{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T11:41:47Z","timestamp":1783597307416,"version":"3.55.0"},"publisher-location":"Cham","reference-count":53,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031200700","type":"print"},{"value":"9783031200717","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\/978-3-031-20071-7_36","type":"book-chapter","created":{"date-parts":[[2022,11,12]],"date-time":"2022-11-12T05:15:09Z","timestamp":1668230109000},"page":"612-630","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":135,"title":["BEAT: A Large-Scale Semantic and\u00a0Emotional Multi-modal Dataset for\u00a0Conversational Gestures Synthesis"],"prefix":"10.1007","author":[{"given":"Haiyang","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zihao","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Naoya","family":"Iwamoto","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yichen","family":"Peng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhengqing","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"You","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Elif","family":"Bozkurt","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,11,13]]},"reference":[{"key":"36_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"248","DOI":"10.1007\/978-3-030-58523-5_15","volume-title":"Computer Vision \u2013 ECCV 2020","author":"C Ahuja","year":"2020","unstructured":"Ahuja, C., Lee, D.W., Nakano, Y.I., Morency, L.-P.: Style transfer for co-speech gesture animation: a multi-speaker conditional-mixture approach. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12363, pp. 248\u2013265. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58523-5_15"},{"key":"36_CR2","doi-asserted-by":"crossref","unstructured":"Alexanderson, S., Henter, G.E., Kucherenko, T., Beskow, J.: Style-controllable speech-driven gesture synthesis using normalising flows. In: Computer Graphics Forum. Wiley Online Library, vol. 39, pp. 487\u2013496 (2020)","DOI":"10.1111\/cgf.13946"},{"key":"36_CR3","doi-asserted-by":"crossref","unstructured":"Alexanderson, S., Sz\u00e9kely, \u00c9., Henter, G.E., Kucherenko, T., Beskow, J.: Generating coherent spontaneous speech and gesture from text. In: Proceedings of the 20th ACM International Conference on Intelligent Virtual Agents, pp. 1\u20133 (2020)","DOI":"10.1145\/3383652.3423874"},{"key":"36_CR4","doi-asserted-by":"crossref","unstructured":"Alghamdi, N., Maddock, S., Marxer, R., Barker, J., Brown, G.J.: A corpus of audio-visual lombard speech with frontal and profile views. J. Acoust. Soc. Am. 143(6), EL523-EL529 (2018)","DOI":"10.1121\/1.5042758"},{"issue":"4\u20135","key":"36_CR5","volume":"31","author":"G Ali","year":"2020","unstructured":"Ali, G., Lee, M., Hwang, J.I.: Automatic text-to-gesture rule generation for embodied conversational agents. Comput. Anim. Virtual Worlds 31(4\u20135), e1944 (2020)","journal-title":"Comput. Anim. Virtual Worlds"},{"key":"36_CR6","unstructured":"Bai, S., Kolter, J.Z., Koltun, V.: An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv preprint arXiv:1803.01271 (2018)"},{"key":"36_CR7","doi-asserted-by":"crossref","unstructured":"Bhattacharya, U., Childs, E., Rewkowski, N., Manocha, D.: Speech2AffectiveGestures: synthesizing co-speech gestures with generative adversarial affective expression learning. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 2027\u20132036 (2021)","DOI":"10.1145\/3474085.3475223"},{"key":"36_CR8","doi-asserted-by":"crossref","unstructured":"Bhattacharya, U., Rewkowski, N., Banerjee, A., Guhan, P., Bera, A., Manocha, D.: Text2Gestures: a transformer-based network for generating emotive body gestures for virtual agents** this work has been supported in part by aro grants w911nf1910069 and w911nf1910315, and intel. code and additional materials available at: https:\/\/gamma.umd.edu\/t2g. In: 2021 IEEE Virtual Reality and 3D User Interfaces (VR), pp. 1-10. IEEE (2021)","DOI":"10.1109\/VR50410.2021.00037"},{"key":"36_CR9","doi-asserted-by":"crossref","unstructured":"Bloom, V., Makris, D., Argyriou, V.: G3D: a gaming action dataset and real time action recognition evaluation framework. In: 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops. IEEE, pp. 7\u201312 (2012)","DOI":"10.1109\/CVPRW.2012.6239175"},{"key":"36_CR10","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1162\/tacl_a_00051","volume":"5","author":"P Bojanowski","year":"2017","unstructured":"Bojanowski, P., Grave, E., Joulin, A., Mikolov, T.: Enriching word vectors with subword information. Trans. Assoc comput. linguist 5, 135\u2013146 (2017)","journal-title":"Trans. Assoc comput. linguist"},{"issue":"4","key":"36_CR11","doi-asserted-by":"publisher","first-page":"377","DOI":"10.1109\/TAFFC.2014.2336244","volume":"5","author":"H Cao","year":"2014","unstructured":"Cao, H., Cooper, D.G., Keutmann, M.K., Gur, R.C., Nenkova, A., Verma, R.: CREMA-D: crowd-sourced emotional multimodal actors dataset. IEEE Trans. Affect. Comput. 5(4), 377\u2013390 (2014)","journal-title":"IEEE Trans. Affect. Comput."},{"issue":"1","key":"36_CR12","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1109\/TPAMI.2019.2929257","volume":"43","author":"Z Cao","year":"2019","unstructured":"Cao, Z., Hidalgo, G., Simon, T., Wei, S.E., Sheikh, Y.: Openpose: realtime multi-person 2D pose estimation using part affinity fields. IEEE Trans. Pattern Anal. Mach. Intell. 43(1), 172\u2013186 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"36_CR13","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? A new model and the kinetics dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6299\u20136308 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"36_CR14","doi-asserted-by":"crossref","unstructured":"Chen, C., Jafari, R., Kehtarnavaz, N.: UTD-MHAD: a multimodal dataset for human action recognition utilizing a depth camera and a wearable inertial sensor. In: 2015 IEEE International conference on image processing (ICIP), IEEE, pp. 168\u2013172 (2015)","DOI":"10.1109\/ICIP.2015.7350781"},{"issue":"5","key":"36_CR15","doi-asserted-by":"publisher","first-page":"2421","DOI":"10.1121\/1.2229005","volume":"120","author":"M Cooke","year":"2006","unstructured":"Cooke, M., Barker, J., Cunningham, S., Shao, X.: An audio-visual corpus for speech perception and automatic speech recognition. J. Acoust. Soc. Am. 120(5), 2421\u20132424 (2006)","journal-title":"J. Acoust. Soc. Am."},{"key":"36_CR16","doi-asserted-by":"crossref","unstructured":"Cudeiro, D., Bolkart, T., Laidlaw, C., Ranjan, A., Black, M.J.: Capture, learning, and synthesis of 3D speaking styles. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10101\u201310111 (2019)","DOI":"10.1109\/CVPR.2019.01034"},{"key":"36_CR17","doi-asserted-by":"crossref","unstructured":"Ferstl, Y., McDonnell, R.: Investigating the use of recurrent motion modelling for speech gesture generation. In: Proceedings of the 18th International Conference on Intelligent Virtual Agents, pp. 93\u201398 (2018)","DOI":"10.1145\/3267851.3267898"},{"key":"36_CR18","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1016\/j.cag.2020.04.007","volume":"89","author":"Y Ferstl","year":"2020","unstructured":"Ferstl, Y., Neff, M., McDonnell, R.: Adversarial gesture generation with realistic gesture phasing. Comput. Graph. 89, 117\u2013130 (2020)","journal-title":"Comput. Graph."},{"key":"36_CR19","doi-asserted-by":"publisher","DOI":"10.1002\/cav.2016","volume":"32","author":"Y Ferstl","year":"2021","unstructured":"Ferstl, Y., Neff, M., McDonnell, R.: ExpressGesture: expressive gesture generation from speech through database matching. Comput. Anim. Virtual Worlds 32, e2016 (2021)","journal-title":"Comput. Anim. Virtual Worlds"},{"key":"36_CR20","doi-asserted-by":"crossref","unstructured":"Ginosar, S., Bar, A., Kohavi, G., Chan, C., Owens, A., Malik, J.: Learning individual styles of conversational gesture. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3497\u20133506 (2019)","DOI":"10.1109\/CVPR.2019.00361"},{"key":"36_CR21","doi-asserted-by":"crossref","unstructured":"Habibie, I., et al.: Learning speech-driven 3D conversational gestures from video. arXiv preprint arXiv:2102.06837 (2021)","DOI":"10.1145\/3472306.3478335"},{"key":"36_CR22","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"issue":"6","key":"36_CR23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3414685.3417836","volume":"39","author":"GE Henter","year":"2020","unstructured":"Henter, G.E., Alexanderson, S., Beskow, J.: MoGlow: probabilistic and controllable motion synthesis using normalising flows. ACM Trans. Graph. (TOG) 39(6), 1\u201314 (2020)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"36_CR24","volume-title":"Oxford Advanced Learner\u2019s Dictionary of Current English","author":"AS Hornby","year":"1974","unstructured":"Hornby, A.S., et al.: Oxford Advanced Learner\u2019s Dictionary of Current English. Oxford University Press, Oxford (1974)"},{"issue":"7","key":"36_CR25","doi-asserted-by":"publisher","first-page":"1325","DOI":"10.1109\/TPAMI.2013.248","volume":"36","author":"C Ionescu","year":"2013","unstructured":"Ionescu, C., Papava, D., Olaru, V., Sminchisescu, C.: Human3.6M: large scale datasets and predictive methods for 3D human sensing in natural environments. IEEE Trans. Pattern Anal. Mach. Intell. 36(7), 1325\u20131339 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"36_CR26","volume-title":"Surrey Audio-Visual Expressed Emotion (SAVEE) Database","author":"P Jackson","year":"2014","unstructured":"Jackson, P., Haq, S.: Surrey Audio-Visual Expressed Emotion (SAVEE) Database. University of Surrey, Guildford, UK (2014)"},{"key":"36_CR27","doi-asserted-by":"crossref","unstructured":"Kapoor, P., Mukhopadhyay, R., Hegde, S.B., Namboodiri, V., Jawahar, C.: Towards automatic speech to sign language generation. arXiv preprint arXiv:2106.12790 (2021)","DOI":"10.21437\/Interspeech.2021-1094"},{"key":"36_CR28","unstructured":"Kay, W., et al.: The kinetics human action video dataset. arXiv preprint arXiv:1705.06950 (2017)"},{"key":"36_CR29","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"36_CR30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1080\/10447318.2021.1883883","volume":"37","author":"T Kucherenko","year":"2021","unstructured":"Kucherenko, T., Hasegawa, D., Kaneko, N., Henter, G.E., Kjellstr\u00f6m, H.: Moving fast and slow: analysis of representations and post-processing in speech-driven automatic gesture generation. Int. J. Hum-Comput. Interact. 37, 1\u201317 (2021)","journal-title":"Int. J. Hum-Comput. Interact."},{"key":"36_CR31","doi-asserted-by":"crossref","unstructured":"Kucherenko, T., et al.: Gesticulator: a framework for semantically-aware speech-driven gesture generation. In: Proceedings of the 2020 International Conference on Multimodal Interaction, pp. 242\u2013250 (2020)","DOI":"10.1145\/3382507.3418815"},{"key":"36_CR32","doi-asserted-by":"crossref","unstructured":"Li, J., et al.: Audio2Gestures: generating diverse gestures from speech audio with conditional variational autoencoders. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11293\u201311302 (2021)","DOI":"10.1109\/ICCV48922.2021.01110"},{"key":"36_CR33","doi-asserted-by":"crossref","unstructured":"Li, R., Yang, S., Ross, D.A., Kanazawa, A.: AI choreographer: music conditioned 3D dance generation with AIST++. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13401\u201313412 (2021)","DOI":"10.1109\/ICCV48922.2021.01315"},{"issue":"7","key":"36_CR34","doi-asserted-by":"publisher","first-page":"1781","DOI":"10.1109\/TCYB.2016.2582918","volume":"47","author":"AA Liu","year":"2016","unstructured":"Liu, A.A., Xu, N., Nie, W.Z., Su, Y.T., Wong, Y., Kankanhalli, M.: Benchmarking a multimodal and multiview and interactive dataset for human action recognition. IEEE Trans. Cybern. 