{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T08:19:14Z","timestamp":1785745154353,"version":"3.56.0"},"publisher-location":"New York, NY, USA","reference-count":67,"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":"Shanghai Municipal Science and Technology Major Project","award":["2021SHZDZX0102"],"award-info":[{"award-number":["2021SHZDZX0102"]}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62203303"],"award-info":[{"award-number":["62203303"]}],"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\/3664647.3681140","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:49Z","timestamp":1729925989000},"page":"4426-4435","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["SMART: Self-Weighted Multimodal Fusion for Diagnostics of Neurodegenerative Disorders"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1210-1306","authenticated-orcid":false,"given":"Qiuhui","family":"Chen","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9065-3691","authenticated-orcid":false,"given":"Yi","family":"Hong","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"VQA-Med: Overview of the medical visual question answering task at ImageCLEF","author":"Abacha Asma Ben","year":"2019","unstructured":"Asma Ben Abacha, Sadid A Hasan, Vivek V Datla, Joey Liu, Dina Demner-Fushman, and Henning M\u00fcller. 2019. VQA-Med: Overview of the medical visual question answering task at ImageCLEF 2019. CLEF (working notes), Vol. 2, 6 (2019)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.3390\/mti2030047"},{"key":"e_1_3_2_1_3_1","volume-title":"Interactive audio-text representation for automated audio captioning with contrastive learning. arXiv preprint arXiv:2203.15526","author":"Chen Chen","year":"2022","unstructured":"Chen Chen, Nana Hou, Yuchen Hu, Heqing Zou, Xiaofeng Qi, and Eng Siong Chng. 2022. Interactive audio-text representation for automated audio captioning with contrastive learning. arXiv preprint arXiv:2203.15526 (2022)."},{"key":"e_1_3_2_1_4_1","volume-title":"Medblip: Bootstrapping language-image pre-training from 3d medical images and texts. arXiv preprint arXiv:2305.10799","author":"Chen Qiuhui","year":"2023","unstructured":"Qiuhui Chen, Xinyue Hu, Zirui Wang, and Yi Hong. 2023. Medblip: Bootstrapping language-image pre-training from 3d medical images and texts. arXiv preprint arXiv:2305.10799 (2023)."},{"key":"e_1_3_2_1_5_1","volume-title":"AliFuse: Aligning and Fusing Multi-modal Medical Data for Computer-Aided Diagnosis. arXiv preprint arXiv:2401.01074","author":"Chen Qiuhui","year":"2024","unstructured":"Qiuhui Chen, Xinyue Hu, Zirui Wang, and Yi Hong. 2024. AliFuse: Aligning and Fusing Multi-modal Medical Data for Computer-Aided Diagnosis. arXiv preprint arXiv:2401.01074 (2024)."},{"key":"e_1_3_2_1_6_1","volume-title":"Med3d: Transfer learning for 3d medical image analysis. arXiv:1904.00625","author":"Chen Sihong","year":"2019","unstructured":"Sihong Chen, Kai Ma, and Yefeng Zheng. 2019. Med3d: Transfer learning for 3d medical image analysis. arXiv:1904.00625 (2019)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1088\/2516-1091\/acc2fe"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0896-6273(03)00568-3"},{"key":"e_1_3_2_1_9_1","volume-title":"The neuropathological diagnosis of Alzheimer's disease. Molecular neurodegeneration","author":"DeTure Michael A","year":"2019","unstructured":"Michael A DeTure and Dennis W Dickson. 2019. The neuropathological diagnosis of Alzheimer's disease. Molecular neurodegeneration, Vol. 14, 1 (2019), 32."},{"key":"e_1_3_2_1_10_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_1_11_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:2010.11929 (2020)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/MMUL.2022.3156471"},{"key":"e_1_3_2_1_13_1","volume-title":"Jonathan Foster, Peter Hudson, Nicola T Lautenschlager, Nat Lenzo, Ralph N Martins, Paul Maruff, et al.","author":"Ellis Kathryn A","year":"2009","unstructured":"Kathryn A Ellis, Ashley I Bush, David Darby, Daniela De Fazio, Jonathan Foster, Peter Hudson, Nicola T Lautenschlager, Nat Lenzo, Ralph N Martins, Paul Maruff, et al. 2009. The Australian Imaging, Biomarkers and Lifestyle (AIBL) study of aging: methodology and baseline characteristics of 1112 individuals recruited for a longitudinal study of Alzheimer's disease. International psychogeriatrics, Vol. 21, 4 (2009), 672--687."