{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T07:16:10Z","timestamp":1781248570559,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":61,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Liaoning Provincial Research Foundation for Basic Research","award":["No. 2022-KF-26-02"],"award-info":[{"award-number":["No. 2022-KF-26-02"]}]},{"name":"National Science Foundation of China","award":["No. 62176115"],"award-info":[{"award-number":["No. 62176115"]}]},{"name":"National Science Foundation of China","award":["No. 62176120"],"award-info":[{"award-number":["No. 62176120"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3611994","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:40Z","timestamp":1698391660000},"page":"5674-5685","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Food-500 Cap: A Fine-Grained Food Caption Benchmark for Evaluating Vision-Language Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-1101-3263","authenticated-orcid":false,"given":"Zheng","family":"Ma","sequence":"first","affiliation":[{"name":"Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5971-5285","authenticated-orcid":false,"given":"Mianzhi","family":"Pan","sequence":"additional","affiliation":[{"name":"Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9448-3479","authenticated-orcid":false,"given":"Wenhan","family":"Wu","sequence":"additional","affiliation":[{"name":"Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4532-1446","authenticated-orcid":false,"given":"Kanzhi","family":"Cheng","sequence":"additional","affiliation":[{"name":"Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-8193-8344","authenticated-orcid":false,"given":"Jianbing","family":"Zhang","sequence":"additional","affiliation":[{"name":"Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4869-0832","authenticated-orcid":false,"given":"Shujian","family":"Huang","sequence":"additional","affiliation":[{"name":"Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9859-6898","authenticated-orcid":false,"given":"Jiajun","family":"Chen","sequence":"additional","affiliation":[{"name":"Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2964315"},{"key":"e_1_3_2_1_3_1","volume-title":"ChineseFoodNet: A large-scale Image Dataset for Chinese Food Recognition. CoRR abs\/1705.02743","author":"Chen Xin","year":"2017","unstructured":"Xin Chen, Hua Zhou, and Liang Diao. 2017. ChineseFoodNet: A large-scale Image Dataset for Chinese Food Recognition. CoRR abs\/1705.02743 (2017). arXiv:1705.02743 http:\/\/arxiv.org\/abs\/1705.02743"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2210.07688"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"J. Deng W. Dong R. Socher L.-J. Li K. Li and L. Fei-Fei. 2009. ImageNet: A Large-Scale Hierarchical Image Database. In CVPR09.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/w14-3348"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2212.10015"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.318"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"e_1_3_2_1_11_1","volume-title":"Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017","author":"Heusel Martin","year":"2017","unstructured":"Martin Heusel, Hubert Ramsauer, Thomas Unterthiner, Bernhard Nessler, and Sepp Hochreiter. 2017. GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium. In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017, Long Beach, CA, USA, Isabelle Guyon, Ulrike von Luxburg, Samy Bengio, Hanna M. Wallach, Rob Fergus, S. V. N. Vishwanathan, and Roman Garnett (Eds.). 6626--6637. https:\/\/proceedings.neurips.cc\/paper\/2017\/hash\/ 8a1d694707eb0fefe65871369074926d-Abstract.html"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3021209"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.38"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-16199-0_1"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"e_1_3_2_1_16_1","unstructured":"Alex Krizhevsky Geoffrey Hinton et al. 2009. Learning multiple layers of features from tiny images. (2009)."},{"key":"e_1_3_2_1_17_1","volume-title":"The Role of ImageNet Classes in Fr\u00e9chet Inception Distance. arXiv preprint arXiv:2203.06026","author":"Kynk\u00e4\u00e4nniemi Tuomas","year":"2022","unstructured":"Tuomas Kynk\u00e4\u00e4nniemi, Tero Karras, Miika Aittala, Timo Aila, and Jaakko Lehtinen. 2022. The Role of ImageNet Classes in Fr\u00e9chet Inception Distance. arXiv preprint arXiv:2203.06026 (2022)."},{"key":"e_1_3_2_1_18_1","volume-title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation. In International Conference on Machine Learning, ICML 2022","volume":"12900","author":"Li Junnan","year":"2022","unstructured":"Junnan Li, Dongxu Li, Caiming Xiong, and Steven C. H. Hoi. 2022. BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation. In International Conference on Machine Learning, ICML 2022, 17-23 July 2022, Baltimore, Maryland, USA (Proceedings of Machine Learning Research, Vol. 162), Kamalika Chaudhuri, Stefanie Jegelka, Le Song, Csaba Szepesv\u00e1ri, Gang Niu, and Sivan Sabato (Eds.). PMLR, 12888--12900. https:\/\/proceedings.mlr.press\/v162\/li22n.html"},{"key":"e_1_3_2_1_19_1","volume-title":"Rouge: A package for automatic evaluation of summaries. In Text summarization branches out. 74--81.","author":"Lin Chin-Yew","year":"2004","unstructured":"Chin-Yew Lin. 2004. Rouge: A package for automatic evaluation of summaries. In Text summarization branches out. 74--81."