{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T03:23:37Z","timestamp":1783567417535,"version":"3.55.0"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726453","type":"print"},{"value":"9783031726460","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"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\/978-3-031-72646-0_20","type":"book-chapter","created":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T08:45:29Z","timestamp":1730105129000},"page":"343-359","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Track Everything Everywhere Fast and\u00a0Robustly"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-9991-8485","authenticated-orcid":false,"given":"Yunzhou","family":"Song","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1108-7953","authenticated-orcid":false,"given":"Jiahui","family":"Lei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9803-7949","authenticated-orcid":false,"given":"Ziyun","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4301-1474","authenticated-orcid":false,"given":"Lingjie","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0498-0758","authenticated-orcid":false,"given":"Kostas","family":"Daniilidis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"issue":"3","key":"20_CR1","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1016\/j.cviu.2007.09.014","volume":"110","author":"H Bay","year":"2008","unstructured":"Bay, H., Ess, A., Tuytelaars, T., Van Gool, L.: Speeded-up robust features (SURF). Comput. Vis. Image Underst. 110(3), 346\u2013359 (2008)","journal-title":"Comput. Vis. Image Underst."},{"key":"20_CR2","unstructured":"Bhat, S.F., Birkl, R., Wofk, D., Wonka, P., M\u00fcller, M.: ZoeDepth: zero-shot transfer by combining relative and metric depth. arXiv preprint arXiv:2302.12288 (2023)"},{"key":"20_CR3","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"},{"key":"20_CR4","unstructured":"Birkl, R., Wofk, D., M\u00fcller, M.: Midas v3. 1\u2013A model zoo for robust monocular relative depth estimation. arXiv preprint arXiv:2307.14460 (2023)"},{"key":"20_CR5","doi-asserted-by":"publisher","unstructured":"Chen, A., Xu, Z., Geiger, A., Yu, J., Su, H.: TensoRF: tensorial radiance fields. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) European Conference on Computer Vision, vol. 13692, pp. 333\u2013350. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19824-3_20","DOI":"10.1007\/978-3-031-19824-3_20"},{"key":"20_CR6","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":"20_CR7","unstructured":"Dinh, L., Sohl-Dickstein, J., Bengio, S.: Density estimation using real NVP. arXiv preprint arXiv:1605.08803 (2016)"},{"key":"20_CR8","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":"20_CR9","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":"20_CR10","doi-asserted-by":"crossref","unstructured":"Guizilini, V., Vasiljevic, I., Chen, D., Ambrus, R., Gaidon, A.: Towards zero-shot scale-aware monocular depth estimation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 9233\u20139243 (2023)","DOI":"10.1109\/ICCV51070.2023.00847"},{"key":"20_CR11","doi-asserted-by":"publisher","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.) European Conference on Computer Vision, vol. 13682, pp. 59\u201375. Springer, Cham (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":"20_CR12","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. Artif. Intell. 17(1\u20133), 185\u2013203 (1981)","journal-title":"Artif. Intell."},{"key":"20_CR13","doi-asserted-by":"crossref","unstructured":"Jiang, S., Campbell, D., Lu, Y., Li, H., Hartley, R.: Learning to estimate hidden motions with global motion aggregation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9772\u20139781 (2021)","DOI":"10.1109\/ICCV48922.2021.00963"},{"key":"20_CR14","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":"20_CR15","doi-asserted-by":"crossref","unstructured":"Ke, B., Obukhov, A., Huang, S., Metzger, N., Daudt, R.C., Schindler, K.: Repurposing diffusion-based image generators for monocular depth estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2024)","DOI":"10.1109\/CVPR52733.2024.00907"},{"key":"20_CR16","unstructured":"Lee, A.X., et\u00a0al.: Beyond pick-and-place: tackling robotic stacking of diverse shapes. In: 5th Annual Conference on Robot Learning (2021)"},{"key":"20_CR17","doi-asserted-by":"crossref","unstructured":"Lei, J., Daniilidis, K.: CaDeX: learning canonical deformation coordinate space for dynamic surface representation via neural homeomorphism. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6624\u20136634 (2022)","DOI":"10.1109\/CVPR52688.2022.00651"},{"key":"20_CR18","doi-asserted-by":"crossref","unstructured":"Li, W.: Superglue-based deep learning method for image matching from multiple viewpoints. In: Proceedings of the 2023 8th International Conference on Mathematics and Artificial Intelligence, pp. 53\u201358 (2023)","DOI":"10.1145\/3594300.3594310"},{"key":"20_CR19","unstructured":"Liu, L., Gu, J., Lin, K.Z., Chua, T.S., Theobalt, C.: Neural sparse voxel fields. In: NeurIPS (2020)"},{"key":"20_CR20","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. Vision 60, 91\u2013110 (2004)","journal-title":"Int. J. Comput. Vision"},{"key":"20_CR21","unstructured":"Lucas, B.D., Kanade, T.: An iterative image registration technique with an application to stereo vision. In: IJCAI 1981: 7th International Joint Conference on Artificial Intelligence, vol.