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1212\/WNL.0000000000009107"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.imu.2021.100513"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2022.107207"},{"key":"e_1_3_2_1_17_1","first-page":"1753","article-title":"Improved deep embedded clustering with local structure preservation","volume":"17","author":"Guo Xifeng","year":"2017","unstructured":"Xifeng Guo, Long Gao, Xinwang Liu, and Jianping Yin. 2017. Improved deep embedded clustering with local structure preservation.. In Ijcai, Vol. 17. 1753--1759.","journal-title":"Ijcai"},{"key":"e_1_3_2_1_18_1","volume-title":"Dimensionality reduction by learning an invariant mapping. In 2006 IEEE computer society conference on computer vision and pattern recognition (CVPR'06)","author":"Hadsell Raia","unstructured":"Raia Hadsell, Sumit Chopra, and Yann LeCun. 2006. Dimensionality reduction by learning an invariant mapping. In 2006 IEEE computer society conference on computer vision and pattern recognition (CVPR'06), Vol. 2. IEEE, 1735--1742."},{"key":"e_1_3_2_1_19_1","volume-title":"Alzheimer's Disease Neuroimaging Initiative, et al","author":"Hao Xiaoke","year":"2020","unstructured":"Xiaoke Hao, Yongjin Bao, Yingchun Guo, Ming Yu, Daoqiang Zhang, Shannon L Risacher, Andrew J Saykin, Xiaohui Yao, Li Shen, Alzheimer's Disease Neuroimaging Initiative, et al. 2020. Multi-modal neuroimaging feature selection with consistent metric constraint for diagnosis of Alzheimer's disease. Medical image analysis, Vol. 60 (2020), 101625."},{"key":"e_1_3_2_1_20_1","volume-title":"Neurodegenerative disorders","author":"Hardiman Orla","unstructured":"Orla Hardiman, Colin P Doherty, Marwa Elamin, and Peter Bede. 2011. Neurodegenerative disorders. Springer."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1002\/ima.22824"},{"key":"e_1_3_2_1_23_1","volume-title":"International conference on machine learning. PMLR, 4651--4664","author":"Jaegle Andrew","year":"2021","unstructured":"Andrew Jaegle, Felix Gimeno, Andy Brock, Oriol Vinyals, Andrew Zisserman, and Joao Carreira. 2021. Perceiver: General perception with iterative attention. In International conference on machine learning. PMLR, 4651--4664."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02006"},{"key":"e_1_3_2_1_25_1","volume-title":"International Conference on Machine Learning. PMLR, 4904--4916","author":"Jia Chao","year":"2021","unstructured":"Chao Jia, Yinfei Yang, Ye Xia, Yi-Ting Chen, Zarana Parekh, Hieu Pham, Quoc Le, Yun-Hsuan Sung, Zhen Li, and Tom Duerig. 2021. Scaling up visual and vision-language representation learning with noisy text supervision. In International Conference on Machine Learning. PMLR, 4904--4916."},{"key":"e_1_3_2_1_26_1","volume-title":"Brain imaging in Alzheimer disease. Cold Spring Harbor perspectives in medicine","author":"Johnson Keith A","year":"2012","unstructured":"Keith A Johnson, Nick C Fox, Reisa A Sperling, and William E Klunk. 2012. Brain imaging in Alzheimer disease. Cold Spring Harbor perspectives in medicine, Vol. 2, 4 (2012), a006213."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(14)61393-3"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43904-9_53"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i4.25643"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1212\/WNL.56.9.1143"},{"key":"e_1_3_2_1_32_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Li Chunyuan","year":"2024","unstructured":"Chunyuan Li, Cliff Wong, Sheng Zhang, Naoto Usuyama, Haotian Liu, Jianwei Yang, Tristan Naumann, Hoifung Poon, and Jianfeng Gao. 2024. Llava-med: Training a large language-and-vision assistant for biomedicine in one day. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_33_1","volume-title":"International Conference on Machine Learning. PMLR, 12888--12900","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 International Conference on Machine Learning. PMLR, 12888--12900."},{"key":"e_1_3_2_1_34_1","volume-title":"Align before fuse: Vision and language representation learning with momentum distillation. Advances in neural information processing systems","author":"Li Junnan","year":"2021","unstructured":"Junnan Li, Ramprasaath Selvaraju, Akhilesh Gotmare, Shafiq Joty, Caiming Xiong, and Steven Chu Hong Hoi. 2021. Align before fuse: Vision and language representation learning with momentum distillation. Advances in neural information processing systems, Vol. 34 (2021), 9694--9705."