{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T22:50:34Z","timestamp":1789253434220,"version":"build-2803163510"},"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":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62222212"],"award-info":[{"award-number":["62222212"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key Research and Development Project of China","award":["2021YFF0901600"],"award-info":[{"award-number":["2021YFF0901600"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3611703","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:40Z","timestamp":1698391660000},"page":"4828-4837","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":16,"title":["Unlocking the Power of Cross-Dimensional Semantic Dependency for Image-Text Matching"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2140-2546","authenticated-orcid":false,"given":"Kun","family":"Zhang","sequence":"first","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2839-8693","authenticated-orcid":false,"given":"Lei","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5508-5732","authenticated-orcid":false,"given":"Bo","family":"Hu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3596-5585","authenticated-orcid":false,"given":"Mengxiao","family":"Zhu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5739-8126","authenticated-orcid":false,"given":"Zhendong","family":"Mao","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, 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":"crossref","unstructured":"Peter Anderson Xiaodong He Chris Buehler Damien Teney Mark Johnson Stephen Gould and Lei Zhang. 2018. Bottom-up and top-down attention for image captioning and visual question answering. In CVPR. 6077--6086.","DOI":"10.1109\/CVPR.2018.00636"},{"key":"e_1_3_2_1_2_1","unstructured":"Mikhail Belkin Siyuan Ma and Soumik Mandal. 2018. To understand deep learning we need to understand kernel learning. In ICML. PMLR 541--549."},{"key":"e_1_3_2_1_3_1","volume-title":"Imram: Iterative matching with recurrent attention memory for cross-modal image-text retrieval. In CVPR. 12655--12663.","author":"Chen Hui","year":"2020","unstructured":"Hui Chen, Guiguang Ding, Xudong Liu, Zijia Lin, Ji Liu, and Jungong Han. 2020b. Imram: Iterative matching with recurrent attention memory for cross-modal image-text retrieval. In CVPR. 12655--12663."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"crossref","unstructured":"Jiacheng Chen Hexiang Hu Hao Wu Yuning Jiang and Changhu Wang. 2021. Learning the best pooling strategy for visual semantic embedding. In CVPR. 15789--15798.","DOI":"10.1109\/CVPR46437.2021.01553"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Tianlang Chen Jiajun Deng and Jiebo Luo. 2020a. Adaptive offline quintuplet loss for image-text matching. In ECCV. 549--565.","DOI":"10.1007\/978-3-030-58601-0_33"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6631"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"crossref","unstructured":"Haiwen Diao Ying Zhang Lin Ma and Huchuan Lu. 2021. Similarity Reasoning and Filtration for Image-Text Matching. In AAAI.","DOI":"10.1609\/aaai.v35i2.16209"},{"key":"e_1_3_2_1_8_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. In arXiv preprint arXiv:1707.05612."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16226"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3227414"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","unstructured":"Zheren Fu Zhendong Mao Yan Song and Yongdong Zhang. 2023. Learning Semantic Relationship Among Instances for Image-Text Matching. In CVPR. 15159--15168.","DOI":"10.1109\/CVPR52729.2023.01455"},{"key":"e_1_3_2_1_12_1","first-page":"4736","article-title":"Self-supervised synthesis ranking for deep metric learning","volume":"32","author":"Fu Zheren","year":"2021","unstructured":"Zheren Fu, Zhendong Mao, Chenggang Yan, An-An Liu, Hongtao Xie, and Yongdong Zhang. 