{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T20:08:17Z","timestamp":1778789297628,"version":"3.51.4"},"publisher-location":"Cham","reference-count":67,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726835","type":"print"},{"value":"9783031726842","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-72684-2_18","type":"book-chapter","created":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T19:02:45Z","timestamp":1730574165000},"page":"306-325","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":27,"title":["Local All-Pair Correspondence for\u00a0Point Tracking"],"prefix":"10.1007","author":[{"given":"Seokju","family":"Cho","sequence":"first","affiliation":[]},{"given":"Jiahui","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Jisu","family":"Nam","sequence":"additional","affiliation":[]},{"given":"Honggyu","family":"An","sequence":"additional","affiliation":[]},{"given":"Seungryong","family":"Kim","sequence":"additional","affiliation":[]},{"given":"Joon-Young","family":"Lee","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,3]]},"reference":[{"key":"18_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"404","DOI":"10.1007\/11744023_32","volume-title":"Computer Vision \u2013 ECCV 2006","author":"H Bay","year":"2006","unstructured":"Bay, H., Tuytelaars, T., Van Gool, L.: SURF: speeded up robust features. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3951, pp. 404\u2013417. Springer, Heidelberg (2006). https:\/\/doi.org\/10.1007\/11744023_32"},{"key":"18_CR2","unstructured":"Bian, W., Huang, Z., Shi, X., Dong, Y., Li, Y., Li, H.: Context-tap: tracking any point demands spatial context features. arXiv preprint arXiv:2306.02000 (2023)"},{"key":"18_CR3","unstructured":"Bradbury, J., et al.: JAX: composable transformations of Python+NumPy programs (2018). http:\/\/github.com\/google\/jax"},{"key":"18_CR4","unstructured":"Chen, L.C., Papandreou, G., Schroff, F., Adam, H.: Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587 (2017)"},{"key":"18_CR5","doi-asserted-by":"publisher","first-page":"640","DOI":"10.1007\/978-3-031-19815-1_37","volume-title":"European Conference on Computer Vision 2022","author":"HK Cheng","year":"2022","unstructured":"Cheng, H.K., Schwing, A.G.: XMem: long-term video object segmentation with an Atkinson-Shiffrin memory model. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13688, pp. 640\u2013658. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19815-1_37"},{"key":"18_CR6","unstructured":"Cho, S., Hong, S., Jeon, S., Lee, Y., Sohn, K., Kim, S.: CATs: cost aggregation transformers for visual correspondence. In: Advances in Neural Information Processing Systems, vol. 34, pp. 9011\u20139023 (2021)"},{"issue":"6","key":"18_CR7","doi-asserted-by":"publisher","first-page":"7174","DOI":"10.1109\/TPAMI.2022.3218727","volume":"45","author":"S Cho","year":"2022","unstructured":"Cho, S., Hong, S., Kim, S.: CATs++: boosting cost aggregation with convolutions and transformers. IEEE Trans. Pattern Anal. Mach. Intell. 45(6), 7174\u20137194 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"18_CR8","doi-asserted-by":"crossref","unstructured":"Cho, S., Huang, J., Kim, S., Lee, J.Y.: FlowTrack: revisiting optical flow for long-range dense tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19268\u201319277 (2024)","DOI":"10.1109\/CVPR52733.2024.01823"},{"key":"18_CR9","doi-asserted-by":"crossref","unstructured":"Dai, J., et al.: Deformable convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 764\u2013773 (2017)","DOI":"10.1109\/ICCV.2017.89"},{"key":"18_CR10","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":"18_CR11","unstructured":"Doersch, C., et al.: TAP-Vid: a benchmark for tracking any point in a video. In: Advances in Neural Information Processing Systems, vol. 35, pp. 13610\u201313626 (2022)"},{"key":"18_CR12","doi-asserted-by":"crossref","unstructured":"Doersch, C., et al.: TAPIR: tracking any point with per-frame initialization and temporal refinement. arXiv preprint arXiv:2306.08637 (2023)","DOI":"10.1109\/ICCV51070.2023.00923"},{"key":"18_CR13","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":"18_CR14","unstructured":"Greff, K., et al.: Kubric: a scalable dataset generator. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3749\u20133761 (2022)"},{"key":"18_CR15","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1007\/978-3-031-20047-2_4","volume-title":"European Conference on Computer Vision 2022","author":"AW Harley","year":"2022","unstructured":"Harley, A.W., Fang, Z., Fragkiadaki, K.: Particle video revisited: tracking through occlusions using point trajectories. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13682, pp. 59\u201375. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20047-2_4"},{"key":"18_CR16","volume-title":"Multiple View Geometry in Computer Vision","author":"R Hartley","year":"2003","unstructured":"Hartley, R., Zisserman, A.: Multiple View Geometry in Computer Vision. Cambridge University Press, Cambridge (2003)"},{"key":"18_CR17","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":"18_CR18","unstructured":"Hong, S., Cho, S., Kim, S., Lin, S.: Unifying feature and cost aggregation with transformers for semantic and visual correspondence. In: The Twelfth International Conference on Learning Representations (2024)"},{"key":"18_CR19","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1007\/978-3-031-19818-2_7","volume-title":"European Conference on Computer Vision 2022","author":"S Hong","year":"2022","unstructured":"Hong, S., Cho, S., Nam, J., Lin, S., Kim, S.: Cost aggregation with 4D convolutional swin transformer for few-shot segmentation. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13689, pp. 108\u2013126. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19818-2_7"},{"key":"18_CR20","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International Conference on Machine Learning, pp. 448\u2013456. PMLR (2015)"},{"issue":"1\u20133","key":"18_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1561\/0600000079","volume":"12","author":"J Janai","year":"2020","unstructured":"Janai, J., G\u00fcney, F., Behl, A., Geiger, A., et al.: Computer vision for autonomous vehicles: problems, datasets and state of the art. Found. Trends\u00ae Comput. Graph. Vis. 12(1\u20133), 1\u2013308 (2020)","journal-title":"Found. Trends\u00ae Comput. Graph. Vis."},{"key":"18_CR22","doi-asserted-by":"crossref","unstructured":"Jiang, W., Trulls, E., Hosang, J., Tagliasacchi, A., Yi, K.M.: COTR: correspondence transformer for matching across images. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6207\u20136217 (2021)","DOI":"10.1109\/ICCV48922.2021.00615"},{"key":"18_CR23","doi-asserted-by":"crossref","unstructured":"Kang, D., Kwon, H., Min, J., Cho, M.: Relational embedding for few-shot classification. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8822\u20138833 (2021)","DOI":"10.1109\/ICCV48922.2021.00870"},{"key":"18_CR24","doi-asserted-by":"crossref","unstructured":"Karaev, N., Rocco, I., Graham, B., Neverova, N., Vedaldi, A., Rupprecht, C.: CoTracker: it is better to track together. arXiv preprint arXiv:2307.07635 (2023)","DOI":"10.1007\/978-3-031-73033-7_2"},{"key":"18_CR25","doi-asserted-by":"crossref","unstructured":"Lee, J., Kim, D., Ponce, J., Ham, B.: SFNet: learning object-aware semantic correspondence. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2278\u20132287 (2019)","DOI":"10.1109\/CVPR.2019.00238"},{"issue":"5","key":"18_CR26","doi-asserted-by":"publisher","first-page":"978","DOI":"10.1109\/TPAMI.2010.147","volume":"33","author":"C Liu","year":"2010","unstructured":"Liu, C., Yuen, J., Torralba, A.: Sift flow: dense correspondence across scenes and its applications. IEEE Trans. Pattern Anal. Mach. Intell. 33(5), 978\u2013994 (2010)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"18_CR27","unstructured":"Loshchilov, I., Hutter, F.: SGDR: stochastic gradient descent with warm restarts. arXiv preprint arXiv:1608.03983 (2016)"},{"key":"18_CR28","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"18_CR29","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":"18_CR30","unstructured":"Manuelli, L., Li, Y., Florence, P., Tedrake, R.: Keypoints into the future: self-supervised correspondence in model-based reinforcement learning. arXiv preprint arXiv:2009.05085 (2020)"},{"key":"18_CR31","doi-asserted-by":"crossref","unstructured":"Melekhov, I., Tiulpin, A., Sattler, T., Pollefeys, M., Rahtu, E., Kannala, J.: DGC-Net: dense geometric correspondence network. In: 2019 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 1034\u20131042. IEEE (2019)","DOI":"10.1109\/WACV.2019.00115"},{"issue":"1","key":"18_CR32","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1145\/3503250","volume":"65","author":"B Mildenhall","year":"2021","unstructured":"Mildenhall, B., Srinivasan, P.P., Tancik, M., Barron, J.T., Ramamoorthi, R., Ng, R.: NeRF: representing scenes as neural radiance fields for view synthesis. Commun. ACM 65(1), 99\u2013106 (2021)","journal-title":"Commun. ACM"},{"key":"18_CR33","doi-asserted-by":"crossref","unstructured":"Min, J., Kang, D., Cho, M.: Hypercorrelation squeeze for few-shot segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6941\u20136952 (2021)","DOI":"10.1109\/ICCV48922.2021.00686"},{"key":"18_CR34","doi-asserted-by":"crossref","unstructured":"Moing, G.L., Ponce, J., Schmid, C.: Dense optical tracking: connecting the dots. arXiv preprint arXiv:2312.00786 (2023)","DOI":"10.1109\/CVPR52733.2024.01815"},{"key":"18_CR35","unstructured":"Nam, J., et al.: DiffMatch: diffusion model for dense matching. arXiv preprint arXiv:2305.19094 (2023)"},{"key":"18_CR36","doi-asserted-by":"crossref","unstructured":"Neoral, M., \u0160er\u1ef3ch, J., Matas, J.: MFT: long-term tracking of every pixel. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 6837\u20136847 (2024)","DOI":"10.1109\/WACV57701.2024.00669"},{"key":"18_CR37","doi-asserted-by":"crossref","unstructured":"Oh, S.W., Lee, J.Y., Xu, N., Kim, S.J.: Video object segmentation using space-time memory networks. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9226\u20139235 (2019)","DOI":"10.1109\/ICCV.2019.00932"},{"key":"18_CR38","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1007\/s11263-007-0086-4","volume":"78","author":"M Pollefeys","year":"2008","unstructured":"Pollefeys, M., et al.: Detailed real-time urban 3D reconstruction from video. Int. J. Comput. Vis. 78, 143\u2013167 (2008)","journal-title":"Int. J. Comput. Vis."},{"key":"18_CR39","unstructured":"Pont-Tuset, J., Perazzi, F., Caelles, S., Arbel\u00e1ez, P., Sorkine-Hornung, A., Van\u00a0Gool, L.: The 2017 DAVIS challenge on video object segmentation. arXiv preprint arXiv:1704.00675 (2017)"},{"key":"18_CR40","unstructured":"Press, O., Smith, N.A., Lewis, M.: Train short, test long: attention with linear biases enables input length extrapolation. arXiv preprint arXiv:2108.12409 (2021)"},{"issue":"1","key":"18_CR41","first-page":"5485","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21(1), 5485\u20135551 (2020)","journal-title":"J. Mach. Learn. Res."},{"key":"18_CR42","doi-asserted-by":"crossref","unstructured":"Rocco, I., Arandjelovic, R., Sivic, J.: Convolutional neural network architecture for geometric matching. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6148\u20136157 (2017)","DOI":"10.1109\/CVPR.2017.12"},{"key":"18_CR43","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":"18_CR44","unstructured":"Rocco, I., Cimpoi, M., Arandjelovi\u0107, R., Torii, A., Pajdla, T., Sivic, J.: Neighbourhood consensus networks. In: Advances in Neural Information Processing Systems, vol. 31 (2018)"},{"key":"18_CR45","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":"18_CR46","doi-asserted-by":"crossref","unstructured":"Sarlin, P.E., DeTone, D., Malisiewicz, T., Rabinovich, A.: SuperGlue: learning feature matching with graph neural networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4938\u20134947 (2020)","DOI":"10.1109\/CVPR42600.2020.00499"},{"key":"18_CR47","doi-asserted-by":"crossref","unstructured":"Schonberger, J.L., Frahm, J.M.: Structure-from-motion revisited. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4104\u20134113 (2016)","DOI":"10.1109\/CVPR.2016.445"},{"key":"18_CR48","doi-asserted-by":"crossref","unstructured":"Shaw, P., Uszkoreit, J., Vaswani, A.: Self-attention with relative position representations. arXiv preprint arXiv:1803.02155 (2018)","DOI":"10.18653\/v1\/N18-2074"},{"key":"18_CR49","doi-asserted-by":"publisher","first-page":"165","DOI":"10.1007\/978-3-031-20047-2_10","volume-title":"European Conference on Computer Vision 2022","author":"D Sun","year":"2022","unstructured":"Sun, D., Herrmann, C., Reda, F., Rubinstein, M., Fleet, D.J., Freeman, W.T.: Disentangling architecture and training for optical flow. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13682, pp. 165\u2013182. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20047-2_10"},{"key":"18_CR50","doi-asserted-by":"crossref","unstructured":"Sun, J., Shen, Z., Wang, Y., Bao, H., Zhou, X.: LoFTR: detector-free local feature matching with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8922\u20138931 (2021)","DOI":"10.1109\/CVPR46437.2021.00881"},{"key":"18_CR51","unstructured":"Tancik, M., et al.: Fourier features let networks learn high frequency functions in low dimensional domains. In: Advances in Neural Information Processing Systems, vol. 33, pp. 7537\u20137547 (2020)"},{"key":"18_CR52","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"402","DOI":"10.1007\/978-3-030-58536-5_24","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Z Teed","year":"2020","unstructured":"Teed, Z., Deng, J.: RAFT: recurrent all-pairs field transforms for optical flow. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12347, pp. 402\u2013419. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58536-5_24"},{"key":"18_CR53","unstructured":"Tolstikhin, I.O., et al.: MLP-Mixer: an all-MLP architecture for vision. In: Advances in Neural Information Processing Systems, vol. 34, pp. 24261\u201324272 (2021)"},{"key":"18_CR54","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"278","DOI":"10.1007\/3-540-44480-7_19","volume-title":"Vision Algorithms: Theory and Practice","author":"PHS Torr","year":"2000","unstructured":"Torr, P.H.S., Zisserman, A.: Feature based methods for structure and motion estimation. In: Triggs, B., Zisserman, A., Szeliski, R. (eds.) IWVA 1999. LNCS, vol. 1883, pp. 278\u2013294. Springer, Heidelberg (2000). https:\/\/doi.org\/10.1007\/3-540-44480-7_19"},{"key":"18_CR55","unstructured":"Truong, P., Danelljan, M., Gool, L.V., Timofte, R.: GOCor: bringing globally optimized correspondence volumes into your neural network. In: Advances in Neural Information Processing Systems, vol. 33, pp. 14278\u201314290 (2020)"},{"key":"18_CR56","doi-asserted-by":"crossref","unstructured":"Truong, P., Danelljan, M., Timofte, R.: GLU-Net: global-local universal network for dense flow and correspondences. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6258\u20136268 (2020)","DOI":"10.1109\/CVPR42600.2020.00629"},{"issue":"8","key":"18_CR57","doi-asserted-by":"publisher","first-page":"10247","DOI":"10.1109\/TPAMI.2023.3249225","volume":"45","author":"P Truong","year":"2023","unstructured":"Truong, P., Danelljan, M., Timofte, R., Van Gool, L.: PDC-Net+: enhanced probabilistic dense correspondence network. IEEE Trans. Pattern Anal. Mach. Intell. 45(8), 10247\u201310266 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"18_CR58","doi-asserted-by":"crossref","unstructured":"Truong, P., Danelljan, M., Van\u00a0Gool, L., Timofte, R.: Learning accurate dense correspondences and when to trust them. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5714\u20135724 (2021)","DOI":"10.1109\/CVPR46437.2021.00566"},{"key":"18_CR59","unstructured":"Ulyanov, D., Vedaldi, A., Lempitsky, V.: Instance normalization: the missing ingredient for fast stylization. arXiv preprint arXiv:1607.08022 (2016)"},{"key":"18_CR60","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"18_CR61","doi-asserted-by":"crossref","unstructured":"Vecerik, M., et al.: RoboTAP: tracking arbitrary points for few-shot visual imitation. arXiv preprint arXiv:2308.15975 (2023)","DOI":"10.1109\/ICRA57147.2024.10611409"},{"key":"18_CR62","doi-asserted-by":"crossref","unstructured":"Wang, Q., et al.: Tracking everything everywhere all at once. arXiv preprint arXiv:2306.05422 (2023)","DOI":"10.1109\/ICCV51070.2023.01813"},{"key":"18_CR63","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-030-01234-2_1","volume-title":"Computer Vision \u2013 ECCV 2018","author":"S Woo","year":"2018","unstructured":"Woo, S., Park, J., Lee, J.-Y., Kweon, I.S.: CBAM: convolutional block attention module. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 3\u201319. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01234-2_1"},{"key":"18_CR64","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-030-01261-8_1","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Y Wu","year":"2018","unstructured":"Wu, Y., He, K.: Group normalization. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11217, pp. 3\u201319. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01261-8_1"},{"key":"18_CR65","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"573","DOI":"10.1007\/978-3-540-24673-2_46","volume-title":"Computer Vision - ECCV 2004","author":"J Xiao","year":"2004","unstructured":"Xiao, J., Chai, J., Kanade, T.: A closed-form solution to non-rigid shape and motion recovery. In: Pajdla, T., Matas, J. (eds.) ECCV 2004. LNCS, vol. 3024, pp. 573\u2013587. Springer, Heidelberg (2004). https:\/\/doi.org\/10.1007\/978-3-540-24673-2_46"},{"key":"18_CR66","doi-asserted-by":"crossref","unstructured":"Yi, K.M., Trulls, E., Ono, Y., Lepetit, V., Salzmann, M., Fua, P.: Learning to find good correspondences. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2666\u20132674 (2018)","DOI":"10.1109\/CVPR.2018.00282"},{"key":"18_CR67","doi-asserted-by":"crossref","unstructured":"Zheng, Y., Harley, A.W., Shen, B., Wetzstein, G., Guibas, L.J.: PointOdyssey: a large-scale synthetic dataset for long-term point tracking. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 19855\u201319865 (2023)","DOI":"10.1109\/ICCV51070.2023.01818"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72684-2_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T19:09:51Z","timestamp":1730574591000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72684-2_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,3]]},"ISBN":["9783031726835","9783031726842"],"references-count":67,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72684-2_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,3]]},"assertion":[{"value":"3 November 2024","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":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}