{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T07:40:32Z","timestamp":1763106032537,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":66,"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":"The Oversea Innovation Team Project of the 20 Regulations for New Universities funding program of Jinan","award":["(Grant no. 2021GXRC073)"],"award-info":[{"award-number":["(Grant no. 2021GXRC073)"]}]},{"name":"Shandong Province Excellent Young Scientists Fund Program (Overseas)","award":["(Grant no. 2022HWYQ-048)"],"award-info":[{"award-number":["(Grant no. 2022HWYQ-048)"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681547","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:27Z","timestamp":1729925967000},"page":"3936-3944","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Modeling Event-level Causal Representation for Video Classification"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-9342-0276","authenticated-orcid":false,"given":"Yuqing","family":"Wang","sequence":"first","affiliation":[{"name":"Shandong University, Jinan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0273-5946","authenticated-orcid":false,"given":"Lei","family":"Meng","sequence":"additional","affiliation":[{"name":"Shandong University & Shandong Research Institute of Industrial Technology, Jinan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4621-5213","authenticated-orcid":false,"given":"Haokai","family":"Ma","sequence":"additional","affiliation":[{"name":"Shandong University, Jinan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4151-8290","authenticated-orcid":false,"given":"Yuqing","family":"Wang","sequence":"additional","affiliation":[{"name":"Shandong University, Jinan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5592-0726","authenticated-orcid":false,"given":"Haibei","family":"Huang","sequence":"additional","affiliation":[{"name":"Inspur, Jinan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7290-5659","authenticated-orcid":false,"given":"Xiangxu","family":"Meng","sequence":"additional","affiliation":[{"name":"Shandong University, Jinan, China"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"crossref","unstructured":"Ehsan Abbasnejad Damien Teney Amin Parvaneh et al. 2020. Counterfactual vision and language learning. In CVPR. 10044--10054.","DOI":"10.1109\/CVPR42600.2020.01006"},{"key":"e_1_3_2_1_2_1","volume-title":"Vivit: A video vision transformer. In CVPR. 6836--6846.","author":"Arnab Anurag","year":"2021","unstructured":"Anurag Arnab, Mostafa Dehghani, Georg Heigold, Chen Sun, et al. 2021. Vivit: A video vision transformer. In CVPR. 6836--6846."},{"key":"e_1_3_2_1_3_1","volume-title":"Scalable k-means. arXiv preprint arXiv:1203.6402","author":"Bahmani Bahman","year":"2012","unstructured":"Bahman Bahmani, Benjamin Moseley, Andrea Vattani, Ravi Kumar, and Sergei Vassilvitskii. 2012. Scalable k-means. arXiv preprint arXiv:1203.6402 (2012)."},{"key":"e_1_3_2_1_4_1","unstructured":"Elias Bareinboim and Judea Pearl. 2012. Controlling selection bias in causal inference. In Artificial Intelligence and Statistics. 100--108."},{"key":"e_1_3_2_1_5_1","first-page":"4","article-title":"Is space-time attention all you need for video understanding?","volume":"2","author":"Bertasius Gedas","year":"2021","unstructured":"Gedas Bertasius, Heng Wang, and Lorenzo Torresani. 2021. Is space-time attention all you need for video understanding?. In ICML, Vol. 2. 4.","journal-title":"ICML"},{"key":"e_1_3_2_1_6_1","volume-title":"Counterfactuals uncover the modular structure of deep generative models. arXiv preprint arXiv:1812.03253","author":"Besserve Michel","year":"2018","unstructured":"Michel Besserve, Arash Mehrjou, R\u00e9my Sun, and Bernhard Sch\u00f6lkopf. 2018. Counterfactuals uncover the modular structure of deep generative models. arXiv preprint arXiv:1812.03253 (2018)."