{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T11:40:06Z","timestamp":1761824406347,"version":"3.40.3"},"publisher-location":"Cham","reference-count":47,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031226946"},{"type":"electronic","value":"9783031226953"}],"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.springernature.com\/gp\/researchers\/text-and-data-mining"},{"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.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-22695-3_3","type":"book-chapter","created":{"date-parts":[[2022,12,2]],"date-time":"2022-12-02T15:11:58Z","timestamp":1669993918000},"page":"29-42","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Diverse Audio-to-Video GAN using Multiscale Image Fusion"],"prefix":"10.1007","author":[{"given":"Nuha","family":"Aldausari","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arcot","family":"Sowmya","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nadine","family":"Marcus","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gelareh","family":"Mohammadi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,12,3]]},"reference":[{"key":"3_CR1","doi-asserted-by":"publisher","first-page":"1348","DOI":"10.1109\/TMI.2018.2827462","volume":"37","author":"Q Yang","year":"2018","unstructured":"Yang, Q., et al.: Low-dose CT image denoising using a generative adversarial network with Wasserstein distance and perceptual loss. IEEE Trans. Med. Imaging 37, 1348\u20131357 (2018)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"3_CR2","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 586\u2013595 (2018)","DOI":"10.1109\/CVPR.2018.00068"},{"key":"3_CR3","doi-asserted-by":"publisher","first-page":"63514","DOI":"10.1109\/ACCESS.2020.2982224","volume":"8","author":"L Wang","year":"2020","unstructured":"Wang, L., Chen, W., Yang, W., Bi, F., Yu, F.: A state-of-the-art review on image synthesis with generative adversarial networks. IEEE Access 8, 63514\u201363537 (2020)","journal-title":"IEEE Access"},{"key":"3_CR4","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. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"3_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3487891","volume":"55","author":"N Aldausari","year":"2022","unstructured":"Aldausari, N., Sowmya, A., Marcus, N., Mohammadi, G.: Video generative adversarial networks: a review. ACM Comput. Surv. (CSUR). 55, 1\u201325 (2022)","journal-title":"ACM Comput. Surv. (CSUR)."},{"key":"3_CR6","doi-asserted-by":"crossref","unstructured":"Hong, Y., Niu, L., Zhang, J., Zhang, L.: Matchinggan: matching-based few-shot image generation. In: 2020 IEEE International Conference on Multimedia And Expo (ICME), pp. 1\u20136 (2020)","DOI":"10.1109\/ICME46284.2020.9102917"},{"key":"3_CR7","unstructured":"Lee, J., Ramanan, D., Girdhar, R.: Metapix: few-shot video retargeting. ArXiv Preprint ArXiv:1910.04742 (2019)"},{"key":"3_CR8","doi-asserted-by":"crossref","unstructured":"Hong, Y., Niu, L., Zhang, J., Zhao, W., Fu, C., Zhang, L.: F2gan: fusing-and-filling gan for few-shot image generation. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 2535\u20132543 (2020)","DOI":"10.1145\/3394171.3413561"},{"key":"3_CR9","doi-asserted-by":"crossref","unstructured":"Gu, Z., Li, W., Huo, J., Wang, L., Gao, Y.: Lofgan: fusing local representations for few-shot image generation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8463\u20138471 (2021)","DOI":"10.1109\/ICCV48922.2021.00835"},{"key":"3_CR10","unstructured":"Bartunov, S., Vetrov, D.: Few-shot generative modelling with generative matching networks. In: International Conference on Artificial Intelligence and Statistics, pp. 670\u2013678 (2018)"},{"key":"3_CR11","doi-asserted-by":"publisher","first-page":"1332","DOI":"10.1126\/science.aab3050","volume":"350","author":"B Lake","year":"2015","unstructured":"Lake, B., Salakhutdinov, R., Tenenbaum, J.: Human-level concept learning through probabilistic program induction. Science 350, 1332\u20131338 (2015)","journal-title":"Science"},{"key":"3_CR12","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. Adv. Neural Inf. Process. Syst. 27 (2014)"},{"key":"3_CR13","unstructured":"Zhang, D., Khoreva, A.: Improving GAN training by progressive augmentation, PA-GAN (2018)"},{"key":"3_CR14","doi-asserted-by":"crossref","unstructured":"Ji, X., et al.: Audio-driven emotional video portraits. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14080\u201314089 (2021)","DOI":"10.1109\/CVPR46437.2021.01386"},{"key":"3_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1007\/978-3-030-58545-7_3","volume-title":"Computer Vision \u2013 ECCV 2020","author":"L Chen","year":"2020","unstructured":"Chen, L., et al.: Talking-head generation with rhythmic head motion. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12354, pp. 35\u201351. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58545-7_3"},{"key":"3_CR16","unstructured":"Song, L., Wu, W., Qian, C., He, R., Loy, C. Everybody\u2019s talkin: let me talk as you want. ArXiv Preprint ArXiv:2001.05201 (2020)"},{"key":"3_CR17","doi-asserted-by":"crossref","unstructured":"Lahiri, A., Kwatra, V., Frueh, C., Lewis, J., Bregler, C. LipSync3D: data-efficient learning of personalized 3D talking faces from video using pose and lighting normalization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2755\u20132764 (2021)","DOI":"10.1109\/CVPR46437.2021.00278"},{"key":"3_CR18","first-page":"1","volume":"39","author":"Y Zhou","year":"2020","unstructured":"Zhou, Y., Han, X., Shechtman, E., Echevarria, J., Kalogerakis, E., Li, D.: MakeltTalk: speaker-aware talking-head animation. ACM Trans. Graph. (TOG). 39, 1\u201315 (2020)","journal-title":"ACM Trans. Graph. (TOG)."},{"key":"3_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"408","DOI":"10.1007\/978-3-030-58577-8_25","volume-title":"Computer Vision \u2013 ECCV 2020","author":"D Das","year":"2020","unstructured":"Das, D., Biswas, S., Sinha, S., Bhowmick, B.: Speech-driven facial animation using cascaded GANs for learning of motion and texture. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12375, pp. 408\u2013424. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58577-8_25"},{"key":"3_CR20","doi-asserted-by":"crossref","unstructured":"Chen, L., Maddox, R., Duan, Z., Xu, C.: Hierarchical cross-modal talking face generation with dynamic pixel-wise loss. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7832\u20137841 (2019)","DOI":"10.1109\/CVPR.2019.00802"},{"key":"3_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"599","DOI":"10.1007\/978-3-030-86340-1_48","volume-title":"Artificial Neural Networks and Machine Learning \u2013 ICANN 2021","author":"N Aldausari","year":"2021","unstructured":"Aldausari, N., Sowmya, A., Marcus, N., Mohammadi, G.: PhonicsGAN: synthesizing graphical videos from phonics songs. In: Farka\u0161, I., Masulli, P., Otte, S., Wermter, S. (eds.) ICANN 2021. LNCS, vol. 12892, pp. 599\u2013610. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86340-1_48"},{"key":"3_CR22","doi-asserted-by":"publisher","first-page":"660","DOI":"10.23919\/TST.2017.8195348","volume":"22","author":"X Wu","year":"2017","unstructured":"Wu, X., Xu, K., Hall, P.: A survey of image synthesis and editing with generative adversarial networks. Tsinghua Sci. Technol. 22, 660\u2013674 (2017)","journal-title":"Tsinghua Sci. Technol."},{"key":"3_CR23","doi-asserted-by":"crossref","unstructured":"Zhou, H., Liu, Y., Liu, Z., Luo, P., Wang, X.: Talking face generation by adversarially disentangled audio-visual representation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 9299\u20139306 (2019)","DOI":"10.1609\/aaai.v33i01.33019299"},{"key":"3_CR24","doi-asserted-by":"crossref","unstructured":"Mittal, G., Wang, B.: Animating face using disentangled audio representations. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 3290\u20133298 (2020)","DOI":"10.1109\/WACV45572.2020.9093527"},{"key":"3_CR25","doi-asserted-by":"crossref","unstructured":"Cao, Q., Shen, L., Xie, W., Parkhi, O., Zisserman, A.: Vggface2: a dataset for recognising faces across pose and age. In: 2018 13th IEEE International Conference On Automatic Face & Gesture Recognition (FG 2018), pp. 67\u201374 (2018)","DOI":"10.1109\/FG.2018.00020"},{"key":"3_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1007\/978-3-642-01793-3_21","volume-title":"Advances in Biometrics","author":"C Sanderson","year":"2009","unstructured":"Sanderson, C., Lovell, B.C.: Multi-region probabilistic histograms for robust and scalable identity inference. In: Tistarelli, M., Nixon, M.S. (eds.) ICB 2009. LNCS, vol. 5558, pp. 199\u2013208. Springer, Heidelberg (2009). https:\/\/doi.org\/10.1007\/978-3-642-01793-3_21"},{"key":"3_CR27","doi-asserted-by":"crossref","unstructured":"Nilsback, M., Zisserman, A.: Automated flower classification over a large number of classes. In: 2008 Sixth Indian Conference On Computer Vision, Graphics Image Processing, pp. 722\u2013729 (2008)","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"3_CR28","doi-asserted-by":"crossref","unstructured":"Liu, M., et al.: Few-shot unsupervised image-to-image translation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10551\u201310560 (2019)","DOI":"10.1109\/ICCV.2019.01065"},{"key":"3_CR29","unstructured":"Tsuchiya, Y., Itazuri, T.: Others generating video from single image and sound. In: CVPR Workshops, pp. 17\u201320 (2019)"},{"key":"3_CR30","unstructured":"Arjovsky, M., Bottou, L.: Towards principled methods for training generative adversarial networks. ArXiv Preprint ArXiv:1701.04862 (2017)"},{"key":"3_CR31","first-page":"12104","volume":"33","author":"T Karras","year":"2020","unstructured":"Karras, T., Aittala, M., Hellsten, J., Laine, S., Lehtinen, J., Aila, T.: Training generative adversarial networks with limited data. Adv. Neural Inf. Process. Syst. 33, 12104\u201312114 (2020)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"3_CR32","doi-asserted-by":"crossref","unstructured":"Wang, Y., Bilinski, P., Bremond, F., Dantcheva, A.: Imaginator: conditional spatio-temporal gan for video generation. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 1160\u20131169 (2020)","DOI":"10.1109\/WACV45572.2020.9093492"},{"key":"3_CR33","doi-asserted-by":"crossref","unstructured":"Wang, Y., Gonzalez-Garcia, A., Berga, D., Herranz, L., Khan, F., Weijer, J. Minegan: effective knowledge transfer from gans to target domains with few images. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9332\u20139341 (2020)","DOI":"10.1109\/CVPR42600.2020.00935"},{"key":"3_CR34","doi-asserted-by":"crossref","unstructured":"Tulyakov, S., Liu, M., et al.: Mocogan: decomposing motion and content for video generation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1526\u20131535 (2018)","DOI":"10.1109\/CVPR.2018.00165"},{"key":"3_CR35","doi-asserted-by":"crossref","unstructured":"Wang, Y., Bilinski, P., Bremond, F., Dantcheva, A.: G3AN: disentangling appearance and motion for video generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5264\u20135273 (2020)","DOI":"10.1109\/CVPR42600.2020.00531"},{"key":"3_CR36","unstructured":"Babaeizadeh, M., et al.: FitVid: overfitting in pixel-level video prediction. ArXiv Preprint ArXiv:2106.13195 (2021)"},{"key":"3_CR37","doi-asserted-by":"crossref","unstructured":"Shahriar, S.: GAN computers generate arts? a survey on visual arts, music, and literary text generation using generative adversarial network. Displays, 102237 (2022)","DOI":"10.1016\/j.displa.2022.102237"},{"key":"3_CR38","doi-asserted-by":"crossref","unstructured":"Yi, X., Walia, E., Babyn, P.: Generative adversarial network in medical imaging: a review. Med. Image Anal. 58, 101552 (2019)","DOI":"10.1016\/j.media.2019.101552"},{"key":"3_CR39","doi-asserted-by":"publisher","first-page":"1175","DOI":"10.1016\/j.acra.2019.12.024","volume":"27","author":"V Sorin","year":"2020","unstructured":"Sorin, V., Barash, Y., Konen, E., Klang, E.: Creating artificial images for radiology applications using generative adversarial networks (GANs)-a systematic review. Acad. Radiol. 