{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,14]],"date-time":"2026-02-14T13:39:43Z","timestamp":1771076383544,"version":"3.50.1"},"publisher-location":"Cham","reference-count":47,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031200526","type":"print"},{"value":"9783031200533","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\/978-3-031-20053-3_28","type":"book-chapter","created":{"date-parts":[[2022,11,5]],"date-time":"2022-11-05T16:21:52Z","timestamp":1667665312000},"page":"480-496","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":44,"title":["ScalableViT: Rethinking the\u00a0Context-Oriented Generalization of\u00a0Vision Transformer"],"prefix":"10.1007","author":[{"given":"Rui","family":"Yang","sequence":"first","affiliation":[]},{"given":"Hailong","family":"Ma","sequence":"additional","affiliation":[]},{"given":"Jie","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Yansong","family":"Tang","sequence":"additional","affiliation":[]},{"given":"Xuefeng","family":"Xiao","sequence":"additional","affiliation":[]},{"given":"Min","family":"Zheng","sequence":"additional","affiliation":[]},{"given":"Xiu","family":"Li","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,11,6]]},"reference":[{"key":"28_CR1","doi-asserted-by":"crossref","unstructured":"Bello, I., Zoph, B., Le, Q., Vaswani, A., Shlens, J.: Attention augmented convolutional networks. In: ICCV, pp. 3285\u20133294. IEEE (2019)","DOI":"10.1109\/ICCV.2019.00338"},{"key":"28_CR2","doi-asserted-by":"crossref","unstructured":"Cao, Y., Xu, J., Lin, S., Wei, F., Hu, H.: GCNet: non-local networks meet squeeze-excitation networks and beyond. In: ICCV, pp. 1971\u20131980 (2019)","DOI":"10.1109\/ICCVW.2019.00246"},{"key":"28_CR3","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":"28_CR4","unstructured":"Chen, K., et al.: MMDetection: open MMLab detection toolbox and benchmark. arXiv preprint arXiv:1906.07155 (2019)"},{"key":"28_CR5","unstructured":"Chu, X., et al.: Twins: revisiting the design of spatial attention in vision transformers. arXiv preprint arXiv:2104.13840 (2021)"},{"key":"28_CR6","unstructured":"Chu, X., et al.: Conditional positional encodings for vision transformers. arXiv preprint arXiv:2102.10882 (2021)"},{"key":"28_CR7","unstructured":"Contributors, M.: MMSegmentation: OpenMMLab semantic segmentation toolbox and benchmark (2020). https:\/\/github.com\/open-mmlab\/mmsegmentation"},{"key":"28_CR8","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: CVPR, pp. 248\u2013255 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"28_CR9","doi-asserted-by":"crossref","unstructured":"Dong, X., et al.: CSWin transformer: a general vision transformer backbone with cross-shaped windows. arXiv preprint arXiv:2107.00652 (2021)","DOI":"10.1109\/CVPR52688.2022.01181"},{"key":"28_CR10","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: ICLR (2021)"},{"key":"28_CR11","unstructured":"Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: Teh, Y.W., Titterington, D.M. (eds.) Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, vol. 9, pp. 249\u2013256 (2010)"},{"key":"28_CR12","unstructured":"Han, K., Xiao, A., Wu, E., Guo, J., Xu, C., Wang, Y.: Transformer in transformer. arXiv preprint arXiv:2103.00112 (2021)"},{"issue":"2","key":"28_CR13","doi-asserted-by":"publisher","first-page":"386","DOI":"10.1109\/TPAMI.2018.2844175","volume":"42","author":"K He","year":"2020","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.B.: Mask R-CNN. IEEE TPAMI 42(2), 386\u2013397 (2020)","journal-title":"IEEE TPAMI"},{"key":"28_CR14","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770\u2013778. IEEE Computer Society (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"28_CR15","doi-asserted-by":"crossref","unstructured":"Hu, H., Zhang, Z., Xie, Z., Lin, S.: Local relation networks for image recognition. In: ICCV, pp. 3463\u20133472 (2019)","DOI":"10.1109\/ICCV.2019.00356"},{"key":"28_CR16","unstructured":"Huang, L., Yuan, Y., Guo, J., Zhang, C., Chen, X., Wang, J.: Interlaced sparse self-attention for semantic segmentation. arXiv preprint arXiv:1907.12273 (2019)"},{"key":"28_CR17","unstructured":"Huang, Z., Ben, Y., Luo, G., Cheng, P., Yu, G., Fu, B.: Shuffle transformer: rethinking spatial shuffle for vision transformer. arXiv preprint arXiv:2106.03650 (2021)"},{"key":"28_CR18","doi-asserted-by":"crossref","unstructured":"Huang, Z., Wang, X., Huang, L., Huang, C., Wei, Y., Liu, W.: CCNet: criss-cross attention for semantic segmentation. In: ICCV, pp. 603\u2013612 (2019)","DOI":"10.1109\/ICCV.2019.00069"},{"key":"28_CR19","unstructured":"Islam, M.A., Jia, S., Bruce, N.D.B.: How much position information do convolutional neural networks encode? In: ICLR (2020)"},{"key":"28_CR20","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Girshick, R.B., He, K., Doll\u00e1r, P.: Panoptic feature pyramid networks. In: CVPR, pp. 6399\u20136408 (2019)","DOI":"10.1109\/CVPR.2019.00656"},{"key":"28_CR21","doi-asserted-by":"crossref","unstructured":"Lin, T., Doll\u00e1r, P., Girshick, R.B., He, K., Hariharan, B., Belongie, S.J.: Feature pyramid networks for object detection. In: CVPR, pp. 936\u2013944 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"issue":"2","key":"28_CR22","doi-asserted-by":"publisher","first-page":"318","DOI":"10.1109\/TPAMI.2018.2858826","volume":"42","author":"T Lin","year":"2020","unstructured":"Lin, T., Goyal, P., Girshick, R.B., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. IEEE TPAMI 42(2), 318\u2013327 (2020)","journal-title":"IEEE TPAMI"},{"key":"28_CR23","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":"28_CR24","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. arXiv preprint arXiv:2103.14030 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"28_CR25","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: ICLR (2019)"},{"key":"28_CR26","unstructured":"Parmar, N., Ramachandran, P., Vaswani, A., Bello, I., Levskaya, A., Shlens, J.: Stand-alone self-attention in vision models. In: NeurIPS, pp. 68\u201380 (2019)"},{"key":"28_CR27","doi-asserted-by":"crossref","unstructured":"Radosavovic, I., Kosaraju, R.P., Girshick, R.B., He, K., Doll\u00e1r, P.: Designing network design spaces. In: CVPR, pp. 10425\u201310433 (2020)","DOI":"10.1109\/CVPR42600.2020.01044"},{"key":"28_CR28","unstructured":"Rao, Y., Zhao, W., Liu, B., Lu, J., Zhou, J., Hsieh, C.J.: Dynamicvit: efficient vision transformers with dynamic token sparsification. arXiv preprint arXiv:2106.02034 (2021)"},{"key":"28_CR29","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: Bengio, Y., LeCun, Y. (eds.) ICLR (2015)"},{"key":"28_CR30","unstructured":"Tan, M., Le, Q.V.: Efficientnet: rethinking model scaling for convolutional neural networks. In: Chaudhuri, K., Salakhutdinov, R. (eds.) Proceedings of the 36th International Conference on Machine Learning, ICML, vol. 97, pp. 6105\u20136114 (2019)"},{"key":"28_CR31","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., J\u00e9gou, H.: Training data-efficient image transformers & distillation through attention. In: Proceedings of the 38th International Conference on Machine Learning, ICML, vol. 139, pp. 10347\u201310357 (2021)"},{"key":"28_CR32","doi-asserted-by":"crossref","unstructured":"Vaswani, A., Ramachandran, P., Srinivas, A., Parmar, N., Hechtman, B.A., Shlens, J.: Scaling local self-attention for parameter efficient visual backbones. In: CVPR, pp. 12894\u201312904 (2021)","DOI":"10.1109\/CVPR46437.2021.01270"},{"key":"28_CR33","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS, pp. 5998\u20136008 (2017)"},{"key":"28_CR34","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1007\/978-3-030-58548-8_7","volume-title":"Computer Vision \u2013 ECCV 2020","author":"H Wang","year":"2020","unstructured":"Wang, H., Zhu, Y., Green, B., Adam, H., Yuille, A., Chen, L.