{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:31:40Z","timestamp":1742913100250,"version":"3.40.3"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031784439"},{"type":"electronic","value":"9783031784446"}],"license":[{"start":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T00:00:00Z","timestamp":1733270400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T00:00:00Z","timestamp":1733270400000},"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\/978-3-031-78444-6_23","type":"book-chapter","created":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T10:38:24Z","timestamp":1733222304000},"page":"348-363","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Attention-Based Patch Matching and\u00a0Motion-Driven Point Association for\u00a0Accurate Point Tracking"],"prefix":"10.1007","author":[{"given":"Han","family":"Zang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianyang","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xue-Feng","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoning","family":"Song","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiao-Jun","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Josef","family":"Kittler","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,4]]},"reference":[{"key":"23_CR1","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":"23_CR2","doi-asserted-by":"crossref","unstructured":"Doersch, C., et al.: Tapir: tracking any point with per-frame initialization and temporal refinement. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10061\u201310072 (2023)","DOI":"10.1109\/ICCV51070.2023.00923"},{"key":"23_CR3","unstructured":"Patraucean, Vet\u00a0al.: Perception test: a diagnostic benchmark for multimodal video models. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"issue":"1","key":"23_CR4","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1007\/s11263-020-01359-2","volume":"129","author":"J Ma","year":"2021","unstructured":"Ma, J., Jiang, X., Fan, A., Jiang, J., Yan, J.: Image matching from handcrafted to deep features: a survey. Int. J. Comput. Vis. 129(1), 23\u201379 (2021)","journal-title":"Int. J. Comput. Vis."},{"key":"23_CR5","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":"23_CR6","doi-asserted-by":"crossref","unstructured":"Bay, H., Tuytelaars, T., Van\u00a0Gool, L.: Surf: speeded up robust features. In: Computer Vision\u2013ECCV 2006: 9th European Conference on Computer Vision, Graz, Austria, May 7-13, 2006. Proceedings, Part I 9, pp. 404\u2013417. Springer (2006)","DOI":"10.1007\/11744023_32"},{"key":"23_CR7","doi-asserted-by":"crossref","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. IEEE (2011)","DOI":"10.1109\/ICCV.2011.6126544"},{"key":"23_CR8","doi-asserted-by":"crossref","unstructured":"Yi, K.M., Trulls, E., Lepetit, V., Fua, P.: Lift: learned invariant feature transform. In: Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11\u201314, 2016, Proceedings, Part VI 14, pp. 467\u2013483. Springer (2016)","DOI":"10.1007\/978-3-319-46466-4_28"},{"key":"23_CR9","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":"23_CR10","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":"23_CR11","unstructured":"Choy, C.B., Gwak, J., Savarese, S., Chandraker, M.: Universal correspondence network. In: Advances in Neural Information Processing Systems, vol. 29 (2016)"},{"key":"23_CR12","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":"23_CR13","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"23_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: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6207\u20136217 (2021)","DOI":"10.1109\/ICCV48922.2021.00615"},{"key":"23_CR15","doi-asserted-by":"crossref","unstructured":"Yu, J., Chang, J., He, J., Zhang, T., Yu, J., Wu, F.: Adaptive spot-guided transformer for consistent local feature matching. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21898\u201321908 (2023)","DOI":"10.1109\/CVPR52729.2023.02097"},{"key":"23_CR16","doi-asserted-by":"crossref","unstructured":"Huang, D., Chen, Y., Liu, Y., Liu, J., Xu, S., Wu, W., Ding, Y., Tang, F., Wang, C.: Adaptive assignment for geometry aware local feature matching. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5425\u20135434 (2023)","DOI":"10.1109\/CVPR52729.2023.00525"},{"key":"23_CR17","doi-asserted-by":"crossref","unstructured":"Zhu, X.F., Xu, T., Wu, X.J., Kittler, J.: Feature enhancement and coarse-to-fine detection for RGB-D tracking. Pattern Recogn. Lett. (2024)","DOI":"10.2139\/ssrn.4328174"},{"key":"23_CR18","doi-asserted-by":"crossref","unstructured":"Xu, T., Kang, Z., Zhu, X., Wu, X.J.: Learning adaptive spatio-temporal inference transformer for coarse-to-fine animal visual tracking: algorithm and benchmark. Int. J. Comput. Vis. 1\u201315 (2024)","DOI":"10.1007\/s11263-024-02008-8"},{"key":"23_CR19","doi-asserted-by":"crossref","unstructured":"Li, Z., Snavely, N.: MegaDepth: learning single-view depth prediction from internet photos. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2041\u20132050 (2018)","DOI":"10.1109\/CVPR.2018.00218"},{"key":"23_CR20","first-page":"13610","volume":"35","author":"C Doersch","year":"2022","unstructured":"Doersch, C., et al.: Tap-vid: a benchmark for tracking any point in a video. Adv. Neural. Inf. Process. Syst. 35, 13610\u201313626 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"23_CR21","doi-asserted-by":"crossref","unstructured":"Harley, A.W., Fang, Z., Fragkiadaki, K.: Particle video revisited: tracking through occlusions using point trajectories. In: European Conference on Computer Vision, pp. 59\u201375. Springer (2022)","DOI":"10.1007\/978-3-031-20047-2_4"},{"key":"23_CR22","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"23_CR23","doi-asserted-by":"crossref","unstructured":"Han, D., Ye, T., Han, Y., Xia, Z., Song, S., Huang, G.: Agent attention: on the integration of softmax and linear attention. arXiv preprint arXiv:2312.08874 (2023)","DOI":"10.1007\/978-3-031-72973-7_8"},{"key":"23_CR24","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"23_CR25","unstructured":"Greff, K., et\u00a0al.: Kubric: a scalable dataset generator. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3749\u20133761 (2022)"},{"key":"23_CR26","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":"23_CR27","doi-asserted-by":"crossref","unstructured":"Lindenberger, P., Sarlin, P.E., Pollefeys, M.: Lightglue: local feature matching at light speed. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 17627\u201317638 (2023)","DOI":"10.1109\/ICCV51070.2023.01616"},{"key":"23_CR28","doi-asserted-by":"crossref","unstructured":"Xu, T., Wu, X.J., Kittler, J.: Non-negative subspace representation learning scheme for correlation filter based tracking. In: 2018 24th International Conference on Pattern Recognition (ICPR), pp. 1888\u20131893. IEEE (2018)","DOI":"10.1109\/ICPR.2018.8546146"},{"key":"23_CR29","unstructured":"Fan, H., et\u00a0al.: Visdrone-sot2020: the vision meets drone single object tracking challenge results. In: Computer Vision\u2013ECCV 2020 Workshops: Glasgow, UK, August 23\u201328, 2020, Proceedings, Part IV 16, pp. 728\u2013749. Springer, Cham (2020)"},{"key":"23_CR30","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1016\/j.neunet.2023.01.003","volume":"161","author":"J Wen","year":"2023","unstructured":"Wen, J., Chu, H., Lai, Z., Xu, T., Shen, L.: Enhanced robust spatial feature selection and correlation filter learning for UAV tracking. Neural Netw. 161, 39\u201354 (2023)","journal-title":"Neural Netw."},{"issue":"1","key":"23_CR31","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1007\/s44267-023-00002-1","volume":"1","author":"T Xu","year":"2023","unstructured":"Xu, T., Zhu, X.F., Wu, X.J.: Learning spatio-temporal discriminative model for affine subspace based visual object tracking. Vis. Intell. 1(1), 4 (2023)","journal-title":"Vis. Intell."},{"key":"23_CR32","unstructured":"Zhao, J., et\u00a0al.: The 3rd anti-UAV workshop & challenge: methods and results. arXiv preprint arXiv:2305.07290 (2023)"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-78444-6_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T11:36:55Z","timestamp":1733225815000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78444-6_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,4]]},"ISBN":["9783031784439","9783031784446"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78444-6_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,12,4]]},"assertion":[{"value":"4 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kolkata","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","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":"1 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}