},{"key":"e_1_3_2_1_7_1","volume-title":"Activitynet: A large-scale video benchmark for human activity understanding. In CVPR. 961--970.","author":"Heilbron Fabian Caba","year":"2015","unstructured":"Fabian Caba Heilbron and Bernard Escorcia, et al. 2015. Activitynet: A large-scale video benchmark for human activity understanding. In CVPR. 961--970."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"crossref","unstructured":"Joao Carreira and Andrew Zisserman. 2017. Quo vadis action recognition? a new model and the kinetics dataset. In CVPR. 6299--6308.","DOI":"10.1109\/CVPR.2017.502"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"crossref","unstructured":"Zitan Chen Zhuang Qi Xiao Cao Xiangxian Li Xiangxu Meng and Lei Meng. 2023. Class-level Structural Relation Modeling and Smoothing for Visual Representation Learning. In ACM MM. 2964--2972.","DOI":"10.1145\/3581783.3612511"},{"key":"e_1_3_2_1_10_1","unstructured":"Alexey Dosovitskiy Beyer 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_11_1","doi-asserted-by":"crossref","unstructured":"Christoph Feichtenhofer. 2020. X3d: Expanding architectures for efficient video recognition. In CVPR. 203--213.","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"crossref","unstructured":"Christoph Feichtenhofer Haoqi Fan Jitendra Malik and Kaiming He. 2019. Slowfast networks for video recognition. In ICCV. 6202--6211.","DOI":"10.1109\/ICCV.2019.00630"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3265645"},{"key":"e_1_3_2_1_14_1","volume-title":"Benchmarking Micro-action Recognition: Dataset, Methods, and Applications","author":"Guo Dan","year":"2024","unstructured":"Dan Guo, Kun Li, Bin Hu, Yan Zhang, and Meng Wang. 2024. Benchmarking Micro-action Recognition: Dataset, Methods, and Applications. IEEE Transactions on Circuits and Systems for Video Technology (2024)."},{"key":"e_1_3_2_1_15_1","unstructured":"Yanbin Hao Hao Zhang Chong-Wah Ngo and Xiangnan He. 2022. Group contextualization for video recognition. In CVPR. 928--938."},{"key":"e_1_3_2_1_16_1","volume-title":"Pin-Yu Chen, Andrew Brown, and Marcel Worring.","author":"Huang Jia-Hong","year":"2022","unstructured":"Jia-Hong Huang, Chao-Han Huck Yang, Pin-Yu Chen, Andrew Brown, and Marcel Worring. 2022. Causal video summarizer for video exploration. In ICME. 1--6."},{"key":"e_1_3_2_1_17_1","volume-title":"Uniformerv2: Spatiotemporal learning by arming image vits with video uniformer. arXiv preprint arXiv:2211.09552","author":"Li Kunchang","year":"2022","unstructured":"Kunchang Li, Yali Wang, Yinan He, Yizhuo Li, Yi Wang, Limin Wang, and Yu Qiao. 2022. Uniformerv2: Spatiotemporal learning by arming image vits with video uniformer. arXiv preprint arXiv:2211.09552 (2022)."},{"key":"e_1_3_2_1_18_1","volume-title":"Cross-modal learning using privileged information for long-tailed image classification. CVM","author":"Li Xiangxian","year":"2024","unstructured":"Xiangxian Li, Yuze Zheng, Haokai Ma, Zhuang Qi, Xiangxu Meng, and Lei Meng. 2024. Cross-modal learning using privileged information for long-tailed image classification. CVM (2024), 1--12."},{"key":"e_1_3_2_1_19_1","volume-title":"Tea: Temporal excitation and aggregation for action recognition. In CVPR. 909--918.","author":"Li Yan","year":"2020","unstructured":"Yan Li, Bin Ji, Xintian Shi, Jianguo Zhang, Bin Kang, and Limin Wang. 2020. Tea: Temporal excitation and aggregation for action recognition. In CVPR. 909--918."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"crossref","unstructured":"Chuang Lin Sicheng Zhao Lei Meng and Tat-Seng Chua. 2020. Multi-source domain adaptation for visual sentiment classification. In AAAI. 2661--2668.","DOI":"10.1609\/aaai.v34i03.5651"},{"key":"e_1_3_2_1_21_1","volume-title":"Tsm: Temporal shift module for efficient video understanding. In ICCV. 7083--7093.","author":"Lin Ji","year":"2019","unstructured":"Ji Lin, Chuang Gan, and Song Han. 2019. Tsm: Temporal shift module for efficient video understanding. In ICCV. 7083--7093."