{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:31:18Z","timestamp":1777656678451,"version":"3.51.4"},"publisher-location":"Singapore","reference-count":70,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819609000","type":"print"},{"value":"9789819609017","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,12,8]],"date-time":"2024-12-08T00:00:00Z","timestamp":1733616000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,8]],"date-time":"2024-12-08T00:00:00Z","timestamp":1733616000000},"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\/978-981-96-0901-7_22","type":"book-chapter","created":{"date-parts":[[2024,12,7]],"date-time":"2024-12-07T07:56:39Z","timestamp":1733558199000},"page":"374-393","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Dense Trajectory Fields: Consistent and\u00a0Efficient Spatio-Temporal Pixel Tracking"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-0501-3394","authenticated-orcid":false,"given":"Marc","family":"Tournadre","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1694-4706","authenticated-orcid":false,"given":"Catherine","family":"Soladi\u00e9","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nicolas","family":"Stoiber","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3201-0177","authenticated-orcid":false,"given":"Pierre-Yves","family":"Richard","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,8]]},"reference":[{"key":"22_CR1","doi-asserted-by":"crossref","unstructured":"Arnab, A., Dehghani, M., Heigold, G., Sun, C., Lu\u010di\u0107, M., Schmid, C.: Vivit: A video vision transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 6836\u20136846 (2021)","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"22_CR2","doi-asserted-by":"crossref","unstructured":"Bai, S., Geng, Z., Savani, Y., Kolter, J.Z.: Deep Equilibrium Optical Flow Estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 620\u2013630 (2022)","DOI":"10.1109\/CVPR52688.2022.00070"},{"key":"22_CR3","unstructured":"Bertasius, G., Wang, H., Torresani, L.: Is space-time attention all you need for video understanding? In: Meila, M., Zhang, T. (eds.) Proceedings of the 38th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol.\u00a0139, pp. 813\u2013824. PMLR (18\u201324 Jul 2021), https:\/\/proceedings.mlr.press\/v139\/bertasius21a.html"},{"key":"22_CR4","unstructured":"Bolya, D., Fu, C.Y., Dai, X., Zhang, P., Feichtenhofer, C., Hoffman, J.: Token merging: Your vit but faster. In: The Eleventh International Conference on Learning Representations (2023), https:\/\/openreview.net\/forum?id=JroZRaRw7Eu"},{"key":"22_CR5","doi-asserted-by":"crossref","unstructured":"Brox, T., Bruhn, A., Papenberg, N., Weickert, J.: High accuracy optical flow estimation based on a theory for warping. In: European conference on computer vision. pp. 25\u201336. Springer (2004)","DOI":"10.1007\/978-3-540-24673-2_3"},{"key":"22_CR6","doi-asserted-by":"crossref","unstructured":"Butler, D.J., Wulff, J., Stanley, G.B., Black, M.J.: A naturalistic open source movie for optical flow evaluation. In: A. Fitzgibbon et al. (Eds.) (ed.) European Conf. on Computer Vision (ECCV). pp. 611\u2013625. Part IV, LNCS 7577, Springer-Verlag (Oct 2012)","DOI":"10.1007\/978-3-642-33783-3_44"},{"key":"22_CR7","doi-asserted-by":"crossref","unstructured":"Chen, Y., Zhu, D., Shi, W., Zhang, G., Zhang, T., Zhang, X., Li, J.: Mfcflow: A motion feature compensated multi-frame recurrent network for optical flow estimation. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision. pp. 5068\u20135077 (2023)","DOI":"10.1109\/WACV56688.2023.00504"},{"key":"22_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":"22_CR9","first-page":"9355","volume":"34","author":"X Chu","year":"2021","unstructured":"Chu, X., Tian, Z., Wang, Y., Zhang, B., Ren, H., Wei, X., Xia, H., Shen, C.: Twins: Revisiting the design of spatial attention in vision transformers. Adv. Neural. Inf. Process. Syst. 34, 9355\u20139366 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"22_CR10","doi-asserted-by":"crossref","unstructured":"Deng, C., Luo, A., Huang, H., Ma, S., Liu, J., Liu, S.: Explicit motion disentangling for efficient optical flow estimation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 9521\u20139530 (2023)","DOI":"10.1109\/ICCV51070.2023.00873"},{"key":"22_CR11","first-page":"13610","volume":"35","author":"C Doersch","year":"2022","unstructured":"Doersch, C., Gupta, A., Markeeva, L., Recasens, A., Smaira, L., Aytar, Y., Carreira, J., Zisserman, A., Yang, Y.: 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":"22_CR12","doi-asserted-by":"crossref","unstructured":"Doersch, C., Yang, Y., Vecerik, M., Gokay, D., Gupta, A., Aytar, Y., Carreira, J., Zisserman, A.: TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinement (2023), _eprint: 2306.08637","DOI":"10.1109\/ICCV51070.2023.00923"},{"key":"22_CR13","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: International Conference on Learning Representations (2021), https:\/\/openreview.net\/forum?id=YicbFdNTTy"},{"key":"22_CR14","doi-asserted-by":"crossref","unstructured":"Dosovitskiy, A., Fischer, P., Ilg, E., Hausser, P., Hazirbas, C., Golkov, V., Van Der\u00a0Smagt, P., Cremers, D., Brox, T.: Flownet: Learning optical flow with convolutional networks. In: Proceedings of the IEEE international conference on computer vision. pp. 2758\u20132766 (2015)","DOI":"10.1109\/ICCV.2015.316"},{"key":"22_CR15","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., Urtasun, R.: Are we ready for Autonomous Driving? The KITTI Vision Benchmark Suite. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2012)","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"22_CR16","doi-asserted-by":"crossref","unstructured":"Greff, K., Belletti, F., Beyer, L., Doersch, C., Du, Y., Duckworth, D., Fleet, D.J., Gnanapragasam, D., Golemo, F., Herrmann, C., Kipf, T., Kundu, A., Lagun, D., Laradji, I., Liu, H.T.D., Meyer, H., Miao, Y., Nowrouzezahrai, D., Oztireli, C., Pot, E., Radwan, N., Rebain, D., Sabour, S., Sajjadi, M.S.M., Sela, M., Sitzmann, V., Stone, A., Sun, D., Vora, S., Wang, Z., Wu, T., Yi, K.M., Zhong, F., Tagliasacchi, A.: Kubric: A Scalable Dataset Generator. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). pp. 3749\u20133761 (Jun 2022)","DOI":"10.1109\/CVPR52688.2022.00373"},{"key":"22_CR17","doi-asserted-by":"crossref","unstructured":"Harley, A.W., Fang, Z., Fragkiadaki, K.: Particle video revisited: Tracking through occlusions using point trajectories. In: ECCV (2022)","DOI":"10.1007\/978-3-031-20047-2_4"},{"key":"22_CR18","unstructured":"Horn, B.K., Schunck, B.G.: Determining optical flow. In: Techniques and Applications of Image Understanding. vol.