2021b. Self-supervised synthesis ranking for deep metric learning. IEEE T-CSVT, Vol. 32, 7 (2021), 4736--4750.","journal-title":"IEEE T-CSVT"},{"key":"e_1_3_2_1_13_1","volume-title":"Dse-gan: Dynamic semantic evolution generative adversarial network for text-to-image generation. In ACM MM. 4345--4354.","author":"Huang Mengqi","year":"2022","unstructured":"Mengqi Huang, Zhendong Mao, Penghui Wang, Quan Wang, and Yongdong Zhang. 2022. Dse-gan: Dynamic semantic evolution generative adversarial network for text-to-image generation. In ACM MM. 4345--4354."},{"key":"e_1_3_2_1_14_1","volume-title":"Acmm: Aligned cross-modal memory for few-shot image and sentence matching. In ICCV. 5774--5783.","author":"Huang Yan","year":"2019","unstructured":"Yan Huang and Liang Wang. 2019. Acmm: Aligned cross-modal memory for few-shot image and sentence matching. In ICCV. 5774--5783."},{"key":"e_1_3_2_1_15_1","unstructured":"Zhong Ji Kexin Chen and Haoran Wang. 2021. Step-Wise Hierarchical Alignment Network for Image-Text Matching. In IJCAI."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"crossref","unstructured":"Andrej Karpathy and Li Fei-Fei. 2015. Deep visual-semantic alignments for generating image descriptions. In CVPR. 3128--3137.","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"e_1_3_2_1_17_1","volume-title":"Deep fragment embeddings for bidirectional image sentence mapping. NeurIPS","author":"Karpathy Andrej","year":"2014","unstructured":"Andrej Karpathy, Armand Joulin, and Li Fei-Fei. 2014. Deep fragment embeddings for bidirectional image sentence mapping. NeurIPS (2014)."},{"key":"e_1_3_2_1_18_1","volume-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL-HLT. 4171--4186.","author":"Ming-Wei Chang Jacob Devlin","year":"2019","unstructured":"Jacob Devlin Ming-Wei Chang Kenton and Lee Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL-HLT. 4171--4186."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"crossref","unstructured":"Benjamin Klein Guy Lev Gil Sadeh and Lior Wolf. 2015. Associating neural word embeddings with deep image representations using fisher vectors. In CVPR. 4437--4446.","DOI":"10.1109\/CVPR.2015.7299073"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"e_1_3_2_1_21_1","unstructured":"Kuang-Huei Lee Xi Chen Gang Hua Houdong Hu and Xiaodong He. 2018. Stacked cross attention for image-text matching. In ECCV. 201--216."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/151"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20020"},{"key":"e_1_3_2_1_24_1","unstructured":"Kunpeng Li Yulun Zhang Kai Li Yuanyuan Li and Yun Fu. 2019. Visual semantic reasoning for image-text matching. In ICCV. 4654--4662."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3148470"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"crossref","unstructured":"Rengang Li Cong Xu Zhenhua Guo Baoyu Fan Runze Zhang Wei Liu Yaqian Zhao Weifeng Gong and Endong Wang. 2022d. AI-VQA: Visual Question Answering based on Agent Interaction with Interpretability. In ACM MM. 5274--5282.","DOI":"10.1145\/3503161.3548387"},{"key":"e_1_3_2_1_27_1","volume-title":"Oscar: Object-semantics aligned pre-training for vision-language tasks","author":"Li Xiujun","year":"2020","unstructured":"Xiujun Li, Xi Yin, Chunyuan Li, Pengchuan Zhang, Xiaowei Hu, Lei Zhang, Lijuan Wang, Houdong Hu, Li Dong, Furu Wei, et al. 2020. Oscar: Object-semantics aligned pre-training for vision-language tasks. In ECCV. Springer, 121--137."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3261443"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"crossref","unstructured":"Zheng Li Caili Guo Zerun Feng Jenq-Neng Hwang and Xijun Xue. 2022a. Multi-View Visual Semantic Embedding. In IJCAI. 1130--1136.","DOI":"10.24963\/ijcai.2022\/158"},{"key":"e_1_3_2_1_30_1","volume-title":"Michael Ying Yang, and Bodo Rosenhahn","author":"Liao Wentong","year":"2022","unstructured":"Wentong Liao, Kai Hu, Michael Ying Yang, and Bodo Rosenhahn. 2022. Text to image generation with semantic-spatial aware gan. In CVPR. 18187--18196."