27, 1175\u20131185 (2020)","journal-title":"Acad. Radiol."},{"key":"3_CR40","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"256","DOI":"10.1007\/978-3-030-58592-1_16","volume-title":"Computer Vision \u2013 ECCV 2020","author":"E Logacheva","year":"2020","unstructured":"Logacheva, E., Suvorov, R., Khomenko, O., Mashikhin, A., Lempitsky, V.: DeepLandscape: adversarial modeling of landscape videos. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12368, pp. 256\u2013272. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58592-1_16"},{"key":"3_CR41","doi-asserted-by":"crossref","unstructured":"Noguchi, A., Harada, T.: Image generation from small datasets via batch statistics adaptation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2750\u20132758 (2019)","DOI":"10.1109\/ICCV.2019.00284"},{"key":"3_CR42","doi-asserted-by":"crossref","unstructured":"Bansal, A., Ma, S., Ramanan, D., Sheikh, Y.: Recycle-gan: Unsupervised video retargeting. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 119\u2013135 (2018)","DOI":"10.1007\/978-3-030-01228-1_8"},{"key":"3_CR43","doi-asserted-by":"publisher","first-page":"16517","DOI":"10.1007\/s11042-019-7556-x","volume":"79","author":"Y Zhong","year":"2020","unstructured":"Zhong, Y., Liu, L., Zhao, D., Li, H.: A generative adversarial network for image denoising. Multimedia Tools Appl. 79, 16517\u201316529 (2020)","journal-title":"Multimedia Tools Appl."},{"key":"3_CR44","doi-asserted-by":"crossref","unstructured":"Jo, Y., Park, J.: Sc-fegan: face editing generative adversarial network with user\u2019s sketch and color. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1745\u20131753 (2019)","DOI":"10.1109\/ICCV.2019.00183"},{"key":"3_CR45","doi-asserted-by":"crossref","unstructured":"Aldausari, N., Sowmya, A., Marcus, N., Mohammadi, G.: Cascaded siamese self-supervised audio to video GAN. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4691\u20134700 (2022)","DOI":"10.1109\/CVPRW56347.2022.00515"},{"key":"3_CR46","unstructured":"Robb, E., Chu, W., Kumar, A., Huang, J.: Few-shot adaptation of generative adversarial networks. ArXiv Preprint ArXiv:2010.11943. (2020)"},{"key":"3_CR47","unstructured":"Phonics Dataset. github.com\/NuhaAldausari\/Cascaded-Siamese-Selfsupervised-Audio-to-Video-GAN. Accessed 2 Oct 2022"}],"container-title":["Lecture Notes in Computer Science","AI 2022: Advances in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-22695-3_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T15:21:17Z","timestamp":1710256877000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-22695-3_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031226946","9783031226953"],"references-count":47,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-22695-3_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"3 December 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"AI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australasian Joint Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Perth, WA","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","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":"5 December 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 December 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"35","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ausai2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ajcai2022.org\/","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":"Easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"90","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":"56","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":"62% - 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","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","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)"}}]}}