{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T10:06:11Z","timestamp":1789207571655,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":66,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032373342","type":"print"},{"value":"9783032373359","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-37335-9_29","type":"book-chapter","created":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T09:13:21Z","timestamp":1789204401000},"page":"529-547","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Seeing Fast and\u00a0Slow: Learning the\u00a0Flow of\u00a0Time in\u00a0Videos"],"prefix":"10.1007","author":[{"given":"Yen-Siang","family":"Wu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rundong","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingsen","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tao","family":"Tu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ali","family":"Farhadi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthew","family":"Wallingford","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu-Chiang Frank","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Steve","family":"Marschner","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei-Chiu","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,13]]},"reference":[{"key":"29_CR1","unstructured":"Azzolini, A., et al.: Cosmos-reason1: from physical common sense to embodied reasoning. arXiv:2503.15558 (2025)"},{"key":"29_CR2","doi-asserted-by":"crossref","unstructured":"Bagad, P., Tapaswi, M., Snoek, C.G.: Test of time: instilling video-language models with a sense of time. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00247"},{"key":"29_CR3","doi-asserted-by":"crossref","unstructured":"Bahmani, S., et al.: AC3D: analyzing and improving 3D camera control in video diffusion transformers. In: CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.02130"},{"key":"29_CR4","unstructured":"Bai, S., et\u00a0al.: Qwen2. 5-VL technical report. arXiv:2502.13923 (2025)"},{"key":"29_CR5","doi-asserted-by":"crossref","unstructured":"Bain, M., Nagrani, A., Varol, G., Zisserman, A.: Frozen in time: a joint video and image encoder for end-to-end retrieval. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"29_CR6","doi-asserted-by":"crossref","unstructured":"Benaim, S., et al.: SpeedNet: learning the speediness in videos. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00994"},{"key":"29_CR7","unstructured":"Blattmann, A., et al.: Stable video diffusion: scaling latent video diffusion models to large datasets. arXiv:2311.15127 (2023)"},{"key":"29_CR8","doi-asserted-by":"crossref","unstructured":"Brooks, T., Barron, J.T.: Learning to synthesize motion blur. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00700"},{"key":"29_CR9","doi-asserted-by":"crossref","unstructured":"Burgert, R., et al.: Go-with-the-flow: motion-controllable video diffusion models using real-time warped noise. In: CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.00011"},{"key":"29_CR10","unstructured":"Chen, J., Jiang, H.: SportsSloMo: a new benchmark and baselines for human-centric video frame interpolation. arXiv:2308.16876 (2023)"},{"key":"29_CR11","doi-asserted-by":"crossref","unstructured":"Chen, T.S., et al.: Panda-70M: captioning 70M videos with multiple cross-modality teachers. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01265"},{"key":"29_CR12","unstructured":"Comanici, G., et al.: Gemini 2.5: pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities. arXiv:2507.06261 (2025)"},{"key":"29_CR13","doi-asserted-by":"crossref","unstructured":"Danier, D., Zhang, F., Bull, D.: FloLPIPS: a bespoke video quality metric for frame interpolation. In: Picture Coding Symposium (2022)","DOI":"10.1109\/PCS56426.2022.10018062"},{"key":"29_CR14","doi-asserted-by":"crossref","unstructured":"Danier, D., Zhang, F., Bull, D.: LDMVFI: video frame interpolation with latent diffusion models. In: AAAI (2024)","DOI":"10.1609\/aaai.v38i2.27912"},{"key":"29_CR15","doi-asserted-by":"crossref","unstructured":"Ding, X., Wang, L.: Do language models understand time? In: ACM WWW (2025)","DOI":"10.1145\/3701716.3717744"},{"key":"29_CR16","doi-asserted-by":"crossref","unstructured":"Dorkenwald, M., Xiao, F., Brattoli, B., Tighe, J., Modolo, D.: SCVRL: shuffled contrastive video representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4132\u20134141 (2022)","DOI":"10.1109\/CVPRW56347.2022.00458"},{"key":"29_CR17","doi-asserted-by":"crossref","unstructured":"Du, Y., Liu, Y., Jin, Q.: Reversed in time: a novel temporal-emphasized benchmark for cross-modal video-text retrieval. In: ACM MM (2024)","DOI":"10.1145\/3664647.3680731"},{"key":"29_CR18","doi-asserted-by":"crossref","unstructured":"Feng, H., et al.: Explorative inbetweening of time and space. In: ECCV (2024)","DOI":"10.1007\/978-3-031-73229-4_22"},{"key":"29_CR19","unstructured":"Gao, X., et al.: The pulse of motion: measuring physical frame rate from visual dynamics. arXiv preprint arXiv:2603.14375 (2026)"},{"key":"29_CR20","unstructured":"Ghodrati, A., Gavves, E., Snoek, C.G.: Video time: properties, encoders and evaluation. arXiv preprint arXiv:1807.06980 (2018)"},{"key":"29_CR21","doi-asserted-by":"crossref","unstructured":"He, C., Zheng, Q., Zhu, R., Zeng, X., Fan, Y., Tu, Z.: Cover: a comprehensive video quality evaluator. In: CVPRW (2024)","DOI":"10.1109\/CVPRW63382.2024.00589"},{"key":"29_CR22","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: GANs trained by a two time-scale update rule converge to a local nash equilibrium. In: NeurIPS (2017)"},{"key":"29_CR23","unstructured":"Huang, Z., et al.: SpaceTimePilot: generative rendering of dynamic scenes across space and time. arXiv:2512.25075 (2025)"},{"key":"29_CR24","doi-asserted-by":"crossref","unstructured":"Huang, Z., Zhang, T., Heng, W., Shi, B., Zhou, S.: Real-time intermediate flow estimation for video frame interpolation. In: ECCV (2022)","DOI":"10.1007\/978-3-031-19781-9_36"},{"key":"29_CR25","doi-asserted-by":"crossref","unstructured":"Jain, S., Watson, D., Tabellion, E., Poole, B., Kontkanen, J.: Video interpolation with diffusion models. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00701"},{"key":"29_CR26","doi-asserted-by":"crossref","unstructured":"Jiang, H., Sun, D., Jampani, V., Yang, M.H., Learned-Miller, E., Kautz, J.: Super slomo: high quality estimation of multiple intermediate frames for video interpolation. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00938"},{"key":"29_CR27","doi-asserted-by":"crossref","unstructured":"Jiang, Z., Han, Z., Mao, C., Zhang, J., Pan, Y., Liu, Y.: VACE: all-in-one video creation and editing. In: ICCV (2025)","DOI":"10.1109\/ICCV51701.2025.01597"},{"key":"29_CR28","doi-asserted-by":"crossref","unstructured":"Karaev, N., Makarov, Y., Wang, J., Neverova, N., Vedaldi, A., Rupprecht, C.: CoTracker3: simpler and better point tracking by pseudo-labelling real videos. In: ICCV (2025)","DOI":"10.1109\/ICCV51701.2025.00568"},{"key":"29_CR29","doi-asserted-by":"crossref","unstructured":"Kiani\u00a0Galoogahi, H., Fagg, A., Huang, C., Ramanan, D., Lucey, S.: Need for speed: a benchmark for higher frame rate object tracking. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.128"},{"key":"29_CR30","doi-asserted-by":"crossref","unstructured":"Lee, H.Y., Huang, J.B., Singh, M., Yang, M.H.: Unsupervised representation learning by sorting sequences. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 667\u2013676 (2017)","DOI":"10.1109\/ICCV.2017.79"},{"key":"29_CR31","unstructured":"Li, K., et al.: VideoChat: chat-centric video understanding. arXiv:2305.06355 (2023)"},{"key":"29_CR32","doi-asserted-by":"crossref","unstructured":"Lin, B., et al.: Video-LLaVA: learning united visual representation by alignment before projection. In: EMNLP (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"29_CR33","doi-asserted-by":"crossref","unstructured":"Liu, Z., Yeh, R.A., Tang, X., Liu, Y., Agarwala, A.: Video frame synthesis using deep voxel flow. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.478"},{"key":"29_CR34","doi-asserted-by":"crossref","unstructured":"Luo, R., Wallingford, M., Farhadi, A., Snavely, N., Ma, W.C.: Beyond the frame: generating 360$$^{\\circ }$$ panoramic videos from perspective videos. In: ICCV (2025)","DOI":"10.1109\/ICCV51701.2025.01330"},{"key":"29_CR35","doi-asserted-by":"crossref","unstructured":"Mercat, A., Viitanen, M., Vanne, J.: UVG dataset: 50\/120fps 4K sequences for video codec analysis and development. In: Proceedings of the 11th ACM Multimedia Systems Conference, pp. 297\u2013302 (2020)","DOI":"10.1145\/3339825.3394937"},{"key":"29_CR36","doi-asserted-by":"publisher","unstructured":"Misra, I., Zitnick, C.L., Hebert, M.: Shuffle and learn: unsupervised learning using temporal order verification. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds) European Conference on Computer Vision, pp. 527\u2013544. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_32","DOI":"10.1007\/978-3-319-46448-0_32"},{"key":"29_CR37","doi-asserted-by":"crossref","unstructured":"Nah, S., Hyun\u00a0Kim, T., Mu\u00a0Lee, K.: Deep multi-scale convolutional neural network for dynamic scene deblurring. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.35"},{"key":"29_CR38","unstructured":"Nan, K., et al.: OpenVid-1M: a large-scale high-quality dataset for text-to-video generation. arXiv:2407.02371 (2024)"},{"key":"29_CR39","doi-asserted-by":"crossref","unstructured":"Niklaus, S., Mai, L., Liu, F.: Video frame interpolation via adaptive convolution. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.244"},{"key":"29_CR40","doi-asserted-by":"crossref","unstructured":"Perazzi, F., Pont-Tuset, J., McWilliams, B., Van Gool, L., Gross, M., Sorkine-Hornung, A.: A benchmark dataset and evaluation methodology for video object segmentation. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.85"},{"key":"29_CR41","doi-asserted-by":"crossref","unstructured":"Pickup, L.C., et al.: Seeing the arrow of time. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.262"},{"key":"29_CR42","doi-asserted-by":"crossref","unstructured":"Reda, F., Kontkanen, J., Tabellion, E., Sun, D., Pantofaru, C., Curless, B.: Film: frame interpolation for large motion. In: ECCV (2022)","DOI":"10.1007\/978-3-031-20071-7_15"},{"key":"29_CR43","doi-asserted-by":"crossref","unstructured":"Sim, H., Oh, J., Kim, M.: XVFI: extreme video frame interpolation. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01422"},{"key":"29_CR44","doi-asserted-by":"crossref","unstructured":"Song, E., et\u00a0al.: MovieChat: from dense token to sparse memory for long video understanding. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01725"},{"key":"29_CR45","doi-asserted-by":"crossref","unstructured":"Soucek, T., Lokoc, J.: TransNet v2: an effective deep network architecture for fast shot transition detection. In: ACM MM (2024)","DOI":"10.1145\/3664647.3685517"},{"key":"29_CR46","doi-asserted-by":"crossref","unstructured":"Steinhof, V., Schroeger, A., Liepelt, R., Sperl, L.: Time and video speed perception: a comprehensive investigation of the relation between estimated video speed, clip duration and original duration: V. Steinhof et al. Cognitive Research: Principles and Implications (2025)","DOI":"10.1186\/s41235-025-00637-2"},{"key":"29_CR47","doi-asserted-by":"crossref","unstructured":"Su, S., Delbracio, M., Wang, J., Sapiro, G., Heidrich, W., Wang, O.: Deep video deblurring for hand-held cameras. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.33"},{"key":"29_CR48","unstructured":"Truong, C., Oudre, L., Vayatis, N.: ruptures: change point detection in Python. arXiv preprint arXiv:1801.00826 (2018)"},{"key":"29_CR49","unstructured":"Unterthiner, T., Van Steenkiste, S., Kurach, K., Marinier, R., Michalski, M., Gelly, S.: FVD: a new metric for video generation. In: ICLRW (2019)"},{"key":"29_CR50","unstructured":"Wan, T., et\u00a0al.: Wan: open and advanced large-scale video generative models. arXiv:2503.20314 (2025)"},{"key":"29_CR51","unstructured":"Wang, A., Huang, H., Fang, Z., Yang, Y., Ma, C.: ATI: any trajectory instruction for controllable video generation. arXiv:2505.22944 (2025)"},{"key":"29_CR52","doi-asserted-by":"crossref","unstructured":"Wang, J., Jiao, J., Liu, Y.H.: Self-supervised video representation learning by pace prediction. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58520-4_30"},{"key":"29_CR53","doi-asserted-by":"crossref","unstructured":"Wang, L., et al.: VideoMAE V2: scaling video masked autoencoders with dual masking. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01398"},{"key":"29_CR54","unstructured":"Wang, X., Zhou, B., Curless, B., Kemelmacher-Shlizerman, I., Holynski, A., Seitz, S.M.: Generative inbetweening: adapting image-to-video models for keyframe interpolation. In: ICLR (2024)"},{"key":"29_CR55","unstructured":"Wang, Y., et\u00a0al.: InternVid: a large-scale video-text dataset for multimodal understanding and generation. arXiv:2307.06942 (2023)"},{"key":"29_CR56","doi-asserted-by":"publisher","unstructured":"Wang, Y., Lipson, L., Deng, J.: SEA-RAFT: simple, efficient, accurate RAFT for optical flow. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds) Computer Vision \u2013 ECCV 2024. ECCV 2024. Lecture Notes in Computer Science, vol. 15065. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-72667-5_3","DOI":"10.1007\/978-3-031-72667-5_3"},{"key":"29_CR57","unstructured":"Wang, Y., et al.: BulletTime: decoupled control of time and camera pose for video generation. arXiv:2512.05076 (2025)"},{"key":"29_CR58","doi-asserted-by":"crossref","unstructured":"Wang, Z., et al.: Paxion: Patching action knowledge in video-language foundation models. In: NeurIPS (2023)","DOI":"10.52202\/075280-0910"},{"key":"29_CR59","doi-asserted-by":"crossref","unstructured":"Wang, Z., et al.: MotionCtrl: a unified and flexible motion controller for video generation. In: SIGGRAPH (2024)","DOI":"10.1145\/3641519.3657518"},{"key":"29_CR60","doi-asserted-by":"crossref","unstructured":"Wei, D., Lim, J.J., Zisserman, A., Freeman, W.T.: Learning and using the arrow of time. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00840"},{"key":"29_CR61","doi-asserted-by":"crossref","unstructured":"Xiang, X., Tian, Y., Zhang, Y., Fu, Y., Allebach, J.P., Xu, C.: Zooming Slow-Mo: fast and accurate one-stage space-time video super-resolution. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00343"},{"key":"29_CR62","doi-asserted-by":"crossref","unstructured":"Xue, Z., Luo, M., Grauman, K.: Seeing the arrow of time in large multimodal models. arXiv preprint arXiv:2506.03340 (2025)","DOI":"10.52202\/085713-3041"},{"key":"29_CR63","doi-asserted-by":"crossref","unstructured":"Yao, Y., Liu, C., Luo, D., Zhou, Y., Ye, Q.: Video playback rate perception for self-supervised spatio-temporal representation learning. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00658"},{"key":"29_CR64","doi-asserted-by":"crossref","unstructured":"Ye, M., Zhang, J., Zhao, S., Liu, J., Du, B., Tao, D.: DPText-DETR: towards better scene text detection with dynamic points in transformer. In: AAAI (2023)","DOI":"10.1609\/aaai.v37i3.25430"},{"key":"29_CR65","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00068"},{"key":"29_CR66","unstructured":"Zhu, J., et al.: InternVL3: exploring advanced training and test-time recipes for open-source multimodal models. arXiv:2504.10479 (2025)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37335-9_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T09:13:38Z","timestamp":1789204418000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37335-9_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032373342","9783032373359"],"references-count":66,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37335-9_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"13 September 2026","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":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}