},{"key":"e_1_3_2_1_31_1","volume-title":"Microsoft coco: Common objects in context","author":"Lin Tsung-Yi","unstructured":"Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Doll\u00e1r, and C Lawrence Zitnick. 2014. Microsoft coco: Common objects in context. In ECCV. Springer, 740--755."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"crossref","unstructured":"Chunxiao Liu Zhendong Mao An-An Liu Tianzhu Zhang Bin Wang and Yongdong Zhang. 2019. Focus your attention: A bidirectional focal attention network for image-text matching. In ACM MM. 3--11.","DOI":"10.1145\/3343031.3350869"},{"key":"e_1_3_2_1_33_1","unstructured":"Chunxiao Liu Zhendong Mao Tianzhu Zhang Hongtao Xie Bin Wang and Yongdong Zhang. 2020. Graph structured network for image-text matching. In CVPR. 10921--10930."},{"key":"e_1_3_2_1_34_1","volume-title":"Glove: Global vectors for word representation. In EMNLP. 1532--1543.","author":"Pennington Jeffrey","year":"2014","unstructured":"Jeffrey Pennington, Richard Socher, and Christopher D Manning. 2014. Glove: Global vectors for word representation. In EMNLP. 1532--1543."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"crossref","unstructured":"Leigang Qu Meng Liu Da Cao Liqiang Nie and Qi Tian. 2020. Context-aware multi-view summarization network for image-text matching. In ACM MM. 1047--1055.","DOI":"10.1145\/3394171.3413961"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"crossref","unstructured":"Leigang Qu Meng Liu Jianlong Wu Zan Gao and Liqiang Nie. 2021. Dynamic modality interaction modeling for image-text retrieval. In ACM SIGIR. 1104--1113.","DOI":"10.1145\/3404835.3462829"},{"key":"e_1_3_2_1_37_1","volume-title":"Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al.","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 ICML. 8748--8763."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"crossref","unstructured":"Bernhard Sch\u00f6lkopf Alexander J Smola Francis Bach et al. 2002. Learning with kernels: support vector machines regularization optimization and beyond. MIT press.","DOI":"10.7551\/mitpress\/4175.001.0001"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"e_1_3_2_1_40_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_41_1","volume-title":"Regularization with dot-product kernels. Advances in neural information processing systems","author":"Smola Alex","year":"2000","unstructured":"Alex Smola, Zolt\u00e1n Ov\u00e1ri, and Robert C Williamson. 2000. Regularization with dot-product kernels. Advances in neural information processing systems, Vol. 13 (2000)."},{"key":"e_1_3_2_1_42_1","article-title":"Visualizing data using t-SNE","volume":"9","author":"der Maaten Laurens Van","year":"2008","unstructured":"Laurens Van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. Journal of machine learning research, Vol. 9, 11 (2008).","journal-title":"Journal of machine learning research"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"crossref","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 WACV. 1508--1517.","DOI":"10.1109\/WACV45572.2020.9093614"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"crossref","unstructured":"Yaxiong Wang Hao Yang Xueming Qian Lin Ma Jing Lu Biao Li and Xin Fan. 2019b. Position focused attention network for image-text matching. In IJCAI. 3792--3798.","DOI":"10.24963\/ijcai.2019\/526"},{"key":"e_1_3_2_1_45_1","volume-title":"Camp: Cross-modal adaptive message passing for text-image retrieval. In ICCV. 5764--5773.","author":"Wang Zihao","year":"2019","unstructured":"Zihao Wang, Xihui Liu, Hongsheng Li, Lu Sheng, Junjie Yan, Xiaogang Wang, and Jing Shao. 2019a. Camp: Cross-modal adaptive message passing for text-image retrieval. In ICCV. 5764--5773."