{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T10:26:29Z","timestamp":1780395989214,"version":"3.54.1"},"publisher-location":"Cham","reference-count":59,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031197895","type":"print"},{"value":"9783031197901","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-19790-1_7","type":"book-chapter","created":{"date-parts":[[2022,10,23]],"date-time":"2022-10-23T11:02:44Z","timestamp":1666522964000},"page":"102-118","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":119,"title":["Long Video Generation with\u00a0Time-Agnostic VQGAN and\u00a0Time-Sensitive Transformer"],"prefix":"10.1007","author":[{"given":"Songwei","family":"Ge","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thomas","family":"Hayes","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Harry","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xi","family":"Yin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guan","family":"Pang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Jacobs","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jia-Bin","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Devi","family":"Parikh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,10,24]]},"reference":[{"key":"7_CR1","unstructured":"Acharya, D., Huang, Z., Paudel, D.P., Van Gool, L.: Towards high resolution video generation with progressive growing of sliced Wasserstein GANs. arXiv preprint arXiv:1810.02419 (2018)"},{"key":"7_CR2","unstructured":"Alsallakh, B., Kokhlikyan, N., Miglani, V., Yuan, J., Reblitz-Richardson, O.: Mind the pad - CNNs can develop blind spots. In: ICLR (2021)"},{"key":"7_CR3","unstructured":"Brock, A., Donahue, J., Simonyan, K.: Large scale GAN training for high fidelity natural image synthesis. In: ICLR (2018)"},{"key":"7_CR4","unstructured":"Brooks, T., et al.: Generating long videos of dynamic scenes. arXiv preprint arXiv:2206.03429 (2022)"},{"key":"7_CR5","unstructured":"Brown, T., et al.: Language models are few-shot learners. In: NeurIPS (2020)"},{"key":"7_CR6","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo Vadis, action recognition? A new model and the kinetics dataset. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"7_CR7","unstructured":"Castrejon, L., Ballas, N., Courville, A.: Hierarchical video generation for complex data. arXiv preprint arXiv:2106.02719 (2021)"},{"key":"7_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"701","DOI":"10.1007\/978-3-030-58583-9_42","volume-title":"Computer Vision \u2013 ECCV 2020","author":"M Chatterjee","year":"2020","unstructured":"Chatterjee, M., Cherian, A.: Sound2Sight: generating visual dynamics from sound and context. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12372, pp. 701\u2013719. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58583-9_42"},{"key":"7_CR9","unstructured":"Clark, A., Donahue, J., Simonyan, K.: Adversarial video generation on complex datasets. arXiv preprint arXiv:1907.06571 (2019)"},{"key":"7_CR10","doi-asserted-by":"crossref","unstructured":"Esser, P., Rombach, R., Ommer, B.: Taming transformers for high-resolution image synthesis. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"7_CR11","doi-asserted-by":"crossref","unstructured":"Fan, A., Lewis, M., Dauphin, Y.: Hierarchical neural story generation (2018)","DOI":"10.18653\/v1\/P18-1082"},{"key":"7_CR12","doi-asserted-by":"crossref","unstructured":"Gemmeke, J.F., et al.: Audio set: an ontology and human-labeled dataset for audio events. In: ICASSP (2017)","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"7_CR13","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: NeurIPS (2014)"},{"key":"7_CR14","doi-asserted-by":"crossref","unstructured":"Hayes, T., et al.: MUGEN: a playground for video-audio-text multimodal understanding and generation. arXiv preprint arXiv:2204.08058 (2022)","DOI":"10.1007\/978-3-031-20074-8_25"},{"key":"7_CR15","unstructured":"Ho, J., Salimans, T., Gritsenko, A., Chan, W., Norouzi, M., Fleet, D.J.: Video diffusion models. arXiv preprint arXiv:2204.03458 (2022)"},{"key":"7_CR16","unstructured":"Hong, W., Ding, M., Zheng, W., Liu, X., Tang, J.: CogVideo: large-scale pretraining for text-to-video generation via transformers. arXiv preprint arXiv:2205.15868 (2022)"},{"key":"7_CR17","unstructured":"Islam, M.A., Jia, S., Bruce, N.D.: How much position information do convolutional neural networks encode? In: ICLR (2019)"},{"key":"7_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"694","DOI":"10.1007\/978-3-319-46475-6_43","volume-title":"Computer Vision \u2013 ECCV 2016","author":"J Johnson","year":"2016","unstructured":"Johnson, J., Alahi, A., Fei-Fei, L.: Perceptual losses for real-time style transfer and super-resolution. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 694\u2013711. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46475-6_43"},{"key":"7_CR19","doi-asserted-by":"publisher","first-page":"506","DOI":"10.1016\/j.neunet.2020.09.016","volume":"132","author":"E Kahembwe","year":"2020","unstructured":"Kahembwe, E., Ramamoorthy, S.: Lower dimensional kernels for video discriminators. Neural Netw. 132, 506\u2013520 (2020)","journal-title":"Neural Netw."},{"key":"7_CR20","unstructured":"Kalchbrenner, N., et al.: Video pixel networks. In: ICML (2017)"},{"key":"7_CR21","unstructured":"Karras, T., et al.: Alias-free generative adversarial networks. In: NeurIPS (2021)"},{"key":"7_CR22","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00453"},{"key":"7_CR23","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., Aila, T.: Analyzing and improving the image quality of StyleGAN. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"7_CR24","unstructured":"Kayhan, O.S., van Gemert, J.C.: On translation invariance in CNNs: convolutional layers can exploit absolute spatial location. In: CVPR (2020)"},{"key":"7_CR25","unstructured":"Le Moing, G., Ponce, J., Schmid, C.: CCVS: context-aware controllable video synthesis. In: NeurIPS (2021)"},{"key":"7_CR26","unstructured":"Luc, P., et al.: Transformation-based adversarial video prediction on large-scale data. arXiv preprint arXiv:2003.04035 (2020)"},{"key":"7_CR27","doi-asserted-by":"crossref","unstructured":"Munoz, A., Zolfaghari, M., Argus, M., Brox, T.: Temporal shift GAN for large scale video generation. In: WACV (2021)","DOI":"10.1109\/WACV48630.2021.00322"},{"key":"7_CR28","unstructured":"Nash, C., et al.: Transframer: arbitrary frame prediction with generative models. arXiv preprint arXiv:2203.09494 (2022)"},{"key":"7_CR29","unstructured":"van den Oord, A., Vinyals, O., Kavukcuoglu, K.: Neural discrete representation learning. In: NeurIPS (2017)"},{"key":"7_CR30","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"key":"7_CR31","unstructured":"Radford, A., Narasimhan, K., Salimans, T., Sutskever, I.: Improving language understanding by generative pre-training (2018)"},{"key":"7_CR32","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I.: Language models are unsupervised multitask learners (2019)"},{"key":"7_CR33","doi-asserted-by":"crossref","unstructured":"Rakhimov, R., Volkhonskiy, D., Artemov, A., Zorin, D., Burnaev, E.: Latent video transformer. arXiv preprint arXiv:2006.10704 (2020)","DOI":"10.5220\/0010241801010112"},{"key":"7_CR34","unstructured":"Ramesh, A., et al.: Zero-shot text-to-image generation. arXiv preprint arXiv:2102.12092 (2021)"},{"key":"7_CR35","unstructured":"Ranzato, M., Szlam, A., Bruna, J., Mathieu, M., Collobert, R., Chopra, S.: Video (language) modeling: a baseline for generative models of natural videos. arXiv preprint arXiv:1412.6604 (2014)"},{"key":"7_CR36","doi-asserted-by":"crossref","unstructured":"Saito, M., Matsumoto, E., Saito, S.: Temporal generative adversarial nets with singular value clipping. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.308"},{"issue":"10","key":"7_CR37","doi-asserted-by":"publisher","first-page":"2586","DOI":"10.1007\/s11263-020-01333-y","volume":"128","author":"M Saito","year":"2020","unstructured":"Saito, M., Saito, S., Koyama, M., Kobayashi, S.: Train sparsely, generate densely: memory-efficient unsupervised training of high-resolution temporal GAN. Int. J. Comput. Vis. 128(10), 2586\u20132606 (2020). https:\/\/doi.org\/10.1007\/s11263-020-01333-y","journal-title":"Int. J. Comput. Vis."