023,2,11]],"date-time":"2023-02-11T09:12:42Z","timestamp":1676106762000},"page":"3-20","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":285,"title":["EdgeNeXt: Efficiently Amalgamated CNN-Transformer Architecture for\u00a0Mobile Vision Applications"],"prefix":"10.1007","author":[{"given":"Muhammad","family":"Maaz","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abdelrahman","family":"Shaker","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hisham","family":"Cholakkal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Salman","family":"Khan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Syed Waqas","family":"Zamir","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rao Muhammad","family":"Anwer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fahad","family":"Shahbaz Khan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,2,12]]},"reference":[{"key":"1_CR1","unstructured":"Ali, A., et al.: XCiT: cross-covariance image transformers. In: Advances in Neural Information Processing Systems (2021)"},{"key":"1_CR2","unstructured":"Ba, J.L., Kiros, J.R., Hinton, G.E.: Layer normalization. arXiv preprint arXiv:1607.06450 (2016)"},{"key":"1_CR3","unstructured":"Chen, L.C., Papandreou, G., Schroff, F., Adam, H.: Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587 (2017)"},{"key":"1_CR4","doi-asserted-by":"crossref","unstructured":"Chen, Y., et al.: Mobile-former: bridging mobilenet and transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2022)","DOI":"10.1109\/CVPR52688.2022.00520"},{"key":"1_CR5","doi-asserted-by":"crossref","unstructured":"Chollet, F.: Xception: deep learning with depthwise separable convolutions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.195"},{"key":"1_CR6","doi-asserted-by":"crossref","unstructured":"Cubuk, E.D., Zoph, B., Shlens, J., Le, Q.: RandAugment: practical automated data augmentation with a reduced search space. In: Advances in Neural Information Processing Systems (2020)","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"1_CR7","unstructured":"Dai, Z., Liu, H., Le, Q., Tan, M.: CoAtNet: marrying convolution and attention for all data sizes. In: Advances in Neural Information Processing Systems (2021)"},{"key":"1_CR8","unstructured":"Dosovitskiy, A., et al.: An image is worth $$16 \\times 16$$ words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"1_CR9","doi-asserted-by":"crossref","unstructured":"d\u2019Ascoli, S., Touvron, H., Leavitt, M.L., Morcos, A.S., Biroli, G., Sagun, L.: ConVit: improving vision transformers with soft convolutional inductive biases. In: International Conference on Machine Learning (2021)","DOI":"10.1088\/1742-5468\/ac9830"},{"issue":"2","key":"1_CR10","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham, M., Van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The pascal visual object classes (VOC) challenge. Int. J. Comput. Vis. 88(2), 303\u2013338 (2010)","journal-title":"Int. J. Comput. Vis."},{"key":"1_CR11","doi-asserted-by":"crossref","unstructured":"Fan, H., et al.: Multiscale vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2021)","DOI":"10.1109\/ICCV48922.2021.00675"},{"issue":"2","key":"1_CR12","doi-asserted-by":"publisher","first-page":"652","DOI":"10.1109\/TPAMI.2019.2938758","volume":"43","author":"SH Gao","year":"2019","unstructured":"Gao, S.H., Cheng, M.M., Zhao, K., Zhang, X.Y., Yang, M.H., Torr, P.: Res2Net: a new multi-scale backbone architecture. IEEE Trans. Pattern Anal. Mach. Intell. 43(2), 652\u2013662 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1_CR13","doi-asserted-by":"crossref","unstructured":"Hariharan, B., Arbel\u00e1ez, P., Bourdev, L., Maji, S., Malik, J.: Semantic contours from inverse detectors. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2011)","DOI":"10.1109\/ICCV.2011.6126343"},{"key":"1_CR14","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"1_CR15","unstructured":"Hendrycks, D., Gimpel, K.: Gaussian error linear units (GELUs). arXiv preprint arXiv:1606.08415 (2016)"},{"key":"1_CR16","doi-asserted-by":"crossref","unstructured":"Howard, A., et al.: Searching for MobileNetV3. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2019)","DOI":"10.1109\/ICCV.2019.00140"},{"key":"1_CR17","unstructured":"Howard, A.G., et al.: MobileNets: efficient convolutional neural networks for mobile vision applications. CoRR abs\/1704.04861 (2017)"},{"key":"1_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"646","DOI":"10.1007\/978-3-319-46493-0_39","volume-title":"Computer Vision \u2013 ECCV 2016","author":"G Huang","year":"2016","unstructured":"Huang, G., Sun, Yu., Liu, Z., Sedra, D., Weinberger, K.Q.: Deep networks with stochastic depth. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 646\u2013661. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_39"},{"key":"1_CR19","unstructured":"Iandola, F.N., Han, S., Moskewicz, M.W., Ashraf, K., Dally, W.J., Keutzer, K.: SqueezeNet: AlexNet-level accuracy with 50$$\\times $$ fewer parameters and $$<$$0.5 mb model size. arXiv preprint arXiv:1602.07360 (2016)"},{"key":"1_CR20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3505244","volume":"54","author":"S Khan","year":"2021","unstructured":"Khan, S., Naseer, M., Hayat, M., Zamir, S.W., Khan, F.S., Shah, M.: Transformers in vision: a survey. ACM Comput. Surv. (CSUR) 54, 1\u201341 (2021)","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"1_CR21","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: Improved multiscale vision transformers for classification and detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2022)","DOI":"10.1109\/CVPR52688.2022.00476"},{"key":"1_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"1_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/978-3-319-46448-0_2","volume-title":"Computer Vision \u2013 ECCV 2016","author":"W Liu","year":"2016","unstructured":"Liu, W., et al.: SSD: single shot multibox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21\u201337. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_2"},{"key":"1_CR24","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 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"1_CR25","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 (2022)","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"1_CR26","unstructured":"Loshchilov, I., Hutter, F.: SGDR: stochastic gradient descent with warm restarts. In: International Conference on Learning Representations (2017)"},{"key":"1_CR27","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: International Conference on Learning Representations (2019)"},{"key":"1_CR28","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"122","DOI":"10.1007\/978-3-030-01264-9_8","volume-title":"Computer Vision \u2013 ECCV 2018","author":"N Ma","year":"2018","unstructured":"Ma, N., Zhang, X., Zheng, H.-T., Sun, J.: ShuffleNet V2: practical guidelines for efficient CNN architecture design. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer Vision \u2013 ECCV 2018. LNCS, vol. 11218, pp. 122\u2013138. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01264-9_8"},{"key":"1_CR29","unstructured":"Mehta, S., Rastegari, M.: MobileViT: light-weight, general-purpose, and mobile-friendly vision transformer. In: International Conference on Learning Representations (2022)"},{"key":"1_CR30","unstructured":"Mehta, S., Rastegari, M.: Separable self-attention for mobile vision transformers. arXiv preprint arXiv:2206.02680 (2022)"},{"key":"1_CR31","doi-asserted-by":"crossref","unstructured":"Mehta, S., Rastegari, M., Shapiro, L., Hajishirzi, H.: ESPNetv2: a light-weight, power efficient, and general purpose convolutional neural network. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.00941"},{"key":"1_CR32","doi-asserted-by":"publisher","first-page":"838","DOI":"10.1137\/0330046","volume":"30","author":"BT Polyak","year":"1992","unstructured":"Polyak, B.T., Juditsky, A.B.: Acceleration of stochastic approximation by averaging. SIAM J. Control Optim. 30, 838\u2013855 (1992)","journal-title":"SIAM J. Control Optim."},{"key":"1_CR33","unstructured":"Ridnik, T., Ben-Baruch, E., Noy, A., Zelnik-Manor, L.: ImageNet-21k pretraining for the masses. arXiv preprint arXiv:2104.10972 (2021)"},{"key":"1_CR34","unstructured":"Ridnik, T., Lawen, H., Ben-Baruch, E., Noy, A.: Solving imagenet: a unified scheme for training any backbone to top results. arXiv preprint arXiv:2204.03475 (2022)"},{"issue":"3","key":"1_CR35","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. 115(3), 211\u2013252 (2015). https:\/\/doi.org\/10.1007\/s11263-015-0816-y","journal-title":"Int. J. Comput. Vis."},{"key":"1_CR36","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: MobileNetv 2: inverted residuals and linear bottlenecks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2018)","DOI":"10.1109\/CVPR.2018.00474"},{"key":"1_CR37","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1016\/j.neunet.2014.09.003","volume":"61","author":"J Schmidhuber","year":"2015","unstructured":"Schmidhuber, J.: Deep learning in neural networks: an overview. Neural Netw. 61, 85\u2013117 (2015)","journal-title":"Neural Netw."},{"key":"1_CR38","doi-asserted-by":"crossref","unstructured":"Srinivas, A., Lin, T.Y., Parmar, N., Shlens, J., Abbeel, P., Vaswani, A.: Bottleneck transformers for visual recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2021)","DOI":"10.1109\/CVPR46437.2021.01625"},{"key":"1_CR39","doi-asserted-by":"crossref","unstructured":"Tan, M., et al.: MnasNet: platform-aware neural architecture search for mobile. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.00293"},{"key":"1_CR40","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., J\u00e9gou, H.: Training data-efficient image transformers & distillation through attention. In: International Conference on Machine Learning (2021)"},{"key":"1_CR41","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems (2017)"},{"key":"1_CR42","unstructured":"Xiao, T., Dollar, P., Singh, M., Mintun, E., Darrell, T., Girshick, R.: Early convolutions help transformers see better. In: Advances in Neural Information Processing Systems (2021)"},{"key":"1_CR43","doi-asserted-by":"crossref","unstructured":"Yu, W., et al.: MetaFormer is actually what you need for vision. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2021)","DOI":"10.1109\/CVPR52688.2022.01055"},{"key":"1_CR44","doi-asserted-by":"crossref","unstructured":"Yuan, L., et al.: Tokens-to-token ViT: training vision transformers from scratch on imagenet. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2021)","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"1_CR45","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"818","DOI":"10.1007\/978-3-319-10590-1_53","volume-title":"Computer Vision \u2013 ECCV 2014","author":"MD Zeiler","year":"2014","unstructured":"Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 818\u2013833. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10590-1_53"},{"key":"1_CR46","unstructured":"Zhang, H., Hu, W., Wang, X.: EdgeFormer: improving light-weight convnets by learning from vision transformers. arXiv preprint arXiv:2203.03952 (2022)"},{"key":"1_CR47","doi-asserted-by":"crossref","unstructured":"Zhang, X., Zhou, X., Lin, M., Sun, J.: ShuffleNet: an extremely efficient convolutional neural network for mobile devices. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2018)","DOI":"10.1109\/CVPR.2018.00716"},{"key":"1_CR48","unstructured":"Zhou, J., Wang, P., Wang, F., Liu, Q., Li, H., Jin, R.: ELSA: enhanced local self-attention for vision transformer. arXiv preprint arXiv:2112.12786 (2021)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-25082-8_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T13:00:54Z","timestamp":1709816454000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-25082-8_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031250811","9783031250828"],"references-count":48,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-25082-8_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"12 February 2023","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":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1645","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"28% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.21","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.91","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"From the workshops, 367 reviewed full papers have been selected for publication","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}