{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T05:07:10Z","timestamp":1781586430882,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":53,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1145\/3731715.3733465","type":"proceedings-article","created":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T18:29:43Z","timestamp":1750876183000},"page":"330-339","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["VLMs bridging-enhanced Scene Semantic Reasoning Framework for Image-Text Matching"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-9828-6344","authenticated-orcid":false,"given":"Yihua","family":"Gao","sequence":"first","affiliation":[{"name":"Chongqing Normal University, Chongqing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8936-633X","authenticated-orcid":false,"given":"Junyu","family":"Chen","sequence":"additional","affiliation":[{"name":"Chongqing Normal University, Chongqing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5517-3633","authenticated-orcid":false,"given":"Mingyong","family":"Li","sequence":"additional","affiliation":[{"name":"Chongqing Normal University, Chongqing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,6,30]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"e_1_3_2_1_2_1","volume-title":"How attentive are graph attention networks? arXiv preprint arXiv:2105.14491","author":"Brody Shaked","year":"2021","unstructured":"Shaked Brody, Uri Alon, and Eran Yahav. 2021. How attentive are graph attention networks? arXiv preprint arXiv:2105.14491 (2021)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2025.113355"},{"key":"e_1_3_2_1_4_1","volume-title":"Proc. Int. Conf. Multimedia and Expo (ICME). IEEE, 1--6.","author":"Chen Junyu","year":"2025","unstructured":"Junyu Chen, Yihua Gao, and Mingyong Li. 2025 a. Visual Semantic Description Generation with MLLMs for Image-Text Matching. In Proc. Int. Conf. Multimedia and Expo (ICME). IEEE, 1--6."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01553"},{"key":"e_1_3_2_1_6_1","volume-title":"2025 c. Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling. arXiv preprint arXiv:2501.17811","author":"Chen Xiaokang","year":"2025","unstructured":"Xiaokang Chen, Zhiyu Wu, Xingchao Liu, Zizheng Pan, Wen Liu, Zhenda Xie, Xingkai Yu, and Chong Ruan. 2025 c. Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling. arXiv preprint arXiv:2501.17811 (2025)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10889632"},{"key":"e_1_3_2_1_8_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint 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 preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16209"},{"key":"e_1_3_2_1_10_1","volume-title":"Proc. Brit. Mach. Vis. Conf. (BMVC).","author":"Faghri Fartash","year":"2018","unstructured":"Fartash Faghri, David J Fleet, Jamie Ryan Kiros, and Sanja Fidler. 2018. VSE: Improving Visual-Semantic Embeddings with Hard Negatives. In Proc. Brit. Mach. Vis. Conf. (BMVC)."},{"key":"e_1_3_2_1_11_1","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"36","author":"Fan Lijie","year":"2024","unstructured":"Lijie Fan, Dilip Krishnan, Phillip Isola, Dina Katabi, and Yonglong Tian. 2024. Improving clip training with language rewrites. In Proc. Adv. Neural Inf. Process. Syst. (NeurIPS), Vol. 36."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01455"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00108"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"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","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20020"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10889917"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3148470"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2025.126943"},{"key":"e_1_3_2_1_21_1","volume-title":"Lizhen Qu, Gholamreza Haffari, Fei Li, Donghong Ji, and Quan Hung Tran.","author":"Li Zhuang","year":"2023","unstructured":"Zhuang Li, Yuyang Chai, Terry Yue Zhuo, Lizhen Qu, Gholamreza Haffari, Fei Li, Donghong Ji, and Quan Hung Tran. 2023. Factual: A benchmark for faithful and consistent textual scene graph parsing. arXiv preprint arXiv:2305.17497 (2023)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"crossref","unstructured":"Zhe Li Lei Zhang Kun Zhang Yongdong Zhang and Zhendong Mao. 2024a. Fast Accurate and Lightweight Memory-Enhanced Embedding Learning Framework for Image-Text Retrieval. IEEE Trans. Circuits Syst. Video Technol. (2024).","DOI":"10.1109\/TCSVT.2024.3358411"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3369656"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01093"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6823"},{"key":"e_1_3_2_1_27_1","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"36","author":"Liu Haotian","year":"2024","unstructured":"Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2024. Visual instruction tuning. Proc. Adv. Neural Inf. Process. Syst. (NeurIPS), Vol. 36."