{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,2]],"date-time":"2026-11-02T11:50:52Z","timestamp":1793620252195,"version":"4.5.0"},"publisher-location":"Cham","reference-count":59,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031200465","type":"print"},{"value":"9783031200472","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.springernature.com\/gp\/researchers\/text-and-data-mining"},{"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.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-20047-2_9","type":"book-chapter","created":{"date-parts":[[2022,10,22]],"date-time":"2022-10-22T06:02:55Z","timestamp":1666418575000},"page":"146-164","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":351,"title":["AiATrack: Attention in\u00a0Attention for\u00a0Transformer Visual Tracking"],"prefix":"10.1007","author":[{"given":"Shenyuan","family":"Gao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chunluan","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chao","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinggang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junsong","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,10,23]]},"reference":[{"key":"9_CR1","unstructured":"Ba, J.L., Kiros, J.R., Hinton, G.E.: Layer normalization. arXiv preprint arXiv:1607.06450 (2016)"},{"key":"9_CR2","doi-asserted-by":"publisher","unstructured":"Bertinetto, L., Valmadre, J., Henriques, J.F., Vedaldi, A., Torr, P.H.: Fully-convolutional Siamese networks for object tracking. In: European Conference on Computer Vision, pp. 850\u2013865. Springer (2016). https:\/\/doi.org\/10.1007\/978-3-319-48881-3_56","DOI":"10.1007\/978-3-319-48881-3_56"},{"key":"9_CR3","doi-asserted-by":"crossref","unstructured":"Bhat, G., Danelljan, M., Gool, L.V., Timofte, R.: Learning discriminative model prediction for tracking. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6182\u20136191 (2019)","DOI":"10.1109\/ICCV.2019.00628"},{"key":"9_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"205","DOI":"10.1007\/978-3-030-58592-1_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"G Bhat","year":"2020","unstructured":"Bhat, G., Danelljan, M., Van Gool, L., Timofte, R.: Know your surroundings: exploiting scene information for object tracking. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12368, pp. 205\u2013221. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58592-1_13"},{"key":"9_CR5","doi-asserted-by":"crossref","unstructured":"Bian, J., Lin, W.Y., Matsushita, Y., Yeung, S.K., Nguyen, T.D., Cheng, M.M.: GMS: grid-based motion statistics for fast, ultra-robust feature correspondence. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4181\u20134190 (2017)","DOI":"10.1109\/CVPR.2017.302"},{"key":"9_CR6","doi-asserted-by":"crossref","unstructured":"Cao, Z., Fu, C., Ye, J., Li, B., Li, Y.: HiFT: hierarchical feature transformer for aerial tracking. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15457\u201315466 (2021)","DOI":"10.1109\/ICCV48922.2021.01517"},{"key":"9_CR7","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":"9_CR8","doi-asserted-by":"crossref","unstructured":"Chen, X., Yan, B., Zhu, J., Wang, D., Yang, X., Lu, H.: Transformer tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8126\u20138135 (2021)","DOI":"10.1109\/CVPR46437.2021.00803"},{"key":"9_CR9","unstructured":"Cho, S., Hong, S., Jeon, S., Lee, Y., Sohn, K., Kim, S.: CATs: cost aggregation transformers for visual correspondence. Adv. Neural Inf. Process. Syst. 34, 9011\u20139023 (2021)"},{"key":"9_CR10","doi-asserted-by":"crossref","unstructured":"Dai, K., Zhang, Y., Wang, D., Li, J., Lu, H., Yang, X.: High-performance long-term tracking with meta-updater. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6298\u20136307 (2020)","DOI":"10.1109\/CVPR42600.2020.00633"},{"key":"9_CR11","doi-asserted-by":"crossref","unstructured":"Danelljan, M., Bhat, G., Khan, F.S., Felsberg, M.: Atom: accurate tracking by overlap maximization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4660\u20134669 (2019)","DOI":"10.1109\/CVPR.2019.00479"},{"key":"9_CR12","doi-asserted-by":"crossref","unstructured":"Danelljan, M., Gool, L.V., Timofte, R.: Probabilistic regression for visual tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7183\u20137192 (2020)","DOI":"10.1109\/CVPR42600.2020.00721"},{"key":"9_CR13","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":"9_CR14","unstructured":"Dosovitskiy, A., et al.: An image is worth 16\u00a0$$\\times $$\u00a016 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"9_CR15","doi-asserted-by":"crossref","unstructured":"Duke, B., Ahmed, A., Wolf, C., Aarabi, P., Taylor, G.W.: SSTVOS: sparse spatiotemporal transformers for video object segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5912\u20135921 (2021)","DOI":"10.1109\/CVPR46437.2021.00585"},{"key":"9_CR16","doi-asserted-by":"publisher","unstructured":"Fan, H., et al.: Lasot: a high-quality large-scale single object tracking benchmark. Int. J. Comput. Vis. 129(2), 439\u2013461 (2021). https:\/\/doi.org\/10.1007\/s11263-020-01387-y","DOI":"10.1007\/s11263-020-01387-y"},{"key":"9_CR17","doi-asserted-by":"crossref","unstructured":"Fan, H., et al.: LaSOT: a high-quality benchmark for large-scale single object tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5374\u20135383 (2019)","DOI":"10.1109\/CVPR.2019.00552"},{"issue":"2","key":"9_CR18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3309665","volume":"52","author":"M Fiaz","year":"2019","unstructured":"Fiaz, M., Mahmood, A., Javed, S., Jung, S.K.: Handcrafted and deep trackers: recent visual object tracking approaches and trends. ACM Comput. Surv. (CSUR) 52(2), 1\u201344 (2019)","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"9_CR19","doi-asserted-by":"crossref","unstructured":"Fu, Z., Liu, Q., Fu, Z., Wang, Y.: STMTrack: template-free visual tracking with space-time memory networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13774\u201313783 (2021)","DOI":"10.1109\/CVPR46437.2021.01356"},{"key":"9_CR20","doi-asserted-by":"crossref","unstructured":"Ge, W., Lu, X., Shen, J.: Video object segmentation using global and instance embedding learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16836\u201316845 (2021)","DOI":"10.1109\/CVPR46437.2021.01656"},{"key":"9_CR21","doi-asserted-by":"crossref","unstructured":"Guo, D., Shao, Y., Cui, Y., Wang, Z., Zhang, L., Shen, C.: Graph attention tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9543\u20139552 (2021)","DOI":"10.1109\/CVPR46437.2021.00942"},{"key":"9_CR22","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"9_CR23","doi-asserted-by":"crossref","unstructured":"He, L., et al.: End-to-end video object detection with spatial-temporal transformers. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 1507\u20131516 (2021)","DOI":"10.1145\/3474085.3475285"},{"issue":"3","key":"9_CR24","doi-asserted-by":"publisher","first-page":"583","DOI":"10.1109\/TPAMI.2014.2345390","volume":"37","author":"JF Henriques","year":"2014","unstructured":"Henriques, J.F., Caseiro, R., Martins, P., Batista, J.: High-speed tracking with kernelized correlation filters. IEEE Trans. Pattern Anal. Mach. Intell. 37(3), 583\u2013596 (2014)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"5","key":"9_CR25","doi-asserted-by":"publisher","first-page":"1562","DOI":"10.1109\/TPAMI.2019.2957464","volume":"43","author":"L Huang","year":"2019","unstructured":"Huang, L., Zhao, X., Huang, K.: Got-10k: a large high-diversity benchmark for generic object tracking in the wild. IEEE Trans. Pattern Anal. Mach. Intell. 43(5), 1562\u20131577 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"9_CR26","doi-asserted-by":"crossref","unstructured":"Huang, L., Wang, W., Chen, J., Wei, X.Y.: Attention on attention for image captioning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4634\u20134643 (2019)","DOI":"10.1109\/ICCV.2019.00473"},{"key":"9_CR27","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: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 603\u2013612 (2019)","DOI":"10.1109\/ICCV.2019.00069"},{"key":"9_CR28","doi-asserted-by":"crossref","unstructured":"Jiang, B., Luo, R., Mao, J., Xiao, T., Jiang, Y.: Acquisition of localization confidence for accurate object detection. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 784\u2013799 (2018)","DOI":"10.1007\/978-3-030-01264-9_48"},{"key":"9_CR29","doi-asserted-by":"crossref","unstructured":"Galoogahi, H.K., Fagg, A., Huang, C., Ramanan, D., Lucey, S.: Need for speed: a benchmark for higher frame rate object tracking. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1125\u20131134 (2017)","DOI":"10.1109\/ICCV.2017.128"},{"key":"9_CR30","unstructured":"Lan, M., Zhang, J., He, F., Zhang, L.: Siamese network with interactive transformer for video object segmentation. arXiv preprint arXiv:2112.13983 (2021)"},{"key":"9_CR31","doi-asserted-by":"crossref","unstructured":"Li, B., Wu, W., Wang, Q., Zhang, F., Xing, J., Yan, J.: SiamRPN++: evolution of Siamese visual tracking with very deep networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4282\u20134291 (2019)","DOI":"10.1109\/CVPR.2019.00441"},{"key":"9_CR32","doi-asserted-by":"crossref","unstructured":"Li, B., Yan, J., Wu, W., Zhu, Z., Hu, X.: High performance visual tracking with Siamese region proposal network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8971\u20138980 (2018)","DOI":"10.1109\/CVPR.2018.00935"},{"key":"9_CR33","doi-asserted-by":"crossref","unstructured":"Li, S., Han, K., Costain, T.W., Howard-Jenkins, H., Prisacariu, V.: Correspondence networks with adaptive neighbourhood consensus. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10196\u201310205 (2020)","DOI":"10.1109\/CVPR42600.2020.01021"},{"key":"9_CR34","doi-asserted-by":"crossref","unstructured":"Mao, Y., Wang, N., Zhou, W., Li, H.: Joint inductive and transductive learning for video object segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9670\u20139679 (2021)","DOI":"10.1109\/ICCV48922.2021.00953"},{"key":"9_CR35","doi-asserted-by":"crossref","unstructured":"Marvasti-Zadeh, S.M., Cheng, L., Ghanei-Yakhdan, H., Kasaei, S.: Deep learning for visual tracking: a comprehensive survey. IEEE Trans. Intell. Transp. Syst. (2021)","DOI":"10.1109\/TITS.2020.3046478"},{"key":"9_CR36","doi-asserted-by":"crossref","unstructured":"Mayer, C., Danelljan, M., Paudel, D.P., Van Gool, L.: Learning target candidate association to keep track of what not to track. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13444\u201313454 (2021)","DOI":"10.1109\/ICCV48922.2021.01319"},{"key":"9_CR37","doi-asserted-by":"crossref","unstructured":"Meinhardt, T., Kirillov, A., Leal-Taixe, L., Feichtenhofer, C.: Trackformer: multi-object tracking with transformers. arXiv preprint arXiv:2101.02702 (2021)","DOI":"10.1109\/CVPR52688.2022.00864"},{"key":"9_CR38","doi-asserted-by":"crossref","unstructured":"Min, J., Cho, M.: Convolutional Hough matching networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2940\u20132950 (2021)","DOI":"10.1109\/CVPR46437.2021.00296"},{"key":"9_CR39","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"445","DOI":"10.1007\/978-3-319-46448-0_27","volume-title":"Computer Vision \u2013 ECCV 2016","author":"M Mueller","year":"2016","unstructured":"Mueller, M., Smith, N., Ghanem, B.: A benchmark and simulator for UAV tracking. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 445\u2013461. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_27"},{"key":"9_CR40","doi-asserted-by":"crossref","unstructured":"Muller, M., Bibi, A., Giancola, S., Alsubaihi, S., Ghanem, B.: TrackingNet: a large-scale dataset and benchmark for object tracking in the wild. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 300\u2013317 (2018)","DOI":"10.1007\/978-3-030-01246-5_19"},{"key":"9_CR41","doi-asserted-by":"crossref","unstructured":"Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., Savarese, S.: Generalized intersection over union: a metric and a loss for bounding box regression. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 658\u2013666 (2019)","DOI":"10.1109\/CVPR.2019.00075"},{"key":"9_CR42","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"605","DOI":"10.1007\/978-3-030-58545-7_35","volume-title":"Computer Vision \u2013 ECCV 2020","author":"I Rocco","year":"2020","unstructured":"Rocco, I., Arandjelovi\u0107, R., Sivic, J.: Efficient neighbourhood consensus networks via submanifold sparse convolutions. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12354, pp. 605\u2013621. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58545-7_35"},{"key":"9_CR43","unstructured":"Rocco, I., Cimpoi, M., Arandjelovi\u0107, R., Torii, A., Pajdla, T., Sivic, J.: Neighbourhood consensus networks. Adv. Neural Inf. Process. Syst. 31 (2018)"},{"key":"9_CR44","doi-asserted-by":"crossref","unstructured":"Sattler, T., Leibe, B., Kobbelt, L.: SCRAMSAC: improving RANSAC\u2019s efficiency with a spatial consistency filter. In: 2009 IEEE 12th International Conference on Computer Vision, pp. 2090\u20132097. IEEE (2009)","DOI":"10.1109\/ICCV.2009.5459459"},{"key":"9_CR45","doi-asserted-by":"crossref","unstructured":"Shechtman, E., Irani, M.: Matching local self-similarities across images and videos. In: 2007 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1\u20138. IEEE (2007)","DOI":"10.1109\/CVPR.2007.383198"},{"key":"9_CR46","unstructured":"Sun, P., et al.: TransTrack: multiple object tracking with transformer. arXiv preprint arXiv:2012.15460 (2020)"},{"key":"9_CR47","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"9_CR48","doi-asserted-by":"crossref","unstructured":"Wang, N., Zhou, W., Wang, J., Li, H.: Transformer meets tracker: exploiting temporal context for robust visual tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1571\u20131580 (2021)","DOI":"10.1109\/CVPR46437.2021.00162"},{"key":"9_CR49","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7794\u20137803 (2018)","DOI":"10.1109\/CVPR.2018.00813"},{"issue":"9","key":"9_CR50","doi-asserted-by":"publisher","first-page":"1834","DOI":"10.1109\/TPAMI.2014.2388226","volume":"37","author":"Y Wu","year":"2015","unstructured":"Wu, Y., Lim, J., Yang, M.: Object tracking benchmark. IEEE Trans. Pattern Anal. Mach. Intell. 37(9), 1834\u20131848 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"9_CR51","doi-asserted-by":"crossref","unstructured":"Xing, D., Evangeliou, N., Tsoukalas, A., Tzes, A.: Siamese transformer pyramid networks for real-time UAV tracking. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 2139\u20132148 (2022)","DOI":"10.1109\/WACV51458.2022.00196"},{"key":"9_CR52","doi-asserted-by":"crossref","unstructured":"Yan, B., Peng, H., Fu, J., Wang, D., Lu, H.: Learning spatio-temporal transformer for visual tracking. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10448\u201310457 (2021)","DOI":"10.1109\/ICCV48922.2021.01028"},{"key":"9_CR53","unstructured":"Yang, Z., Wei, Y., Yang, Y.: Associating objects with transformers for video object segmentation. Adv. Neural Inf. Process. Syst. 34 (2021)"},{"key":"9_CR54","doi-asserted-by":"crossref","unstructured":"Yu, B., et al.: High-performance discriminative tracking with transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9856\u20139865 (2021)","DOI":"10.1109\/ICCV48922.2021.00971"},{"key":"9_CR55","doi-asserted-by":"crossref","unstructured":"Yu, Y., Xiong, Y., Huang, W., Scott, M.R.: Deformable Siamese attention networks for visual object tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6728\u20136737 (2020)","DOI":"10.1109\/CVPR42600.2020.00676"},{"key":"9_CR56","doi-asserted-by":"crossref","unstructured":"Zhang, L., Gonzalez-Garcia, A., Weijer, J.V.d., Danelljan, M., Khan, F.S.: Learning the model update for Siamese trackers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4010\u20134019 (2019)","DOI":"10.1109\/ICCV.2019.00411"},{"key":"9_CR57","doi-asserted-by":"crossref","unstructured":"Zhang, Y., et al.: ByteTrack: multi-object tracking by associating every detection box. arXiv preprint arXiv:2110.06864 (2021)","DOI":"10.1007\/978-3-031-20047-2_1"},{"key":"9_CR58","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"771","DOI":"10.1007\/978-3-030-58589-1_46","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Z Zhang","year":"2020","unstructured":"Zhang, Z., Peng, H., Fu, J., Li, B., Hu, W.: Ocean: object-aware anchor-free tracking. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12366, pp. 771\u2013787. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58589-1_46"},{"key":"9_CR59","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable DETR: deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159 (2020)"}],"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\/978-3-031-20047-2_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,22]],"date-time":"2026-10-22T00:17:10Z","timestamp":1792628230000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/chapter\/10.1007\/978-3-031-20047-2_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031200465","9783031200472"],"references-count":59,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20047-2_9","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":"23 October 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)"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}