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i10.17037"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01112"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"crossref","unstructured":"Siqi Liu Sidong Liu Weidong Cai Hangyu Che Sonia Pujol Ron Kikinis Dagan Feng Michael J Fulham et al. 2014. Multimodal neuroimaging feature learning for multiclass diagnosis of Alzheimer's disease. IEEE transactions on biomedical engineering Vol. 62 4 (2014) 1132--1140.","DOI":"10.1109\/TBME.2014.2372011"},{"key":"e_1_3_2_1_38_1","volume-title":"Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692","author":"Liu Yinhan","year":"2019","unstructured":"Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)."},{"key":"e_1_3_2_1_39_1","unstructured":"Kenneth Marek Danna Jennings Shirley Lasch Andrew Siderowf Caroline Tanner Tanya Simuni Chris Coffey Karl Kieburtz Emily Flagg Sohini Chowdhury et al. 2011. The Parkinson progression marker initiative (PPMI). Progress in neurobiology Vol. 95 4 (2011) 629--635."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2022.3207502"},{"key":"e_1_3_2_1_41_1","volume-title":"Eduardo Pontes Reis, and Pranav Rajpurkar","author":"Moor Michael","year":"2023","unstructured":"Michael Moor, Qian Huang, Shirley Wu, Michihiro Yasunaga, Yash Dalmia, Jure Leskovec, Cyril Zakka, Eduardo Pontes Reis, and Pranav Rajpurkar. 2023. Med-flamingo: a multimodal medical few-shot learner. In Machine Learning for Health (ML4H). PMLR, 353--367."},{"key":"e_1_3_2_1_42_1","volume-title":"Comparison of AdaBoost and support vector machines for detecting Alzheimer's disease through automated hippocampal segmentation","author":"Morra Jonathan H","year":"2009","unstructured":"Jonathan H Morra, Zhuowen Tu, Liana G Apostolova, Amity E Green, Arthur W Toga, and Paul M Thompson. 2009. Comparison of AdaBoost and support vector machines for detecting Alzheimer's disease through automated hippocampal segmentation. IEEE transactions on medical imaging, Vol. 29, 1 (2009), 30--43."},{"key":"e_1_3_2_1_43_1","volume-title":"Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748","author":"van den Oord Aaron","year":"2018","unstructured":"Aaron van den Oord, Yazhe Li, and Oriol Vinyals. 2018. Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1212\/WNL.0b013e3181cb3e25"},{"key":"e_1_3_2_1_45_1","volume-title":"Paul Allen, Philip McGuire, and Andrea Mechelli.","author":"Pettersson-Yeo William","year":"2014","unstructured":"William Pettersson-Yeo, Stefania Benetti, Andre F Marquand, Richard Joules, Marco Catani, Steve CR Williams, Paul Allen, Philip McGuire, and Andrea Mechelli. 2014. An empirical comparison of different approaches for combining multimodal neuroimaging data with support vector machine. Frontiers in neuroscience, Vol. 8 (2014), 189."},{"key":"e_1_3_2_1_46_1","volume-title":"Continual few-shot relation learning via embedding space regularization and data augmentation. arXiv preprint arXiv:2203.02135","author":"Qin Chengwei","year":"2022","unstructured":"Chengwei Qin and Shafiq Joty. 2022. Continual few-shot relation learning via embedding space regularization and data augmentation. arXiv preprint arXiv:2203.02135 (2022)."},{"key":"e_1_3_2_1_47_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, 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_48_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2011.11.075"},{"key":"e_1_3_2_1_49_1","volume-title":"Feature selection using factor analysis for Alzheimer's diagnosis using 18F-FDG PET images. Medical physics","author":"Salas-Gonzalez Diego","year":"2010","unstructured":"Diego Salas-Gonzalez, Juan Gorriz, Javier Ram\u00edrez, Ignacio Illan, Miriam L\u00f3pez, F Segovia, R Chaves, P. Padilla, and Carlos Puntonet. 2010. Feature selection using factor analysis for Alzheimer's diagnosis using 18F-FDG PET images. Medical physics, Vol. 37 (11 2010), 6084--95."},{"key":"e_1_3_2_1_50_1","volume-title":"Healthcare","volume":"9","author":"S\u00e1nchez-Reyna Ana G","year":"2021","unstructured":"Ana G S\u00e1nchez-Reyna, Jos\u00e9 M Celaya-Padilla, Carlos E Galvan-Tejada, Huizilopoztli Luna-Garcia, Hamurabi Gamboa-Rosales, Andres Ramirez-Morales, Jorge I Galv\u00e1n-Tejada, and Alzheimer's Disease Neuroimaging Initiative. 