{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T04:20:18Z","timestamp":1727756418930},"reference-count":63,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2024,4,25]],"date-time":"2024-04-25T00:00:00Z","timestamp":1714003200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,4,25]],"date-time":"2024-04-25T00:00:00Z","timestamp":1714003200000},"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":["Vis Comput"],"published-print":{"date-parts":[[2024,10]]},"DOI":"10.1007\/s00371-024-03389-0","type":"journal-article","created":{"date-parts":[[2024,4,25]],"date-time":"2024-04-25T11:01:37Z","timestamp":1714042897000},"page":"7307-7322","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Using scale-equivariant CNN to enhance scale robustness in feature matching"],"prefix":"10.1007","volume":"40","author":[{"given":"Yun","family":"Liao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peiyu","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuning","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhixuan","family":"Pan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kaijun","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junhui","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qing","family":"Duan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,4,25]]},"reference":[{"doi-asserted-by":"publisher","unstructured":"Lindenberger, P., Sarlin, P.-E., Larsson, V., Pollefeys, M.: Pixel-perfect structure-from-motion with feature metric refinement. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 5967\u20135977 (2021). https:\/\/doi.org\/10.1109\/ICCV48922.2021.00593","key":"3389_CR1","DOI":"10.1109\/ICCV48922.2021.00593"},{"doi-asserted-by":"publisher","unstructured":"Sch\u00f6nberger, J.L., Frahm, J.-M.: Structure-from-motion revisited. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4104\u20134113 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.445","key":"3389_CR2","DOI":"10.1109\/CVPR.2016.445"},{"issue":"21","key":"3389_CR3","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(21), 6264 (2021). https:\/\/doi.org\/10.1364\/ao.424280","journal-title":"Appl. Opt."},{"issue":"3","key":"3389_CR4","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(3), 611\u2013625 (2018). https:\/\/doi.org\/10.1109\/TPAMI.2017.2658577","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3389_CR5","doi-asserted-by":"publisher","DOI":"10.1002\/cav.2088","author":"L Zhou","year":"2022","unstructured":"Zhou, L., Kong, M., Liu, Z., Li, L.: Vision sensor-based SLAM problem for small UAVs in dynamic indoor environments. Comput. Animat. Virtual Worlds (2022). https:\/\/doi.org\/10.1002\/cav.2088","journal-title":"Comput. Animat. Virtual Worlds"},{"doi-asserted-by":"publisher","unstructured":"Li, S., Yuan, L., Sun, J., Quan, L.: Dual-feature warping-based motion model estimation. In: 2015 IEEE International Conference on Computer Vision (ICCV), pp. 4283\u20134291 (2015). https:\/\/doi.org\/10.1109\/ICCV.2015.487","key":"3389_CR6","DOI":"10.1109\/ICCV.2015.487"},{"key":"3389_CR7","doi-asserted-by":"publisher","DOI":"10.1002\/cav.2078","author":"Y Wu","year":"2022","unstructured":"Wu, Y., Wang, C.: Parallel-branch network for 3d human pose and shape estimation in video. Comput. Animat. Virtual Worlds (2022). https:\/\/doi.org\/10.1002\/cav.2078","journal-title":"Comput. Animat. Virtual Worlds"},{"key":"3389_CR8","doi-asserted-by":"publisher","DOI":"10.1002\/cav.2187","author":"L Sun","year":"2023","unstructured":"Sun, L., Tang, T., Qu, Y., Qin, W.: Bidirectional temporal feature for 3d human pose and shape estimation from a video. Comput. Animat. Virtual Worlds (2023). https:\/\/doi.org\/10.1002\/cav.2187","journal-title":"Comput. Animat. Virtual Worlds"},{"doi-asserted-by":"crossref","unstructured":"Sarlin, P., Cadena, C., Siegwart, R., Dymczyk, M.: From coarse to fine: robust hierarchical localization at large scale. CoRR (2018). arXiv:abs\/1812.03506","key":"3389_CR9","DOI":"10.1109\/CVPR.2019.01300"},{"issue":"4","key":"3389_CR10","doi-asserted-by":"publisher","first-page":"1293","DOI":"10.1109\/TPAMI.2019.2952114","volume":"43","author":"H Taira","year":"2021","unstructured":"Taira, H., Okutomi, M., Sattler, T., Cimpoi, M., Pollefeys, M., Sivic, J., Pajdla, T., Torii, A.: InLoc: indoor visual localization with dense matching and view synthesis. IEEE Trans. Pattern Anal. Mach. Intell. 43(4), 1293\u20131307 (2021). https:\/\/doi.org\/10.1109\/TPAMI.2019.2952114","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"4","key":"3389_CR11","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. Automat. Lett. 6(4), 8726\u20138733 (2021). https:\/\/doi.org\/10.1109\/lra.2021.3111760","journal-title":"IEEE Robot. Automat. Lett."},{"issue":"6","key":"3389_CR12","doi-asserted-by":"publisher","first-page":"2091","DOI":"10.1007\/s00371-021-02270-8","volume":"38","author":"N Li","year":"2022","unstructured":"Li, N., Ai, H.: EfiLoc: large-scale visual indoor localization with efficient correlation between sparse features and 3D points. Visual Comput. 38(6), 2091\u20132106 (2022). https:\/\/doi.org\/10.1007\/s00371-021-02270-8","journal-title":"Visual Comput."},{"issue":"2","key":"3389_CR13","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). https:\/\/doi.org\/10.1023\/B:VISI.0000029664.99615.94","journal-title":"Int. J. Comput. Vis."},{"doi-asserted-by":"publisher","unstructured":"Rublee, E., Rabaud, V., Konolige, K., Bradski, G.: Orb: an efficient alternative to sift or surf. In: 2011 International Conference on Computer Vision, pp. 2564\u20132571 (2011). https:\/\/doi.org\/10.1109\/ICCV.2011.6126544","key":"3389_CR14","DOI":"10.1109\/ICCV.2011.6126544"},{"unstructured":"Mishchuk, A., Mishkin, D., Radenovic, F., Matas, J.: Working hard to know your neighbor\u2019s margins: local descriptor learning loss. CoRR (2017). arXiv:1705.10872","key":"3389_CR15"},{"doi-asserted-by":"publisher","unstructured":"Tian, Y., Yu, X., Fan, B., Wu, F., Heijnen, H., Balntas, V.: SOSNet: second order similarity regularization for local descriptor learning. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11008\u201311017 (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.01127","key":"3389_CR16","DOI":"10.1109\/CVPR.2019.01127"},{"unstructured":"Tian, Y., Laguna, A.B., Ng, T., Balntas, V., Mikolajczyk, K.: HyNet: Local descriptor with hybrid similarity measure and triplet loss. CoRR (2020). arXiv:2006.10202","key":"3389_CR17"},{"doi-asserted-by":"crossref","unstructured":"Tian, Y., Balntas, V., Ng, T., Laguna, A.B., Demiris, Y., Mikolajczyk, K.: D2D: keypoint extraction with describe to detect approach. CoRR (2020). arXiv:2005.13605","key":"3389_CR18","DOI":"10.1007\/978-3-030-69535-4_14"},{"doi-asserted-by":"publisher","unstructured":"Dusmanu, M., Rocco, I., Pajdla, T., Pollefeys, M., Sivic, J., Torii, A., Sattler, T.: D2-net: a trainable CNN for joint description and detection of local features. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8084\u20138093 (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.00828","key":"3389_CR19","DOI":"10.1109\/CVPR.2019.00828"},{"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","key":"3389_CR20","DOI":"10.1109\/ICCV.2017.374"},{"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","key":"3389_CR21","DOI":"10.1109\/CVPRW.2018.00060"},{"unstructured":"Revaud, J., Weinzaepfel, P., Souza, C.R., Pion, N., Csurka, G., Cabon, Y., Humenberger, M.: R2D2: repeatable and reliable detector and descriptor. CoRR (2019). arXiv:1906.06195","key":"3389_CR22"},{"unstructured":"Tyszkiewicz, M.J., Fua, P., Trulls, E.: DISK: learning local features with policy gradient. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M., Lin, H. (eds.) Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6\u201312, 2020, Virtual (2020). https:\/\/proceedings.neurips.cc\/paper\/2020\/hash\/a42a596fc71e17828440030074d15e74-Abstract.html","key":"3389_CR23"},{"doi-asserted-by":"crossref","unstructured":"Li, K., Wang, L., Liu, L., Ran, Q., Xu, K., Guo, Y.: Decoupling makes weakly supervised local feature better. CoRR (2022). arXiv:2201.02861","key":"3389_CR24","DOI":"10.1109\/CVPR52688.2022.01538"},{"issue":"2","key":"3389_CR25","doi-asserted-by":"publisher","first-page":"2388","DOI":"10.1609\/aaai.v36i2.20138","volume":"36","author":"C Wang","year":"2022","unstructured":"Wang, C., Xu, R., Zhang, Y., Xu, S., Meng, W., Fan, B., Zhang, X.: MTLDesc: looking wider to describe better. Proc. AAAI Conf. Artif. Intell. 36(2), 2388\u20132396 (2022). https:\/\/doi.org\/10.1609\/aaai.v36i2.20138","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"doi-asserted-by":"publisher","unstructured":"Sun, J., Shen, Z., Wang, Y., Bao, H., Zhou, X.: Loftr: detector-free local feature matching with transformers. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2021, Virtual, June 19\u201325, 2021, pp. 8922\u20138931. https:\/\/doi.org\/10.1109\/CVPR46437.2021.00881","key":"3389_CR26","DOI":"10.1109\/CVPR46437.2021.00881"},{"doi-asserted-by":"publisher","unstructured":"Wang, Q., Zhang, J., Yang, K., Peng, K., Stiefelhagen, R.: Matchformer: interleaving attention in transformers for feature matching. In: Wang, L., Gall, J., Chin, T., Sato, I., Chellappa, R. (eds.) Computer Vision\u2014ACCV 2022\u201416th Asian Conference on Computer Vision, Macao, China, December 4-8, 2022, Proceedings, Part III. Lecture Notes in Computer Science, vol. 13843, pp. 256\u2013273. https:\/\/doi.org\/10.1007\/978-3-031-26313-2_16","key":"3389_CR27","DOI":"10.1007\/978-3-031-26313-2_16"},{"doi-asserted-by":"crossref","unstructured":"Wang, Q., Zhou, X., Hariharan, B., Snavely, N.: Learning feature descriptors using camera pose supervision. CoRR (2020). arXiv:2004.13324","key":"3389_CR28","DOI":"10.1007\/978-3-030-58452-8_44"},{"doi-asserted-by":"publisher","unstructured":"Zhou, Q., Sattler, T., Leal-Taix\u00e9, L.: Patch2pix: Epipolar-guided pixel-level correspondences. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2021, Virtual, June 19\u201325, pp. 4669\u20134678, 2021. https:\/\/doi.org\/10.1109\/CVPR46437.2021.00464","key":"3389_CR29","DOI":"10.1109\/CVPR46437.2021.00464"},{"doi-asserted-by":"publisher","unstructured":"B\u00f6kman, G., Kahl, F.: A case for using rotation invariant features in state of the art feature matchers. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2022, New Orleans, LA, USA, June 19\u201320, pp. 5106\u20135115, 2022. https:\/\/doi.org\/10.1109\/CVPRW56347.2022.00559","key":"3389_CR30","DOI":"10.1109\/CVPRW56347.2022.00559"},{"key":"3389_CR31","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-023-02851-9","author":"Z Shen","year":"2023","unstructured":"Shen, Z., Kong, B., Dong, X.: MAIM: a mixer MLP architecture for image matching. Visual Comput. (2023). https:\/\/doi.org\/10.1007\/s00371-023-02851-9","journal-title":"Visual Comput."},{"unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: Bengio, Y., LeCun, Y. (eds.) 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7\u20139, 2015, Conference Track Proceedings (2015). arXiv:1409.1556","key":"3389_CR32"},{"doi-asserted-by":"publisher","unstructured":"Jiang, W., Trulls, E., Hosang, J., Tagliasacchi, A., Yi, K.M.: COTR: correspondence transformer for matching across images. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 6187\u20136197 (2021). https:\/\/doi.org\/10.1109\/ICCV48922.2021.00615","key":"3389_CR33","DOI":"10.1109\/ICCV48922.2021.00615"},{"doi-asserted-by":"publisher","unstructured":"Chen, H., Luo, Z., Zhou, L., Tian, Y., Zhen, M., Fang, T., McKinnon, D., Tsin, Y., Quan, L.: ASpanFormer: detector-free image matching with adaptive span transformer. In: Computer Vision - ECCV 2022 - 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part XXXII. Lecture Notes in Computer Science, vol. 13692, pp. 20\u201336. https:\/\/doi.org\/10.1007\/978-3-031-19824-3_2","key":"3389_CR34","DOI":"10.1007\/978-3-031-19824-3_2"},{"unstructured":"Tang, S., Zhang, J., Zhu, S., Tan, P.: Quadtree attention for vision transformers. In: International Conference on Learning Representations (2022). https:\/\/openreview.net\/forum?id=fR-EnKWL_Zb","key":"3389_CR35"},{"key":"3389_CR36","doi-asserted-by":"publisher","first-page":"2226","DOI":"10.1109\/TMM.2022.3144890","volume":"25","author":"N Jiang","year":"2023","unstructured":"Jiang, N., Sheng, B., Li, P., Lee, T.-Y.: PhotoHelper: portrait photographing guidance via deep feature retrieval and fusion. IEEE Trans. Multimedia 25, 2226\u20132238 (2023). https:\/\/doi.org\/10.1109\/TMM.2022.3144890","journal-title":"IEEE Trans. Multimedia"},{"doi-asserted-by":"publisher","unstructured":"Sarlin, P., DeTone, D., Malisiewicz, T., Rabinovich, A.: Superglue: Learning feature matching with graph neural networks. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020, Seattle, WA, USA, June 13\u201319, 2020, pp. 4937\u20134946. https:\/\/doi.org\/10.1109\/CVPR42600.2020.00499","key":"3389_CR37","DOI":"10.1109\/CVPR42600.2020.00499"},{"issue":"8","key":"3389_CR38","doi-asserted-by":"publisher","first-page":"4499","DOI":"10.1109\/TNNLS.2021.3116209","volume":"34","author":"Z Xie","year":"2023","unstructured":"Xie, Z., Zhang, W., Sheng, B., Li, P., Chen, C.L.P.: BaGFN: broad attentive graph fusion network for high-order feature interactions. IEEE Trans. Neural Netw. Learn. Syst. 34(8), 4499\u20134513 (2023). https:\/\/doi.org\/10.1109\/TNNLS.2021.3116209","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L.u., Polosukhin, I.: Attention is all you need. In: Guyon, I., Luxburg, U.V., Bengio, S., Wallach, H., Fergus, R., Vishwanathan, S., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 30 (2017). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2017\/file\/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf","key":"3389_CR39"},{"doi-asserted-by":"publisher","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., Guo, B.: Swin transformer: Hierarchical vision transformer using shifted windows. In: 2021 IEEE\/CVF International Conference on Computer Vision, ICCV 2021, Montreal, QC, Canada, October 10-17, 2021, pp. 9992\u201310002. IEEE(2021). https:\/\/doi.org\/10.1109\/ICCV48922.2021.00986","key":"3389_CR40","DOI":"10.1109\/ICCV48922.2021.00986"},{"doi-asserted-by":"publisher","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. (eds.) Computer Vision\u2014ECCV 2020\u201416th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part I. Lecture Notes in Computer Science, vol. 12346, pp. 213\u2013229. https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13","key":"3389_CR41","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"3389_CR42","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-023-02860-8","author":"L Ai","year":"2023","unstructured":"Ai, L., Xie, Z., Yao, R., Yang, M.: MVTr: multi-feature voxel transformer for 3d object detection. Visual Comput. (2023). https:\/\/doi.org\/10.1007\/s00371-023-02860-8","journal-title":"Visual Comput."},{"doi-asserted-by":"publisher","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: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 4086\u20134095 (2021). https:\/\/doi.org\/10.1109\/ICCV48922.2021.00407","key":"3389_CR43","DOI":"10.1109\/ICCV48922.2021.00407"},{"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: Ranzato, M., Beygelzimer, A., Dauphin, Y., Liang, P.S., Vaughan, J.W. (eds.) Advances in Neural Information Processing Systems, vol. 34, pp. 12077\u201312090 (2021). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2021\/file\/64f1f27bf1b4ec22924fd0acb550c235-Paper.pdf","key":"3389_CR44"},{"key":"3389_CR45","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-022-02656-2","author":"L Chen","year":"2022","unstructured":"Chen, L., Wan, L.: CTUNet: automatic pancreas segmentation using a channel-wise transformer and 3D U-Net. Visual Comput. (2022). https:\/\/doi.org\/10.1007\/s00371-022-02656-2","journal-title":"Visual Comput."},{"unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., Houlsby, N.: An image is worth 16x16 words: transformers for image recognition at scale. In: 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3\u20137, 2021. https:\/\/openreview.net\/forum?id=YicbFdNTTy","key":"3389_CR46"},{"doi-asserted-by":"publisher","unstructured":"Chen, Z., Zhu, Y., Zhao, C., Hu, G., Zeng, W., Wang, J., Tang, M.: DPT: deformable patch-based transformer for visual recognition. In: Shen, H.T., Zhuang, Y., Smith, J.R., Yang, Y., C\u00e9sar, P., Metze, F., Prabhakaran, B. (eds.) MM\u201921: ACM Multimedia Conference, Virtual Event, China, October 20\u201324, 2021, pp. 2899\u20132907 (2021). https:\/\/doi.org\/10.1145\/3474085.3475467","key":"3389_CR47","DOI":"10.1145\/3474085.3475467"},{"doi-asserted-by":"publisher","unstructured":"Lin, X., Sun, S., Huang, W., Sheng, B., Li, P., Feng, D.D.: Eapt: Efficient attention pyramid transformer for image processing. IEEE Trans. Multimedia 25, 50\u201361 (2023) https:\/\/doi.org\/10.1109\/TMM.2021.3120873","key":"3389_CR48","DOI":"10.1109\/TMM.2021.3120873"},{"unstructured":"Xu, Y., Xiao, T., Zhang, J., Yang, K., Zhang, Z.: Scale-invariant convolutional neural networks. CoRR (2014). arXiv:1411.6369","key":"3389_CR49"},{"unstructured":"Kanazawa, A., Sharma, A., Jacobs, D.W.: Locally scale-invariant convolutional neural networks. CoRR (2014). arXiv:1412.5104","key":"3389_CR50"},{"unstructured":"Marcos, D., Kellenberger, B., Lobry, S., Tuia, D.: Scale equivariance in CNNs with vector fields. CoRR (2018) arXiv:1807.11783","key":"3389_CR51"},{"unstructured":"Worrall, D.E., Welling, M.: Deep scale-spaces: equivariance over scale. In: Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8-14, 2019, Vancouver, BC, Canada, pp. 7364\u20137376 (2019). https:\/\/proceedings.neurips.cc\/paper\/2019\/hash\/f04cd7399b2b0128970efb6d20b5c551-Abstract.html","key":"3389_CR52"},{"unstructured":"Ghosh, R., Gupta, A.K.: Scale steerable filters for locally scale-invariant convolutional neural networks. CoRR (2019). arXiv:1906.03861","key":"3389_CR53"},{"unstructured":"Sosnovik, I., Szmaja, M., Smeulders, A.W.M.: Scale-equivariant steerable networks. In: 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26+-30, 2020. https:\/\/openreview.net\/forum?id=HJgpugrKPS","key":"3389_CR54"},{"unstructured":"Kondor, R., Trivedi, S.: On the generalization of equivariance and convolution in neural networks to the action of compact groups. In: Dy, J.G., Krause, A. (eds.) Proceedings of the 35th International Conference on Machine Learning, ICML 2018, Stockholmsm\u00e4ssan, Stockholm, Sweden, July 10-15, 2018. Proceedings of Machine Learning Research, vol. 80, pp. 2752\u20132760. http:\/\/proceedings.mlr.press\/v80\/kondor18a.html","key":"3389_CR55"},{"doi-asserted-by":"publisher","unstructured":"Li, Z., Snavely, N.: Megadepth: learning single-view depth prediction from internet photos. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2041\u20132050 (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00218","key":"3389_CR56","DOI":"10.1109\/CVPR.2018.00218"},{"unstructured":"Li, X., Han, K., Li, S., Prisacariu, V.: Dual-resolution correspondence networks. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M., Lin, H. (eds.) Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6\u201312, 2020, Virtual (2020). https:\/\/proceedings.neurips.cc\/paper\/2020\/hash\/c91591a8d461c2869b9f535ded3e213e-Abstract.html","key":"3389_CR57"},{"doi-asserted-by":"publisher","unstructured":"Chen, Y., Huang, D., Xu, S., Liu, J., Liu, Y.: Guide local feature matching by overlap estimation. In: Thirty-Sixth AAAI Conference on Artificial Intelligence, AAAI 2022, Thirty-Fourth Conference on Innovative Applications of Artificial Intelligence, IAAI 2022, The Twelveth Symposium on Educational Advances in Artificial Intelligence, EAAI 2022 Virtual Event, February 22\u2013March 1, 2022, pp. 365\u2013373. https:\/\/doi.org\/10.1609\/aaai.v36i1.19913","key":"3389_CR58","DOI":"10.1609\/aaai.v36i1.19913"},{"doi-asserted-by":"publisher","unstructured":"Luo, Z., Zhou, L., Bai, X., Chen, H., Zhang, J., Yao, Y., Li, S., Fang, T., Quan, L.: Aslfeat: Learning local features of accurate shape and localization. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020, Seattle, WA, USA, June 13\u201319, 2020, pp. 6588\u20136597. https:\/\/doi.org\/10.1109\/CVPR42600.2020.00662","key":"3389_CR59","DOI":"10.1109\/CVPR42600.2020.00662"},{"issue":"2","key":"3389_CR60","doi-asserted-by":"publisher","first-page":"2447","DOI":"10.1609\/aaai.v37i2.25341","volume":"37","author":"K Truong Giang","year":"2023","unstructured":"Truong Giang, K., Song, S., Jo, S.: TopicFM: robust and interpretable topic-assisted feature matching. Proc. AAAI Conf. Artif. Intell. 37(2), 2447\u20132455 (2023). https:\/\/doi.org\/10.1609\/aaai.v37i2.25341","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"issue":"11","key":"3389_CR61","doi-asserted-by":"publisher","first-page":"2825","DOI":"10.1109\/TPAMI.2019.2915233","volume":"42","author":"V Balntas","year":"2020","unstructured":"Balntas, V., Lenc, K., Vedaldi, A., Tuytelaars, T., Matas, J., Mikolajczyk, K.: $$\\mathbb{H} $$h-patches: a benchmark and evaluation of handcrafted and learned local descriptors. IEEE Trans. Pattern Anal. Mach. Intell. 42(11), 2825\u20132841 (2020). https:\/\/doi.org\/10.1109\/TPAMI.2019.2915233","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"doi-asserted-by":"crossref","unstructured":"Sarlin, P.-E., Cadena, C., Siegwart, R., Dymczyk, M.: From coarse to fine: robust hierarchical localization at large scale (2019)","key":"3389_CR62","DOI":"10.1109\/CVPR.2019.01300"},{"doi-asserted-by":"crossref","unstructured":"Taira, H., Okutomi, M., Sattler, T., Cimpoi, M., Pollefeys, M., Sivic, J., Pajdla, T., Torii, A.: InLoc: indoor visual localization with dense matching and view synthesis (2018)","key":"3389_CR63","DOI":"10.1109\/CVPR.2018.00752"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-024-03389-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-024-03389-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-024-03389-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T10:12:47Z","timestamp":1727691167000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-024-03389-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,25]]},"references-count":63,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2024,10]]}},"alternative-id":["3389"],"URL":"https:\/\/doi.org\/10.1007\/s00371-024-03389-0","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"type":"print","value":"0178-2789"},{"type":"electronic","value":"1432-2315"}],"subject":[],"published":{"date-parts":[[2024,4,25]]},"assertion":[{"value":"24 March 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 April 2024","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflicts of interests or conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}