{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T01:24:20Z","timestamp":1779931460318,"version":"3.53.1"},"publisher-location":"New York, NY, USA","reference-count":51,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Natural Science Foundation of China","award":["62206200"],"award-info":[{"award-number":["62206200"]}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62206137"],"award-info":[{"award-number":["62206137"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681625","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:49Z","timestamp":1729925989000},"page":"10114-10123","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Modal-Enhanced Semantic Modeling for Fine-Grained 3D Human Motion Retrieval"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-7845-781X","authenticated-orcid":false,"given":"Haoyu","family":"Shi","sequence":"first","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":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"crossref","unstructured":"Relja Arandjelovic Petr Gronat Akihiko Torii Tomas Pajdla and Josef Sivic. 2016. NetVLAD: CNN architecture for weakly supervised place recognition.","DOI":"10.1109\/CVPR.2016.572"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01163"},{"key":"e_1_3_2_1_3_1","volume-title":"Rethinking Benchmarks for Cross-Modal Image-Text Retrieval. In ACM SIGIR (SIGIR '23)","author":"Chen Weijing","year":"2023","unstructured":"Weijing Chen, Linli Yao, and Qin Jin. 2023. Rethinking Benchmarks for Cross-Modal Image-Text Retrieval. In ACM SIGIR (SIGIR '23). Association for Computing Machinery, 1241--1251."},{"key":"e_1_3_2_1_4_1","volume-title":"Faisal Ahmed, Zhe Gan, Yu Cheng, and Jingjing Liu.","author":"Chen Yen-Chun","year":"2020","unstructured":"Yen-Chun Chen, Linjie Li, Licheng Yu, Ahmed El Kholy, Faisal Ahmed, Zhe Gan, Yu Cheng, and Jingjing Liu. 2020. UNITER: UNiversal Image-TExt Representation Learning. , 104--120 pages."},{"key":"e_1_3_2_1_5_1","volume-title":"Probabilistic Embeddings for Cross-Modal Retrieval. In Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Chun Sanghyuk","year":"2021","unstructured":"Sanghyuk Chun, Seong Joon Oh, Rafael Sampaio De Rezende, Yannis Kalantidis, and Diane Larlus. 2021. Probabilistic Embeddings for Cross-Modal Retrieval. In Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01434"},{"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","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01038"},{"key":"e_1_3_2_1_9_1","volume-title":"Self-Contrastive Learning with Hard Negative Sampling for Self-supervised Point Cloud Learning. In MM '21: ACM Multimedia Conference","author":"Du Bi'an","year":"2021","unstructured":"Bi'an Du, Xiang Gao, Wei Hu, and Xin Li. 2021. Self-Contrastive Learning with Hard Negative Sampling for Self-supervised Point Cloud Learning. In MM '21: ACM Multimedia Conference, Virtual Event, China, October 20 - 24, 2021. ACM, 3133--3142."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-022-00980-0"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01262"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413635"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01818"},{"key":"e_1_3_2_1_15_1","volume-title":"SIMBAD 2015, Copenhagen, Denmark, October 12--14, 2015. Proceedings 3. Springer, 84--92","author":"Hoffer Elad","year":"2015","unstructured":"Elad Hoffer and Nir Ailon. 2015. Deep metric learning using triplet network. In Similarity-based pattern recognition: third international workshop, SIMBAD 2015, Copenhagen, Denmark, October 12--14, 2015. Proceedings 3. Springer, 84--92."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00635"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"e_1_3_2_1_18_1","unstructured":"Jihoon Kim Youngjae Yu Seungyoun Shin Taehyun Byun and Sungjoon Choi. 2022. Learning Joint Representation of Human Motion and Language."},{"key":"e_1_3_2_1_19_1","volume-title":"Kingma and Jimmy Ba","author":"Diederik","year":"2017","unstructured":"Diederik P. Kingma and Jimmy Ba. 2017. Adam: A Method for Stochastic Optimization."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612101"},{"key":"e_1_3_2_1_22_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_23_1","volume-title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation. In ICML.","author":"Li Junnan","year":"2022","unstructured":"Junnan Li, Dongxu Li, Caiming Xiong, and Steven Hoi. 2022. BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation. In ICML."