-C.: Axial-DeepLab: stand-alone axial-attention for panoptic segmentation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12349, pp. 108\u2013126. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58548-8_7"},{"key":"28_CR35","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: Pyramid vision transformer: a versatile backbone for dense prediction without convolutions. arXiv preprint arXiv:2102.12122 (2021)","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"28_CR36","unstructured":"Wang, W., et al.: Crossformer: a versatile vision transformer hinging on cross-scale attention. arXiv preprint arXiv:2108.00154 (2021)"},{"key":"28_CR37","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R.B., Gupta, A., He, K.: Non-local neural networks. In: CVPR, pp. 7794\u20137803 (2018)","DOI":"10.1109\/CVPR.2018.00813"},{"key":"28_CR38","doi-asserted-by":"crossref","unstructured":"Wu, H., et al.: CVT: introducing convolutions to vision transformers. arXiv preprint arXiv:2103.15808 (2021)","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"28_CR39","unstructured":"Xia, X., et al.: TRT-ViT: TensorRT-oriented vision transformer. arXiv preprint arXiv:2205.09579 (2022)"},{"key":"28_CR40","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"432","DOI":"10.1007\/978-3-030-01228-1_26","volume-title":"Computer Vision \u2013 ECCV 2018","author":"T Xiao","year":"2018","unstructured":"Xiao, T., Liu, Y., Zhou, B., Jiang, Y., Sun, J.: Unified perceptual parsing for scene understanding. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11209, pp. 432\u2013448. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01228-1_26"},{"key":"28_CR41","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R.B., Doll\u00e1r, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: CVPR, pp. 5987\u20135995 (2017)","DOI":"10.1109\/CVPR.2017.634"},{"key":"28_CR42","doi-asserted-by":"crossref","unstructured":"Xu, W., Xu, Y., Chang, T., Tu, Z.: Co-scale conv-attentional image transformers. arXiv preprint arXiv:2104.06399 (2021)","DOI":"10.1109\/ICCV48922.2021.00983"},{"key":"28_CR43","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"191","DOI":"10.1007\/978-3-030-58555-6_12","volume-title":"Computer Vision \u2013 ECCV 2020","author":"M Yin","year":"2020","unstructured":"Yin, M., et al.: Disentangled non-local neural networks. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12360, pp. 191\u2013207. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58555-6_12"},{"key":"28_CR44","doi-asserted-by":"crossref","unstructured":"Yuan, K., Guo, S., Liu, Z., Zhou, A., Yu, F., Wu, W.: Incorporating convolution designs into visual transformers. arXiv preprint arXiv:2103.11816 (2021)","DOI":"10.1109\/ICCV48922.2021.00062"},{"key":"28_CR45","doi-asserted-by":"crossref","unstructured":"Yuan, L., et al.: Tokens-to-token ViT: training vision transformers from scratch on imagenet. arXiv preprint arXiv:2101.11986 (2021)","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"28_CR46","unstructured":"Yuan, Y., et al.: HRFormer: high-resolution transformer for dense prediction. arXiv preprint arXiv:2110.09408 (2021)"},{"issue":"3","key":"28_CR47","doi-asserted-by":"publisher","first-page":"302","DOI":"10.1007\/s11263-018-1140-0","volume":"127","author":"B Zhou","year":"2019","unstructured":"Zhou, B., et al.: Semantic understanding of scenes through the ADE20K dataset. Int. J. Comput. Vis. 127(3), 302\u2013321 (2019)","journal-title":"Int. J. Comput. Vis."}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-20053-3_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,5]],"date-time":"2022-11-05T16:33:38Z","timestamp":1667666018000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20053-3_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031200526","9783031200533"],"references-count":47,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20053-3_28","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":"6 November 2022","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)"}}]}}