{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T09:34:14Z","timestamp":1769074454300,"version":"3.49.0"},"publisher-location":"Cham","reference-count":53,"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_42","type":"book-chapter","created":{"date-parts":[[2022,11,5]],"date-time":"2022-11-05T16:21:52Z","timestamp":1667665312000},"page":"727-744","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["Sliced Recursive Transformer"],"prefix":"10.1007","author":[{"given":"Zhiqiang","family":"Shen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zechun","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eric","family":"Xing","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,11,6]]},"reference":[{"key":"42_CR1","unstructured":"https:\/\/github.com\/pytorch\/fairseq\/blob\/master\/examples\/translation\/README.md"},{"key":"42_CR2","unstructured":"https:\/\/workshop2014.iwslt.org\/downloads\/proceeding.pdf"},{"key":"42_CR3","unstructured":"https:\/\/www.statmt.org\/wmt14\/translation-task.html"},{"key":"42_CR4","unstructured":"Bagherinezhad, H., Horton, M., Rastegari, M., Farhadi, A.: Label refinery: Improving imagenet classification through label progression. arXiv preprint arXiv:1805.02641 (2018)"},{"key":"42_CR5","unstructured":"Bai, S., Kolter, J.Z., Koltun, V.: Deep equilibrium models. In: Proceedings of the International Conference on Neural Information Processing Systems (2019)"},{"key":"42_CR6","unstructured":"Bai, S., Kolter, J.Z., Koltun, V.: Trellis networks for sequence modeling. In: ICLR (2019)"},{"key":"42_CR7","unstructured":"Bai, S., Koltun, V., Kolter, J.Z.: Multiscale deep equilibrium models. In: Proceedings of the International Conference on Neural Information Processing Systems (2020)"},{"key":"42_CR8","unstructured":"Brown, T.B., et al.: Language models are few-shot learners. arXiv preprint arXiv:2005.14165 (2020)"},{"key":"42_CR9","doi-asserted-by":"crossref","unstructured":"Chen, M., Peng, H., Fu, J., Ling, H.: Autoformer: searching transformers for visual recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.01205"},{"key":"42_CR10","unstructured":"Chowdhury, J.R., Caragea, C.: Modeling hierarchical structures with continuous recursive neural networks. In: Proceedings of the 38th International Conference on Machine Learning, pp. 1975\u20131988 (2021)"},{"key":"42_CR11","unstructured":"Dehghani, M., Gouws, S., Vinyals, O., Uszkoreit, J., Kaiser, L.: Universal transformers. In: International Conference on Learning Representations (2018)"},{"key":"42_CR12","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE conference on computer vision and pattern recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"42_CR13","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 4171\u20134186 (2019)"},{"key":"42_CR14","doi-asserted-by":"crossref","unstructured":"Dong, L., Xu, S., Xu, B.: Speech-transformer: a no-recurrence sequence-to-sequence model for speech recognition. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5884\u20135888 (2018)","DOI":"10.1109\/ICASSP.2018.8462506"},{"key":"42_CR15","unstructured":"Dosovitskiy, A., et al.: An image is worth 16 $$\\times $$ 16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (2021)"},{"key":"42_CR16","unstructured":"FAIR: https:\/\/github.com\/pytorch\/fairseq"},{"key":"42_CR17","doi-asserted-by":"crossref","unstructured":"Guo, Q., Yu, Z., Wu, Y., Liang, D., Qin, H., Yan, J.: Dynamic recursive neural network. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5147\u20135156 (2019)","DOI":"10.1109\/CVPR.2019.00529"},{"key":"42_CR18","unstructured":"Han, K., Xiao, A., Wu, E., Guo, J., Xu, C., Wang, Y.: Transformer in transformer. arXiv preprint arXiv:2103.00112 (2021)"},{"key":"42_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"630","DOI":"10.1007\/978-3-319-46493-0_38","volume-title":"Computer Vision \u2013 ECCV 2016","author":"K He","year":"2016","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Identity mappings in deep residual networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 630\u2013645. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_38"},{"key":"42_CR20","doi-asserted-by":"crossref","unstructured":"Hendricks, L.A., Mellor, J., Schneider, R., Alayrac, J.B., Nematzadeh, A.: Decoupling the role of data, attention, and losses in multimodal transformers. arXiv preprint arXiv:2102.00529 (2021)","DOI":"10.1162\/tacl_a_00385"},{"key":"42_CR21","unstructured":"Hendrycks, D., Gimpel, K.: Gaussian error linear units (gelus). arXiv preprint arXiv:1606.08415 (2016)"},{"key":"42_CR22","doi-asserted-by":"crossref","unstructured":"Heo, B., Yun, S., Han, D., Chun, S., Choe, J., Oh, S.J.: Rethinking spatial dimensions of vision transformers. arXiv preprint arXiv:2103.16302 (2021)","DOI":"10.1109\/ICCV48922.2021.01172"},{"key":"42_CR23","doi-asserted-by":"crossref","unstructured":"Kim, J., Lee, J.K., Lee, K.M.: Deeply-recursive convolutional network for image super-resolution. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1637\u20131645 (2016)","DOI":"10.1109\/CVPR.2016.181"},{"key":"42_CR24","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"42_CR25","unstructured":"Lan, Z., Chen, M., Goodman, S., Gimpel, K., Sharma, P., Soricut, R.: Albert: a lite bert for self-supervised learning of language representations. arXiv preprint arXiv:1909.11942 (2019)"},{"key":"42_CR26","unstructured":"Li, H., Xu, Z., Taylor, G., Studer, C., Goldstein, T.: Visualizing the loss landscape of neural nets. In: Proceedings of the 32nd International Conference on Neural Information Processing Systems, pp. 6391\u20136401 (2018)"},{"key":"42_CR27","unstructured":"Li, Y., Zhang, K., Cao, J., Timofte, R., Van Gool, L.: Localvit: bringing locality to vision transformers. arXiv preprint arXiv:2104.05707 (2021)"},{"key":"42_CR28","unstructured":"Liang, M., Hu, X.: Recurrent convolutional neural network for object recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3367\u20133375 (2015)"},{"key":"42_CR29","doi-asserted-by":"crossref","unstructured":"Liu, F., Gao, M., Liu, Y., Lei, K.: Self-adaptive scaling for learnable residual structure. In: Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL) (2019)","DOI":"10.18653\/v1\/K19-1080"},{"key":"42_CR30","doi-asserted-by":"crossref","unstructured":"Liu, S., Yang, N., Li, M., Zhou, M.: A recursive recurrent neural network for statistical machine translation. In: Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 1491\u20131500 (2014)","DOI":"10.3115\/v1\/P14-1140"},{"key":"42_CR31","unstructured":"Liu, Y., et al.: Roberta: a robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)"},{"key":"42_CR32","doi-asserted-by":"crossref","unstructured":"Liu, Y., et al.: Cbnet: a novel composite backbone network architecture for object detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 11653\u201311660 (2020)","DOI":"10.1609\/aaai.v34i07.6834"},{"key":"42_CR33","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":"42_CR34","doi-asserted-by":"crossref","unstructured":"Luong, M.T., Pham, H., Manning, C.D.: Effective approaches to attention-based neural machine translation. In: Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pp. 1412\u20131421 (2015)","DOI":"10.18653\/v1\/D15-1166"},{"key":"42_CR35","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: Bleu: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics (2002)","DOI":"10.3115\/1073083.1073135"},{"issue":"8","key":"42_CR36","first-page":"9","volume":"1","author":"A Radford","year":"2019","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I.: Language models are unsupervised multitask learners. OpenAI Blog 1(8), 9 (2019)","journal-title":"OpenAI Blog"},{"key":"42_CR37","unstructured":"Romero, A., Ballas, N., Kahou, S.E., Chassang, A., Gatta, C., Bengio, Y.: Fitnets: Hints for thin deep nets. arXiv preprint arXiv:1412.6550 (2014)"},{"key":"42_CR38","doi-asserted-by":"crossref","unstructured":"Shen, Z., He, Z., Xue, X.: Meal: multi-model ensemble via adversarial learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 4886\u20134893 (2019)","DOI":"10.1609\/aaai.v33i01.33014886"},{"key":"42_CR39","unstructured":"Shen, Z., Liu, Z., Xu, D., Chen, Z., Cheng, K.T., Savvides, M.: Is label smoothing truly incompatible with knowledge distillation: an empirical study. In: International Conference on Learning Representations (2021)"},{"key":"42_CR40","doi-asserted-by":"crossref","unstructured":"Shen, Z., Liu, Z., Li, J., Jiang, Y.G., Chen, Y., Xue, X.: Dsod: learning deeply supervised object detectors from scratch. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1919\u20131927 (2017)","DOI":"10.1109\/ICCV.2017.212"},{"issue":"3","key":"42_CR41","doi-asserted-by":"publisher","first-page":"714","DOI":"10.1109\/72.572108","volume":"8","author":"A Sperduti","year":"1997","unstructured":"Sperduti, A., Starita, A.: Supervised neural networks for the classification of structures. IEEE Trans. Neural Netw. 8(3), 714\u2013735 (1997)","journal-title":"IEEE Trans. Neural Netw."},{"key":"42_CR42","doi-asserted-by":"crossref","unstructured":"Srinivas, A., Lin, T.Y., Parmar, N., Shlens, J., Abbeel, P., Vaswani, A.: Bottleneck transformers for visual recognition. arXiv preprint arXiv:2101.11605 (2021)","DOI":"10.1109\/CVPR46437.2021.01625"},{"key":"42_CR43","unstructured":"Tolstikhin, I., et al.: Mlp-mixer: an all-mlp architecture for vision. arXiv preprint arXiv:2105.01601 (2021)"},{"key":"42_CR44","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., J\u00e9gou, H.: Training data-efficient image transformers & distillation through attention. arXiv preprint arXiv:2012.12877 (2020)"},{"key":"42_CR45","doi-asserted-by":"crossref","unstructured":"Touvron, H., Cord, M., Sablayrolles, A., Synnaeve, G., J\u00e9gou, H.: Going deeper with image transformers. arXiv preprint arXiv:2103.17239 (2021)","DOI":"10.1109\/ICCV48922.2021.00010"},{"key":"42_CR46","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NIPS (2017)"},{"key":"42_CR47","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":"42_CR48","doi-asserted-by":"crossref","unstructured":"Wang, Y., et al.: Transformer in action: a comparative study of transformer-based acoustic models for large scale speech recognition applications. In: ICASSP 2021\u20132021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6778\u20136782. IEEE (2021)","DOI":"10.1109\/ICASSP39728.2021.9414087"},{"key":"42_CR49","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":"42_CR50","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":"42_CR51","unstructured":"Yang, Z., Dai, Z., Yang, Y., Carbonell, J., Salakhutdinov, R.R., Le, Q.V.: Xlnet: generalized autoregressive pretraining for language understanding. In: Advances in Neural Information Processing Systems (2019)"},{"key":"42_CR52","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":"42_CR53","unstructured":"Zhou, D., et al.: Deepvit: towards deeper vision transformer. arXiv preprint arXiv:2103.11886 (2021)"}],"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_42","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,5]],"date-time":"2022-11-05T16:37:58Z","timestamp":1667666278000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20053-3_42"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031200526","9783031200533"],"references-count":53,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20053-3_42","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)"}}]}}