47(7), 1781\u20131794 (2016)","journal-title":"IEEE Trans. Cybern."},{"issue":"5","key":"36_CR35","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0196391","volume":"13","author":"SR Livingstone","year":"2018","unstructured":"Livingstone, S.R., Russo, F.A.: The Ryerson audio-visual database of emotional speech and song (RAVDESS): a dynamic, multimodal set of facial and vocal expressions in north American english. PLoS ONE 13(5), e0196391 (2018)","journal-title":"PLoS ONE"},{"key":"36_CR36","doi-asserted-by":"crossref","unstructured":"Lu, J., Liu, T., Xu, S., Shimodaira, H.: Double-DCCCAE: estimation of body gestures from speech waveform. In: ICASSP 2021\u20132021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, pp. 900\u2013904 (2021)","DOI":"10.1109\/ICASSP39728.2021.9414660"},{"key":"36_CR37","doi-asserted-by":"crossref","unstructured":"McAuliffe, M., Socolof, M., Mihuc, S., Wagner, M., Sonderegger, M.: Montreal forced aligner: trainable text-speech alignment using kaldi. In: Interspeech, vol. 2017, pp. 498\u2013502 (2017)","DOI":"10.21437\/Interspeech.2017-1386"},{"key":"36_CR38","doi-asserted-by":"crossref","unstructured":"Ng, E., Ginosar, S., Darrell, T., Joo, H.: Body2Hands: learning to infer 3D hands from conversational gesture body dynamics. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11865\u201311874 (2021)","DOI":"10.1109\/CVPR46437.2021.01169"},{"key":"36_CR39","doi-asserted-by":"crossref","unstructured":"Pavllo, D., Feichtenhofer, C., Grangier, D., Auli, M.: 3D human pose estimation in video with temporal convolutions and semi-supervised training. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7753\u20137762 (2019)","DOI":"10.1109\/CVPR.2019.00794"},{"issue":"5","key":"36_CR40","doi-asserted-by":"publisher","first-page":"405","DOI":"10.1109\/THMS.2020.2971958","volume":"50","author":"AG Perera","year":"2020","unstructured":"Perera, A.G., Law, Y.W., Ogunwa, T.T., Chahl, J.: A multiviewpoint outdoor dataset for human action recognition. IEEE Trans Hum-Mach. Syst 50(5), 405\u2013413 (2020)","journal-title":"IEEE Trans Hum-Mach. Syst"},{"key":"36_CR41","doi-asserted-by":"crossref","unstructured":"Punnakkal, A.R., Chandrasekaran, A., Athanasiou, N., Quiros-Ramirez, A., Black, M.J.: BABEL: bodies, action and behavior with english labels. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 722\u2013731 (2021)","DOI":"10.1109\/CVPR46437.2021.00078"},{"key":"36_CR42","doi-asserted-by":"crossref","unstructured":"Richard, A., Zollh\u00f6fer, M., Wen, Y., De la Torre, F., Sheikh, Y.: MeshTalk: 3D face animation from speech using cross-modality disentanglement. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1173\u20131182 (2021)","DOI":"10.1109\/ICCV48922.2021.00121"},{"key":"36_CR43","doi-asserted-by":"crossref","unstructured":"Singh, S., Velastin, S.A., Ragheb, H.: Muhavi: A multicamera human action video dataset for the evaluation of action recognition methods. In: 2010 7th IEEE International Conference on Advanced Video and Signal Based Surveillance, pp. 48\u201355. IEEE (2010)","DOI":"10.1109\/AVSS.2010.63"},{"key":"36_CR44","doi-asserted-by":"crossref","unstructured":"Song, S., Lan, C., Xing, J., Zeng, W., Liu, J.: An end-to-end spatio-temporal attention model for human action recognition from skeleton data. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 31 (2017)","DOI":"10.1609\/aaai.v31i1.11212"},{"key":"36_CR45","doi-asserted-by":"crossref","unstructured":"Takeuchi, K., Hasegawa, D., Shirakawa, S., Kaneko, N., Sakuta, H., Sumi, K.: Speech-to-gesture generation: a challenge in deep learning approach with bi-directional LSTM. In: Proceedings of the 5th International Conference on Human Agent Interaction, pp. 365\u2013369 (2017)","DOI":"10.1145\/3125739.3132594"},{"key":"36_CR46","series-title":"Communications in Computer and Information Science","doi-asserted-by":"publisher","first-page":"198","DOI":"10.1007\/978-3-319-58750-9_28","volume-title":"HCI International 2017 \u2013 Posters\u2019 Extended Abstracts","author":"K Takeuchi","year":"2017","unstructured":"Takeuchi, K., Kubota, S., Suzuki, K., Hasegawa, D., Sakuta, H.: Creating a gesture-speech dataset for speech-based automatic gesture generation. In: Stephanidis, C. (ed.) HCI 2017. CCIS, vol. 713, pp. 198\u2013202. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-58750-9_28"},{"issue":"12","key":"36_CR47","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0113647","volume":"9","author":"E Volkova","year":"2014","unstructured":"Volkova, E., De La Rosa, S., B\u00fclthoff, H.H., Mohler, B.: The MPI emotional body expressions database for narrative scenarios. PLoS ONE 9(12), e113647 (2014)","journal-title":"PLoS ONE"},{"key":"36_CR48","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"872","DOI":"10.1007\/978-3-642-33709-3_62","volume-title":"Computer Vision \u2013 ECCV 2012","author":"J Wang","year":"2012","unstructured":"Wang, J., Liu, Z., Chorowski, J., Chen, Z., Wu, Y.: Robust 3D action recognition with random occupancy patterns. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7573, pp. 872\u2013885. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33709-3_62"},{"key":"36_CR49","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"700","DOI":"10.1007\/978-3-030-58589-1_42","volume-title":"Computer Vision \u2013 ECCV 2020","author":"K Wang","year":"2020","unstructured":"Wang, K., et al.: MEAD: a large-scale audio-visual dataset for emotional talking-face generation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12366, pp. 700\u2013717. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58589-1_42"},{"key":"36_CR50","doi-asserted-by":"crossref","unstructured":"Wu, B., Ishi, C., Ishiguro, H., et al.: Probabilistic human-like gesture synthesis from speech using GRU-based WGAN. In: GENEA: Generation and Evaluation of Non-verbal Behaviour for Embodied Agents Workshop 2021 (2021)","DOI":"10.1145\/3461615.3485407"},{"issue":"3","key":"36_CR51","doi-asserted-by":"publisher","first-page":"228","DOI":"10.3390\/electronics10030228","volume":"10","author":"B Wu","year":"2021","unstructured":"Wu, B., Liu, C., Ishi, C.T., Ishiguro, H.: Modeling the conditional distribution of co-speech upper body gesture jointly using conditional-GAN and unrolled-GAN. Electronics 10(3), 228 (2021)","journal-title":"Electronics"},{"issue":"6","key":"36_CR52","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3414685.3417838","volume":"39","author":"Y Yoon","year":"2020","unstructured":"Yoon, Y.: Speech gesture generation from the trimodal context of text, audio, and speaker identity. ACM Trans. Graph. (TOG) 39(6), 1\u201316 (2020)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"36_CR53","doi-asserted-by":"crossref","unstructured":"Yoon, Y., Ko, W.R., Jang, M., Lee, J., Kim, J., Lee, G.: Robots learn social skills: end-to-end learning of co-speech gesture generation for humanoid robots. In: 2019 International Conference on Robotics and Automation (ICRA), pp. 4303\u20134309. IEEE (2019)","DOI":"10.1109\/ICRA.2019.8793720"}],"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\/978-3-031-20071-7_36","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,12]],"date-time":"2022-11-12T05:30:55Z","timestamp":1668231055000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20071-7_36"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031200700","9783031200717"],"references-count":53,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20071-7_36","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":"13 November 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)"}}]}}