\u00a0281, pp. 319\u2013331. International Society for Optics and Photonics (1981)"},{"key":"22_CR19","doi-asserted-by":"crossref","unstructured":"Huang, Z., Shi, X., Zhang, C., Wang, Q., Cheung, K.C., Qin, H., Dai, J., Li, H.: FlowFormer: A transformer architecture for optical flow. ECCV (2022)","DOI":"10.1007\/978-3-031-19790-1_40"},{"key":"22_CR20","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: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 2462\u20132470 (2017)","DOI":"10.1109\/CVPR.2017.179"},{"key":"22_CR21","unstructured":"Jaegle, A., Borgeaud, S., Alayrac, J.B., Doersch, C., Ionescu, C., Ding, D., Koppula, S., Zoran, D., Brock, A., Shelhamer, E., Henaff, O.J., Botvinick, M., Zisserman, A., Vinyals, O., Carreira, J.: Perceiver IO: A general architecture for structured inputs & outputs. In: International Conference on Learning Representations (2022), https:\/\/openreview.net\/forum?id=fILj7WpI-g"},{"key":"22_CR22","doi-asserted-by":"crossref","unstructured":"Janai, J., Guney, F., Ranjan, A., Black, M., Geiger, A.: Unsupervised learning of multi-frame optical flow with occlusions. In: Proceedings of the European conference on computer vision (ECCV). pp. 690\u2013706 (2018)","DOI":"10.1007\/978-3-030-01270-0_42"},{"key":"22_CR23","doi-asserted-by":"crossref","unstructured":"Jiang, S., Campbell, D., Lu, Y., Li, H., Hartley, R.: Learning to Estimate Hidden Motions with Global Motion Aggregation (2021), 00006 _eprint: 2104.02409","DOI":"10.1109\/ICCV48922.2021.00963"},{"key":"22_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":"22_CR25","doi-asserted-by":"crossref","unstructured":"Khan, S., Naseer, M., Hayat, M., Zamir, S.W., Khan, F.S., Shah, M.: Transformers in vision: A survey. ACM computing surveys (CSUR) 54(10s), 1\u201341 (2022), publisher: ACM New York, NY","DOI":"10.1145\/3505244"},{"key":"22_CR26","doi-asserted-by":"crossref","unstructured":"Kim, T.H., Sajjadi, M.S., Hirsch, M., Scholkopf, B.: Spatio-temporal transformer network for video restoration. In: Proceedings of the European Conference on Computer Vision (ECCV). pp. 106\u2013122 (2018)","DOI":"10.1007\/978-3-030-01219-9_7"},{"key":"22_CR27","doi-asserted-by":"crossref","unstructured":"Kondermann, D., Nair, R., Meister, S., Mischler, W., G\u00fcssefeld, B., Hofmann, S., Brenner, C., J\u00e4hne, B.: Stereo ground truth with error bars. In: Asian Conference on Computer Vision, ACCV 2014 (2014)","DOI":"10.1007\/978-3-319-16814-2_39"},{"key":"22_CR28","doi-asserted-by":"crossref","unstructured":"Kong, L., Yang, X., Yang, J.: OAS-Net: Occlusion Aware Sampling Network for Accurate Optical Flow. In: ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). pp. 2475\u20132479. IEEE (2021). https:\/\/doi.org\/10\/gn298w, 00002","DOI":"10.1109\/ICASSP39728.2021.9413531"},{"key":"22_CR29","doi-asserted-by":"crossref","unstructured":"Le\u00a0Moing, G., Ponce, J., Schmid, C.: Dense optical tracking: Connecting the dots. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). pp. 19187\u201319197 (June 2024)","DOI":"10.1109\/CVPR52733.2024.01815"},{"key":"22_CR30","first-page":"18114","volume":"34","author":"J Li","year":"2021","unstructured":"Li, J., Li, B., Lu, Y.: Deep contextual video compression. Adv. Neural. Inf. Process. Syst. 34, 18114\u201318125 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"22_CR31","unstructured":"Li, J., Niu, Y.: Cgcv: Context guided correlation volume for optical flow neural networks. arXiv e-prints pp. arXiv\u20132212 (2022)"},{"key":"22_CR32","doi-asserted-by":"crossref","unstructured":"Lu, Y., Wang, Q., Ma, S., Geng, T., Chen, Y.V., Chen, H., Liu, D.: Transflow: Transformer as flow learner. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 18063\u201318073 (2023)","DOI":"10.1109\/CVPR52729.2023.01732"},{"key":"22_CR33","doi-asserted-by":"crossref","unstructured":"Luo, A., Yang, F., Luo, K., Li, X., Fan, H., Liu, S.: Learning optical flow with adaptive graph reasoning. In: Proceedings of the AAAI Conference on Artificial Intelligence (AAAI) (2022)","DOI":"10.1609\/aaai.v36i2.20083"},{"key":"22_CR34","doi-asserted-by":"crossref","unstructured":"Mayer, N., Ilg, E., H\u00e4usser, P., Fischer, P., Cremers, D., Dosovitskiy, A., Brox, T.: A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation. In: IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) (2016), http:\/\/lmb.informatik.uni-freiburg.de\/Publications\/2016\/MIFDB16","DOI":"10.1109\/CVPR.2016.438"},{"key":"22_CR35","doi-asserted-by":"crossref","unstructured":"Neimark, D., Bar, O., Zohar, M., Asselmann, D.: Video transformer network. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 3163\u20133172 (2021)","DOI":"10.1109\/ICCVW54120.2021.00355"},{"key":"22_CR36","doi-asserted-by":"crossref","unstructured":"Neoral, M., \u0160er\u00fdch, J., Matas, J.: Mft: Long-term tracking of every pixel (2023)","DOI":"10.1109\/WACV57701.2024.00669"},{"key":"22_CR37","unstructured":"Parmar, N., Vaswani, A., Uszkoreit, J., Kaiser, L., Shazeer, N., Ku, A., Tran, D.: Image transformer. In: International Conference on Machine Learning. pp. 4055\u20134064. PMLR (2018), 00000"},{"key":"22_CR38","unstructured":"Press, O., Smith, N., Lewis, M.: Train short, test long: Attention with linear biases enables input length extrapolation. In: International Conference on Learning Representations (2021)"},{"key":"22_CR39","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. Vis. 80, 72\u201391 (2008)","journal-title":"Int. J. Comput. Vis."},{"key":"22_CR40","doi-asserted-by":"crossref","unstructured":"Sevilla-Lara, L., Liao, Y., G\u00fcney, F., Jampani, V., Geiger, A., Black, M.J.: On the integration of optical flow and action recognition. In: Pattern Recognition: 40th German Conference, GCPR 2018, Stuttgart, Germany, October 9-12, 2018, Proceedings 40. pp. 281\u2013297. Springer (2019)","DOI":"10.1007\/978-3-030-12939-2_20"},{"key":"22_CR41","doi-asserted-by":"crossref","unstructured":"Shi, X., Huang, Z., Bian, W., Li, D., Zhang, M., Cheung, K.C., See, S., Qin, H., Dai, J., Li, H.: Videoflow: Exploiting temporal cues for multi-frame optical flow estimation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 12469\u201312480 (2023)","DOI":"10.1109\/ICCV51070.2023.01146"},{"key":"22_CR42","doi-asserted-by":"crossref","unstructured":"Shi, X., Huang, Z., Li, D., Zhang, M., Cheung, K.C., See, S., Qin, H., Dai, J., Li, H.: Flowformer++: Masked cost volume autoencoding for pretraining optical flow estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 1599\u20131610 (2023)","DOI":"10.1109\/CVPR52729.2023.00160"},{"key":"22_CR43","doi-asserted-by":"crossref","unstructured":"Sui, X., Li, S., Geng, X., Wu, Y., Xu, X., Liu, Y., Goh, R., Zhu, H.: CRAFT: Cross-Attentional Flow Transformer for Robust Optical Flow. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 17602\u201317611 (2022)","DOI":"10.1109\/CVPR52688.2022.01708"},{"key":"22_CR44","doi-asserted-by":"crossref","unstructured":"Sun, D., Herrmann, C., Reda, F., Rubinstein, M., Fleet, D.J., Freeman, W.T.: What Makes RAFT Better Than PWC-Net? (Disentangling Architecture and Training for Optical Flow). In: ECCV (2022)","DOI":"10.1007\/978-3-031-20047-2_10"},{"key":"22_CR45","doi-asserted-by":"crossref","unstructured":"Sun, D., Vlasic, D., Herrmann, C., Jampani, V., Krainin, M., Chang, H., Zabih, R., Freeman, W.T., Liu, C.: Autoflow: Learning a better training set for optical flow. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 10093\u201310102 (2021)","DOI":"10.1109\/CVPR46437.2021.00996"},{"key":"22_CR46","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 (2018), 01207 _eprint: 1709.02371","DOI":"10.1109\/CVPR.2018.00931"},{"key":"22_CR47","doi-asserted-by":"crossref","unstructured":"Sun, S., Kuang, Z., Sheng, L., Ouyang, W., Zhang, W.: Optical flow guided feature: A fast and robust motion representation for video action recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 1390\u20131399 (2018)","DOI":"10.1109\/CVPR.2018.00151"},{"key":"22_CR48","doi-asserted-by":"crossref","unstructured":"Tang, C., Sheng, X., Li, Z., Zhang, H., Li, L., Liu, D.: Offline and online optical flow enhancement for deep video compression. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol.\u00a038, pp. 5118\u20135126 (2024)","DOI":"10.1609\/aaai.v38i6.28317"},{"key":"22_CR49","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":"22_CR50","doi-asserted-by":"crossref","unstructured":"Teed, Z., Deng, J.: Raft: Recurrent all-pairs field transforms for optical flow. In: European Conference on Computer Vision. pp. 402\u2013419. Springer (2020), 00000","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"22_CR51","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \\., Polosukhin, I.: Attention is all you need. In: Advances in neural information processing systems. pp. 5998\u20136008 (2017), 34320"},{"key":"22_CR52","unstructured":"Wang, C., Eckart, B., Lucey, S., Gallo, O.: Neural Trajectory Fields for Dynamic Novel View Synthesis (2021), _eprint: 2105.05994"},{"key":"22_CR53","doi-asserted-by":"crossref","unstructured":"Wang, Q., Chang, Y.Y., Cai, R., Li, Z., Hariharan, B., Holynski, A., Snavely, N.: Tracking everything everywhere all at once. In: International Conference on Computer Vision (2023)","DOI":"10.1109\/ICCV51070.2023.01813"},{"key":"22_CR54","unstructured":"Wang, S., Li, B.Z., Khabsa, M., Fang, H., Ma, H.: Linformer: Self-attention with linear complexity. arXiv e-prints pp. arXiv\u20132006 (2020)"},{"key":"22_CR55","doi-asserted-by":"crossref","unstructured":"Wang, W., Xie, E., Li, X., Fan, D.P., Song, K., Liang, D., Lu, T., Luo, P., Shao, L.: Pyramid vision transformer: A versatile backbone for dense prediction without convolutions. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 568\u2013578 (2021)","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"22_CR56","doi-asserted-by":"publisher","unstructured":"Wang, W., Xie, E., Li, X., Fan, D.P., Song, K., Liang, D., Lu, T., Luo, P., Shao, L.: PVT v2: Improved baselines with Pyramid Vision Transformer. Computational Visual Media 8(3), 415\u2013424 (Mar 2022https:\/\/doi.org\/10.1007\/s41095-022-0274-8, https:\/\/doi.org\/10.1007%2Fs41095-022-0274-8, publisher: Springer Science and Business Media LLC","DOI":"10.1007\/s41095-022-0274-8"},{"key":"22_CR57","doi-asserted-by":"crossref","unstructured":"Wang, W., Zhu, D., Wang, X., Hu, Y., Qiu, Y., Wang, C., Hu, Y., Kapoor, A., Scherer, S.: Tartanair: A dataset to push the limits of visual slam. In: 2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS). pp. 4909\u20134916. IEEE (2020)","DOI":"10.1109\/IROS45743.2020.9341801"},{"key":"22_CR58","doi-asserted-by":"crossref","unstructured":"Weinzaepfel, P., Revaud, J., Harchaoui, Z., Schmid, C.: DeepFlow: Large displacement optical flow with deep matching. In: Proceedings of the IEEE international conference on computer vision. pp. 1385\u20131392 (2013), 00000","DOI":"10.1109\/ICCV.2013.175"},{"key":"22_CR59","unstructured":"Wu, B., Xu, C., Dai, X., Wan, A., Zhang, P., Yan, Z., Tomizuka, M., Gonzalez, J., Keutzer, K., Vajda, P.: Visual transformers: Token-based image representation and processing for computer