{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T23:22:06Z","timestamp":1771629726511,"version":"3.50.1"},"publisher-location":"Cham","reference-count":58,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031262838","type":"print"},{"value":"9783031262845","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\/978-3-031-26284-5_13","type":"book-chapter","created":{"date-parts":[[2023,2,22]],"date-time":"2023-02-22T08:02:59Z","timestamp":1677052979000},"page":"204-221","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Patch Embedding as\u00a0Local Features: Unifying Deep Local and\u00a0Global Features via\u00a0Vision Transformer for\u00a0Image Retrieval"],"prefix":"10.1007","author":[{"given":"Lam","family":"Phan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hiep Thi Hong","family":"Nguyen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Harikrishna","family":"Warrier","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yogesh","family":"Gupta","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,2,23]]},"reference":[{"key":"13_CR1","unstructured":"Ali, A., et al.: XCiT: cross-covariance image transformers. In: Advances in Neural Information Processing Systems 34 (2021)"},{"key":"13_CR2","doi-asserted-by":"crossref","unstructured":"Arandjelovi\u0107, R., Gronat, P., Torii, A., Pajdla, T., Sivic, J.: NetVLAD: CNN architecture for weakly supervised place recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.572"},{"key":"13_CR3","doi-asserted-by":"crossref","unstructured":"Arnab, A., Dehghani, M., Heigold, G., Sun, C., Lu\u010di\u0107, M., Schmid, C.: ViViT: a video vision transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6836\u20136846 (2021)","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"13_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11263-013-0659-3","volume":"107","author":"Y Avrithis","year":"2014","unstructured":"Avrithis, Y., Tolias, G.: Hough pyramid matching: Speeded-up geometry re-ranking for large scale image retrieval. Int. J. Comput. Vision 107, 1\u201319 (2014)","journal-title":"Int. J. Comput. Vision"},{"key":"13_CR5","doi-asserted-by":"crossref","unstructured":"Balntas, V., Riba, E., Ponsa, D., Mikolajczyk, K.: Learning local feature descriptors with triplets and shallow convolutional neural networks. In: BMVC, p. 3 (2016)","DOI":"10.5244\/C.30.119"},{"key":"13_CR6","doi-asserted-by":"crossref","unstructured":"Barroso-Laguna, A., Riba, E., Ponsa, D., Mikolajczyk, K.: Key.Net: keypoint detection by handcrafted and learned CNN filters. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5836\u20135844 (2019)","DOI":"10.1109\/ICCV.2019.00593"},{"issue":"3","key":"13_CR7","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1016\/j.cviu.2007.09.014","volume":"110","author":"H Bay","year":"2008","unstructured":"Bay, H., Ess, A., Tuytelaars, T., Gool, L.V.: Speeded-up robust features (surf). Comput. Vis. Image Underst. 110(3), 346\u2013359 (2008)","journal-title":"Comput. Vis. Image Underst."},{"key":"13_CR8","unstructured":"Bertasius, G., Wang, H., Torresani, L.: Is space-time attention all you need for video understanding. arXiv preprint arXiv:2102.05095 2(3), 4 (2021)"},{"key":"13_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"726","DOI":"10.1007\/978-3-030-58565-5_43","volume-title":"Computer Vision \u2013 ECCV 2020","author":"B Cao","year":"2020","unstructured":"Cao, B., Araujo, A., Sim, J.: Unifying deep local and global features for image search. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12365, pp. 726\u2013743. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58565-5_43"},{"key":"13_CR10","unstructured":"Chen, L.C., Papandreou, G., Schroff, F., Adam, H.: Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587 (2017)"},{"key":"13_CR11","doi-asserted-by":"crossref","unstructured":"Chopra, S., Hadsell, R., LeCun, Y.: Learning a similarity metric discriminatively, with application to face verification. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005, vol. 1, pp. 539\u2013546. IEEE (2005)","DOI":"10.1109\/CVPR.2005.202"},{"key":"13_CR12","doi-asserted-by":"crossref","unstructured":"Deng, J., Guo, J., Xue, N., Zafeiriou, S.: ArcFace: additive angular margin loss for deep face recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4690\u20134699 (2019)","DOI":"10.1109\/CVPR.2019.00482"},{"key":"13_CR13","doi-asserted-by":"publisher","unstructured":"DeTone, D., Malisiewicz, T., Rabinovich, A.: SuperPoint: self-supervised interest point detection and description. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 337\u201333712 (2018). https:\/\/doi.org\/10.1109\/CVPRW.2018.00060","DOI":"10.1109\/CVPRW.2018.00060"},{"key":"13_CR14","doi-asserted-by":"crossref","unstructured":"DeTone, D., Malisiewicz, T., Rabinovich, A.: SuperPoint: self-supervised interest point detection and description. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 224\u2013236 (2018)","DOI":"10.1109\/CVPRW.2018.00060"},{"key":"13_CR15","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: ICLR (2021)"},{"key":"13_CR16","doi-asserted-by":"crossref","unstructured":"Dusmanu, M., et al.: D2-Net: a trainable CNN for joint detection and description of local features. arXiv preprint arXiv:1905.03561 (2019)","DOI":"10.1109\/CVPR.2019.00828"},{"key":"13_CR17","doi-asserted-by":"crossref","unstructured":"Fan, H., et al.: Multiscale vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6824\u20136835 (2021)","DOI":"10.1109\/ICCV48922.2021.00675"},{"issue":"6","key":"13_CR18","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1145\/358669.358692","volume":"24","author":"MA Fischler","year":"1981","unstructured":"Fischler, M.A., Bolles, R.C.: Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun. ACM 24(6), 381\u2013395 (1981)","journal-title":"Commun. ACM"},{"key":"13_CR19","unstructured":"Gordo, A., Almaz\u00e1n, J., Revaud, J., Larlus, D.: End-to-end learning of deep visual representations for image retrieval. CoRR abs\/1610.07940 (2016)"},{"key":"13_CR20","doi-asserted-by":"crossref","unstructured":"He, K., Lu, Y., Sclaroff, S.: Local descriptors optimized for average precision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 596\u2013605 (2018)","DOI":"10.1109\/CVPR.2018.00069"},{"key":"13_CR21","unstructured":"Hinton, G.E.: Connectionist learning procedures. In: Machine Learning, pp. 555\u2013610. Elsevier (1990)"},{"key":"13_CR22","doi-asserted-by":"crossref","unstructured":"J\u00e9gou, H., Douze, M., Schmid, C., P\u00e9rez, P.: Aggregating local descriptors into a compact representation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3304\u20133311 (2010)","DOI":"10.1109\/CVPR.2010.5540039"},{"key":"13_CR23","doi-asserted-by":"crossref","unstructured":"J\u00e9gou, H., Chum, O.: Negative evidences and co-occurrences in image retrieval: the benefit of PCA and whitening, pp. 774\u2013787 (10 2012)","DOI":"10.1007\/978-3-642-33709-3_55"},{"issue":"9","key":"13_CR24","doi-asserted-by":"publisher","first-page":"1704","DOI":"10.1109\/TPAMI.2011.235","volume":"34","author":"H J\u00e9gou","year":"2012","unstructured":"J\u00e9gou, H., Perronnin, F., Douze, M., S\u00e1nchez, J., P\u00e9rez, P., Schmid, C.: Aggregating local image descriptors into compact codes. IEEE Trans. Pattern Anal. Mach. Intell. 34(9), 1704\u20131716 (2012)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"13_CR25","unstructured":"Li, Z., Wang, X., Liu, X., Jiang, J.: BinsFormer: revisiting adaptive bins for monocular depth estimation. arXiv preprint arXiv:2204.00987 (2022)"},{"key":"13_CR26","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin Transformer V2: scaling up capacity and resolution. arXiv preprint arXiv:2111.09883 (2021)","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"13_CR27","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"issue":"2","key":"13_CR28","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"DG Lowe","year":"2004","unstructured":"Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60(2), 91\u2013110 (2004)","journal-title":"Int. J. Comput. Vis."},{"key":"13_CR29","doi-asserted-by":"crossref","unstructured":"Luo, Z., et al.: ContextDesc: local descriptor augmentation with cross-modality context. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2527\u20132536 (2019)","DOI":"10.1109\/CVPR.2019.00263"},{"key":"13_CR30","unstructured":"Mishchuk, A., Mishkin, D., Radenovi\u0107, F., Matas, J.: Working hard to know your neighbor\u2019s margins: local descriptor learning loss. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, NIPS 2017, pp. 4829\u20134840. Curran Associates Inc., Red Hook, NY, USA (2017)"},{"key":"13_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1007\/978-3-030-01240-3_18","volume-title":"Computer Vision \u2013 ECCV 2018","author":"D Mishkin","year":"2018","unstructured":"Mishkin, D., Radenovi\u0107, F., Matas, J.: Repeatability is not enough: learning affine regions via discriminability. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11213, pp. 287\u2013304. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01240-3_18"},{"key":"13_CR32","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1007\/978-3-030-58595-2_16","volume-title":"Computer Vision \u2013 ECCV 2020","author":"T Ng","year":"2020","unstructured":"Ng, T., Balntas, V., Tian, Y., Mikolajczyk, K.: SOLAR: second-order loss and attention for image retrieval. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12370, pp. 253\u2013270. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58595-2_16"},{"key":"13_CR33","doi-asserted-by":"publisher","unstructured":"Nister, D., Stewenius, H.: Scalable recognition with a vocabulary tree. In: 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006, vol. 2, pp. 2161\u20132168 (2006). https:\/\/doi.org\/10.1109\/CVPR.2006.264","DOI":"10.1109\/CVPR.2006.264"},{"key":"13_CR34","doi-asserted-by":"publisher","unstructured":"Noh, H., Araujo, A., Sim, J., Weyand, T., Han, B.: Large-scale image retrieval with attentive deep local features. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 3476\u20133485 (2017). https:\/\/doi.org\/10.1109\/ICCV.2017.374","DOI":"10.1109\/ICCV.2017.374"},{"key":"13_CR35","doi-asserted-by":"crossref","unstructured":"Philbin, J., Chum, O., Isard, M., Sivic, J., Zisserman, A.: Object retrieval with large vocabularies and fast spatial matching. In: 2007 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1\u20138. IEEE (2007)","DOI":"10.1109\/CVPR.2007.383172"},{"key":"13_CR36","doi-asserted-by":"crossref","unstructured":"Philbin, J., Chum, O., Isard, M., Sivic, J., Zisserman, A.: Lost in quantization: improving particular object retrieval in large scale image databases. In: 2008 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1\u20138. IEEE (2008)","DOI":"10.1109\/CVPR.2008.4587635"},{"key":"13_CR37","doi-asserted-by":"crossref","unstructured":"Radenovi\u0107, F., Iscen, A., Tolias, G., Avrithis, Y., Chum, O.: Revisiting Oxford and Paris: large-scale image retrieval benchmarking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5706\u20135715 (2018)","DOI":"10.1109\/CVPR.2018.00598"},{"issue":"7","key":"13_CR38","doi-asserted-by":"publisher","first-page":"1655","DOI":"10.1109\/TPAMI.2018.2846566","volume":"41","author":"F Radenovic","year":"2019","unstructured":"Radenovic, F., Tolias, G., Chum, O.: Fine-tuning CNN image retrieval with no human annotation. IEEE Trans. Pattern Anal. Mach. Intell. 41(7), 1655\u20131668 (2019). https:\/\/doi.org\/10.1109\/TPAMI.2018.2846566","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"13_CR39","unstructured":"Raghu, M., Unterthiner, T., Kornblith, S., Zhang, C., Dosovitskiy, A.: Do vision transformers see like convolutional neural networks? In: Advances in Neural Information Processing Systems 34 (2021)"},{"key":"13_CR40","doi-asserted-by":"crossref","unstructured":"Ranftl, R., Bochkovskiy, A., Koltun, V.: Vision transformers for dense prediction. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 12179\u201312188 (2021)","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"13_CR41","doi-asserted-by":"crossref","unstructured":"Revaud, J., Almaz\u00e1n, J., Rezende, R.S., Souza, C.R.: Learning with average precision: training image retrieval with a listwise loss. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5107\u20135116 (2019)","DOI":"10.1109\/ICCV.2019.00521"},{"key":"13_CR42","unstructured":"Revaud, J., et al.: R2d2: repeatable and reliable detector and descriptor. arXiv preprint arXiv:1906.06195 (2019)"},{"key":"13_CR43","doi-asserted-by":"crossref","unstructured":"Sarlin, P.E., Cadena, C., Siegwart, R., Dymczyk, M.: From coarse to fine: robust hierarchical localization at large scale. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12716\u201312725 (2019)","DOI":"10.1109\/CVPR.2019.01300"},{"key":"13_CR44","doi-asserted-by":"crossref","unstructured":"Simeoni, O., Avrithis, Y., Chum, O.: Local features and visual words emerge in activations. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (June 2019)","DOI":"10.1109\/CVPR.2019.01192"},{"key":"13_CR45","doi-asserted-by":"crossref","unstructured":"Teichmann, M., Araujo, A., Zhu, M., Sim, J.: Detect-to-retrieve: efficient regional aggregation for image search. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5109\u20135118 (2019)","DOI":"10.1109\/CVPR.2019.00525"},{"issue":"3","key":"13_CR46","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1007\/s11263-015-0810-4","volume":"116","author":"G Tolias","year":"2016","unstructured":"Tolias, G., Avrithis, Y., J\u00e9gou, H.: Image search with selective match kernels: aggregation across single and multiple images. Int. J. Comput. Vis. 116(3), 247\u2013261 (2016)","journal-title":"Int. J. Comput. Vis."