{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T15:22:14Z","timestamp":1783610534790,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":82,"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":["62301432"],"award-info":[{"award-number":["62301432"]}]},{"name":"the National Natural Science Foundation of China","award":["62306240"],"award-info":[{"award-number":["62306240"]}]},{"name":"China Postdoctoral Science Foundation","award":["2023TQ0272"],"award-info":[{"award-number":["2023TQ0272"]}]},{"name":"the Fundamental Research Funds for the Central Universities","award":["D5000220431"],"award-info":[{"award-number":["D5000220431"]}]},{"name":"the National Natural Science Foundation of China","award":["U23B2013"],"award-info":[{"award-number":["U23B2013"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681442","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:41Z","timestamp":1729925981000},"page":"9301-9310","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":38,"title":["Weakly Supervised Video Anomaly Detection and Localization with Spatio-Temporal Prompts"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2938-6798","authenticated-orcid":false,"given":"Peng","family":"Wu","sequence":"first","affiliation":[{"name":"Northwestern Polytechnical University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0460-6009","authenticated-orcid":false,"given":"Xuerong","family":"Zhou","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9877-2716","authenticated-orcid":false,"given":"Guansong","family":"Pang","sequence":"additional","affiliation":[{"name":"Singapore Management University, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9896-4518","authenticated-orcid":false,"given":"Zhiwei","family":"Yang","sequence":"additional","affiliation":[{"name":"Xidian University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1010-3540","authenticated-orcid":false,"given":"Qingsen","family":"Yan","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7689-3405","authenticated-orcid":false,"given":"Peng","family":"Wang","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2977-8057","authenticated-orcid":false,"given":"Yanning","family":"Zhang","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University, Xi'an, 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":"publisher","DOI":"10.1109\/CVPR52688.2022.01951"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3112814"},{"key":"e_1_3_2_1_4_1","volume-title":"CLIP-AD: A Language-Guided Staged Dual-Path Model for Zero-shot Anomaly Detection. arXiv preprint arXiv:2311.00453","author":"Chen Xuhai","year":"2023","unstructured":"Xuhai Chen, Jiangning Zhang, Guanzhong Tian, Haoyang He, Wuhao Zhang, Yabiao Wang, Chengjie Wang, Yunsheng Wu, and Yong Liu. 2023. CLIP-AD: A Language-Guided Staged Dual-Path Model for Zero-shot Anomaly Detection. arXiv preprint arXiv:2311.00453 (2023)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19915"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995434"},{"key":"e_1_3_2_1_7_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly et al. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.316"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01379"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475693"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01255"},{"key":"e_1_3_2_1_12_1","first-page":"4505","article-title":"A background-agnostic framework with adversarial training for abnormal event detection in video","volume":"44","author":"Georgescu Mariana Iuliana","year":"2021","unstructured":"Mariana Iuliana Georgescu, Radu Tudor Ionescu, Fahad Shahbaz Khan, Marius Popescu, and Mubarak Shah. 2021. A background-agnostic framework with adversarial training for abnormal event detection in video. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 44, 9 (2021), 4505--4523.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_2_1_13_1","volume-title":"Weakly-supervised spatiotemporal anomaly detection","author":"Gianchandani Urvi","unstructured":"Urvi Gianchandani, Praveen Tirupattur, and Mubarak Shah. 2019. Weakly-supervised spatiotemporal anomaly detection. University of Central Florida Center for Research in Computer Vision REU (2019)."},{"key":"e_1_3_2_1_14_1","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision. 1705--1714","author":"Gong Dong","unstructured":"Dong Gong, Lingqiao Liu, Vuong Le, Budhaditya Saha, Moussa Reda Mansour, Svetha Venkatesh, and Anton van den Hengel. 2019. Memorizing normality to detect anomaly: Memory-augmented deep autoencoder for unsupervised anomaly detection. In Proceedings of the IEEE\/CVF International Conference on Computer Vision. 1705--1714."