{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T01:22:07Z","timestamp":1779931327857,"version":"3.53.1"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,7,10]],"date-time":"2024-07-10T00:00:00Z","timestamp":1720569600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100006374","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62206137, 62206200"],"award-info":[{"award-number":["62206137, 62206200"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Program for Young Talents of Science and Technology in Universities of Inner Mongolia Autonomous Region","award":["NJYT23105"],"award-info":[{"award-number":["NJYT23105"]}]},{"DOI":"10.13039\/501100006374","name":"Natural Science Foundation of Inner Mongolia","doi-asserted-by":"publisher","award":["2022MS06025"],"award-info":[{"award-number":["2022MS06025"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,7,10]]},"DOI":"10.1145\/3626772.3657804","type":"proceedings-article","created":{"date-parts":[[2024,7,11]],"date-time":"2024-07-11T12:40:05Z","timestamp":1720701605000},"page":"1083-1092","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Hierarchical Semantics Alignment for 3D Human Motion Retrieval"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2690-7180","authenticated-orcid":false,"given":"Yang","family":"Yang","sequence":"first","affiliation":[{"name":"Inner Mongolia University, Hohhot, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7845-781X","authenticated-orcid":false,"given":"Haoyu","family":"Shi","sequence":"additional","affiliation":[{"name":"Inner Mongolia University, Hohhot, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3183-9218","authenticated-orcid":false,"given":"Huaiwen","family":"Zhang","sequence":"additional","affiliation":[{"name":"Inner Mongolia University, Hohhot, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,7,11]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"On a measure of divergence between two multinomial populations. Sankhy=a: the indian journal of statistics","author":"Bhattacharyya Anil","year":"1946","unstructured":"Anil Bhattacharyya. 1946. On a measure of divergence between two multinomial populations. Sankhy=a: the indian journal of statistics (1946), 401--406."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591758"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00831"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00831"},{"key":"e_1_3_2_1_5_1","volume-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL-HLT","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL-HLT 2019, Minneapolis, MN, USA, June 2-7, 2019, Volume 1 (Long and Short Papers). Association for Computational Linguistics, 4171--4186."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(96)00034-3"},{"key":"e_1_3_2_1_7_1","volume-title":"From Region to Patch: Attribute-Aware Foreground-Background Contrastive Learning for Fine-Grained Fashion Retrieval. arXiv preprint arXiv:2305.10260","author":"Dong Jianfeng","year":"2023","unstructured":"Jianfeng Dong, Xiaoman Peng, Zhe Ma, Daizong Liu, Xiaoye Qu, Xun Yang, Jixiang Zhu, and Baolong Liu. 2023. From Region to Patch: Attribute-Aware Foreground-Background Contrastive Learning for Fine-Grained Fashion Retrieval. arXiv preprint arXiv:2305.10260 (2023)."},{"key":"e_1_3_2_1_8_1","volume-title":"ICLR 2021","author":"Dosovitskiy Alexey","year":"2021","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby. 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In ICLR 2021, Virtual Event, Austria, May 3-7, 2021. OpenReview.net."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-022-00980-0"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01262"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413635"},{"key":"e_1_3_2_1_13_1","volume-title":"Adam: A Method for Stochastic Optimization. In ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings.","author":"Diederik","unstructured":"Diederik P. Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. In ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings."},{"key":"e_1_3_2_1_14_1","volume-title":"Auto-Encoding Variational Bayes. In ICLR 2014, Banff, AB, Canada, April 14--16, 2014, Conference Track Proceedings.","author":"Diederik","unstructured":"Diederik P. Kingma and Max Welling. 2014. Auto-Encoding Variational Bayes. In ICLR 2014, Banff, AB, Canada, April 14--16, 2014, Conference Track Proceedings."},{"key":"e_1_3_2_1_15_1","volume-title":"Fine-Grained Semantically Aligned Vision-Language Pre-Training. ArXiv","author":"Li Juncheng","year":"2022","unstructured":"Juncheng Li, Xin He, Longhui Wei, Long Qian, Linchao Zhu, Lingxi Xie, Yueting Zhuang, Qi Tian, and Siliang Tang. 2022. Fine-Grained Semantically Aligned Vision-Language Pre-Training. ArXiv, Vol. abs\/2208.02515 (2022)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00871"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818013"},{"key":"e_1_3_2_1_18_1","volume-title":"HumanTOMATO: Text-aligned Whole-body Motion Generation. arxiv:2310.12978","author":"Lu Shunlin","year":"2023","unstructured":"Shunlin Lu, Ling-Hao Chen, Ailing Zeng, Jing Lin, Ruimao Zhang, Lei Zhang, and Heung-Yeung Shum. 2023. HumanTOMATO: Text-aligned Whole-body Motion Generation. arxiv:2310.12978 (2023)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547910"},{"key":"e_1_3_2_1_20_1","volume-title":"AMASS: Archive of Motion Capture As Surface Shapes. In 2019 IEEE\/CVF International Conference on Computer Vision, ICCV 2019","author":"Mahmood Naureen","year":"2019","unstructured":"Naureen Mahmood, Nima Ghorbani, Nikolaus F. Troje, Gerard Pons-Moll, and Michael J. Black. 