2021. Multimodal early alzheimer's detection, a genetic algorithm approach with support vector machines. In Healthcare, Vol. 9. MDPI, 971."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(15)01124-1"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02024"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.3390\/jimaging6060047"},{"key":"e_1_3_2_1_54_1","volume-title":"Expert-level detection of pathologies from unannotated chest X-ray images via self-supervised learning. Nature Biomedical Engineering","author":"Tiu Ekin","year":"2022","unstructured":"Ekin Tiu, Ellie Talius, Pujan Patel, Curtis P Langlotz, Andrew Y Ng, and Pranav Rajpurkar. 2022. Expert-level detection of pathologies from unannotated chest X-ray images via self-supervised learning. Nature Biomedical Engineering (2022), 1--8."},{"key":"e_1_3_2_1_55_1","volume-title":"Attention is all you need. Advances in neural information processing systems","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_56_1","volume-title":"Git: A generative image-to-text transformer for vision and language. arXiv:2205.14100","author":"Wang Jianfeng","year":"2022","unstructured":"Jianfeng Wang, Zhengyuan Yang, Xiaowei Hu, Linjie Li, Kevin Lin, Zhe Gan, Zicheng Liu, Ce Liu, and Lijuan Wang. 2022. Git: A generative image-to-text transformer for vision and language. arXiv:2205.14100 (2022)."},{"key":"e_1_3_2_1_57_1","volume-title":"Medclip: Contrastive learning from unpaired medical images and text. arXiv:2210.10163","author":"Wang Zifeng","year":"2022","unstructured":"Zifeng Wang, Zhenbang Wu, Dinesh Agarwal, and Jimeng Sun. 2022. Medclip: Contrastive learning from unpaired medical images and text. arXiv:2210.10163 (2022)."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2012.04.056"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01558"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20204"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.3934\/mbe.2023382"},{"key":"e_1_3_2_1_62_1","volume-title":"Mapping multi-modal brain connectome for brain disorder diagnosis via cross-modal mutual learning","author":"Yang Yanwu","year":"2023","unstructured":"Yanwu Yang, Chenfei Ye, Xutao Guo, Tao Wu, Yang Xiang, and Ting Ma. 2023. Mapping multi-modal brain connectome for brain disorder diagnosis via cross-modal mutual learning. IEEE Transactions on Medical Imaging (2023)."},{"key":"e_1_3_2_1_63_1","volume-title":"Coca: Contrastive captioners are image-text foundation models. arXiv:2205.01917","author":"Yu Jiahui","year":"2022","unstructured":"Jiahui Yu, Zirui Wang, Vijay Vasudevan, Legg Yeung, Mojtaba Seyedhosseini, and Yonghui Wu. 2022. Coca: Contrastive captioners are image-text foundation models. arXiv:2205.01917 (2022)."},{"key":"e_1_3_2_1_64_1","volume-title":"Michael A Hedderich, and Dietrich Klakow.","author":"Zhang Miaoran","year":"2022","unstructured":"Miaoran Zhang, Marius Mosbach, David Ifeoluwa Adelani, Michael A Hedderich, and Dietrich Klakow. 2022. MCSE: Multimodal contrastive learning of sentence embeddings. arXiv preprint arXiv:2204.10931 (2022)."},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2020.09.002"},{"key":"e_1_3_2_1_66_1","volume-title":"A transformer-based representation-learning model with unified processing of multimodal input for clinical diagnostics. Nature Biomedical Engineering","author":"Zhou Hong-Yu","year":"2023","unstructured":"Hong-Yu Zhou, Yizhou Yu, Chengdi Wang, Shu Zhang, Yuanxu Gao, Jia Pan, Jun Shao, Guangming Lu, Kang Zhang, and Weimin Li. 2023. A transformer-based representation-learning model with unified processing of multimodal input for clinical diagnostics. Nature Biomedical Engineering (2023), 1--13."},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10470-6_21"}],"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\/3664647.3681140","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681140","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:57:53Z","timestamp":1750294673000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681140"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":67,"alternative-id":["10.1145\/3664647.3681140","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681140","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"}}]}}