{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,12]],"date-time":"2026-07-12T00:22:57Z","timestamp":1783815777081,"version":"3.55.0"},"publisher-location":"Cham","reference-count":38,"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_3","type":"book-chapter","created":{"date-parts":[[2023,2,11]],"date-time":"2023-02-11T09:12:42Z","timestamp":1676106762000},"page":"35-49","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":68,"title":["Hydra Attention: Efficient Attention with\u00a0Many Heads"],"prefix":"10.1007","author":[{"given":"Daniel","family":"Bolya","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cheng-Yang","family":"Fu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoliang","family":"Dai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peizhao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Judy","family":"Hoffman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,2,12]]},"reference":[{"key":"3_CR1","doi-asserted-by":"crossref","unstructured":"Abnar, S., Zuidema, W.: Quantifying attention flow in transformers. arXiv:2005.00928 [cs.LG] (2020)","DOI":"10.18653\/v1\/2020.acl-main.385"},{"key":"3_CR2","doi-asserted-by":"crossref","unstructured":"Babiloni, F., Marras, I., Kokkinos, F., Deng, J., Chrysos, G., Zafeiriou, S.: Poly-NL: linear complexity non-local layers with 3rd order polynomials. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01035"},{"key":"3_CR3","unstructured":"Chen, B., Wang, R., Ming, D., Feng, X.: ViT-P: rethinking data-efficient vision transformers from locality. arXiv:2203.02358 [cs.CV] (2022)"},{"key":"3_CR4","doi-asserted-by":"crossref","unstructured":"Chen, Y., et al.: Mobile-former: bridging mobilenet and transformer. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00520"},{"key":"3_CR5","unstructured":"Choromanski, K., et al.: Rethinking attention with performers. arXiv:2009.14794 [cs.LG] (2020)"},{"key":"3_CR6","unstructured":"Chowdhery, A., et al.: PaLM: scaling language modeling with pathways. arXiv:2204.02311 [cs.CL] (2022)"},{"key":"3_CR7","doi-asserted-by":"crossref","unstructured":"Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.350"},{"key":"3_CR8","unstructured":"Dao, T., Fu, D.Y., Ermon, S., Rudra, A., R\u00e9, C.: FlashAttention: fast and memory-efficient exact attention with IO-awareness. arXiv:2205.14135 [cs.LG] (2022)"},{"key":"3_CR9","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 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"3_CR10","unstructured":"Dosovitskiy, A., et al.: An image is worth $$16 \\times 16$$ words: transformers for image recognition at scale. In: ICLR (2020)"},{"key":"3_CR11","doi-asserted-by":"crossref","unstructured":"Fan, H., et al.: Multiscale vision transformers. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"3_CR12","unstructured":"Feichtenhofer, C., Fan, H., Li, Y., He, K.: Masked autoencoders as spatiotemporal learners. arXiv:2205.09113 [cs.CV] (2022)"},{"key":"3_CR13","doi-asserted-by":"crossref","unstructured":"Graham, B., et al.: LeViT: a vision transformer in convnet\u2019s clothing for faster inference. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01204"},{"key":"3_CR14","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"3_CR15","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"3_CR16","unstructured":"Katharopoulos, A., Vyas, A., Pappas, N., Fleuret, F.: Transformers are RNNs: fast autoregressive transformers with linear attention. In: ICML (2020)"},{"key":"3_CR17","unstructured":"Kenton, J.D.M.W.C., Toutanova, L.K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL-HLT (2019)"},{"key":"3_CR18","doi-asserted-by":"crossref","unstructured":"Kong, Z., et al.: SPViT: enabling faster vision transformers via soft token pruning. arXiv:2112.13890 [cs.CV] (2021)","DOI":"10.1007\/978-3-031-20083-0_37"},{"key":"3_CR19","doi-asserted-by":"crossref","unstructured":"Li, Y., Mao, H., Girshick, R., He, K.: Exploring plain vision transformer backbones for object detection. arXiv:2203.16527 [cs.CV] (2022)","DOI":"10.1007\/978-3-031-20077-9_17"},{"key":"3_CR20","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: MViTv2: improved multiscale vision transformers for classification and detection. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00476"},{"key":"3_CR21","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"3_CR22","unstructured":"Mehta, S., Rastegari, M.: MobileViT: light-weight, general-purpose, and mobile-friendly vision transformer. arXiv:2110.02178 [cs.CV] (2021)"},{"key":"3_CR23","unstructured":"Michel, P., Levy, O., Neubig, G.: Are sixteen heads really better than one? In: NeurIPS (2019)"},{"key":"3_CR24","unstructured":"Peng, H., Pappas, N., Yogatama, D., Schwartz, R., Smith, N.A., Kong, L.: Random feature attention. arXiv:2103.02143 [cs.CL] (2021)"},{"key":"3_CR25","unstructured":"Radford, A., et al.: Language models are unsupervised multitask learners. OpenAI Blog (2019)"},{"key":"3_CR26","unstructured":"Rao, Y., Zhao, W., Liu, B., Lu, J., Zhou, J., Hsieh, C.J.: DynamicViT: efficient vision transformers with dynamic token sparsification. In: NeurIPS (2021)"},{"key":"3_CR27","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-CAM: visual explanations from deep networks via gradient-based localization. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.74"},{"key":"3_CR28","unstructured":"Shen, Z., Zhang, M., Zhao, H., Yi, S., Li, H.: Efficient attention: attention with linear complexities. In: WACV (2021)"},{"key":"3_CR29","unstructured":"Song, J.: UFO-ViT: high performance linear vision transformer without softmax. arXiv:2109.14382 [cs.CV] (2021)"},{"key":"3_CR30","unstructured":"Tong, Z., Song, Y., Wang, J., Wang, L.: VideoMAE: masked autoencoders are data-efficient learners for self-supervised video pre-training. arXiv:2203.12602 [cs.CV] (2022)"},{"key":"3_CR31","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., J\u00e9gou, H.: Training data-efficient image transformers & distillation through attention. arXiv:2012.12877 [cs.CV] (2020)"},{"key":"3_CR32","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS (2017)"},{"key":"3_CR33","doi-asserted-by":"crossref","unstructured":"Voita, E., Talbot, D., Moiseev, F., Sennrich, R., Titov, I.: Analyzing multi-head self-attention: specialized heads do the heavy lifting, the rest can be pruned. arXiv:1905.09418 [cs.CL] (2019)","DOI":"10.18653\/v1\/P19-1580"},{"key":"3_CR34","unstructured":"Wang, S., Li, B.Z., Khabsa, M., Fang, H., Ma, H.: Linformer: self-attention with linear complexity. arXiv:2006.04768 [cs.LG] (2020)"},{"key":"3_CR35","doi-asserted-by":"crossref","unstructured":"Yang, C., et al.: Lite vision transformer with enhanced self-attention. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01169"},{"key":"3_CR36","doi-asserted-by":"crossref","unstructured":"Yin, H., Vahdat, A., Alvarez, J., Mallya, A., Kautz, J., Molchanov, P.: AdaViT: adaptive tokens for efficient vision transformer. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01054"},{"key":"3_CR37","unstructured":"Zhai, S., et al.: An attention free transformer. arXiv:2105.14103 [cs.LG] (2021)"},{"key":"3_CR38","doi-asserted-by":"crossref","unstructured":"Zhai, X., Kolesnikov, A., Houlsby, N., Beyer, L.: Scaling vision transformers. arXiv:2106.04560 [cs.CV] (2021)","DOI":"10.1109\/CVPR52688.2022.01179"}],"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_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T13:01:20Z","timestamp":1709816480000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-25082-8_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031250811","9783031250828"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-25082-8_3","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)"}}]}}