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"crossref","unstructured":"Jinxing Liu Junjin Xiao Haokai Ma Xiangxian Li Zhuang Qi Xiangxu Meng and Lei Meng. 2022 d. Prompt learning with cross-modal feature alignment for visual domain adaptation. In CICAI. 416--428.","DOI":"10.1007\/978-3-031-20497-5_34"},{"key":"e_1_3_2_1_23_1","unstructured":"Jiang-Jiang Liu Qibin Hou and Ming-Ming Cheng et al. 2019. A simple pooling-based design for real-time salient object detection. In CVPR. 3917--3926."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"crossref","unstructured":"Ruyang Liu Hao Liu Ge Li et al. 2022. Contextual debiasing for visual recognition with causal mechanisms. In CVPR. 12755--12765.","DOI":"10.1109\/CVPR52688.2022.01242"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3284038"},{"key":"e_1_3_2_1_26_1","first-page":"485","article-title":"Causal reasoning meets visual representation learning: A prospective study","volume":"19","author":"Liu Yang","year":"2022","unstructured":"Yang Liu, Yu-Shen Wei, Hong Yan, Guan-Bin Li, and Liang Lin. 2022. Causal reasoning meets visual representation learning: A prospective study. MIR, Vol. 19, 6 (2022), 485--511.","journal-title":"MIR"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"crossref","unstructured":"Ze Liu Jia Ning Yue Cao Yixuan Wei Zheng Zhang Stephen Lin and Han Hu. 2022. Video swin transformer. In CVPR. 3202--3211.","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"e_1_3_2_1_28_1","volume-title":"Tam: Temporal adaptive module for video recognition. In ICCV. 13708--13718.","author":"Liu Zhaoyang","year":"2021","unstructured":"Zhaoyang Liu, Limin Wang, Wayne Wu, Chen Qian, and Tong Lu. 2021. Tam: Temporal adaptive module for video recognition. In ICCV. 13708--13718."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3475724.3483600"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i8.28736"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"crossref","unstructured":"Lei Meng Long Chen Xun Yang Dacheng Tao Hanwang Zhang Chunyan Miao and Tat-Seng Chua. 2019. Learning using privileged information for food recognition. In ACM MM. 557--565.","DOI":"10.1145\/3343031.3350870"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"crossref","unstructured":"Lei Meng Fuli Feng Xiangnan He Xiaoyan Gao and Tat-Seng Chua. 2020. Heterogeneous fusion of semantic and collaborative information for visually-aware food recommendation. In ACM MM. 3460--3468.","DOI":"10.1145\/3394171.3413598"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"crossref","unstructured":"Lei Meng Zhuang Qi Lei Wu Xiaoyu Du Li et al. 2024. Improving Global Generalization and Local Personalization for Federated Learning. TNNLS (2024).","DOI":"10.1109\/TNNLS.2024.3417452"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"crossref","unstructured":"Lei Meng Ah-Hwee Tan Cyril Leung Liqiang Nie Tat-Seng Chua and Chunyan Miao. 2015. Online multimodal co-indexing and retrieval of weakly labeled web image collections. In ICMR. 219--226.","DOI":"10.1145\/2671188.2749362"},{"key":"e_1_3_2_1_35_1","unstructured":"Guoshun Nan Rui Qiao Yao Xiao et al. 2021. Interventional video grounding with dual contrastive learning. In CVPR. 2765--2775."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"crossref","unstructured":"Judea Pearl. 2009. Causal inference in statistics: An overview. (2009).","DOI":"10.1214\/09-SS057"},{"volume-title":"Causal inference in statistics: A primer","author":"Pearl Judea","key":"e_1_3_2_1_37_1","unstructured":"Judea Pearl, Madelyn Glymour, and Nicholas P Jewell. 2016. Causal inference in statistics: A primer. John Wiley & Sons."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"crossref","unstructured":"Zhuang Qi Lei Meng and Zitan Chen et al. 2023. Cross-silo prototypical calibration for federated learning with non-iid data. In ACM MM. 3099--3107.","DOI":"10.1145\/3581783.3612481"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"crossref","unstructured":"Zhuang Qi Yuqing Wang Zitan Chen Ran Wang Xiangxu Meng and Lei Meng. 2022. Clustering-based curriculum construction for sample-balanced federated learning. In CICAI. 