{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T15:39:07Z","timestamp":1772725147069,"version":"3.50.1"},"publisher-location":"Cham","reference-count":60,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031192104","type":"print"},{"value":"9783031192111","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-19211-1_33","type":"book-chapter","created":{"date-parts":[[2022,11,17]],"date-time":"2022-11-17T00:03:45Z","timestamp":1668643425000},"page":"393-405","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":20,"title":["EdgeViT: Efficient Visual Modeling for\u00a0Edge Computing"],"prefix":"10.1007","author":[{"given":"Zekai","family":"Chen","sequence":"first","affiliation":[]},{"given":"Fangtian","family":"Zhong","sequence":"additional","affiliation":[]},{"given":"Qi","family":"Luo","sequence":"additional","affiliation":[]},{"given":"Xiao","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Yanwei","family":"Zheng","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,11,17]]},"reference":[{"key":"33_CR1","unstructured":"Brown, T.B., et al.: Language models are few-shot learners. In: NeurIPS (2020)"},{"key":"33_CR2","doi-asserted-by":"crossref","unstructured":"Chen, C.F., Fan, Q., Panda, R.: CrossViT: cross-attention multi-scale vision transformer for image classification. In: ICCV, pp. 347\u2013356 (2021)","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"33_CR3","unstructured":"Chen, L.C., Papandreou, G., Schroff, F., Adam, H.: Rethinking atrous convolution for semantic image segmentation. ArXiv abs\/1706.05587 (2017)"},{"key":"33_CR4","doi-asserted-by":"crossref","unstructured":"Chen, Y., Dai, X., Chen, D., Liu, M., Dong, X., Yuan, L., Liu, Z.: Mobile-former: bridging mobilenet and transformer. arXiv abs\/2108.05895 (2021)","DOI":"10.1109\/CVPR52688.2022.00520"},{"key":"33_CR5","doi-asserted-by":"publisher","first-page":"9179","DOI":"10.1109\/JIOT.2021.3100509","volume":"9","author":"Z Chen","year":"2022","unstructured":"Chen, Z., Chen, D., Yuan, Z., Cheng, X., Zhang, X.: Learning graph structures with transformer for multivariate time-series anomaly detection in IoT. IEEE Internet Things J. 9, 9179\u20139189 (2022)","journal-title":"IEEE Internet Things J."},{"key":"33_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Z., Jiaze, E., Zhang, X., Sheng, H., Cheng, X.: Multi-task time series forecasting with shared attention. In: ICDMW, pp. 917\u2013925 (2020)","DOI":"10.1109\/ICDMW51313.2020.00132"},{"key":"33_CR7","doi-asserted-by":"crossref","unstructured":"Chen, Z., Shi, M., Zhang, X., Ying, H.: Asm2tv: an adaptive semi-supervised multi-task multi-view learning framework. In: AAAI (2022)","DOI":"10.1609\/aaai.v36i6.20584"},{"key":"33_CR8","doi-asserted-by":"crossref","unstructured":"Chollet, F.: Xception: deep learning with depthwise separable convolutions. In: CVPR, pp. 1800\u20131807 (2017)","DOI":"10.1109\/CVPR.2017.195"},{"key":"33_CR9","unstructured":"Courbariaux, M., Hubara, I., Soudry, D., El-Yaniv, R., Bengio, Y.: Binarized neural networks: Training deep neural networks with weights and activations constrained to +1 or -1. arxiv abs\/1602.02830 (2016)"},{"key":"33_CR10","doi-asserted-by":"crossref","unstructured":"Cubuk, E.D., Zoph, B., Man\u00e9, D., Vasudevan, V., Le, Q.V.: Autoaugment: learning augmentation strategies from data. In: CVPR, pp. 113\u2013123 (2019)","DOI":"10.1109\/CVPR.2019.00020"},{"key":"33_CR11","unstructured":"Dai, Z., Liu, H., Le, Q.V., Tan, M.: CoAtNet: marrying convolution and attention for all data sizes. In: NeurIPS (2021)"},{"key":"33_CR12","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: ICML (2021)","DOI":"10.1088\/1742-5468\/ac9830"},{"key":"33_CR13","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL (2019)"},{"key":"33_CR14","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: ICLR (2020)"},{"key":"33_CR15","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1007\/s11263-014-0733-5","volume":"111","author":"M Everingham","year":"2014","unstructured":"Everingham, M., Eslami, S.M.A., Gool, L.V., Williams, C.K.I., Winn, J.M., Zisserman, A.: The pascal visual object classes challenge: a retrospective. IJCV 111, 98\u2013136 (2014)","journal-title":"IJCV"},{"key":"33_CR16","doi-asserted-by":"crossref","unstructured":"Graham, B., et al.: LeViT: a vision transformer in convnet\u2019s clothing for faster inference. In: ICCV, pp. 12239\u201312249 (2021)","DOI":"10.1109\/ICCV48922.2021.01204"},{"key":"33_CR17","unstructured":"Han, S., Mao, H., Dally, W.J.: Deep compression: compressing deep neural network with pruning, trained quantization and huffman coding. In: NeurIPS (2016)"},{"key":"33_CR18","unstructured":"Han, S., Pool, J., Tran, J., Dally, W.J.: Learning both weights and connections for efficient neural network. In: NeurIPS (2015)"},{"key":"33_CR19","doi-asserted-by":"crossref","unstructured":"Hariharan, B., Arbel\u00e1ez, P., Bourdev, L.D., Maji, S., Malik, J.: Semantic contours from inverse detectors. In: ICCV, pp. 991\u2013998 (2011)","DOI":"10.1109\/ICCV.2011.6126343"},{"key":"33_CR20","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"33_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"815","DOI":"10.1007\/978-3-030-01234-2_48","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Y He","year":"2018","unstructured":"He, Y., Lin, J., Liu, Z., Wang, H., Li, L.-J., Han, S.: AMC: AutoML for model compression and acceleration on mobile devices. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 815\u2013832. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01234-2_48"},{"key":"33_CR22","doi-asserted-by":"crossref","unstructured":"He, Y., Zhang, X., Sun, J.: Channel pruning for accelerating very deep neural networks. In: ICCV, pp. 1398\u20131406 (2017)","DOI":"10.1109\/ICCV.2017.155"},{"key":"33_CR23","doi-asserted-by":"crossref","unstructured":"Heo, B., Yun, S., Han, D., Chun, S., Choe, J., Oh, S.J.: Rethinking spatial dimensions of vision transformers. In: ICCV, pp. 11916\u201311925 (2021)","DOI":"10.1109\/ICCV48922.2021.01172"},{"key":"33_CR24","doi-asserted-by":"crossref","unstructured":"Howard, A.G., et al.: Searching for mobilenetv3. In: ICCV, pp. 1314\u20131324 (2019)","DOI":"10.1109\/ICCV.2019.00140"},{"key":"33_CR25","unstructured":"Howard, A.G., et al.: Mobilenets: efficient convolutional neural networks for mobile vision applications. arXiv abs\/1704.04861 (2017)"},{"key":"33_CR26","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Weinberger, K.Q.: Densely connected convolutional networks. In: CVPR, pp. 2261\u20132269 (2017)","DOI":"10.1109\/CVPR.2017.243"},{"key":"33_CR27","doi-asserted-by":"crossref","unstructured":"Jacob, B., et al.: Quantization and training of neural networks for efficient integer-arithmetic-only inference. In: CVPR, pp. 2704\u20132713 (2018)","DOI":"10.1109\/CVPR.2018.00286"},{"key":"33_CR28","unstructured":"Jin, J., Dundar, A., Culurciello, E.: Flattened convolutional neural networks for feedforward acceleration. CoRR abs\/1412.5474 (2015)"},{"key":"33_CR29","unstructured":"Li, Y., Zhang, K., Cao, J., Timofte, R., Gool, L.V.: LocalViT: bringing locality to vision transformers. arXiv abs\/2104.05707 (2021)"},{"key":"33_CR30","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":"33_CR31","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: ICCV, pp. 9992\u201310002 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"33_CR32","doi-asserted-by":"crossref","unstructured":"Liu, Z., Mu, H., Zhang, X., Guo, Z., Yang, X., Cheng, K., Sun, J.: MetaPruning: meta learning for automatic neural network channel pruning. In: ICCV, pp. 3295\u20133304 (2019)","DOI":"10.1109\/ICCV.2019.00339"},{"key":"33_CR33","doi-asserted-by":"crossref","unstructured":"Liu, Z., Li, J., Shen, Z., Huang, G., Yan, S., Zhang, C.: Learning efficient convolutional networks through network slimming. In: ICCV, pp. 2755\u20132763 (2017)","DOI":"10.1109\/ICCV.2017.298"},{"key":"33_CR34","unstructured":"Loshchilov, I., Hutter, F.: SGDR: stochastic gradient descent with warm restarts. In: ICLR (2016)"},{"key":"33_CR35","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: ICLR (2019)"},{"key":"33_CR36","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":"33_CR37","first-page":"2322","volume":"19","author":"Y Mao","year":"2017","unstructured":"Mao, Y., You, C., Zhang, J., Huang, K., Letaief, K.B.: A survey on mobile edge computing: the communication perspective. IEEE CST 19, 2322\u20132358 (2017)","journal-title":"IEEE CST"},{"key":"33_CR38","unstructured":"Mehta, S., Rastegari, M.: MobileViT: light-weight, general-purpose, and mobile-friendly vision transformer. arXiv abs\/2110.02178 (2021)"},{"key":"33_CR39","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"561","DOI":"10.1007\/978-3-030-01249-6_34","volume-title":"Computer Vision \u2013 ECCV 2018","author":"S Mehta","year":"2018","unstructured":"Mehta, S., Rastegari, M., Caspi, A., Shapiro, L., Hajishirzi, H.: ESPNet: efficient spatial pyramid of dilated convolutions for semantic segmentation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11214, pp. 561\u2013580. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01249-6_34"},{"key":"33_CR40","doi-asserted-by":"crossref","unstructured":"Ranftl, R., Bochkovskiy, A., Koltun, V.: Vision transformers for dense prediction. In: ICCV, pp. 12159\u201312168 (2021)","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"33_CR41","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. IJCV 115, 211\u2013252 (2015)","journal-title":"IJCV"},{"key":"33_CR42","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A.G., Zhu, M., Zhmoginov, A., Chen, L.C.: MobileNetv 2: inverted residuals and linear bottlenecks. In: CVPR, pp. 4510\u20134520 (2018)","DOI":"10.1109\/CVPR.2018.00474"},{"key":"33_CR43","first-page":"637","volume":"3","author":"W Shi","year":"2016","unstructured":"Shi, W., Cao, J., Zhang, Q., Li, Y., Xu, L.: Edge computing: Vvsion and challenges. IEEE IoTJ 3, 637\u2013646 (2016)","journal-title":"IEEE IoTJ"},{"key":"33_CR44","doi-asserted-by":"crossref","unstructured":"Srinivas, A., Lin, T.Y., Parmar, N., Shlens, J., Abbeel, P., Vaswani, A.: Bottleneck transformers for visual recognition. In: CVPR, pp. 16514\u201316524 (2021)","DOI":"10.1109\/CVPR46437.2021.01625"},{"key":"33_CR45","doi-asserted-by":"crossref","unstructured":"Tan, M., Chen, B., Pang, R., Vasudevan, V., Le, Q.V.: MnasNet: platform-aware neural architecture search for mobile. In: CVPR, pp. 2815\u20132823 (2019)","DOI":"10.1109\/CVPR.2019.00293"},{"key":"33_CR46","unstructured":"Tan, M., Le, Q.V.: EfficientNet: rethinking model scaling for convolutional neural networks. In: ICML (2019)"},{"key":"33_CR47","unstructured":"Tan, M., Le, Q.V.: MixConv: mixed depthwise convolutional kernels. arXiv abs\/1907.09595 (2019)"},{"key":"33_CR48","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., J\u2019egou, H.: Training data-efficient image transformers & distillation through attention. In: ICML (2021)"},{"key":"33_CR49","doi-asserted-by":"crossref","unstructured":"Touvron, H., Cord, M., Sablayrolles, A., Synnaeve, G., J\u2019egou, H.: Going deeper with image transformers. In: ICCV, pp. 32\u201342 (2021)","DOI":"10.1109\/ICCV48922.2021.00010"},{"key":"33_CR50","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS (2017)"},{"key":"33_CR51","doi-asserted-by":"crossref","unstructured":"Wang, K., Liu, Z., Lin, Y., Lin, J., Han, S.: HAQ: hardware-aware automated quantization with mixed precision. In: CVPR, pp. 8604\u20138612 (2019)","DOI":"10.1109\/CVPR.2019.00881"},{"key":"33_CR52","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: Pyramid vision transformer: a versatile backbone for dense prediction without convolutions. In: ICCV, pp. 548\u2013558 (2021)","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"33_CR53","doi-asserted-by":"crossref","unstructured":"Wu, H., Xiao, B., Codella, N.C.F., Liu, M., Dai, X., Yuan, L., Zhang, L.: CvT: introducing convolutions to vision transformers. In: ICCV, pp. 22\u201331 (2021)","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"33_CR54","unstructured":"Wu, Z., Liu, Z., Lin, J., Lin, Y., Han, S.: Lite transformer with long-short range attention. In: ICLR (2020)"},{"key":"33_CR55","unstructured":"Xiao, T., Singh, M., Mintun, E., Darrell, T., Doll\u00e1r, P., Girshick, R.B.: Early convolutions help transformers see better. In: NeurIPS (2021)"},{"key":"33_CR56","doi-asserted-by":"crossref","unstructured":"Yu, H., et al.: FedHAR: semi-supervised online learning for personalized federated human activity recognition. IEEE Transactions on Mobile Computing (2021)","DOI":"10.1109\/TMC.2021.3136853"},{"key":"33_CR57","doi-asserted-by":"crossref","unstructured":"Yuan, L., et al.: Tokens-to-token ViT: training vision transformers from scratch on imagenet. In: ICCV, pp. 538\u2013547 (2021)","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"33_CR58","unstructured":"Zhang, H., Ciss\u00e9, M., Dauphin, Y., Lopez-Paz, D.: mixup: beyond empirical risk minimization. arXiv abs\/1710.09412 (2018)"},{"key":"33_CR59","doi-asserted-by":"crossref","unstructured":"Zhong, Z., Zheng, L., Kang, G., Li, S., Yang, Y.: Random erasing data augmentation. In: AAAI (2020)","DOI":"10.1609\/aaai.v34i07.7000"},{"key":"33_CR60","unstructured":"Zhou, D., et al.: DeepViT: towards deeper vision transformer. arXiv abs\/2103.11886 (2021)"}],"container-title":["Lecture Notes in Computer Science","Wireless Algorithms, Systems, and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-19211-1_33","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,12]],"date-time":"2023-03-12T14:56:56Z","timestamp":1678633016000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19211-1_33"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031192104","9783031192111"],"references-count":60,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19211-1_33","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"17 November 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"WASA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Wireless Algorithms, Systems, and Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Dalian","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"24 November 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 November 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":"wasa2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/wasa-conference.org\/WASA2022\/","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":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"265","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":"95","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":"62","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":"36% - 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":"4","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":"8","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)"}}]}}