{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T01:19:08Z","timestamp":1777339148805,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":44,"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":"University Stability Support program of Shenzhen","award":["20220811121315001"],"award-info":[{"award-number":["20220811121315001"]}]},{"name":"Guangdong Provincial Nat- ural Science Foundation","award":["2023A1515012584, 2022A1515010129"],"award-info":[{"award-number":["2023A1515012584, 2022A1515010129"]}]},{"name":"National Science Foundation of China","award":["92270122,62206179"],"award-info":[{"award-number":["92270122,62206179"]}]},{"name":"Shenzhen Re- search Foundation for Basic Research","award":["JCYJ20210324093000002"],"award-info":[{"award-number":["JCYJ20210324093000002"]}]},{"name":"National Key R&D program of China","award":["2021YFB3301500"],"award-info":[{"award-number":["2021YFB3301500"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681671","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:41Z","timestamp":1729925981000},"page":"9165-9174","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["ReCoS: A Novel Benchmark for Cross-Modal Image-Text Retrieval in Complex Real-Life Scenarios"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2818-4652","authenticated-orcid":false,"given":"Xiaojun","family":"Chen","sequence":"first","affiliation":[{"name":"Shenzhen University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3091-8270","authenticated-orcid":false,"given":"Jimeng","family":"Lou","sequence":"additional","affiliation":[{"name":"Shenzhen University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2465-5613","authenticated-orcid":false,"given":"Wenxi","family":"Huang","sequence":"additional","affiliation":[{"name":"Shenzhen University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2518-3300","authenticated-orcid":false,"given":"Ting","family":"Wan","sequence":"additional","affiliation":[{"name":"Xi'an University of Technology, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1449-5046","authenticated-orcid":false,"given":"Qin","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shenzhen University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7345-5071","authenticated-orcid":false,"given":"Min","family":"Yang","sequence":"additional","affiliation":[{"name":"Shenzhen Institute of Advanced Technology (SIAT), Chinese Academy of Sciences (CAS), Shenzhen, China, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Empirical Evaluation of Gated Recurrent Neural Network Architectures in Aviation Delay Prediction. In 2020 5th International Conference on Computing, Communication and Security (ICCCS). 1--7.","author":"Ballakur Amulya Arun","year":"2020","unstructured":"Amulya Arun Ballakur and Arti Arya. 2020. Empirical Evaluation of Gated Recurrent Neural Network Architectures in Aviation Delay Prediction. In 2020 5th International Conference on Computing, Communication and Security (ICCCS). 1--7."},{"key":"e_1_3_2_1_2_1","first-page":"32897","article-title":"Vlmo: Unified vision-language pre-training with mixture-of-modality-experts","volume":"35","author":"Bao Hangbo","year":"2022","unstructured":"Hangbo Bao, Wenhui Wang, Li Dong, Qiang Liu, Owais Khan Mohammed, Kriti Aggarwal, Subhojit Som, Songhao Piao, and Furu Wei. 2022. Vlmo: Unified vision-language pre-training with mixture-of-modality-experts. Advances in Neural Information Processing Systems, Vol. 35 (2022), 32897--32912.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591758"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10032-019-00334-z"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16209"},{"key":"e_1_3_2_1_7_1","volume-title":"Dual Encoding for Zero-Example Video Retrieval. In 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 9338--9347","author":"Dong Jianfeng","year":"2019","unstructured":"Jianfeng Dong, Xirong Li, Chaoxi Xu, Shouling Ji, Yuan He, Gang Yang, and Xun Wang. 2019. Dual Encoding for Zero-Example Video Retrieval. In 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 9338--9347."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01763"},{"key":"e_1_3_2_1_9_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_10_1","first-page":"6616","article-title":"Large-scale adversarial training for vision-and-language representation learning","volume":"33","author":"Gan Zhe","year":"2020","unstructured":"Zhe Gan, Yen-Chun Chen, Linjie Li, Chen Zhu, Yu Cheng, and Jingjing Liu. 2020. Large-scale adversarial training for vision-and-language representation learning. Advances in Neural Information Processing Systems, Vol. 33 (2020), 6616--6628.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_11_1","volume-title":"Barun Patra, et al.","author":"Huang Shaohan","year":"2024","unstructured":"Shaohan Huang, Li Dong, Wenhui Wang, Yaru Hao, Saksham Singhal, Shuming Ma, Tengchao Lv, Lei Cui, Owais Khan Mohammed, Barun Patra, et al. 2024. Language is not all you need: Aligning perception with language models. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"e_1_3_2_1_13_1","volume-title":"International Conference on Machine Learning. PMLR, 5583--5594","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. PMLR, 5583--5594."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"e_1_3_2_1_16_1","volume-title":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations). Association for Computational Linguistics","author":"Li Dongxu","unstructured":"Dongxu Li, Junnan Li, Hung Le, Guangsen Wang, Silvio Savarese, and Steven C.H. Hoi. 2023. LAVIS: A One-stop Library for Language-Vision Intelligence. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations). Association for Computational Linguistics, Toronto, Canada, 31--41."},{"key":"e_1_3_2_1_17_1","volume-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.12597","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023. Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.12597 (2023)."},{"key":"e_1_3_2_1_18_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_19_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_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00475"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350869"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01093"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01029"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3451390"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01847"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01847"},{"key":"e_1_3_2_1_29_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_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"e_1_3_2_1_31_1","first-page":"2","article-title":"Knowledge Aware Semantic Concept Expansion for Image-Text Matching","volume":"1","author":"Shi Botian","year":"2019","unstructured":"Botian Shi, Lei Ji, Pan Lu, Zhendong Niu, and Nan Duan. 2019. Knowledge Aware Semantic Concept Expansion for Image-Text Matching.. In IJCAI, Vol. 1. 2.","journal-title":"IJCAI"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6430"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2797921"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.541"},{"key":"e_1_3_2_1_35_1","volume-title":"Cross-modal Scene Graph Matching for Relationship-aware Image-Text Retrieval. In 2020 IEEE Winter Conference on Applications of Computer Vision (WACV). 1497--1506","author":"Wang Sijin","year":"2020","unstructured":"Sijin Wang, Ruiping Wang, Ziwei Yao, Shiguang Shan, and Xilin Chen. 2020. Cross-modal Scene Graph Matching for Relationship-aware Image-Text Retrieval. In 2020 IEEE Winter Conference on Applications of Computer Vision (WACV). 1497--1506."},{"key":"e_1_3_2_1_36_1","volume-title":"Sampling Matters in Deep Embedding Learning. In 2017 IEEE International Conference on Computer Vision (ICCV). 2859--2867","author":"Wu Chao-Yuan","year":"2017","unstructured":"Chao-Yuan Wu, R. Manmatha, Alexander J. Smola, and Philipp Kr\u00e4henb\u00fchl. 2017. Sampling Matters in Deep Embedding Learning. In 2017 IEEE International Conference on Computer Vision (ICCV). 2859--2867."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01213"},{"key":"e_1_3_2_1_39_1","volume-title":"Multi-grained vision language pre-training: Aligning texts with visual concepts. arXiv preprint arXiv:2111.08276","author":"Zeng Yan","year":"2021","unstructured":"Yan Zeng, Xinsong Zhang, and Hang Li. 2021. Multi-grained vision language pre-training: Aligning texts with visual concepts. arXiv preprint arXiv:2111.08276 (2021)."},{"key":"e_1_3_2_1_40_1","volume-title":"X 2-vlm: All-in-one pre-trained model for vision-language tasks","author":"Zeng Yan","year":"2023","unstructured":"Yan Zeng, Xinsong Zhang, Hang Li, Jiawei Wang, Jipeng Zhang, and Wangchunshu Zhou. 2023. X 2-vlm: All-in-one pre-trained model for vision-language tasks. IEEE Transactions on Pattern Analysis and Machine Intelligence (2023)."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"e_1_3_2_1_42_1","unstructured":"Yang Zhang. 2023. A New Fine-grained Alignment Method for Image-text Matching."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3383184"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3383184"}],"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\/3664647.3681671","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681671","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:50Z","timestamp":1750295870000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681671"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":44,"alternative-id":["10.1145\/3664647.3681671","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681671","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"}}]}}