155--166.","DOI":"10.1007\/978-3-031-20503-3_13"},{"key":"e_1_3_2_1_40_1","first-page":"1033","article-title":"Causal interventional training for image recognition","volume":"25","author":"Qin Wei","year":"2021","unstructured":"Wei Qin, Hanwang Zhang, Richang Hong, Ee-Peng Lim, and Qianru Sun. 2021. Causal interventional training for image recognition. TMM, Vol. 25 (2021), 1033--1044.","journal-title":"TMM"},{"key":"e_1_3_2_1_41_1","volume-title":"EM algorithms for PCA and SPCA. Advances in neural information processing systems","author":"Roweis Sam","year":"1997","unstructured":"Sam Roweis. 1997. EM algorithms for PCA and SPCA. Advances in neural information processing systems, Vol. 10 (1997)."},{"key":"e_1_3_2_1_42_1","volume-title":"Grad-cam: Visual explanations from deep networks via gradient-based localization. In ICCV. 618--626.","author":"Selvaraju Ramprasaath R","year":"2017","unstructured":"Ramprasaath R Selvaraju, Michael Cogswell, Abhishek Das, Ramakrishna Vedantam, Devi Parikh, and Dhruv Batra. 2017. Grad-cam: Visual explanations from deep networks via gradient-based localization. In ICCV. 618--626."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3133717"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"crossref","unstructured":"Yi Tan Yanbin Hao Hao Zhang et al. 2022. Hierarchical Hourglass Convolutional Network for Efficient Video Classification. In ACM MM. 5880--5891.","DOI":"10.1145\/3503161.3547841"},{"key":"e_1_3_2_1_45_1","article-title":"Visualizing data using t-SNE","volume":"9","author":"der Maaten Laurens Van","year":"2008","unstructured":"Laurens Van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. Journal of machine learning research, Vol. 9, 11 (2008).","journal-title":"Journal of machine learning research"},{"key":"e_1_3_2_1_46_1","volume-title":"Tdn: Temporal difference networks for efficient action recognition. In CVPR. 1895--1904.","author":"Wang Limin","year":"2021","unstructured":"Limin Wang, Zhan Tong, Bin Ji, and Gangshan Wu. 2021. Tdn: Temporal difference networks for efficient action recognition. In CVPR. 1895--1904."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"crossref","unstructured":"Limin Wang Yuanjun Xiong and Zhe Wang et al. 2018. Temporal segment networks for action recognition in videos. TPAMI (2018) 2740--2755.","DOI":"10.1109\/TPAMI.2018.2868668"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"crossref","unstructured":"Tan Wang Jianqiang Huang Hanwang Zhang and Qianru Sun. 2020. Visual commonsense r-cnn. In CVPR. 10760--10770.","DOI":"10.1109\/CVPR42600.2020.01077"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"crossref","unstructured":"Tao Wang Yu Li et al. 2020. The devil is in classification: A simple framework for long-tail instance segmentation. In ECCV. 728--744.","DOI":"10.1007\/978-3-030-58568-6_43"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"crossref","unstructured":"Xiaolong Wang and other. 2018. Non-local neural networks. In CVPR. 7794--7803.","DOI":"10.1109\/CVPR.2018.00813"},{"key":"e_1_3_2_1_51_1","volume-title":"Causal inference for out-of-distribution recognition via sample balancing. CAAI Transactions on Intelligence Technology","author":"Wang Yuqing","year":"2024","unstructured":"Yuqing Wang, Xiangxian Li, Yannan Liu, Xiao Cao, Xiangxu Meng, and Lei Meng. 2024. Causal inference for out-of-distribution recognition via sample balancing. CAAI Transactions on Intelligence Technology (2024)."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"crossref","unstructured":"Yuqing Wang Xiangxian Li Haokai Ma Zhuang Qi Xiangxu Meng and Lei Meng. 2022. Causal inference with sample balancing for out-of-distribution detection in visual classification. In CICAI. 