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6915"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"crossref","unstructured":"Hao Wei Shuhui Wang Xinzhe Han Zhe Xue Bin Ma Xiaoming Wei and Xiaolin Wei. 2022. Synthesizing Counterfactual Samples for Effective Image-Text Matching. In ACM MM. 4355--4364.","DOI":"10.1145\/3503161.3547814"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"crossref","unstructured":"Jiwei Wei Xing Xu Yang Yang Yanli Ji Zheng Wang and Heng Tao Shen. 2020. Universal weighting metric learning for cross-modal matching. In CVPR. 13005--13014.","DOI":"10.1109\/CVPR42600.2020.01302"},{"key":"e_1_3_2_1_49_1","first-page":"2866","article-title":"Learning dual semantic relations with graph attention for image-text matching","volume":"31","author":"Wen Keyu","year":"2020","unstructured":"Keyu Wen, Xiaodong Gu, and Qingrong Cheng. 2020. Learning dual semantic relations with graph attention for image-text matching. IEEE T-CSVT, Vol. 31, 7 (2020), 2866--2879.","journal-title":"IEEE T-CSVT"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"crossref","unstructured":"Yiling Wu Shuhui Wang Guoli Song and Qingming Huang. 2019. Learning fragment self-attention embeddings for image-text matching. In ACM MM. 2088--2096.","DOI":"10.1145\/3343031.3350940"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3045530"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"crossref","unstructured":"Shiyang Yan Li Yu and Yuan Xie. 2021. Discrete-continuous Action Space Policy Gradient-based Attention for Image-Text Matching. In CVPR. 8096--8105.","DOI":"10.1109\/CVPR46437.2021.00800"},{"key":"e_1_3_2_1_53_1","volume-title":"Electronics and Mobile Communication Conference. 0258--0265","author":"Zeng Zhixian","year":"2021","unstructured":"Zhixian Zeng, Jianjun Cao, Nianfeng Weng, Guoquan Jiang, Yizhuo Rao, and Yuxin Xu. 2021. Softmax Pooling for Super Visual Semantic Embedding. In IEEE 12th Annual Information Technology, Electronics and Mobile Communication Conference. 0258--0265."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20235"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"crossref","unstructured":"Jingjing Zhang Shancheng Fang Zhendong Mao Zhiwei Zhang and Yongdong Zhang. 2022a. Fine-tuning with Multi-modal Entity Prompts for News Image Captioning. In ACM MM. 4365--4373.","DOI":"10.1145\/3503161.3547883"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3141603"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"crossref","unstructured":"Kun Zhang Zhendong Mao Quan Wang and Yongdong Zhang. 2022c. Negative-aware attention framework for image-text matching. In CVPR. 15661--15670.","DOI":"10.1109\/CVPR52688.2022.01521"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"crossref","unstructured":"Qi Zhang Zhen Lei Zhaoxiang Zhang and Stan Z Li. 2020. Context-aware attention network for image-text retrieval. In CVPR. 3536--3545.","DOI":"10.1109\/CVPR42600.2020.00359"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7006"},{"key":"e_1_3_2_1_60_1","volume-title":"ESA: External Space Attention Aggregation for Image-Text Retrieval","author":"Zhu Hongguang","year":"2023","unstructured":"Hongguang Zhu, Chunjie Zhang, Yunchao Wei, Shujuan Huang, and Yao Zhao. 2023. ESA: External Space Attention Aggregation for Image-Text Retrieval. IEEE T-CSVT (2023), 1--13."},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"crossref","unstructured":"Jianwei Zhu Zhixin Li Yufei Zeng Jiahui Wei and Huifang Ma. 2022. Image-Text Matching with Fine-Grained Relational Dependency and Bidirectional Attention-Based Generative Networks. In ACM MM. 395--403.","DOI":"10.1145\/3503161.3548058"}],"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\/3581783.3611703","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3611703","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:06:08Z","timestamp":1755821168000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611703"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":61,"alternative-id":["10.1145\/3581783.3611703","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3611703","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"}}]}}