},{"key":"e_1_3_2_1_28_1","volume-title":"Kaipeng Zhang, and Yang You.","author":"Liu Yanqing","year":"2023","unstructured":"Yanqing Liu, Kai Wang, Wenqi Shao, Ping Luo, Yu Qiao, Mike Zheng Shou, Kaipeng Zhang, and Yang You. 2023. Mllms-augmented visual-language representation learning. arXiv preprint arXiv:2311.18765 (2023)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00252"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3381337"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2321376"},{"key":"e_1_3_2_1_32_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_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01847"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3369968"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01361"},{"key":"e_1_3_2_1_36_1","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML). 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 Proc. Int. Conf. Mach. Learn. (ICML). PMLR, 8748--8763."},{"key":"e_1_3_2_1_37_1","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"28","author":"Ren Shaoqing","year":"2015","unstructured":"Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun. 2015. Faster r-cnn: Towards real-time object detection with region proposal networks. In Proc. Adv. Neural Inf. Process. Syst. (NeurIPS), Vol. 28."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00208"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00032"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_40"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58586-0_2"},{"key":"e_1_3_2_1_42_1","volume-title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution. arXiv preprint arXiv:2409.12191","author":"Wang Peng","year":"2024","unstructured":"Peng Wang, Shuai Bai, Sinan Tan, Shijie Wang, Zhihao Fan, Jinze Bai, Keqin Chen, Xuejing Liu, Jialin Wang, Wenbin Ge, Yang Fan, Kai Dang, Mengfei Du, Xuancheng Ren, Rui Men, Dayiheng Liu, Chang Zhou, Jingren Zhou, and Junyang Lin. 2024. Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution. arXiv preprint arXiv:2409.12191 (2024)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350940"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00461"},{"key":"e_1_3_2_1_45_1","volume-title":"C-pack: Packaged resources to advance general chinese embedding. arXiv preprint arXiv:2309.07597","author":"Xiao Shitao","year":"2023","unstructured":"Shitao Xiao, Zheng Liu, Peitian Zhang, and Niklas Muennighof. 2023. C-pack: Packaged resources to advance general chinese embedding. arXiv preprint arXiv:2309.07597 (2023)."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20235"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28538"},{"key":"e_1_3_2_1_49_1","volume-title":"Enhanced semantic similarity learning framework for image-text matching","author":"Zhang Kun","year":"2023","unstructured":"Kun Zhang, Bo Hu, Huatian Zhang, Zhe Li, and Zhendong Mao. 2023. Enhanced semantic similarity learning framework for image-text matching. IEEE Trans. Circuits Syst. Video Technol. (2023)."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01521"},{"key":"e_1_3_2_1_51_1","volume-title":"USER: Unified semantic enhancement with momentum contrast for image-text retrieval","author":"Zhang Yan","year":"2024","unstructured":"Yan Zhang, Zhong Ji, Di Wang, Yanwei Pang, and Xuelong Li. 2024a. USER: Unified semantic enhancement with momentum contrast for image-text retrieval. IEEE Trans. Image Process. (2024)."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/BigComp60711.2024.00024"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3253548"}],"event":{"name":"ICMR '25: International Conference on Multimedia Retrieval","location":"Chicago IL USA","acronym":"ICMR '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 2025 International Conference on Multimedia Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3731715.3733465","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T04:13:06Z","timestamp":1755749586000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3731715.3733465"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":53,"alternative-id":["10.1145\/3731715.3733465","10.1145\/3731715"],"URL":"https:\/\/doi.org\/10.1145\/3731715.3733465","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]},"assertion":[{"value":"2025-06-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}