{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,2]],"date-time":"2026-08-02T19:14:12Z","timestamp":1785698052161,"version":"3.56.0"},"publisher-location":"Cham","reference-count":41,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726835","type":"print"},{"value":"9783031726842","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-72684-2_17","type":"book-chapter","created":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T19:02:45Z","timestamp":1730574165000},"page":"289-305","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":56,"title":["Rotary Position Embedding for\u00a0Vision Transformer"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2134-6345","authenticated-orcid":false,"given":"Byeongho","family":"Heo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4332-9733","authenticated-orcid":false,"given":"Song","family":"Park","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9130-8195","authenticated-orcid":false,"given":"Dongyoon","family":"Han","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0417-8450","authenticated-orcid":false,"given":"Sangdoo","family":"Yun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,11,3]]},"reference":[{"key":"17_CR1","doi-asserted-by":"crossref","unstructured":"Beyer, L., et al.: Flexivit: one model for all patch sizes. In: CVPR, pp. 14496\u201314506 (2023)","DOI":"10.1109\/CVPR52729.2023.01393"},{"key":"17_CR2","doi-asserted-by":"crossref","unstructured":"Cheng, B., Misra, I., Schwing, A.G., Kirillov, A., Girdhar, R.: Masked-attention mask transformer for universal image segmentation (2022)","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"17_CR3","unstructured":"Chu, X., et al.: Conditional positional encodings for vision transformers. arXiv preprint arXiv:2102.10882 (2021)"},{"key":"17_CR4","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: CVPR, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"17_CR5","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"17_CR6","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"17_CR7","doi-asserted-by":"crossref","unstructured":"Fang, Y., Sun, Q., Wang, X., Huang, T., Wang, X., Cao, Y.: Eva-02: a visual representation for neon genesis. arXiv preprint arXiv:2303.11331 (2023)","DOI":"10.2139\/ssrn.4813567"},{"key":"17_CR8","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":"17_CR9","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. 11936\u201311945 (2021)","DOI":"10.1109\/ICCV48922.2021.01172"},{"key":"17_CR10","unstructured":"Howard, A.G., et al.: Mobilenets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)"},{"key":"17_CR11","doi-asserted-by":"crossref","unstructured":"Jeevan, P., Sethi, A.: Resource-efficient hybrid x-formers for vision. In: WACV, pp. 2982\u20132990 (2022)","DOI":"10.1109\/WACV51458.2022.00361"},{"key":"17_CR12","unstructured":"Jiang, A.Q., et\u00a0al.: Mistral 7b. arXiv preprint arXiv:2310.06825 (2023)"},{"key":"17_CR13","unstructured":"Krizhevsky, A., Hinton, G., et\u00a0al.: Learning multiple layers of features from tiny images (2009)"},{"key":"17_CR14","unstructured":"Le, Y., Yang, X.: Tiny imagenet visual recognition challenge. CS 231N 7(7), 3 (2015)"},{"key":"17_CR15","first-page":"16079","volume":"34","author":"T Likhomanenko","year":"2021","unstructured":"Likhomanenko, T., Xu, Q., Synnaeve, G., Collobert, R., Rogozhnikov, A.: Cape: encoding relative positions with continuous augmented positional embeddings. NeruIPS 34, 16079\u201316092 (2021)","journal-title":"NeruIPS"},{"key":"17_CR16","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":"17_CR17","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: ICCV, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"17_CR18","doi-asserted-by":"crossref","unstructured":"Lu, J., et al.: Unified-io 2: scaling autoregressive multimodal models with vision, language, audio, and action. arXiv preprint arXiv:2312.17172 (2023)","DOI":"10.1109\/CVPR52733.2024.02497"},{"key":"17_CR19","unstructured":"Lu, Z., et al.: Fit: flexible vision transformer for diffusion model. arXiv preprint arXiv:2402.12376 (2024)"},{"key":"17_CR20","unstructured":"Park, N., Kim, W., Heo, B., Kim, T., Yun, S.: What do self-supervised vision transformers learn? arXiv preprint arXiv:2305.00729 (2023)"},{"key":"17_CR21","unstructured":"Peng, Z., Dong, L., Bao, H., Ye, Q., Wei, F.: Beit v2: masked image modeling with vector-quantized visual tokenizers. arXiv preprint arXiv:2208.06366 (2022)"},{"key":"17_CR22","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML, pp. 8748\u20138763. PMLR (2021)"},{"key":"17_CR23","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. JMLR 