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_1_22_1","volume-title":"Recipe1M: A Dataset for Learning Cross-Modal Embeddings for Cooking Recipes and Food Images. CoRR abs\/1810.06553","author":"Mar\u00edn Javier","year":"2018","unstructured":"Javier Mar\u00edn, Aritro Biswas, Ferda Ofli, Nicholas Hynes, Amaia Salvador, Yusuf Aytar, Ingmar Weber, and Antonio Torralba. 2018. Recipe1M: A Dataset for Learning Cross-Modal Embeddings for Cooking Recipes and Food Images. CoRR abs\/1810.06553 (2018). arXiv:1810.06553 http:\/\/arxiv.org\/abs\/1810.06553"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2927476"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2759499"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3329168"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3414031"},{"key":"e_1_3_2_1_27_1","volume-title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models. In International Conference on Machine Learning, ICML 2022","volume":"16804","author":"Nichol Alexander Quinn","year":"2022","unstructured":"Alexander Quinn Nichol, Prafulla Dhariwal, Aditya Ramesh, Pranav Shyam, Pamela Mishkin, Bob McGrew, Ilya Sutskever, and Mark Chen. 2022. GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models. In International Conference on Machine Learning, ICML 2022, 17-23 July 2022, Baltimore, Maryland, USA (Proceedings of Machine Learning Research, Vol. 162), Kamalika Chaudhuri, Stefanie Jegelka, Le Song, Csaba Szepesv\u00e1ri, Gang Niu, and Sivan Sabato (Eds.). PMLR, 16784--16804. https:\/\/proceedings.mlr.press\/ v162\/nichol22a.html"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.3115\/1073083"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.567"},{"key":"e_1_3_2_1_30_1","volume-title":"Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks 1, NeurIPS Datasets and Benchmarks 2021","author":"Park Dong Huk","year":"2021","unstructured":"Dong Huk Park, Samaneh Azadi, Xihui Liu, Trevor Darrell, and Anna Rohrbach. 2021. Benchmark for Compositional Text-to-Image Synthesis. In Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks 1, NeurIPS Datasets and Benchmarks 2021, December 2021, virtual, Joaquin Vanschoren and Sai-Kit Yeung (Eds.). https:\/\/datasets-benchmarks-proceedings.neurips.cc\/paper\/2021\/hash\/0a09c8844ba8f0936c20bd791130d6b6-Abstract-round1.html"},{"key":"e_1_3_2_1_31_1","volume-title":"Mining Discriminative Food Regions for Accurate Food Recognition. In 30th British Machine Vision Conference 2019, BMVC 2019","author":"Qiu Jianing","year":"2019","unstructured":"Jianing Qiu, Frank Po Wen Lo, Yingnan Sun, Siyao Wang, and Benny Lo. 2019. Mining Discriminative Food Regions for Accurate Food Recognition. In 30th British Machine Vision Conference 2019, BMVC 2019, Cardiff, UK, September 9-12, 2019. BMVA Press, 158. https:\/\/bmvc2019.org\/wp-content\/uploads\/papers\/0839-paper.pdf"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2212.08044"},{"key":"e_1_3_2_1_33_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning, 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 Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18-24 July 2021, Virtual Event (Proceedings of Machine Learning Research, Vol. 139), Marina Meila and Tong Zhang (Eds.). PMLR, 8748--8763. http:\/\/proceedings.mlr.press\/v139\/radford21a.html"},{"key":"e_1_3_2_1_34_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning, ICML 2021","volume":"8831","author":"Ramesh Aditya","year":"2021","unstructured":"Aditya Ramesh, Mikhail Pavlov, Gabriel Goh, Scott Gray, Chelsea Voss, Alec Radford, Mark Chen, and Ilya Sutskever. 2021. Zero-Shot Text-to-Image Generation. 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), Marina Meila and Tong Zhang (Eds.). PMLR, 8821--8831. http:\/\/proceedings.mlr.press\/v139\/ramesh21a.html"},{"key":"e_1_3_2_1_35_1","volume-title":"Classification Accuracy Score for Conditional Generative Models. In Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019","author":"Suman","year":"2019","unstructured":"Suman V. Ravuri and Oriol Vinyals. 2019. Classification Accuracy Score for Conditional Generative Models. In Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8-14, 2019, Vancouver, BC, Canada, Hanna M. Wallach, Hugo Larochelle, Alina Beygelzimer, Florence d'Alch\u00e9-Buc, Emily B. Fox, and Roman Garnett (Eds.). 12247--12258. https:\/\/proceedings.neurips.cc\/paper\/2019\/ hash\/fcf55a303b71b84d326fb1d06e332a26-Abstract.html"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1437"},{"key":"e_1_3_2_1_37_1","volume-title":"5th International Conference on Learning Representations, ICLR","author":"Rolfe Jason Tyler","year":"2017","unstructured":"Jason Tyler Rolfe. 2017. Discrete Variational Autoencoders. In 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24-26, 2017, Conference Track Proceedings. OpenReview.net. https:\/\/openreview.net\/forum?id=ryMxXPFex"},{"key":"e_1_3_2_1_38_1","volume-title":"High-Resolution Image Synthesis with Latent Diffusion Models. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022","author":"Rombach Robin","year":"2022","unstructured":"Robin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser, and Bj\u00f6rn Ommer. 2022. High-Resolution Image Synthesis with Latent Diffusion Models. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, LA, USA, June 18--24, 2022. IEEE, 10674--10685. https:\/\/doi.org\/10. 1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_39_1","volume-title":"Probing the Role of Positional Information in Vision-Language Models. In Findings of the Association for Computational Linguistics: NAACL 2022","author":"Philipp","year":"2022","unstructured":"Philipp J. R\u00f6sch and Jindrich Libovick\u00fd. 2022. Probing the Role of Positional Information in Vision-Language Models. In Findings of the Association for Computational Linguistics: NAACL 2022, Seattle, WA, United States, July 10-15, 2022, Marine Carpuat, Marie-Catherine de Marneffe, and Iv\u00e1n Vladimir Meza Ru\u00edz (Eds.). Association for Computational Linguistics, 1031--1041. https:\/\/doi.org\/10. 18653\/v1\/2022.findings-naacl.77"},{"key":"e_1_3_2_1_40_1","volume-title":"Sanghun Cho and Woonhyuk Baek","author":"Doyup Lee Saehoon Kim Chiheon Kim","year":"2021","unstructured":"Chiheon Kim Doyup Lee Saehoon Kim, Sanghun Cho and Woonhyuk Baek. 2021. minDALL-E on Conceptual Captions. https:\/\/github.com\/kakaobrain\/minDALL-E."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2205.11487"},{"key":"e_1_3_2_1_42_1","volume-title":"LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs. CoRR abs\/2111.02114","author":"Schuhmann Christoph","year":"2021","unstructured":"Christoph Schuhmann, Richard Vencu, Romain Beaumont, Robert Kaczmarczyk, Clayton Mullis, Aarush Katta, Theo Coombes, Jenia Jitsev, and Aran Komatsuzaki. 2021. LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs. CoRR abs\/2111.02114 (2021). arXiv:2111.02114 https:\/\/arxiv.org\/abs\/2111.02114"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.346"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01519"},{"key":"e_1_3_2_1_45_1","volume-title":"VL-BERT: Pre-training of Generic Visual-Linguistic Representations. In 8th International Conference on Learning Representations, ICLR 2020","author":"Su Weijie","year":"2020","unstructured":"Weijie Su, Xizhou Zhu, Yue Cao, Bin Li, Lewei Lu, Furu Wei, and Jifeng Dai. 2020. VL-BERT: Pre-training of Generic Visual-Linguistic Representations. In 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26-30, 2020. OpenReview.net. https:\/\/openreview.net\/forum?id= SygXPaEYvH"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00517"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2209.06103"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2205.14100"},{"key":"e_1_3_2_1_52_1","volume-title":"International Conference on Machine Learning, ICML 2022","volume":"23340","author":"Wang Peng","year":"2022","unstructured":"Peng Wang, An Yang, Rui Men, Junyang Lin, Shuai Bai, Zhikang Li, Jianxin Ma, Chang Zhou, Jingren Zhou, and Hongxia Yang. 2022. OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework. In International Conference on Machine Learning, ICML 2022, 17-23 July 2022, Baltimore, Maryland, USA (Proceedings of Machine Learning Research, Vol. 162), Kamalika Chaudhuri, Stefanie Jegelka, Le Song, Csaba Szepesv\u00e1ri, Gang Niu, and Sivan Sabato (Eds.). PMLR, 23318--23340. https: \/\/proceedings.mlr.pres\/v162\/wang22al.html"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW.2015.7169757"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475201"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01522"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"e_1_3_2_1_57_1","volume-title":"When and why vision-language models behave like bags-of-words, and what to do about it? CoRR abs\/2210.01936","author":"Y\u00fcksekg\u00f6n\u00fcl Mert","year":"2022","unstructured":"Mert Y\u00fcksekg\u00f6n\u00fcl, Federico Bianchi, Pratyusha Kalluri, Dan Jurafsky, and James Zou. 2022. When and why vision-language models behave like bags-of-words, and what to do about it? CoRR abs\/2210.01936 (2022). https:\/\/doi.org\/10.48550\/ arXiv.2210.01936 arXiv:2210.01936"},{"key":"e_1_3_2_1_58_1","volume-title":"Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts. In International Conference on Machine Learning, ICML 2022","volume":"26009","author":"Zeng Yan","year":"2022","unstructured":"Yan Zeng, Xinsong Zhang, and Hang Li. 2022. Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts. In International Conference on Machine Learning, ICML 2022, 17-23 July 2022, Baltimore, Maryland, USA (Proceedings of Machine Learning Research, Vol. 162), Kamalika Chaudhuri, Stefanie Jegelka, Le Song, Csaba Szepesv\u00e1ri, Gang Niu, and Sivan Sabato (Eds.). PMLR, 25994-26009. https:\/\/proceedings.mlr.press\/v162\/zeng22c.html"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2207.00221"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2205.15237"}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","location":"Ottawa ON Canada","acronym":"MM '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611994","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3611994","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:12:23Z","timestamp":1755821543000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611994"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":61,"alternative-id":["10.1145\/3581783.3611994","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3611994","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}