2019. AMASS: Archive of Motion Capture As Surface Shapes. In 2019 IEEE\/CVF International Conference on Computer Vision, ICCV 2019, Seoul, Korea (South), October 27 - November 2, 2019. IEEE, 5441--5450."},{"key":"e_1_3_2_1_21_1","volume-title":"Text-to-Motion Retrieval: Towards Joint Understanding of Human Motion Data and Natural Language. In SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2023","author":"Messina Nicola","year":"2023","unstructured":"Nicola Messina, Jan Sedmidubsk\u00fd, Fabrizio Falchi, and Tom\u00e1s Rebok. 2023. Text-to-Motion Retrieval: Towards Joint Understanding of Human Motion Data and Natural Language. In SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2023, Taipei, Taiwan, July 23-27, 2023. ACM, 2420--2425."},{"key":"e_1_3_2_1_22_1","volume-title":"Tel Aviv","volume":"497","author":"Petrovich Mathis","year":"2022","unstructured":"Mathis Petrovich, Michael J. Black, and G\u00fcl Varol. 2022. TEMOS: Generating Diverse Human Motions from Textual Descriptions. In Computer Vision - ECCV 2022 - 17th European Conference, Tel Aviv, Israel, October 23-27, 2022, Proceedings, Part XXII (Lecture Notes in Computer Science, Vol. 13682). Springer, 480--497."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00870"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1089\/big.2016.0028"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00219"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591712"},{"key":"e_1_3_2_1_27_1","volume-title":"Learning Transferable Visual Models From Natural Language Supervision. In ICML 2021","volume":"8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. In ICML 2021, 18-24 July 2021, Virtual Event (Proceedings of Machine Learning Research, Vol. 139). PMLR, 8748--8763."},{"key":"e_1_3_2_1_28_1","volume-title":"a distilled version of BERT: smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108","author":"Sanh Victor","year":"2019","unstructured":"Victor Sanh, Lysandre Debut, Julien Chaumond, and Thomas Wolf. 2019. DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108 (2019)."},{"key":"e_1_3_2_1_29_1","volume-title":"Let 2D Diffusion Model Know 3D-Consistency for Robust Text-to-3D Generation. CoRR","author":"Seo Junyoung","year":"2023","unstructured":"Junyoung Seo, Wooseok Jang, Minseop Kwak, Jaehoon Ko, Hyeonsu Kim, Junho Kim, Jin-Hwa Kim, Jiyoung Lee, and Seungryong Kim. 2023. Let 2D Diffusion Model Know 3D-Consistency for Robust Text-to-3D Generation. CoRR, Vol. abs\/2303.07937 (2023)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00208"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00464"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00457"},{"key":"e_1_3_2_1_33_1","volume-title":"Representation Learning with Contrastive Predictive Coding. CoRR","author":"van den Oord A\u00e4ron","year":"2018","unstructured":"A\u00e4ron van den Oord, Yazhe Li, and Oriol Vinyals. 2018. Representation Learning with Contrastive Predictive Coding. CoRR, Vol. abs\/1807.03748 (2018). [arXiv]1807.03748"},{"key":"e_1_3_2_1_34_1","volume-title":"T2VLAD: Global-Local Sequence Alignment for Text-Video Retrieval. CoRR","author":"Wang Xiaohan","year":"2021","unstructured":"Xiaohan Wang, Linchao Zhu, and Yi Yang. 2021. T2VLAD: Global-Local Sequence Alignment for Text-Video Retrieval. CoRR, Vol. abs\/2104.10054 (2021). [arXiv]2104.10054"},{"key":"e_1_3_2_1_35_1","volume-title":"Virtual Event","author":"Zhang Hao","year":"2021","unstructured":"Hao Zhang, Aixin Sun, Wei Jing, Guoshun Nan, Liangli Zhen, Joey Tianyi Zhou, and Rick Siow Mong Goh. 2021. Video Corpus Moment Retrieval with Contrastive Learning. In ACM SIGIR, Virtual Event, Canada, July 11-15, 2021. ACM, 685--695."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611919"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3248873"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3239183"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01415"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591705"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00857"},{"key":"e_1_3_2_1_42_1","volume-title":"Multi-grained Representation Learning for Cross-modal Retrieval. SIGIR Conference on Research and Development in Information Retrieval, SIGIR","author":"Zhao Shengwei","year":"2023","unstructured":"Shengwei Zhao, Linhai Xu, Yuying Liu, and S. Du. 2023. Multi-grained Representation Learning for Cross-modal Retrieval. SIGIR Conference on Research and Development in Information Retrieval, SIGIR, Taipei, Taiwan, July 23-27 (2023)."}],"event":{"name":"SIGIR 2024: The 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Washington DC USA","acronym":"SIGIR 2024","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626772.3657804","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3626772.3657804","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T05:22:31Z","timestamp":1755840151000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626772.3657804"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,10]]},"references-count":42,"alternative-id":["10.1145\/3626772.3657804","10.1145\/3626772"],"URL":"https:\/\/doi.org\/10.1145\/3626772.3657804","relation":{},"subject":[],"published":{"date-parts":[[2024,7,10]]},"assertion":[{"value":"2024-07-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}