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01018"},{"key":"e_1_3_2_1_25_1","volume-title":"Exploring Negatives in Contrastive Learning for Unpaired Image-to-Image Translation. In MM '22: The 30th ACM International Conference on Multimedia","author":"Lin Yupei","year":"2022","unstructured":"Yupei Lin, Sen Zhang, Tianshui Chen, Yongyi Lu, Guangping Li, and Yukai Shi. 2022. Exploring Negatives in Contrastive Learning for Unpaired Image-to-Image Translation. In MM '22: The 30th ACM International Conference on Multimedia, Lisboa, Portugal, October 10 - 14, 2022. ACM, 1186--1194."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"crossref","unstructured":"Ziyu Liu Hongwen Zhang Zhenghao Chen Zhiyong Wang and Wanli Ouyang. 2020. Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition.","DOI":"10.1109\/CVPR42600.2020.00022"},{"key":"e_1_3_2_1_27_1","volume-title":"X-CLIP: End-to-End Multi-grained Contrastive Learning for Video-Text Retrieval. ACM Multimedia","author":"Ma Yiwei","year":"2022","unstructured":"Yiwei Ma, Guohai Xu, Xiaoshuai Sun, Ming Yan, Ji Zhang, and Rongrong Ji. 2022. X-CLIP: End-to-End Multi-grained Contrastive Learning for Video-Text Retrieval. ACM Multimedia (2022)."},{"key":"e_1_3_2_1_28_1","volume-title":"AMASS: Archive of Motion Capture As Surface Shapes. In 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 ICCV 2019, Seoul, Korea (South), October 27 - November 2, 2019. IEEE, 5441--5450."},{"key":"e_1_3_2_1_29_1","volume-title":"Text-to-Motion Retrieval: Towards Joint Understanding of Human Motion Data and Natural Language. In ACM 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 ACM SIGIR 2023, Taipei, Taiwan, July 23--27, 2023. ACM, 2420--2425."},{"key":"e_1_3_2_1_31_1","volume-title":"Proceedings, Part XXII (Lecture Notes in Computer Science","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_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00870"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1089\/big.2016.0028"},{"key":"e_1_3_2_1_34_1","volume-title":"Learnable Pillar-Based Re-Ranking for Image-Text Retrieval. In ACM SIGIR (SIGIR '23)","author":"Qu Leigang","year":"2023","unstructured":"Leigang Qu, Meng Liu, Wenjie Wang, Zhedong Zheng, Liqiang Nie, and Tat-Seng Chua. 2023. Learnable Pillar-Based Re-Ranking for Image-Text Retrieval. In ACM SIGIR (SIGIR '23). 1252--1261."},{"key":"e_1_3_2_1_35_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18--24","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 Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18--24 July 2021, Virtual Event (Proceedings of Machine Learning Research, Vol. 139). PMLR, 8748--8763."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"crossref","unstructured":"Yu Rong Takaaki Shiratori and Hanbyul Joo. 2021. FrankMocap: A Monocular 3D Whole-Body Pose Estimation System via Regression and Integration.","DOI":"10.1109\/ICCVW54120.2021.00201"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01850"},{"key":"e_1_3_2_1_38_1","volume-title":"a distilled version of BERT: smaller, faster, cheaper and lighter. CoRR","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. CoRR, Vol. abs\/1910.01108 (2019)."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3028207"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00464"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00457"},{"key":"e_1_3_2_1_42_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)."},{"key":"e_1_3_2_1_43_1","volume-title":"Unified Coarse-to-Fine Alignment for Video-Text Retrieval. In 2023 IEEE\/CVF International Conference on Computer Vision (ICCV). 2804--2815","author":"Wang Ziyang","year":"2023","unstructured":"Ziyang Wang, Yi-Lin Sung, Feng Cheng, Gedas Bertasius, and Mohit Bansal. 2023. Unified Coarse-to-Fine Alignment for Video-Text Retrieval. In 2023 IEEE\/CVF International Conference on Computer Vision (ICCV). 2804--2815."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01031"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3595916.3626459"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657804"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3248873"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3239183"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591705"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00857"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3592025"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611932"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681625","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681625","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:49Z","timestamp":1750295869000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681625"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":51,"alternative-id":["10.1145\/3664647.3681625","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681625","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}