},{"key":"e_1_3_2_1_15_1","first-page":"1","article-title":"Bic-net: Learning efficient spatio-temporal relation for text-video retrieval","volume":"20","author":"Han Ning","year":"2023","unstructured":"Ning Han, Yawen Zeng, Chuhao Shi, Guangyi Xiao, Hao Chen, and Jingjing Chen. 2023. Bic-net: Learning efficient spatio-temporal relation for text-video retrieval. ACM Transactions on Multimedia Computing, Communications and Applications, Vol. 20, 3 (2023), 1--21.","journal-title":"ACM Transactions on Multimedia Computing, Communications and Applications"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00685"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.86"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00867"},{"key":"e_1_3_2_1_19_1","volume-title":"Weakly Supervised Video Anomaly Detection via Self-Guided Temporal Discriminative Transformer","author":"Huang Chao","year":"2022","unstructured":"Chao Huang, Chengliang Liu, Jie Wen, Lian Wu, Yong Xu, Qiuping Jiang, and Yaowei Wang. 2022. Weakly Supervised Video Anomaly Detection via Self-Guided Temporal Discriminative Transformer. IEEE Transactions on Cybernetics (2022)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548082"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548369"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00803"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01878"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP49359.2023.10222289"},{"key":"e_1_3_2_1_25_1","volume-title":"Tel Aviv","author":"Ju Chen","year":"2022","unstructured":"Chen Ju, Tengda Han, Kunhao Zheng, Ya Zhang, and Weidi Xie. 2022. Prompting visual-language models for efficient video understanding. In Computer Vision-ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23-27, 2022, Proceedings, Part XXXV. Springer, 105--124."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.472"},{"key":"e_1_3_2_1_27_1","volume-title":"Cees GM Snoek, and Rita Cucchiara","author":"Landi Federico","year":"2019","unstructured":"Federico Landi, Cees GM Snoek, and Rita Cucchiara. 2019. Anomaly locality in video surveillance. arXiv preprint arXiv:1901.10364 (2019)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_20"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2984093"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20028"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1109\/TPAMI.2013.111","article-title":"Anomaly detection and localization in crowded scenes","volume":"36","author":"Li Weixin","year":"2013","unstructured":"Weixin Li, Vijay Mahadevan, and Nuno Vasconcelos. 2013. Anomaly detection and localization in crowded scenes. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 36, 1 (2013), 18--32.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12333"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350998"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00684"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612393"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.338"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2017.8019325"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00775"},{"key":"e_1_3_2_1_40_1","volume-title":"Tel Aviv","author":"Nag Sauradip","year":"2022","unstructured":"Sauradip Nag, Xiatian Zhu, Yi-Zhe Song, and Tao Xiang. 2022. Zero-shot temporal action detection via vision-language prompting. In Computer Vision-ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23-27, 2022, Proceedings, Part III. Springer, 681--697."},{"key":"e_1_3_2_1_41_1","volume-title":"Tel Aviv","author":"Ni Bolin","year":"2022","unstructured":"Bolin Ni, Houwen Peng, Minghao Chen, Songyang Zhang, Gaofeng Meng, Jianlong Fu, Shiming Xiang, and Haibin Ling. 2022. Expanding language-image pretrained models for general video recognition. In Computer Vision-ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23-27, 2022, Proceedings, Part IV. Springer, 1--18."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00053"},{"key":"e_1_3_2_1_43_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 12173--12182","author":"Pang Guansong","unstructured":"Guansong Pang, Cheng Yan, Chunhua Shen, Anton van den Hengel, and Xiao Bai. 2020. Self-trained deep ordinal regression for end-to-end video anomaly detection. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 12173--12182."},{"key":"e_1_3_2_1_44_1","volume-title":"Learning Prompt-Enhanced Context Features for Weakly-Supervised Video Anomaly Detection. arXiv preprint arXiv:2306.14451","author":"Pu Yujiang","year":"2023","unstructured":"Yujiang Pu, Xiaoyu Wu, and Shengjin Wang. 2023. Learning Prompt-Enhanced Context Features for Weakly-Supervised Video Anomaly Detection. arXiv preprint arXiv:2306.14451 (2023)."},{"key":"e_1_3_2_1_45_1","volume-title":"International Conference on Machine Learning. PMLR, 8748--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, et al. 2021. Learning transferable visual models from natural language supervision. In International Conference on Machine Learning. PMLR, 8748--8763."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"e_1_3_2_1_47_1","volume-title":"Marius Popescu, Fahad Shahbaz Khan, and Mubarak Shah.","author":"Ristea Nicolae-Catalin","year":"2023","unstructured":"Nicolae-Catalin Ristea, Florinel-Alin Croitoru, Radu Tudor Ionescu, Marius Popescu, Fahad Shahbaz Khan, and Mubarak Shah. 2023. Self-distilled masked auto-encoders are efficient video anomaly detectors. arXiv preprint arXiv:2306.12041 (2023)."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01321"},{"key":"e_1_3_2_1_49_1","volume-title":"Advances in Neural Information Processing Systems","volume":"12","author":"Sch\u00f6lkopf Bernhard","year":"1999","unstructured":"Bernhard Sch\u00f6lkopf, Robert C Williamson, Alex Smola, John Shawe-Taylor, and John Platt. 1999. Support vector method for novelty detection. Advances in Neural Information Processing Systems, Vol. 12 (1999)."