},{"key":"13_CR47","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"460","DOI":"10.1007\/978-3-030-58452-8_27","volume-title":"Computer Vision \u2013 ECCV 2020","author":"G Tolias","year":"2020","unstructured":"Tolias, G., Jenicek, T., Chum, O.: Learning and aggregating deep local descriptors for instance-level recognition. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 460\u2013477. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_27"},{"key":"13_CR48","unstructured":"Tolias, G., Sicre, R., J\u00e9gou, H.: Particular object retrieval with integral max-pooling of CNN activations (2016)"},{"key":"13_CR49","doi-asserted-by":"crossref","unstructured":"Wang, H., et al.: CosFace: large margin cosine loss for deep face recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5265\u20135274 (2018)","DOI":"10.1109\/CVPR.2018.00552"},{"key":"13_CR50","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: Pyramid vision transformer: a versatile backbone for dense prediction without convolutions. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 568\u2013578 (2021)","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"13_CR51","doi-asserted-by":"publisher","unstructured":"Wu, H., Wang, M., Zhou, W., Li, H.: Learning deep local features with multiple dynamic attentions for large-scale image retrieval. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 11396\u201311405 (2021). https:\/\/doi.org\/10.1109\/ICCV48922.2021.01122","DOI":"10.1109\/ICCV48922.2021.01122"},{"key":"13_CR52","unstructured":"Xie, E., Wang, W., Yu, Z., Anandkumar, A., Alvarez, J.M., Luo, P.: SegFormer: simple and efficient design for semantic segmentation with transformers. In: Advances in Neural Information Processing Systems 34 (2021)"},{"key":"13_CR53","unstructured":"Yan, H., Zhang, C., Wu, M.: Lawin transformer: improving semantic segmentation transformer with multi-scale representations via large window attention. arXiv preprint arXiv:2201.01615 (2022)"},{"key":"13_CR54","doi-asserted-by":"crossref","unstructured":"Yandex, A.B., Lempitsky, V.: Aggregating local deep features for image retrieval. In: 2015 IEEE International Conference on Computer Vision (ICCV), pp. 1269\u20131277 (2015)","DOI":"10.1109\/ICCV.2015.150"},{"key":"13_CR55","doi-asserted-by":"crossref","unstructured":"Yang, M., et al.: DOLG: single-stage image retrieval with deep orthogonal fusion of local and global features. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 11772\u201311781 (October 2021)","DOI":"10.1109\/ICCV48922.2021.01156"},{"key":"13_CR56","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"467","DOI":"10.1007\/978-3-319-46466-4_28","volume-title":"Computer Vision \u2013 ECCV 2016","author":"KM Yi","year":"2016","unstructured":"Yi, K.M., Trulls, E., Lepetit, V., Fua, P.: LIFT: learned invariant feature transform. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9910, pp. 467\u2013483. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46466-4_28"},{"key":"13_CR57","unstructured":"Zhang, H., et al.: DINO: DETR with improved denoising anchor boxes for end-to-end object detection. arXiv preprint arXiv:2203.03605 (2022)"},{"issue":"1","key":"13_CR58","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1007\/s13042-010-0001-0","volume":"1","author":"Y Zhang","year":"2010","unstructured":"Zhang, Y., Jin, R., Zhou, Z.H.: Understanding bag-of-words model: a statistical framework. Int. J. Mach. Learn. Cybern. 1(1), 43\u201352 (2010)","journal-title":"Int. J. Mach. Learn. Cybern."}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-26284-5_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T21:30:51Z","timestamp":1728941451000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-26284-5_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031262838","9783031262845"],"references-count":58,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-26284-5_13","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":"23 February 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Macao","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"4 December 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 December 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.accv2022.org","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 Microsoft","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"836","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":"277","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":"33% - 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":"3.3","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":"2.6","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":"For the ACCV 2022 workshops 25 papers have been accepted from 40 submissions","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)"}}]}}