{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T21:50:41Z","timestamp":1784238641154,"version":"3.55.0"},"publisher-location":"Cham","reference-count":54,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031263125","type":"print"},{"value":"9783031263132","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\/978-3-031-26313-2_16","type":"book-chapter","created":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T08:02:32Z","timestamp":1677657752000},"page":"256-273","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":159,"title":["MatchFormer: Interleaving Attention in\u00a0Transformers for\u00a0Feature Matching"],"prefix":"10.1007","author":[{"given":"Qing","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaming","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kailun","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kunyu","family":"Peng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rainer","family":"Stiefelhagen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,3,2]]},"reference":[{"key":"16_CR1","doi-asserted-by":"crossref","unstructured":"Balntas, V., Lenc, K., Vedaldi, A., Mikolajczyk, K.: HPatches: a benchmark and evaluation of handcrafted and learned local descriptors. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.410"},{"key":"16_CR2","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: CVPR (2017)","DOI":"10.1109\/CVPR.2017.302"},{"key":"16_CR3","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":"16_CR4","doi-asserted-by":"publisher","first-page":"6264","DOI":"10.1364\/AO.424280","volume":"60","author":"H Chen","year":"2021","unstructured":"Chen, H., Hu, W., Yang, K., Bai, J., Wang, K.: Panoramic annular SLAM with loop closure and global optimization. Appl. Opt. 60, 6264\u20136274 (2021)","journal-title":"Appl. Opt."},{"key":"16_CR5","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"LC Chen","year":"2018","unstructured":"Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Trans. Pattern Anal. Mach. Intell. 40, 834\u2013848 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"16_CR6","doi-asserted-by":"crossref","unstructured":"Cheng, R., Wang, K., Lin, L., Yang, K.: Visual localization of key positions for visually impaired people. In: ICPR (2018)","DOI":"10.1109\/ICPR.2018.8545141"},{"key":"16_CR7","doi-asserted-by":"crossref","unstructured":"Dai, A., Chang, A.X., Savva, M., Halber, M., Funkhouser, T., Nie\u00dfner, M.: ScanNet: richly-annotated 3D reconstructions of indoor scenes. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.261"},{"key":"16_CR8","doi-asserted-by":"crossref","unstructured":"DeTone, D., Malisiewicz, T., Rabinovich, A.: SuperPoint: self-supervised interest point detection and description. In: CVPRW (2018)","DOI":"10.1109\/CVPRW.2018.00060"},{"key":"16_CR9","unstructured":"Dosovitskiy, A., et al.: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale. In: ICLR (2021)"},{"key":"16_CR10","doi-asserted-by":"crossref","unstructured":"Dusmanu, M., et al.: D2-net: a trainable CNN for joint detection and description of local features. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00828"},{"key":"16_CR11","doi-asserted-by":"publisher","first-page":"611","DOI":"10.1109\/TPAMI.2017.2658577","volume":"40","author":"J Engel","year":"2018","unstructured":"Engel, J., Koltun, V., Cremers, D.: Direct sparse odometry. IEEE Trans. Pattern Anal. Mach. Intell. 40, 611\u2013625 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"16_CR12","doi-asserted-by":"crossref","unstructured":"Esser, P., Rombach, R., Ommer, B.: Taming transformers for high-resolution image synthesis. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"16_CR13","doi-asserted-by":"crossref","unstructured":"Fang, Y., Wang, K., Cheng, R., Yang, K.: CFVL: a coarse-to-fine vehicle localizer with omnidirectional perception across severe appearance variations. In: IV (2020)","DOI":"10.1109\/IV47402.2020.9304612"},{"key":"16_CR14","doi-asserted-by":"crossref","unstructured":"Jiang, W., Trulls, E., Hosang, J., Tagliasacchi, A., Yi, K.M.: COTR: correspondence transformer for matching across images. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00615"},{"key":"16_CR15","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2015)"},{"key":"16_CR16","doi-asserted-by":"crossref","unstructured":"Li, S., Yuan, L., Sun, J., Quan, L.: Dual-feature warping-based motion model estimation. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.487"},{"key":"16_CR17","unstructured":"Li, X., Han, K., Li, S., Prisacariu, V.: Dual-resolution correspondence networks. In: NeurIPS (2020)"},{"key":"16_CR18","doi-asserted-by":"crossref","unstructured":"Li, Z., Snavely, N.: MegaDepth: learning single-view depth prediction from internet photos. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00218"},{"key":"16_CR19","doi-asserted-by":"crossref","unstructured":"Lindenberger, P., Sarlin, P.E., Larsson, V., Pollefeys, M.: Pixel-perfect structure-from-motion with featuremetric refinement. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00593"},{"key":"16_CR20","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":"16_CR21","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, 91\u2013110 (2004)","journal-title":"Int. J. Comput. Vis."},{"key":"16_CR22","doi-asserted-by":"crossref","unstructured":"Luo, Z., et al.: ContextDesc: local descriptor augmentation with cross-modality context. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00263"},{"key":"16_CR23","doi-asserted-by":"crossref","unstructured":"Luo, Z., et al.: ASLFeat: learning local features of accurate shape and localization. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00662"},{"key":"16_CR24","doi-asserted-by":"crossref","unstructured":"Ma, W.C., Yang, A.J., Wang, S., Urtasun, R., Torralba, A.: Virtual correspondence: humans as a cue for extreme-view geometry. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01546"},{"key":"16_CR25","unstructured":"Revaud, J., De Souza, C., Humenberger, M., Weinzaepfel, P.: R2D2: reliable and repeatable detector and descriptor. In: NeurIPS (2019)"},{"key":"16_CR26","doi-asserted-by":"crossref","unstructured":"Revaud, J., Leroy, V., Weinzaepfel, P., Chidlovskii, B.: PUMP: pyramidal and uniqueness matching priors for unsupervised learning of local descriptors. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00390"},{"key":"16_CR27","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":"16_CR28","doi-asserted-by":"crossref","unstructured":"Rublee, E., Rabaud, V., Konolige, K., Bradski, G.: ORB: an efficient alternative to SIFT or SURF. In: ICCV (2011)","DOI":"10.1109\/ICCV.2011.6126544"},{"key":"16_CR29","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: CVPR (2019)","DOI":"10.1109\/CVPR.2019.01300"},{"key":"16_CR30","doi-asserted-by":"crossref","unstructured":"Sarlin, P.E., DeTone, D., Malisiewicz, T., Rabinovich, A.: SuperGlue: learning feature matching with graph neural networks. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00499"},{"key":"16_CR31","doi-asserted-by":"crossref","unstructured":"Schonberger, J.L., Frahm, J.M.: Structure-from-motion revisited. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.445"},{"key":"16_CR32","unstructured":"Shen, Z., Zhang, M., Zhao, H., Yi, S., Li, H.: Efficient attention: attention with linear complexities. In: WACV (2021)"},{"key":"16_CR33","doi-asserted-by":"crossref","unstructured":"Shi, Y., Cai, J.X., Shavit, Y., Mu, T.J., Feng, W., Zhang, K.: ClusterGNN: cluster-based coarse-to-fine graph neural network for efficient feature matching. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01219"},{"key":"16_CR34","doi-asserted-by":"crossref","unstructured":"Sun, J., Shen, Z., Wang, Y., Bao, H., Zhou, X.: LoFTR: detector-free local feature matching with transformers. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00881"},{"key":"16_CR35","doi-asserted-by":"crossref","unstructured":"Taira, H., et al.: InLoc: indoor visual localization with dense matching and view synthesis. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00752"},{"key":"16_CR36","doi-asserted-by":"crossref","unstructured":"Tang, S., Tang, C., Huang, R., Zhu, S., Tan, P.: Learning camera localization via dense scene matching. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00187"},{"key":"16_CR37","unstructured":"Tang, S., Zhang, J., Zhu, S., Tan, P.: Quadtree attention for vision transformers. In: ICLR (2022)"},{"key":"16_CR38","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., J\u00e9gou, H.: Training data-efficient image transformers & distillation through attention. In: ICML (2021)"},{"key":"16_CR39","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS (2017)"},{"key":"16_CR40","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"757","DOI":"10.1007\/978-3-030-58452-8_44","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Q Wang","year":"2020","unstructured":"Wang, Q., Zhou, X., Hariharan, B., Snavely, N.: Learning feature descriptors using camera pose supervision. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 757\u2013774. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_44"},{"key":"16_CR41","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: Pyramid vision transformer: a versatile backbone for dense prediction without convolutions. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"16_CR42","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: NeurIPS (2021)"},{"key":"16_CR43","doi-asserted-by":"crossref","unstructured":"Yi, K.M., Trulls, E., Ono, Y., Lepetit, V., Salzmann, M., Fua, P.: Learning to find good correspondences. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00282"},{"key":"16_CR44","doi-asserted-by":"publisher","first-page":"8726","DOI":"10.1109\/LRA.2021.3111760","volume":"6","author":"S Yoon","year":"2021","unstructured":"Yoon, S., Kim, A.: Line as a visual sentence: context-aware line descriptor for visual localization. IEEE Robot. Autom. Lett. 6, 8726\u20138733 (2021)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"16_CR45","unstructured":"Yu, F., Koltun, V.: Multi-scale context aggregation by dilated convolutions. In: ICLR (2016)"},{"key":"16_CR46","doi-asserted-by":"crossref","unstructured":"Yuan, L., et al.: Tokens-to-token ViT: training vision transformers from scratch on ImageNet. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"16_CR47","doi-asserted-by":"crossref","unstructured":"Zhang, J., et al.: Learning two-view correspondences and geometry using order-aware network. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00594"},{"key":"16_CR48","doi-asserted-by":"crossref","unstructured":"Zhang, J., Yang, K., Constantinescu, A., Peng, K., M\u00fcller, K., Stiefelhagen, R.: Trans4Trans: efficient transformer for transparent object segmentation to help visually impaired people navigate in the real world. In: ICCVW (2021)","DOI":"10.1109\/ICCVW54120.2021.00202"},{"key":"16_CR49","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Jiang, Y., Jiang, J., Wang, X., Luo, P., Gu, J.: STAR: a structure-aware lightweight transformer for real-time image enhancement. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00407"},{"key":"16_CR50","doi-asserted-by":"crossref","unstructured":"Zheng, S., et al.: Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"16_CR51","doi-asserted-by":"publisher","first-page":"105512","DOI":"10.1016\/j.knosys.2020.105512","volume":"193","author":"G Zhong","year":"2020","unstructured":"Zhong, G., Pun, C.M.: Subspace clustering by simultaneously feature selection and similarity learning. Knowl. Based Syst. 193, 105512 (2020)","journal-title":"Knowl. Based Syst."},{"key":"16_CR52","doi-asserted-by":"crossref","unstructured":"Zhou, Q., Sattler, T., Leal-Taixe, L.: Patch2Pix: epipolar-guided pixel-level correspondences. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00464"},{"key":"16_CR53","first-page":"539","volume":"4","author":"Z Zhou","year":"2020","unstructured":"Zhou, Z., Wu, Q.M.J., Wan, S., Sun, W., Sun, X.: Integrating SIFT and CNN feature matching for partial-duplicate image detection. IEEE Trans. Emerg. Topics Comput. Intell. 4, 539\u2013604 (2020)","journal-title":"IEEE Trans. Emerg. Topics Comput. Intell."},{"key":"16_CR54","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable DETR: deformable transformers for end-to-end object detection. In: ICLR (2021)"}],"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\/978-3-031-26313-2_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T08:09:08Z","timestamp":1677658148000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-26313-2_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031263125","9783031263132"],"references-count":54,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-26313-2_16","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":"2 March 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)"}}]}}