{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T10:00:13Z","timestamp":1775815213414,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":27,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,21]],"date-time":"2024-10-21T00:00:00Z","timestamp":1729468800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,21]]},"DOI":"10.1145\/3627673.3679680","type":"proceedings-article","created":{"date-parts":[[2024,10,20]],"date-time":"2024-10-20T19:34:21Z","timestamp":1729452861000},"page":"3207-3216","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["MSKR: Advancing Multi-modal Structured Knowledge Representation with Synergistic Hard Negative Samples"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-6196-8263","authenticated-orcid":false,"given":"Shuili","family":"Zhang","sequence":"first","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences & School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0378-4587","authenticated-orcid":false,"given":"Hongzhang","family":"Mu","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences & School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0750-6923","authenticated-orcid":false,"given":"Tingwen","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences & School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1617-012X","authenticated-orcid":false,"given":"Qianqian","family":"Tong","sequence":"additional","affiliation":[{"name":"Department of Strategic and Advanced Interdisciplinary Research, Peng Cheng Laboratory, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4865-982X","authenticated-orcid":false,"given":"Jiawei","family":"Sheng","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2024,10,21]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3592025"},{"key":"e_1_3_2_1_2_1","volume-title":"SimVLM: Simple Visual Language Model Pretraining with Weak Supervision. In International Conference on Learning Representations.","author":"Wang Zirui","year":"2021","unstructured":"Zirui Wang, Jiahui Yu, Adams Wei Yu, Zihang Dai, Yulia Tsvetkov, and Yuan Cao. 2021. SimVLM: Simple Visual Language Model Pretraining with Weak Supervision. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_3_1","volume-title":"Learning Transferable Visual Models From Natural Language Supervision. In International Conference on Machine Learning. 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. 8748--8763."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01519"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00517"},{"key":"e_1_3_2_1_6_1","volume-title":"The Eleventh International Conference on Learning Representations.","author":"Yuksekgonul Mert","year":"2023","unstructured":"Mert Yuksekgonul, Federico Bianchi, Pratyusha Kalluri, Dan Jurafsky, and James Zou. 2023. When and Why Vision-Language Models Behave Like Bags-of-Words, and What to Do About It?. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.28017"},{"key":"e_1_3_2_1_8_1","volume-title":"VL-Checklist: Evaluating Pre-Trained Vision-Language Models with Objects, Attributes, and Relations. arXiv preprint arXiv:2207.00221","author":"Zhao Tiancheng","year":"2022","unstructured":"Tiancheng Zhao, Tianqi Zhang, Mingwei Zhu, Haozhan Shen, Kyusong Lee, Xiaopeng Lu, and Jianwei Yin. 2022. VL-Checklist: Evaluating Pre-Trained Vision-Language Models with Objects, Attributes, and Relations. arXiv preprint arXiv:2207.00221 (2022)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00261"},{"key":"e_1_3_2_1_10_1","volume-title":"Enhancing Conceptual Understanding in Multimodal Contrastive Learning through Hard Negative Samples. CoRR","author":"R\u00f6sch Philipp Jonas","year":"2024","unstructured":"Philipp Jonas R\u00f6sch, Norbert Oswald, Michaela Geierhos, and Jindrich Libovick\u1ef3. 2024. Enhancing Conceptual Understanding in Multimodal Contrastive Learning through Hard Negative Samples. CoRR (2024)."},{"key":"e_1_3_2_1_11_1","volume-title":"Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing. 680--690","author":"Turney Peter","year":"2011","unstructured":"Peter Turney, Yair Neuman, Dan Assaf, and Yohai Cohen. 2011. Literal and Metaphorical Sense Identification through Concrete and Abstract Context. In Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing. 680--690."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/219717.219748"},{"key":"e_1_3_2_1_13_1","volume-title":"Proceedings of the 27th International Conference on Computational Linguistics. 3715--3727","author":"Shi Haoyue","year":"2018","unstructured":"Haoyue Shi, Jiayuan Mao, Tete Xiao, Yuning Jiang, and Jian Sun. 2018. Learning Visually-Grounded Semantics from Contrastive Adversarial Samples. In Proceedings of the 27th International Conference on Computational Linguistics. 3715--3727."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00695"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_16_1","volume-title":"Zero-Shot Text-to-Image Generation. In International Conference on Machine Learning. 8821--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 International Conference on Machine Learning. 8821--8831."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"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. 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. 12888--12900."},{"key":"e_1_3_2_1_19_1","volume-title":"International conference on machine learning","volume":"139","author":"Kim Wonjae","year":"2021","unstructured":"Wonjae Kim, Bokyung Son, and Ildoo Kim. 2021. ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision. In International conference on machine learning, Vol. 139. 5583--5594."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"e_1_3_2_1_21_1","first-page":"1","article-title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","volume":"21","author":"Raffel Colin","year":"2020","unstructured":"Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J Liu. 2020. Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer. Journal of machine learning research, Vol. 21, 140 (2020), 1--67.","journal-title":"Journal of machine learning research"},{"key":"e_1_3_2_1_22_1","volume-title":"Xi Victoria Lin, et al","author":"Zhang Susan","year":"2022","unstructured":"Susan Zhang, Stephen Roller, Naman Goyal, Mikel Artetxe, Moya Chen, Shuohui Chen, Christopher Dewan, Mona Diab, Xian Li, Xi Victoria Lin, et al. 2022. OPT: Open Pre-trained Transformer Language Models. arXiv preprint arXiv:2205.01068 (2022)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16431"},{"key":"e_1_3_2_1_24_1","volume-title":"Devise: A Deep Visual-Semantic Embedding Model. Advances in neural information processing systems","author":"Frome Andrea","year":"2013","unstructured":"Andrea Frome, Greg S Corrado, Jon Shlens, Samy Bengio, Jeff Dean, Marc'Aurelio Ranzato, and Tomas Mikolov. 2013. Devise: A Deep Visual-Semantic Embedding Model. Advances in neural information processing systems, Vol. 26 (2013)."},{"key":"e_1_3_2_1_25_1","volume-title":"Jamie Ryan Kiros, and Sanja Fidler","author":"Faghri Fartash","year":"2017","unstructured":"Fartash Faghri, David J Fleet, Jamie Ryan Kiros, and Sanja Fidler. 2017. VSE: Improving Visual-Semantic Embeddings with Hard Negatives. arXiv preprint arXiv:1707.05612 (2017)."},{"key":"e_1_3_2_1_26_1","volume-title":"Devise: A Deep Visual-Semantic Embedding Model. Advances in neural information processing systems","author":"Frome Andrea","year":"2013","unstructured":"Andrea Frome, Greg S Corrado, Jon Shlens, Samy Bengio, Jeff Dean, Marc'Aurelio Ranzato, and Tomas Mikolov. 2013. Devise: A Deep Visual-Semantic Embedding Model. Advances in neural information processing systems, Vol. 26 (2013)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00677"}],"event":{"name":"CIKM '24: The 33rd ACM International Conference on Information and Knowledge Management","location":"Boise ID USA","acronym":"CIKM '24","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 33rd ACM International Conference on Information and Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3627673.3679680","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3627673.3679680","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:58:13Z","timestamp":1750294693000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3627673.3679680"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,21]]},"references-count":27,"alternative-id":["10.1145\/3627673.3679680","10.1145\/3627673"],"URL":"https:\/\/doi.org\/10.1145\/3627673.3679680","relation":{},"subject":[],"published":{"date-parts":[[2024,10,21]]},"assertion":[{"value":"2024-10-21","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}