},{"key":"7_CR38","unstructured":"Siarohin, A., Lathuili\u00e8re, S., Tulyakov, S., Ricci, E., Sebe, N.: First order motion model for image animation. In: NeurIPS (2019)"},{"key":"7_CR39","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"7_CR40","unstructured":"Sitzmann, V., Martel, J., Bergman, A., Lindell, D., Wetzstein, G.: Implicit neural representations with periodic activation functions. In: NeurIPS (2020)"},{"key":"7_CR41","doi-asserted-by":"crossref","unstructured":"Skorokhodov, I., Tulyakov, S., Elhoseiny, M.: StyleGAN-V: a continuous video generator with the price, image quality and perks of StyleGAN2. arXiv preprint arXiv:2112.14683 (2021)","DOI":"10.1109\/CVPR52688.2022.00361"},{"key":"7_CR42","unstructured":"Soomro, K., Zamir, A.R., Shah, M.: UCF101: a dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:1212.0402 (2012)"},{"key":"7_CR43","unstructured":"Srivastava, N., Mansimov, E., Salakhudinov, R.: Unsupervised learning of video representations using LSTMs. In: ICML (2015)"},{"key":"7_CR44","unstructured":"Tancik, M., et al.: Fourier features let networks learn high frequency functions in low dimensional domains. In: NeurIPS (2020)"},{"key":"7_CR45","unstructured":"Tian, Y., et al.: A good image generator is what you need for high-resolution video synthesis. In: ICLR (2021)"},{"key":"7_CR46","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3D convolutional networks. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"7_CR47","doi-asserted-by":"crossref","unstructured":"Tulyakov, S., Liu, M.Y., Yang, X., Kautz, J.: MoCoGAN: decomposing motion and content for video generation. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00165"},{"key":"7_CR48","unstructured":"Unterthiner, T., van Steenkiste, S., Kurach, K., Marinier, R., Michalski, M., Gelly, S.: Towards accurate generative models of video: a new metric & challenges. In: ICLR (2019)"},{"key":"7_CR49","unstructured":"Vondrick, C., Pirsiavash, H., Torralba, A.: Generating videos with scene dynamics. In: NeurIPS (2016)"},{"key":"7_CR50","unstructured":"Wang, T.C., et al.: Video-to-video synthesis. In: NeurIPS (2018)"},{"key":"7_CR51","doi-asserted-by":"crossref","unstructured":"Wang, T.C., Liu, M.Y., Zhu, J.Y., Tao, A., Kautz, J., Catanzaro, B.: High-resolution image synthesis and semantic manipulation with conditional GANs. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00917"},{"key":"7_CR52","unstructured":"Weissenborn, D., T\u00e4ckstr\u00f6m, O., Uszkoreit, J.: Scaling autoregressive video models. In: ICLR (2020)"},{"key":"7_CR53","unstructured":"Wu, C., et al.: GODIVA: generating open-domain videos from natural descriptions. arXiv preprint arXiv:2104.14806 (2021)"},{"key":"7_CR54","doi-asserted-by":"crossref","unstructured":"Wu, C., et al.: N\u00dcWA: visual synthesis pre-training for neural visual world creation. arXiv preprint arXiv:2111.12417 (2021)","DOI":"10.1007\/978-3-031-19787-1_41"},{"key":"7_CR55","doi-asserted-by":"crossref","unstructured":"Xiong, W., Luo, W., Ma, L., Liu, W., Luo, J.: Learning to generate time-lapse videos using multi-stage dynamic generative adversarial networks. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00251"},{"key":"7_CR56","doi-asserted-by":"crossref","unstructured":"Xu, R., Wang, X., Chen, K., Zhou, B., Loy, C.C.: Positional encoding as spatial inductive bias in GANs. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01336"},{"key":"7_CR57","unstructured":"Yan, W., Zhang, Y., Abbeel, P., Srinivas, A.: VideoGPT: cideo generation using VQ-VAE and transformers. arXiv preprint arXiv:2104.10157 (2021)"},{"key":"7_CR58","unstructured":"Yu, S., et al.: Generating videos with dynamics-aware implicit generative adversarial networks. In: ICLR (2021)"},{"key":"7_CR59","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"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-19790-1_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T14:58:59Z","timestamp":1710255539000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19790-1_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031197895","9783031197901"],"references-count":59,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19790-1_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"24 October 2022","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":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","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":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1645","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"28% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.21","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.91","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}