572--583.","DOI":"10.1007\/978-3-031-20497-5_47"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"crossref","unstructured":"Yuqing Wang Xiangxian Li Zhuang Qi et al. 2022. Meta-causal feature learning for out-of-distribution generalization. In ECCV. 530--545.","DOI":"10.1007\/978-3-031-25075-0_36"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"crossref","unstructured":"Yuqing Wang Zhuang Qi Xiangxian Li Jinxing Liu Xiangxu Meng and Lei Meng. 2023. Multi-channel attentive weighting of visual frames for multimodal video classification. In IJCNN. 1--8.","DOI":"10.1109\/IJCNN54540.2023.10192036"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"crossref","unstructured":"Yushen Wei Yang Liu Hong Yan Guanbin Li and Liang Lin. 2023. Visual causal scene refinement for video question answering. In ACM MM. 377--386.","DOI":"10.1145\/3581783.3611873"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3062192"},{"key":"e_1_3_2_1_57_1","unstructured":"Saining Xie Chen Sun et al. 2018. Rethinking spatiotemporal feature learning: Speed-accuracy trade-offs in video classification. In ECCV. 305--321."},{"key":"e_1_3_2_1_58_1","volume-title":"Msr-vtt: A large video description dataset for bridging video and language. In CVPR. 5288--5296.","author":"Xu Jun","year":"2016","unstructured":"Jun Xu, Tao Mei, Ting Yao, and Yong Rui. 2016. Msr-vtt: A large video description dataset for bridging video and language. In CVPR. 5288--5296."},{"key":"e_1_3_2_1_59_1","unstructured":"Kelvin Xu Jimmy Ba Ryan Kiros Kyunghyun Cho Aaron Courville Ruslan Salakhudinov Rich Zemel and Yoshua Bengio. 2015. Show attend and tell: Neural image caption generation with visual attention. In ICML. 2048--2057."},{"key":"e_1_3_2_1_60_1","unstructured":"Xun Yang Tianyu Chang et al. 2024. Learning Hierarchical Visual Transformation for Domain Generalizable Visual Matching and Recognition. International Journal of Computer Vision (2024) 1--27."},{"key":"e_1_3_2_1_61_1","first-page":"12996","article-title":"Deconfounded image captioning: A causal retrospect","volume":"45","author":"Yang Xu","year":"2021","unstructured":"Xu Yang, Hanwang Zhang, and Jianfei Cai. 2021. Deconfounded image captioning: A causal retrospect. TPAMI, Vol. 45, 11 (2021), 12996--13010.","journal-title":"TPAMI"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"crossref","unstructured":"Chuanqi Zang and Hanqing Wang et al. 2023. Discovering the real association: Multimodal causal reasoning in video question answering. In CVPR. 19027--19036.","DOI":"10.1109\/CVPR52729.2023.01824"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"crossref","unstructured":"Hao Zhang Lechao Cheng et al. 2022. Long-term leap attention short-term periodic shift for video classification. In ACM MM. 5773--5782.","DOI":"10.1145\/3503161.3547908"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"crossref","unstructured":"Hao Zhang Yanbin Hao and Chong-Wah Ngo. 2021. Token shift transformer for video classification. In ACM MM. 917--925.","DOI":"10.1145\/3474085.3475272"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"crossref","unstructured":"Xiheng Zhang Yongkang Wong Xiaofei Wu Juwei Lu et al. 2021. Learning causal representation for training cross-domain pose estimator via generative interventions. In ICCV. 11270--11280.","DOI":"10.1109\/ICCV48922.2021.01108"},{"key":"e_1_3_2_1_66_1","unstructured":"Yuze Zheng Zixuan Li Xiangxian Li Jinxing Liu Yuqing Wang Xiangxu Meng and Lei Meng. 2024. Unifying Visual and Semantic Feature Spaces with Diffusion Models for Enhanced Cross-Modal Alignment. arxiv: 2407.18854 [cs.CV] https:\/\/arxiv.org\/abs\/2407.18854"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Melbourne VIC Australia","acronym":"MM '24"},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681547","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681547","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:57:48Z","timestamp":1750294668000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681547"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":66,"alternative-id":["10.1145\/3664647.3681547","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681547","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"}}]}}