\u00a02, pp. 674\u2013679 (1981)"},{"key":"20_CR22","doi-asserted-by":"crossref","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. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58452-8_24"},{"issue":"4","key":"20_CR23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3528223.3530127","volume":"41","author":"T M\u00fcller","year":"2022","unstructured":"M\u00fcller, T., Evans, A., Schied, C., Keller, A.: Instant neural graphics primitives with a multiresolution hash encoding. ACM Trans. Graph. (ToG) 41(4), 1\u201315 (2022)","journal-title":"ACM Trans. Graph. (ToG)"},{"key":"20_CR24","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":"20_CR25","unstructured":"Oquab, M., et\u00a0al.: DINOv2: learning robust visual features without supervision. arXiv preprint arXiv:2304.07193 (2023)"},{"key":"20_CR26","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":"20_CR27","doi-asserted-by":"crossref","unstructured":"Pumarola, A., Corona, E., Pons-Moll, G., Moreno-Noguer, F.: D-NERF: neural radiance fields for dynamic scenes. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10318\u201310327 (2021)","DOI":"10.1109\/CVPR46437.2021.01018"},{"key":"20_CR28","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":"20_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. Int. J. Comput. Vision 80, 72\u201391 (2008)","journal-title":"Int. J. Comput. Vision"},{"key":"20_CR30","doi-asserted-by":"crossref","unstructured":"Shi, J., Tomasi, C.: Good features to track. In: Computer Vision and Pattern Recognition, 1994. Proceedings CVPR 1994., 1994 IEEE Computer Society Conference on, pp. 593\u2013600. IEEE (1994)","DOI":"10.1109\/CVPR.1994.323794"},{"key":"20_CR31","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8934\u20138943 (2018)","DOI":"10.1109\/CVPR.2018.00931"},{"key":"20_CR32","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":"20_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":"20_CR34","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":"20_CR35","doi-asserted-by":"crossref","unstructured":"Wang, X., Jabri, A., Efros, A.A.: Learning correspondence from the cycle-consistency of time. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2566\u20132576 (2019)","DOI":"10.1109\/CVPR.2019.00267"},{"key":"20_CR36","doi-asserted-by":"crossref","unstructured":"Xian, K., et al.: Monocular relative depth perception with web stereo data supervision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00040"},{"key":"20_CR37","doi-asserted-by":"crossref","unstructured":"Xu, H., Yang, J., Cai, J., Zhang, J., Tong, X.: High-resolution optical flow from 1D attention and correlation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10498\u201310507 (2021)","DOI":"10.1109\/ICCV48922.2021.01033"},{"key":"20_CR38","doi-asserted-by":"crossref","unstructured":"Xu, H., Zhang, J., Cai, J., Rezatofighi, H., Tao, D.: GMFlow: learning optical flow via global matching. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8121\u20138130 (2022)","DOI":"10.1109\/CVPR52688.2022.00795"},{"key":"20_CR39","doi-asserted-by":"crossref","unstructured":"Yang, L., Kang, B., Huang, Z., Xu, X., Feng, J., Zhao, H.: Depth anything: unleashing the power of large-scale unlabeled data. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"20_CR40","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":"20_CR41","doi-asserted-by":"crossref","unstructured":"Zhang, F., Woodford, O.J., Prisacariu, V.A., Torr, P.H.: Separable flow: learning motion cost volumes for optical flow estimation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10807\u201310817 (2021)","DOI":"10.1109\/ICCV48922.2021.01063"},{"issue":"1","key":"20_CR42","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1109\/TPAMI.2014.2339815","volume":"37","author":"ML Zhang","year":"2014","unstructured":"Zhang, M.L., Wu, L.: Lift: multi-label learning with label-specific features. IEEE Trans. Pattern Anal. Mach. Intell. 37(1), 107\u2013120 (2014)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"20_CR43","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\/978-3-031-72646-0_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,30]],"date-time":"2024-11-30T10:13:01Z","timestamp":1732961581000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72646-0_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"ISBN":["9783031726453","9783031726460"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72646-0_20","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"28 October 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"}}]}}