{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T08:07:20Z","timestamp":1761898040795,"version":"3.40.3"},"publisher-location":"Cham","reference-count":44,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031732195"},{"type":"electronic","value":"9783031732201"}],"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\/978-3-031-73220-1_13","type":"book-chapter","created":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T20:05:25Z","timestamp":1730577925000},"page":"220-235","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Decomposition Betters Tracking Everything Everywhere"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-3102-0932","authenticated-orcid":false,"given":"Rui","family":"Li","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9100-2906","authenticated-orcid":false,"given":"Dong","family":"Liu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,3]]},"reference":[{"key":"13_CR1","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1023\/B:VISI.0000011205.11775.fd","volume":"56","author":"S Baker","year":"2004","unstructured":"Baker, S., Matthews, I.: Lucas-kanade 20 years on: a unifying framework. IJCV 56, 221\u2013255 (2004)","journal-title":"IJCV"},{"key":"13_CR2","doi-asserted-by":"crossref","unstructured":"Barron, J.T., Mildenhall, B., Verbin, D., Srinivasan, P.P., Hedman, P.: Mip-nerf 360: unbounded anti-aliased neural radiance fields. In: CVPR, pp. 5470\u20135479 (2022)","DOI":"10.1109\/CVPR52688.2022.00539"},{"key":"13_CR3","unstructured":"Bian, W., Huang, Z., Shi, X., Dong, Y., Li, Y., Li, H.: Context-tap: tracking any point demands spatial context features. In: NeurIPS (2023)"},{"key":"13_CR4","doi-asserted-by":"crossref","unstructured":"Bian, Z., Jabri, A., Efros, A.A., Owens, A.: Learning pixel trajectories with multiscale contrastive random walks. In: CVPR, pp. 6508\u20136519 (2022)","DOI":"10.1109\/CVPR52688.2022.00640"},{"issue":"1\u201310","key":"13_CR5","first-page":"4","volume":"5","author":"JY Bouguet","year":"2001","unstructured":"Bouguet, J.Y., et al.: Pyramidal implementation of the affine lucas kanade feature tracker description of the algorithm. Intel Corporat. 5(1\u201310), 4 (2001)","journal-title":"Intel Corporat."},{"key":"13_CR6","doi-asserted-by":"crossref","unstructured":"Caron, M., Touvron, H., Misra, I., J\u00e9gou, H., Mairal, J., Bojanowski, P., Joulin, A.: Emerging properties in self-supervised vision transformers. In: ICCV, pp. 9650\u20139660 (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"issue":"4","key":"13_CR7","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"LC Chen","year":"2017","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. PAMI 40(4), 834\u2013848 (2017)","journal-title":"IEEE Trans. PAMI"},{"key":"13_CR8","unstructured":"Dinh, L., Sohl-Dickstein, J., Bengio, S.: Density estimation using real nvp. arXiv preprint arXiv:1605.08803 (2016)"},{"key":"13_CR9","unstructured":"Doersch, C., et al.: Tap-vid: a benchmark for tracking any point in a video. In: NeurIPS, vol.\u00a035, pp. 13610\u201313626 (2022)"},{"key":"13_CR10","doi-asserted-by":"crossref","unstructured":"Doersch, C., et al.: Tapir: Tracking any point with per-frame initialization and temporal refinement. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00923"},{"key":"13_CR11","doi-asserted-by":"crossref","unstructured":"Dosovitskiy, A., et al.: Flownet: learning optical flow with convolutional networks. In: ICCV, pp. 2758\u20132766 (2015)","DOI":"10.1109\/ICCV.2015.316"},{"key":"13_CR12","unstructured":"Fathony, R., Sahu, A.K., Willmott, D., Kolter, J.Z.: Multiplicative filter networks. In: ICLR (2020)"},{"key":"13_CR13","doi-asserted-by":"crossref","unstructured":"Gao, C., Saraf, A., Kopf, J., Huang, J.B.: Dynamic view synthesis from dynamic monocular video. In: ICCV, pp. 5712\u20135721 (2021)","DOI":"10.1109\/ICCV48922.2021.00566"},{"key":"13_CR14","doi-asserted-by":"publisher","unstructured":"Harley, A.W., Fang, Z., Fragkiadaki, K.: Particle video revisited: Tracking through occlusions using point trajectories. In: ECCV 2022, pp. 59\u201375. Springer, Heidelberg (2022). https:\/\/doi.org\/10.1007\/978-3-031-20047-2_4","DOI":"10.1007\/978-3-031-20047-2_4"},{"issue":"1\u20133","key":"13_CR15","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1016\/0004-3702(81)90024-2","volume":"17","author":"BK Horn","year":"1981","unstructured":"Horn, B.K., Schunck, B.G.: Determining optical flow. Arti. Intell. 17(1\u20133), 185\u2013203 (1981)","journal-title":"Arti. Intell."},{"key":"13_CR16","doi-asserted-by":"crossref","unstructured":"Ilg, E., Mayer, N., Saikia, T., Keuper, M., Dosovitskiy, A., Brox, T.: Flownet 2.0: evolution of optical flow estimation with deep networks. In: CVPR, pp. 2462\u20132470 (2017)","DOI":"10.1109\/CVPR.2017.179"},{"key":"13_CR17","unstructured":"Jabri, A., Owens, A., Efros, A.: Space-time correspondence as a contrastive random walk. In: NeurIPS, vol.\u00a033, pp. 19545\u201319560 (2020)"},{"key":"13_CR18","doi-asserted-by":"crossref","unstructured":"Lai, Z., Lu, E., Xie, W.: Mast: a memory-augmented self-supervised tracker. In: CVPR, pp. 6479\u20136488 (2020)","DOI":"10.1109\/CVPR42600.2020.00651"},{"key":"13_CR19","doi-asserted-by":"crossref","unstructured":"Li, R., Liu, D.: Spatial-then-temporal self-supervised learning for video correspondence. In: CVPR, pp. 2279\u20132288 (2023)","DOI":"10.1109\/CVPR52729.2023.00226"},{"key":"13_CR20","doi-asserted-by":"crossref","unstructured":"Li, R., Zhang, Y., Qiu, Z., Yao, T., Liu, D., Mei, T.: Motion-focused contrastive learning of video representations. In: ICCV, pp. 2105\u20132114 (2021)","DOI":"10.1109\/ICCV48922.2021.00211"},{"key":"13_CR21","doi-asserted-by":"crossref","unstructured":"Li, R., Zhou, S., Liu, D.: Learning fine-grained features for pixel-wise video correspondences. In: ICCV, pp. 9632\u20139641 (2023)","DOI":"10.1109\/ICCV51070.2023.00883"},{"key":"13_CR22","unstructured":"Li, X., Liu, S., De\u00a0Mello, S., Wang, X., Kautz, J., Yang, M.H.: Joint-task self-supervised learning for temporal correspondence. In: NeurIPS, vol.\u00a032 (2019)"},{"key":"13_CR23","doi-asserted-by":"crossref","unstructured":"Li, Z., Niklaus, S., Snavely, N., Wang, O.: Neural scene flow fields for space-time view synthesis of dynamic scenes. In: CVPR, pp. 6498\u20136508 (2021)","DOI":"10.1109\/CVPR46437.2021.00643"},{"key":"13_CR24","doi-asserted-by":"crossref","unstructured":"Li, Z., Wang, Q., Cole, F., Tucker, R., Snavely, N.: Dynibar: neural dynamic image-based rendering. In: CVPR, pp. 4273\u20134284 (2023)","DOI":"10.1109\/CVPR52729.2023.00416"},{"key":"13_CR25","doi-asserted-by":"crossref","unstructured":"Martin-Brualla, R., Radwan, N., Sajjadi, M.S., Barron, J.T., Dosovitskiy, A., Duckworth, D.: Nerf in the wild: neural radiance fields for unconstrained photo collections. In: CVPR, pp. 7210\u20137219 (2021)","DOI":"10.1109\/CVPR46437.2021.00713"},{"issue":"1","key":"13_CR26","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":"13_CR27","doi-asserted-by":"crossref","unstructured":"Neoral, M., \u0160er\u1ef3ch, J., Matas, J.: Mft: long-term tracking of every pixel. In: WACV, pp. 6837\u20136847 (2024)","DOI":"10.1109\/WACV57701.2024.00669"},{"key":"13_CR28","doi-asserted-by":"crossref","unstructured":"Park, K., et al.: Nerfies: deformable neural radiance fields. In: ICCV, pp. 5865\u20135874 (2021)","DOI":"10.1109\/ICCV48922.2021.00581"},{"key":"13_CR29","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1007\/s11263-008-0136-6","volume":"80","author":"P Sand","year":"2008","unstructured":"Sand, P., Teller, S.: Particle video: long-range motion estimation using point trajectories. IJCV 80, 72\u201391 (2008)","journal-title":"IJCV"},{"key":"13_CR30","doi-asserted-by":"crossref","unstructured":"Shi, X., et al.: Videoflow: exploiting temporal cues for multi-frame optical flow estimation. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01146"},{"key":"13_CR31","doi-asserted-by":"crossref","unstructured":"Strudel, R., Garcia, R., Laptev, I., Schmid, C.: Segmenter: transformer for semantic segmentation. In: ICCV, pp. 7262\u20137272 (2021)","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"13_CR32","doi-asserted-by":"crossref","unstructured":"Sun, D., Yang, X., Liu, M.Y., Kautz, J.: Pwc-net: Cnns for optical flow using pyramid, warping, and cost volume. In: CVPR, pp. 8934\u20138943 (2018)","DOI":"10.1109\/CVPR.2018.00931"},{"key":"13_CR33","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":"13_CR34","doi-asserted-by":"crossref","unstructured":"Vondrick, C., Shrivastava, A., Fathi, A., Guadarrama, S., Murphy, K.: Tracking emerges by colorizing videos. In: ECCV, pp. 391\u2013408 (2018)","DOI":"10.1007\/978-3-030-01261-8_24"},{"key":"13_CR35","doi-asserted-by":"crossref","unstructured":"Wang, C., MacDonald, L.E., Jeni, L.A., Lucey, S.: Flow supervision for deformable nerf. In: CVPR, pp. 21128\u201321137 (2023)","DOI":"10.1109\/CVPR52729.2023.02024"},{"key":"13_CR36","doi-asserted-by":"crossref","unstructured":"Wang, Q., et al.: Tracking everything everywhere all at once. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01813"},{"key":"13_CR37","doi-asserted-by":"crossref","unstructured":"Wang, X., Jabri, A., Efros, A.A.: Learning correspondence from the cycle-consistency of time. In: CVPR, pp. 2566\u20132576 (2019)","DOI":"10.1109\/CVPR.2019.00267"},{"key":"13_CR38","unstructured":"Xie, J., Xie, W., Zisserman, A.: Segmenting moving objects via an object-centric layered representation. In: NeurIPS, vol.\u00a035, pp. 28023\u201328036 (2022)"},{"key":"13_CR39","doi-asserted-by":"crossref","unstructured":"Xu, H., Zhang, J., Cai, J., Rezatofighi, H., Tao, D.: Gmflow: learning optical flow via global matching. In: CVPR, pp. 8121\u20138130 (2022)","DOI":"10.1109\/CVPR52688.2022.00795"},{"key":"13_CR40","doi-asserted-by":"crossref","unstructured":"Xu, J., Wang, X.: Rethinking self-supervised correspondence learning: a video frame-level similarity perspective. In: ICCV, pp. 10075\u201310085 (2021)","DOI":"10.1109\/ICCV48922.2021.00992"},{"key":"13_CR41","doi-asserted-by":"crossref","unstructured":"Ye, V., Li, Z., Tucker, R., Kanazawa, A., Snavely, N.: Deformable sprites for unsupervised video decomposition. In: CVPR, pp. 2657\u20132666 (2022)","DOI":"10.1109\/CVPR52688.2022.00268"},{"key":"13_CR42","doi-asserted-by":"crossref","unstructured":"Yuan, Y., et al.: Isomer: isomerous transformer for zero-shot video object segmentation. In: ICCV, pp. 966\u2013976 (2023)","DOI":"10.1109\/ICCV51070.2023.00095"},{"key":"13_CR43","doi-asserted-by":"publisher","unstructured":"Zhao, W., Liu, S., Guo, H., Wang, W., Liu, Y.J.: Particlesfm: exploiting dense point trajectories for localizing moving cameras in the wild. In: ECCV 2022, pp. 523\u2013542. Springer, Heidelberg (2022). https:\/\/doi.org\/10.1007\/978-3-031-19824-3_31","DOI":"10.1007\/978-3-031-19824-3_31"},{"key":"13_CR44","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: ICCV, 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\/978-3-031-73220-1_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T20:06:14Z","timestamp":1730577974000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73220-1_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,3]]},"ISBN":["9783031732195","9783031732201"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73220-1_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"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"}}]}}