vision. arXiv e-prints pp. arXiv\u20132006 (2020)"},{"key":"22_CR60","unstructured":"Wu, C., Wu, F., Qi, T., Huang, Y., Xie, X.: Fastformer: Additive attention can be all you need. arXiv e-prints pp. arXiv\u20132108 (2021)"},{"key":"22_CR61","doi-asserted-by":"crossref","unstructured":"Wu, G., Liu, X., Luo, K., Liu, X., Zheng, Q., Liu, S., Jiang, X., Zhai, G., Wang, W.: Accflow: Backward accumulation for long-range optical flow. arXiv preprint arXiv:2308.13133 (2023)","DOI":"10.1109\/ICCV51070.2023.01113"},{"key":"22_CR62","doi-asserted-by":"crossref","unstructured":"Wulff, J., Butler, D.J., Stanley, G.B., Black, M.J.: Lessons and insights from creating a synthetic optical flow benchmark. In: A. Fusiello et al. (Eds.) (ed.) ECCV Workshop on Unsolved Problems in Optical Flow and Stereo Estimation. pp. 168\u2013177. Part II, LNCS 7584, Springer-Verlag (Oct 2012)","DOI":"10.1007\/978-3-642-33868-7_17"},{"key":"22_CR63","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), 00001","DOI":"10.1109\/ICCV48922.2021.01033"},{"key":"22_CR64","doi-asserted-by":"crossref","unstructured":"Xu, H., Zhang, J., Cai, J., Rezatofighi, H., Yu, F., Tao, D., Geiger, A.: Unifying flow, stereo and depth estimation. IEEE Transactions on Pattern Analysis and Machine Intelligence (2023)","DOI":"10.1109\/TPAMI.2023.3298645"},{"key":"22_CR65","doi-asserted-by":"crossref","unstructured":"Yoon, J., Kim, S., Kwak, S., Cho, M.: Optical flow domain adaptation via target style transfer. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision. pp. 2111\u20132121 (2024)","DOI":"10.1109\/WACV57701.2024.00211"},{"key":"22_CR66","doi-asserted-by":"crossref","unstructured":"Zhai, X., Kolesnikov, A., Houlsby, N., Beyer, L.: Scaling vision transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 12104\u201312113 (2022)","DOI":"10.1109\/CVPR52688.2022.01179"},{"key":"22_CR67","unstructured":"Zhang, H., Li, F., Rawlekar, S., Ahuja, N.: S3O: A Dual-Phase Approach for Reconstructing Dynamic Shape and Skeleton of Articulated Objects from Single Monocular Video. arXiv preprint arXiv:2405.12607 (2024)"},{"key":"22_CR68","doi-asserted-by":"crossref","unstructured":"Zhao, S., Zhao, L., Zhang, Z., Zhou, E., Metaxas, D.: Global Matching with Overlapping Attention for Optical Flow Estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 17592\u201317601 (2022)","DOI":"10.1109\/CVPR52688.2022.01707"},{"key":"22_CR69","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 (2023), _eprint: 2307.15055","DOI":"10.1109\/ICCV51070.2023.01818"},{"key":"22_CR70","doi-asserted-by":"crossref","unstructured":"Zheng, Z., Nie, N., Ling, Z., Xiong, P., Liu, J., Wang, H., Li, J.: DIP: Deep Inverse Patchmatch for High-Resolution Optical Flow. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 8925\u20138934 (2022)","DOI":"10.1109\/CVPR52688.2022.00872"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-0901-7_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,7]],"date-time":"2024-12-07T08:12:58Z","timestamp":1733559178000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-0901-7_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,8]]},"ISBN":["9789819609000","9789819609017"],"references-count":70,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-0901-7_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,8]]},"assertion":[{"value":"8 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hanoi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vietnam","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":"8 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}