21(1), 5485\u20135551 (2020)"},{"key":"17_CR24","unstructured":"Ren, T., et al.: detrex: benchmarking detection transformers (2023)"},{"key":"17_CR25","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: CVPR, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"17_CR26","unstructured":"Roziere, B., et\u00a0al.: Code llama: open foundation models for code. arXiv preprint arXiv:2308.12950 (2023)"},{"key":"17_CR27","doi-asserted-by":"crossref","unstructured":"Shaw, P., Uszkoreit, J., Vaswani, A.: Self-attention with relative position representations. In: ACL (2018)","DOI":"10.18653\/v1\/N18-2074"},{"key":"17_CR28","unstructured":"Steiner, A., Kolesnikov, A., Zhai, X., Wightman, R., Uszkoreit, J., Beyer, L.: How to train your vit? data, augmentation, and regularization in vision transformers. arXiv preprint arXiv:2106.10270 (2021)"},{"key":"17_CR29","doi-asserted-by":"publisher","first-page":"127063","DOI":"10.1016\/j.neucom.2023.127063","volume":"568","author":"J Su","year":"2024","unstructured":"Su, J., Ahmed, M., Lu, Y., Pan, S., Bo, W., Liu, Y.: Roformer: enhanced transformer with rotary position embedding. Neurocomputing 568, 127063 (2024)","journal-title":"Neurocomputing"},{"key":"17_CR30","doi-asserted-by":"crossref","unstructured":"Tian, R., Wu, Z., Dai, Q., Hu, H., Qiao, Y., Jiang, Y.G.: Resformer: scaling vits with multi-resolution training. In: CVPR, pp. 22721\u201322731 (2023)","DOI":"10.1109\/CVPR52729.2023.02176"},{"key":"17_CR31","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., J\u00e9gou, H.: Training data-efficient image transformers & distillation through attention. In: ICML, pp. 10347\u201310357. PMLR (2021)"},{"key":"17_CR32","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"516","DOI":"10.1007\/978-3-031-20053-3_30","volume-title":"ECCV 2022","author":"H Touvron","year":"2022","unstructured":"Touvron, H., Cord, M., J\u00e9gou, H.: Deit iii: revenge of the vit. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13684, pp. 516\u2013533. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20053-3_30"},{"key":"17_CR33","unstructured":"Touvron, H., et\u00a0al.: Llama 2: open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)"},{"key":"17_CR34","unstructured":"Vaswani, A., et al.: Attention is all you need. NeruIPS 30 (2017)"},{"key":"17_CR35","unstructured":"Wightman, R., Touvron, H., J\u00e9gou, H.: Resnet strikes back: an improved training procedure in timm. arXiv preprint arXiv:2110.00476 (2021)"},{"key":"17_CR36","doi-asserted-by":"crossref","unstructured":"Wu, K., Peng, H., Chen, M., Fu, J., Chao, H.: Rethinking and improving relative position encoding for vision transformer. In: ICCV, pp. 10033\u201310041 (2021)","DOI":"10.1109\/ICCV48922.2021.00988"},{"key":"17_CR37","doi-asserted-by":"crossref","unstructured":"Xiao, T., Liu, Y., Zhou, B., Jiang, Y., Sun, J.: Unified perceptual parsing for scene understanding. In: ECCV, pp. 418\u2013434 (2018)","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"17_CR38","doi-asserted-by":"crossref","unstructured":"Yu, R., et al.: Lape: layer-adaptive position embedding for vision transformers with independent layer normalization. In: ICCV, pp. 5886\u20135896 (2023)","DOI":"10.1109\/ICCV51070.2023.00541"},{"key":"17_CR39","unstructured":"Zhang, H., et al.: Dino: detr with improved denoising anchor boxes for end-to-end object detection (2022)"},{"key":"17_CR40","doi-asserted-by":"crossref","unstructured":"Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., Torralba, A.: Scene parsing through ade20k dataset. In: CVPR, pp. 633\u2013641 (2017)","DOI":"10.1109\/CVPR.2017.544"},{"issue":"3","key":"17_CR41","doi-asserted-by":"publisher","first-page":"302","DOI":"10.1007\/s11263-018-1140-0","volume":"127","author":"B Zhou","year":"2018","unstructured":"Zhou, B., et al.: Semantic Understanding of Scenes Through the ADE20K Dataset. Int. J. Comput. Vis. 127(3), 302\u2013321 (2018). https:\/\/doi.org\/10.1007\/s11263-018-1140-0","journal-title":"Int. J. Comput. Vis."}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72684-2_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T19:08:15Z","timestamp":1730574495000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72684-2_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,3]]},"ISBN":["9783031726835","9783031726842"],"references-count":41,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72684-2_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,3]]},"assertion":[{"value":"3 November 2024","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":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}