},{"key":"e_1_3_2_1_50_1","volume-title":"Advances in Neural Information Processing Systems","volume":"27","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Two-stream convolutional networks for action recognition in videos. Advances in Neural Information Processing Systems, Vol. 27 (2014)."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2950530"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00678"},{"key":"e_1_3_2_1_53_1","volume-title":"Long-Short Temporal Co-Teaching for Weakly Supervised Video Anomaly Detection. arXiv preprint arXiv:2303.18044","author":"Sun Shengyang","year":"2023","unstructured":"Shengyang Sun and Xiaojin Gong. 2023. Long-Short Temporal Co-Teaching for Weakly Supervised Video Anomaly Detection. arXiv preprint arXiv:2303.18044 (2023)."},{"key":"e_1_3_2_1_54_1","volume-title":"Self-supervised pseudo multi-class pre-training for unsupervised anomaly detection and segmentation in medical images. Medical image analysis","author":"Tian Yu","year":"2023","unstructured":"Yu Tian, Fengbei Liu, Guansong Pang, Yuanhong Chen, Yuyuan Liu, Johan W Verjans, Rajvinder Singh, and Gustavo Carneiro. 2023. Self-supervised pseudo multi-class pre-training for unsupervised anomaly detection and segmentation in medical images. Medical image analysis, Vol. 90 (2023), 102930."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00493"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_29"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00155"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00193"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240615"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413529"},{"key":"e_1_3_2_1_64_1","volume-title":"Weakly-supervised spatio-temporal anomaly detection in surveillance video. arXiv preprint arXiv:2108.03825","author":"Wu Jie","year":"2021","unstructured":"Jie Wu, Wei Zhang, Guanbin Li, Wenhao Wu, Xiao Tan, Yingying Li, Errui Ding, and Liang Lin. 2021. Weakly-supervised spatio-temporal anomaly detection in surveillance video. arXiv preprint arXiv:2108.03825 (2021)."},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107515"},{"key":"e_1_3_2_1_66_1","first-page":"2609","article-title":"A deep one-class neural network for anomalous event detection in complex scenes","volume":"31","author":"Wu Peng","year":"2019","unstructured":"Peng Wu, Jing Liu, and Fang Shen. 2019. A deep one-class neural network for anomalous event detection in complex scenes. IEEE Transactions on Neural Networks and Learning Systems, Vol. 31, 7 (2019), 2609--2622.","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_20"},{"key":"e_1_3_2_1_68_1","volume-title":"Weakly supervised audio-visual violence detection","author":"Wu Peng","year":"2022","unstructured":"Peng Wu, Xiaotao Liu, and Jing Liu. 2022. Weakly supervised audio-visual violence detection. IEEE Transactions on Multimedia (2022), 1674--1685."},{"key":"e_1_3_2_1_69_1","volume-title":"DSS-Net: Dynamic Self-Supervised Network for Video Anomaly Detection","author":"Wu Peihao","year":"2023","unstructured":"Peihao Wu, Wenqian Wang, Faliang Chang, Chunsheng Liu, and Bin Wang. 2023. DSS-Net: Dynamic Self-Supervised Network for Video Anomaly Detection. IEEE Transactions on Multimedia (2023)."},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01732"},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28423"},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.105835"},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01402"},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350899"},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413973"},{"key":"e_1_3_2_1_76_1","volume-title":"Claws: Clustering assisted weakly supervised learning with normalcy suppression for anomalous event detection. In Computer Vision-ECCV 2020: 16th European Conference","author":"Zaheer Muhammad Zaigham","year":"2020","unstructured":"Muhammad Zaigham Zaheer, Arif Mahmood, Marcella Astrid, and Seung-Ik Lee. 2020. Claws: Clustering assisted weakly supervised learning with normalcy suppression for anomalous event detection. In Computer Vision-ECCV 2020: 16th European Conference, Glasgow, UK, August 23-28, 2020, Proceedings, Part XXII 16. Springer, 358--376."},{"key":"e_1_3_2_1_77_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123451"},{"key":"e_1_3_2_1_78_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00133"},{"key":"e_1_3_2_1_79_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25489"},{"key":"e_1_3_2_1_80_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"e_1_3_2_1_81_1","volume-title":"Anomalyclip: Object-agnostic prompt learning for zero-shot anomaly detection. arXiv preprint arXiv:2310.18961","author":"Zhou Qihang","year":"2023","unstructured":"Qihang Zhou, Guansong Pang, Yu Tian, Shibo He, and Jiming Chen. 2023. Anomalyclip: Object-agnostic prompt learning for zero-shot anomaly detection. arXiv preprint arXiv:2310.18961 (2023)."},{"key":"e_1_3_2_1_82_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01688"}],"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\/3664647.3681442","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681442","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:57:47Z","timestamp":1750294667000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681442"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":82,"alternative-id":["10.1145\/3664647.3681442","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681442","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"}}]}}