{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:04:14Z","timestamp":1750309454001,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":53,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"publisher","award":["CGS D - 577775 - 2023"],"award-info":[{"award-number":["CGS D - 577775 - 2023"]}],"id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,12,3]]},"DOI":"10.1145\/3696409.3700188","type":"proceedings-article","created":{"date-parts":[[2024,12,28]],"date-time":"2024-12-28T09:55:23Z","timestamp":1735379723000},"page":"1-8","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["LMoW: A Latent Random Variable Model for Unconditional Human Motion Generation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-6656-4496","authenticated-orcid":false,"given":"Faisal","family":"Ahmed","sequence":"first","affiliation":[{"name":"Department of Computing Science, University of Alberta, Edmonton, AB, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9270-5177","authenticated-orcid":false,"given":"Justin","family":"Rozeboom","sequence":"additional","affiliation":[{"name":"Department of Computing Science, University of Alberta, Edmonton, AB, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6066-753X","authenticated-orcid":false,"given":"Hanran","family":"Song","sequence":"additional","affiliation":[{"name":"Department of Computing Science, University of Alberta, Edmonton, AB, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4574-4815","authenticated-orcid":false,"given":"Chenqiu","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Computing Science, University of Alberta, Edmonton, AB, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7695-4148","authenticated-orcid":false,"given":"Anup","family":"Basu","sequence":"additional","affiliation":[{"name":"Department of Computing Science, University of Alberta, Edmonton, AB, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,12,28]]},"reference":[{"key":"e_1_3_3_1_2_2","unstructured":"[n. d.]. Carnegie Mellon University - CMU Graphics Lab - motion capture library. http:\/\/mocap.cs.cmu.edu\/. Accessed: 2024-07-17."},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2019.00084"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"crossref","unstructured":"Simon Alexanderson Rajmund Nagy Jonas Beskow and Gustav\u00a0Eje Henter. 2023. Listen denoise action! audio-driven motion synthesis with diffusion models. ACM Transactions on Graphics (TOG) 42 4 (2023) 1\u201320.","DOI":"10.1145\/3592458"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00882"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01381"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/276"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/VR50410.2021.00037"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"crossref","unstructured":"Sam Bond-Taylor Adam Leach Yang Long and Chris\u00a0G Willcocks. 2021. Deep generative modelling: A comparative review of vaes gans normalizing flows energy-based and autoregressive models. IEEE transactions on pattern analysis and machine intelligence 44 11 (2021) 7327\u20137347.","DOI":"10.1109\/TPAMI.2021.3116668"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01144"},{"key":"e_1_3_3_1_11_2","first-page":"5253","volume-title":"32nd USENIX Security Symposium (USENIX Security 23)","author":"Carlini Nicolas","year":"2023","unstructured":"Nicolas Carlini, Jamie Hayes, Milad Nasr, Matthew Jagielski, Vikash Sehwag, Florian Tramer, Borja Balle, Daphne Ippolito, and Eric Wallace. 2023. Extracting training data from diffusion models. In 32nd USENIX Security Symposium (USENIX Security 23). 5253\u20135270."},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"crossref","unstructured":"Xinyu Chen Jiajie Xu Rui Zhou Wei Chen Junhua Fang and Chengfei Liu. 2021. TrajVAE: A Variational AutoEncoder model for trajectory generation. Neurocomputing 428 (2021) 332\u2013339.","DOI":"10.1016\/j.neucom.2020.03.120"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00281"},{"key":"e_1_3_3_1_14_2","unstructured":"Prafulla Dhariwal and Alexander Nichol. 2021. Diffusion models beat gans on image synthesis. Advances in neural information processing systems 34 (2021) 8780\u20138794."},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"crossref","unstructured":"Ian Goodfellow Jean Pouget-Abadie Mehdi Mirza Bing Xu David Warde-Farley Sherjil Ozair Aaron Courville and Yoshua Bengio. 2020. Generative adversarial networks. Commun. ACM 63 11 (2020) 139\u2013144.","DOI":"10.1145\/3422622"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413635"},{"key":"e_1_3_3_1_18_2","unstructured":"Jonathan Ho Ajay Jain and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. Advances in neural information processing systems 33 (2020) 6840\u20136851."},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"crossref","unstructured":"Daniel Holden Taku Komura and Jun Saito. 2017. Phase-functioned neural networks for character control. ACM Transactions on Graphics (TOG) 36 4 (2017) 1\u201313.","DOI":"10.1145\/3072959.3073663"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"e_1_3_3_1_21_2","unstructured":"Diederik Kingma and Ruiqi Gao. 2024. Understanding diffusion objectives as the elbo with simple data augmentation. Advances in Neural Information Processing Systems 36 (2024)."},{"key":"e_1_3_3_1_22_2","unstructured":"Diederik\u00a0P Kingma and Max Welling. 2013. Auto-encoding variational bayes. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1312.6114 (2013)."