{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T17:50:20Z","timestamp":1743097820365,"version":"3.40.3"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031263507"},{"type":"electronic","value":"9783031263514"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-26351-4_27","type":"book-chapter","created":{"date-parts":[[2023,2,25]],"date-time":"2023-02-25T09:03:18Z","timestamp":1677315798000},"page":"442-458","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["QS-Craft: Learning to\u00a0Quantize, Scrabble and\u00a0Craft for\u00a0Conditional Human Motion Animation"],"prefix":"10.1007","author":[{"given":"Yuxin","family":"Hong","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuelin","family":"Qian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Simian","family":"Luo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guodong","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangyang","family":"Xue","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanwei","family":"Fu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,2,26]]},"reference":[{"key":"27_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"122","DOI":"10.1007\/978-3-030-01228-1_8","volume-title":"Computer Vision \u2013 ECCV 2018","author":"A Bansal","year":"2018","unstructured":"Bansal, A., Ma, S., Ramanan, D., Sheikh, Y.: Recycle-GAN: unsupervised video retargeting. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11209, pp. 122\u2013138. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01228-1_8"},{"key":"27_CR2","unstructured":"Berthelot, D., Schumm, T., Metz, L.: Began: boundary equilibrium generative adversarial networks. arXiv preprint arXiv:1703.10717 (2017)"},{"key":"27_CR3","doi-asserted-by":"crossref","unstructured":"Blanz, V., Vetter, T.: A morphable model for the synthesis of 3D faces. In: Proceedings of the 26th Annual Conference on Computer Graphics and Interactive Techniques, pp. 187\u2013194 (1999)","DOI":"10.1145\/311535.311556"},{"key":"27_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"374","DOI":"10.1007\/978-3-030-01216-8_23","volume-title":"Computer Vision \u2013 ECCV 2018","author":"H Cai","year":"2018","unstructured":"Cai, H., Bai, C., Tai, Y.-W., Tang, C.-K.: Deep video generation, prediction and completion of human action sequences. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11206, pp. 374\u2013390. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01216-8_23"},{"issue":"4","key":"27_CR5","first-page":"1","volume":"33","author":"C Cao","year":"2014","unstructured":"Cao, C., Hou, Q., Zhou, K.: Displaced dynamic expression regression for real-time facial tracking and animation. ACM Trans. graph. (TOG) 33(4), 1\u201310 (2014)","journal-title":"ACM Trans. graph. (TOG)"},{"key":"27_CR6","unstructured":"Cao, C., et al.: The image local autoregressive transformer. In: NeuPIS (2021)"},{"key":"27_CR7","doi-asserted-by":"crossref","unstructured":"Cao, Z., Simon, T., Wei, S.E., Sheikh, Y.: Realtime multi-person 2D pose estimation using part affinity fields. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7291\u20137299 (2017)","DOI":"10.1109\/CVPR.2017.143"},{"key":"27_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"27_CR9","unstructured":"Chen, M., et al.: Generative pretraining from pixels. In: International Conference on Machine Learning, pp. 1691\u20131703. PMLR (2020)"},{"key":"27_CR10","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"27_CR11","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"27_CR12","doi-asserted-by":"crossref","unstructured":"Esser, P., Rombach, R., Ommer, B.: Taming transformers for high-resolution image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12873\u201312883 (2021)","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"27_CR13","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. arXiv preprint arXiv:1706.08500 (2017)"},{"key":"27_CR14","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational Bayes. arXiv preprint arXiv:1312.6114 (2013)"},{"key":"27_CR15","unstructured":"Kumar, M., Weissenborn, D., Kalchbrenner, N.: Colorization transformer. arXiv preprint arXiv:2102.04432 (2021)"},{"key":"27_CR16","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. arXiv preprint arXiv:2103.14030 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"27_CR17","doi-asserted-by":"crossref","unstructured":"Ma, L., Jia, X., Sun, Q., Schiele, B., Tuytelaars, T., Van Gool, L.: Pose guided person image generation. arXiv preprint arXiv:1705.09368 (2017)","DOI":"10.1109\/CVPR.2018.00018"},{"key":"27_CR18","doi-asserted-by":"crossref","unstructured":"Ma, L., Sun, Q., Georgoulis, S., Van Gool, L., Schiele, B., Fritz, M.: Disentangled person image generation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 99\u2013108 (2018)","DOI":"10.1109\/CVPR.2018.00018"},{"key":"27_CR19","doi-asserted-by":"crossref","unstructured":"Mao, X., Li, Q., Xie, H., Lau, R.Y., Wang, Z., Paul Smolley, S.: Least squares generative adversarial networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2794\u20132802 (2017)","DOI":"10.1109\/ICCV.2017.304"},{"key":"27_CR20","unstructured":"van den Oord, A., Vinyals, O., Kavukcuoglu, K.: Neural discrete representation learning. arXiv preprint arXiv:1711.00937 (2017)"},{"issue":"5","key":"27_CR21","doi-asserted-by":"publisher","first-page":"1118","DOI":"10.1007\/s11263-019-01265-2","volume":"128","author":"GJ Qi","year":"2020","unstructured":"Qi, G.J.: Loss-sensitive generative adversarial networks on Lipschitz densities. Int. J. Comput. Vision 128(5), 1118\u20131140 (2020)","journal-title":"Int. J. Comput. Vision"},{"key":"27_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"661","DOI":"10.1007\/978-3-030-01240-3_40","volume-title":"Computer Vision \u2013 ECCV 2018","author":"X Qian","year":"2018","unstructured":"Qian, X., et al.: Pose-normalized image generation for person re-identification. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11213, pp. 661\u2013678. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01240-3_40"},{"key":"27_CR23","unstructured":"Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv preprint arXiv:1511.06434 (2015)"},{"key":"27_CR24","unstructured":"Radford, A., Narasimhan, K., Salimans, T., Sutskever, I.: Improving language understanding by generative pre-training (2018)"},{"key":"27_CR25","unstructured":"Ramesh, A., et al.: Zero-shot text-to-image generation. arXiv preprint arXiv:2102.12092 (2021)"},{"key":"27_CR26","doi-asserted-by":"crossref","unstructured":"Siarohin, A., Lathuili\u00e8re, S., Tulyakov, S., Ricci, E., Sebe, N.: Animating arbitrary objects via deep motion transfer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2377\u20132386 (2019)","DOI":"10.1109\/CVPR.2019.00248"},{"key":"27_CR27","first-page":"7137","volume":"32","author":"A Siarohin","year":"2019","unstructured":"Siarohin, A., Lathuili\u00e8re, S., Tulyakov, S., Ricci, E., Sebe, N.: First order motion model for image animation. Adv. Neural. Inf. Process. Syst. 32, 7137\u20137147 (2019)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"27_CR28","doi-asserted-by":"crossref","unstructured":"Siarohin, A., Woodford, O.J., Ren, J., Chai, M., Tulyakov, S.: Motion representations for articulated animation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13653\u201313662 (2021)","DOI":"10.1109\/CVPR46437.2021.01344"},{"key":"27_CR29","unstructured":"S\u00f8nderby, C.K., Raiko, T., Maal\u00f8e, L., S\u00f8nderby, S.K., Winther, O.: Ladder variational autoencoders. arXiv preprint arXiv:1602.02282 (2016)"},{"key":"27_CR30","doi-asserted-by":"crossref","unstructured":"Thies, J., Zollhofer, M., Stamminger, M., Theobalt, C., Nie\u00dfner, M.: Face2Face: real-time face capture and reenactment of RGB videos. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2387\u20132395 (2016)","DOI":"10.1109\/CVPR.2016.262"},{"key":"27_CR31","doi-asserted-by":"crossref","unstructured":"Tulyakov, S., Liu, M.Y., Yang, X., Kautz, J.: 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":"27_CR32","unstructured":"Vaswani, A., et al.: Attention is all you need. arXiv preprint arXiv:1706.03762 (2017)"},{"key":"27_CR33","unstructured":"Wang, T.C., et al.: Video-to-video synthesis. arXiv preprint arXiv:1808.06601 (2018)"},{"key":"27_CR34","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"690","DOI":"10.1007\/978-3-030-01261-8_41","volume-title":"Computer Vision \u2013 ECCV 2018","author":"O Wiles","year":"2018","unstructured":"Wiles, O., Koepke, A.S., Zisserman, A.: X2Face: a network for controlling face generation using images, audio, and pose codes. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11217, pp. 690\u2013706. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01261-8_41"},{"key":"27_CR35","doi-asserted-by":"publisher","first-page":"9060","DOI":"10.1109\/TIP.2020.3023853","volume":"29","author":"C Xu","year":"2020","unstructured":"Xu, C., Fu, Y., Wen, C., Pan, Y., Jiang, Y.G., Xue, X.: Pose-guided person image synthesis in the non-iconic views. IEEE Trans. Image Process. 29, 9060\u20139072 (2020)","journal-title":"IEEE Trans. Image Process."},{"key":"27_CR36","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"204","DOI":"10.1007\/978-3-030-01249-6_13","volume-title":"Computer Vision \u2013 ECCV 2018","author":"C Yang","year":"2018","unstructured":"Yang, C., Wang, Z., Zhu, X., Huang, C., Shi, J., Lin, D.: Pose guided human video generation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11214, pp. 204\u2013219. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01249-6_13"},{"key":"27_CR37","doi-asserted-by":"publisher","unstructured":"Zhang, W., Zhu, M., Derpanis, K.G.: From actemes to action: a strongly-supervised representation for detailed action understanding. In: 2013 IEEE International Conference on Computer Vision, pp. 2248\u20132255 (2013). https:\/\/doi.org\/10.1109\/ICCV.2013.280","DOI":"10.1109\/ICCV.2013.280"},{"key":"27_CR38","doi-asserted-by":"crossref","unstructured":"Zhu, Z., Huang, T., Shi, B., Yu, M., Wang, B., Bai, X.: Progressive pose attention transfer for person image generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2347\u20132356 (2019)","DOI":"10.1109\/CVPR.2019.00245"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-26351-4_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,25]],"date-time":"2023-02-25T09:14:17Z","timestamp":1677316457000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-26351-4_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031263507","9783031263514"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-26351-4_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"26 February 2023","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":"Macao","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"4 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":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.accv2022.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":"CMT Microsoft","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"836","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":"277","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":"33% - 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":"3.3","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":"2.6","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":"For the ACCV 2022 workshops 25 papers have been accepted from 40 submissions","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)"}}]}}