{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T15:19:38Z","timestamp":1742915978487,"version":"3.40.3"},"publisher-location":"Cham","reference-count":37,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030921842"},{"type":"electronic","value":"9783030921859"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":[[2021]]},"DOI":"10.1007\/978-3-030-92185-9_4","type":"book-chapter","created":{"date-parts":[[2021,12,5]],"date-time":"2021-12-05T17:02:46Z","timestamp":1638723766000},"page":"40-53","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi Modal Normalization"],"prefix":"10.1007","author":[{"given":"Neeraj","family":"Kumar","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ankur","family":"Narang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Brejesh","family":"lall","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Srishti","family":"Goel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,12,6]]},"reference":[{"key":"4_CR1","unstructured":"Assael, Y.M., Shillingford, B., Whiteson, S., de Freitas, N.: Lipnet: end-to-end sentence-level lipreading. In: GPU Technology Conference (2017)"},{"key":"4_CR2","unstructured":"Ba, J., Kiros, J., Hinton, G.: Layer normalization (2016)"},{"key":"4_CR3","doi-asserted-by":"crossref","unstructured":"Bulat, A., Tzimiropoulos, G.: How far are we from solving the 2d & 3d face alignment problem? (and a dataset of 230,000 3d facial landmarks). In: International Conference on Computer Vision (2017)","DOI":"10.1109\/ICCV.2017.116"},{"key":"4_CR4","doi-asserted-by":"publisher","unstructured":"Cao, H., Cooper, D., Keutmann, M., Gur, R., Nenkova, A., Verma, R.: Crema-d: Crowd-sourced emotional multimodal actors dataset. IEEE Trans. affective Comput. 5, 377\u2013390 (2014). https:\/\/doi.org\/10.1109\/TAFFC.2014.2336244","DOI":"10.1109\/TAFFC.2014.2336244"},{"key":"4_CR5","doi-asserted-by":"crossref","unstructured":"Cao, Z., Hidalgo, G., Simon, T., Wei, S.E., Sheikh, Y.: OpenPose: realtime multi-person 2D pose estimation using Part Affinity Fields. In: arXiv preprint arXiv:1812.08008 (2018)","DOI":"10.1109\/CVPR.2017.143"},{"key":"4_CR6","doi-asserted-by":"crossref","unstructured":"Chen, L., Li, Z., Maddox, R.K., Duan, Z., Xu, C.: Lip movements generation at a glance (2018)","DOI":"10.1007\/978-3-030-01234-2_32"},{"key":"4_CR7","doi-asserted-by":"crossref","unstructured":"Chen, L., Maddox, R., Duan, Z., Xu, C.: Hierarchical cross-modal talking face generation with dynamic pixel-wise loss (2019)","DOI":"10.1109\/CVPR.2019.00802"},{"key":"4_CR8","doi-asserted-by":"crossref","unstructured":"Chung, J.S., Nagrani, A., Zisserman, A.: Voxceleb2: Deep speaker recognition. In: INTERSPEECH (2018)","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"4_CR9","unstructured":"Chung, J.S., Jamaludin, A., Zisserman, A.: You said that? In: British Machine Vision Conference (2017)"},{"key":"4_CR10","unstructured":"Cooke, M., Barker, J., Cunningham, S., Shao, X.: Grid AV speech corpus sample (2013)"},{"key":"4_CR11","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":"4_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"363","DOI":"10.1007\/3-540-45103-X_50","volume-title":"Image Analysis","author":"G Farneb\u00e4ck","year":"2003","unstructured":"Farneb\u00e4ck, G.: Two-frame motion estimation based on polynomial expansion. In: Bigun, J., Gustavsson, T. (eds.) SCIA 2003. LNCS, vol. 2749, pp. 363\u2013370. Springer, Heidelberg (2003). https:\/\/doi.org\/10.1007\/3-540-45103-X_50"},{"key":"4_CR13","unstructured":"Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press, New York (2016). http:\/\/www.deeplearningbook.org"},{"key":"4_CR14","doi-asserted-by":"publisher","unstructured":"Huang, X., Belongie, S.: Arbitrary style transfer in real-time with adaptive instance normalization. In: Proceedings of the IEEE International Conference on Computer Vision, pp.1510\u20131519 (2017). https:\/\/doi.org\/10.1109\/ICCV.2017.167","DOI":"10.1109\/ICCV.2017.167"},{"key":"4_CR15","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: Accelerating deep network training by reducing internal covariate shift (2015)"},{"key":"4_CR16","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks (2019)","DOI":"10.1109\/CVPR.2019.00453"},{"key":"4_CR17","unstructured":"Kim, J., Kim, M., Kang, H.W., Lee, K.: U-gat-it: Unsupervised generative attentional networks with adaptive layer-instance normalization for image-to-image translation (2019)"},{"key":"4_CR18","unstructured":"Kingma, D., Ba, J.: Adam: A method for stochastic optimization. International Conference on Learning Representations (2014)"},{"key":"4_CR19","doi-asserted-by":"crossref","unstructured":"Kumar, N., Goel, S., Narang, A., Hasan, M.: Robust one shot audio to video generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops (2020)","DOI":"10.1109\/CVPRW50498.2020.00393"},{"key":"4_CR20","doi-asserted-by":"crossref","unstructured":"Liu, D., Vu, M.T., Chatterjee, S., Rasmussen, L.: Neural network based explicit mixture models and expectation-maximization based learning. In: 2020 International Joint Conference on Neural Networks (IJCNN) pp. 1\u201310 (2020)","DOI":"10.1109\/IJCNN48605.2020.9207086"},{"key":"4_CR21","unstructured":"Liu, G., Shih, K.J., Wang, T.C., Reda, F.A., Sapra, K., Yu, Z., Tao, A., Catanzaro, B.: Partial convolution based padding. arXiv preprint arXiv:1811.11718 (2018)"},{"key":"4_CR22","doi-asserted-by":"crossref","unstructured":"Mallya, A., Wang, T.C., Sapra, K., Liu, M.Y.: World-consistent video-to-video synthesis (2020)","DOI":"10.1007\/978-3-030-58598-3_22"},{"key":"4_CR23","doi-asserted-by":"publisher","unstructured":"Alghamdi, N., Maddock, S., Marxer, R., Barker, J., Brown, G.J..: A corpus of audio-visual lombard speech with frontal and profile view. The Journal of the Acoustical Society of America 143, EL523\u2013EL529 (2018). https:\/\/doi.org\/10.1121\/1.5042758","DOI":"10.1121\/1.5042758"},{"key":"4_CR24","unstructured":"Nam, H., Kim, H.E.: Batch-instance normalization for adaptively style-invariant neural networks (05 2018)"},{"key":"4_CR25","doi-asserted-by":"crossref","unstructured":"Park, T., Liu, M.Y., Wang, T.C., Zhu, J.Y.: Semantic image synthesis with spatially-adaptive normalization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.00244"},{"key":"4_CR26","doi-asserted-by":"crossref","unstructured":"Pf\u00fclb, B., Gepperth, A.: Overcoming catastrophic forgetting with gaussian mixture replay. ArXiv abs\/2104.09220 (2021)","DOI":"10.1109\/IJCNN52387.2021.9533880"},{"key":"4_CR27","unstructured":"Richardson, E., Weiss, Y.: On GANs and GMMs. In: NeurIPS (2018)"},{"key":"4_CR28","unstructured":"Soukupova, T., Cech, J.: Real-time eye blink detection using facial landmarks (2016)"},{"key":"4_CR29","series-title":"Unsupervised and Semi-Supervised Learning","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1007\/978-3-030-32583-1_3","volume-title":"Deep Biometrics","author":"G Storey","year":"2020","unstructured":"Storey, G., Bouridane, A., Jiang, R., Li, C.-T.: Atypical facial landmark localisation with stacked hourglass networks: a study on 3D facial modelling for medical diagnosis. In: Jiang, R., Li, C.-T., Crookes, D., Meng, W., Rosenberger, C. (eds.) Deep Biometrics. USL, pp. 37\u201349. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-32583-1_3"},{"key":"4_CR30","doi-asserted-by":"crossref","unstructured":"Tulyakov, S., Liu, M.Y., Yang, X., Kautz, J.: MoCoGAN: Decomposing motion and content for video generation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1526\u20131535 (2018)","DOI":"10.1109\/CVPR.2018.00165"},{"key":"4_CR31","unstructured":"Ulyanov, D., Vedaldi, A., Lempitsky, V.: Instance normalization: The missing ingredient for fast stylization (2016)"},{"issue":"1","key":"4_CR32","first-page":"234","volume":"14","author":"K Vougioukas","year":"2004","unstructured":"Vougioukas, K., Petridi, S., Pantic, M.: End-to-end speech-driven facial animation with temporal GANs. J. Foo 14(1), 234\u2013778 (2004)","journal-title":"J. Foo"},{"key":"4_CR33","doi-asserted-by":"crossref","unstructured":"Wang, Q., Wu, B., Zhu, P., Li, P., Zuo, W., Hu, Q.: ECA-Net: Efficient channel attention for deep convolutional neural networks (2019)","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"4_CR34","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2018)","DOI":"10.1109\/CVPR.2018.00917"},{"key":"4_CR35","doi-asserted-by":"crossref","unstructured":"Wiles, O., Koepke, A., Zisserman, A.: X2face: A network for controlling face generation by using images, audio, and pose codes. In: European Conference on Computer Vision (2018)","DOI":"10.1007\/978-3-030-01261-8_41"},{"key":"4_CR36","doi-asserted-by":"crossref","unstructured":"Zhou, B., Khosla, A., A., L., Oliva, A., Torralba, A.: Learning deep features for discriminative localization. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.319"},{"key":"4_CR37","doi-asserted-by":"crossref","unstructured":"Zhu, H., Huang, H., Li, Y., Zheng, A., He, R.: Arbitrary talking face generation via attentional audio-visual coherence learning. arXiv: Computer Vision and Pattern Recognition (2020)","DOI":"10.24963\/ijcai.2020\/327"}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-92185-9_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T18:40:42Z","timestamp":1710355242000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-92185-9_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030921842","9783030921859"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-92185-9_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"6 December 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sanur, Bali","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Indonesia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 December 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 December 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iconip2021.apnns.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-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":"1093","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":"226","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":"177","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":"21% - 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":"2.57","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":"6","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)"}},{"value":"Due to the COVID-19 pandemic the conference was held online.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}