},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01123"},{"key":"e_1_3_3_1_24_2","unstructured":"Hsin-Ying Lee Xiaodong Yang Ming-Yu Liu Ting-Chun Wang Yu-Ding Lu Ming-Hsuan Yang and Jan Kautz. 2019. Dancing to music. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/3DV53792.2021.00086"},{"key":"e_1_3_3_1_26_2","unstructured":"Zimo Li Yi Zhou Shuangjiu Xiao Chong He Zeng Huang and Hao Li. 2017. Auto-conditioned recurrent networks for extended complex human motion synthesis. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1707.05363 (2017)."},{"key":"e_1_3_3_1_27_2","unstructured":"Han Liang Wenqian Zhang Wenxuan Li Jingyi Yu and Lan Xu. 2024. Intergen: Diffusion-based multi-human motion generation under complex interactions. International Journal of Computer Vision (2024) 1\u201321."},{"key":"e_1_3_3_1_28_2","unstructured":"Angela\u00a0S Lin Lemeng Wu Rodolfo Corona Kevin Tai Qixing Huang and Raymond\u00a0J Mooney. 2018. Generating animated videos of human activities from natural language descriptions. Learning 1 2018 (2018) 1."},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/3596711.3596800"},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00082"},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00554"},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICAR.2015.7251476"},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01080"},{"key":"e_1_3_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_28"},{"key":"e_1_3_3_1_35_2","doi-asserted-by":"publisher","unstructured":"Matthias Plappert Christian Mandery and Tamim Asfour. 2016. The KIT Motion-Language Dataset. Big Data 4 4 (dec 2016) 236\u2013252. 10.1089\/big.2016.0028","DOI":"10.1089\/big.2016.0028"},{"key":"e_1_3_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01333"},{"key":"e_1_3_3_1_37_2","unstructured":"Ali Razavi Aaron Van\u00a0den Oord and Oriol Vinyals. 2019. Generating diverse high-fidelity images with vq-vae-2. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096441"},{"key":"e_1_3_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_3_1_40_2","first-page":"2256","volume-title":"International conference on machine learning","author":"Sohl-Dickstein Jascha","year":"2015","unstructured":"Jascha Sohl-Dickstein, Eric Weiss, Niru Maheswaranathan, and Surya Ganguli. 2015. Deep unsupervised learning using nonequilibrium thermodynamics. In International conference on machine learning. PMLR, 2256\u20132265."},{"key":"e_1_3_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00165"},{"key":"e_1_3_3_1_42_2","unstructured":"Arash Vahdat and Jan Kautz. 2020. NVAE: A deep hierarchical variational autoencoder. Advances in neural information processing systems 33 (2020) 19667\u201319679."},{"key":"e_1_3_3_1_43_2","unstructured":"Arash Vahdat Karsten Kreis and Jan Kautz. 2021. Score-based generative modeling in latent space. Advances in neural information processing systems 34 (2021) 11287\u201311302."},{"key":"e_1_3_3_1_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02014"},{"key":"e_1_3_3_1_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01340"},{"key":"e_1_3_3_1_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561315"},{"key":"e_1_3_3_1_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00212"},{"key":"e_1_3_3_1_48_2","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123277"},{"key":"e_1_3_3_1_49_2","doi-asserted-by":"crossref","unstructured":"Tairan Yin Ludovic Hoyet Marc Christie Marie-Paule Cani and Julien Pettr\u00e9. 2022. The One-Man-Crowd: Single user generation of crowd motions using virtual reality. IEEE Transactions on Visualization and Computer Graphics 28 5 (2022) 2245\u20132255.","DOI":"10.1109\/TVCG.2022.3150507"},{"key":"e_1_3_3_1_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01102"},{"key":"e_1_3_3_1_51_2","doi-asserted-by":"crossref","unstructured":"Mingyuan Zhang Zhongang Cai Liang Pan Fangzhou Hong Xinying Guo Lei Yang and Ziwei Liu. 2024. Motiondiffuse: Text-driven human motion generation with diffusion model. IEEE Transactions on Pattern Analysis and Machine Intelligence (2024).","DOI":"10.1109\/TPAMI.2024.3355414"},{"key":"e_1_3_3_1_52_2","unstructured":"Yufeng Zhang Jialu Pan Li\u00a0Ken Li Wanwei Liu Zhenbang Chen Xinwang Liu and Ji Wang. 2024. On the properties of Kullback-Leibler divergence between multivariate Gaussian distributions. Advances in Neural Information Processing Systems 36 (2024)."},{"key":"e_1_3_3_1_53_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00589"},{"key":"e_1_3_3_1_54_2","unstructured":"Wentao Zhu Xiaoxuan Ma Dongwoo Ro Hai Ci Jinlu Zhang Jiaxin Shi Feng Gao Qi Tian and Yizhou Wang. 2023. Human motion generation: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence (2023)."}],"event":{"name":"MMAsia '24: ACM Multimedia Asia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Auckland New Zealand","acronym":"MMAsia '24"},"container-title":["Proceedings of the 6th ACM International Conference on Multimedia in Asia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3696409.3700188","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3696409.3700188","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:10:11Z","timestamp":1750295411000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3696409.3700188"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,3]]},"references-count":53,"alternative-id":["10.1145\/3696409.3700188","10.1145\/3696409"],"URL":"https:\/\/doi.org\/10.1145\/3696409.3700188","relation":{},"subject":[],"published":{"date-parts":[[2024,12,3]]},"assertion":[{"value":"2024-12-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}