{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T04:53:32Z","timestamp":1781585612543,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":50,"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":"National Key R&D Program of China","award":["2022ZD0118201"],"award-info":[{"award-number":["2022ZD0118201"]}]},{"name":"the National Natural Science Foundation of China","award":["U21B2037, U22B2051, 623B2088, 62072389, U21A20472"],"award-info":[{"award-number":["U21B2037, U22B2051, 623B2088, 62072389, U21A20472"]}]},{"name":"the National Science Fund for Distinguished Young Scholars","award":["62025603"],"award-info":[{"award-number":["62025603"]}]},{"name":"the Natural Science Foundation of Fujian Province of China","award":["2021J01002, 2022J06001"],"award-info":[{"award-number":["2021J01002, 2022J06001"]}]},{"name":"CCF-NetEase ThunderFire Innovation Research Funding","award":["CCF-Netease 202301"],"award-info":[{"award-number":["CCF-Netease 202301"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681058","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:33Z","timestamp":1729925973000},"page":"4177-4186","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["QueryMatch: A Query-based Contrastive Learning Framework for Weakly Supervised Visual Grounding"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-7125-8999","authenticated-orcid":false,"given":"Shengxin","family":"Chen","sequence":"first","affiliation":[{"name":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, Fujian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5334-1843","authenticated-orcid":false,"given":"Gen","family":"Luo","sequence":"additional","affiliation":[{"name":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, Fujian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5110-4526","authenticated-orcid":false,"given":"Yiyi","family":"Zhou","sequence":"additional","affiliation":[{"name":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, Fujian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3912-9306","authenticated-orcid":false,"given":"Xiaoshuai","family":"Sun","sequence":"additional","affiliation":[{"name":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, Fujian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4355-5711","authenticated-orcid":false,"given":"Guannan","family":"Jiang","sequence":"additional","affiliation":[{"name":"Intelligent Manufacturing Department, Contemporary Amperex Technology Co., Limited, Ningde, Fujian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9163-2932","authenticated-orcid":false,"given":"Rongrong","family":"Ji","sequence":"additional","affiliation":[{"name":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, Fujian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00182"},{"key":"e_1_3_2_1_2_1","volume-title":"Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473","author":"Bahdanau Dzmitry","year":"2014","unstructured":"Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. 2014. Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"e_1_3_2_1_5_1","volume-title":"Learning from box annotations for referring image segmentation","author":"Feng Guang","year":"2022","unstructured":"Guang Feng, Lihe Zhang, Zhiwei Hu, and Huchuan Lu. 2022. Learning from box annotations for referring image segmentation. IEEE Transactions on Neural Networks and Learning Systems (2022)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_44"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"e_1_3_2_1_8_1","unstructured":"Geoffrey Hinton Oriol Vinyals Jeff Dean et al. 2015. Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 Vol. 2 7 (2015)."},{"key":"e_1_3_2_1_9_1","volume-title":"Audio-Visual Contrastive Learning with Temporal Self-Supervision. arXiv preprint arXiv:2302.07702","author":"Jenni Simon","year":"2023","unstructured":"Simon Jenni, Alexander Black, and John Collomosse. 2023. Audio-Visual Contrastive Learning with Temporal Self-Supervision. arXiv preprint arXiv:2302.07702 (2023)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00263"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01425"},{"key":"e_1_3_2_1_12_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01999"},{"key":"e_1_3_2_1_14_1","volume-title":"Eng Gee Lim, and Yao Zhao","author":"Li Hui","year":"2023","unstructured":"Hui Li, Mingjie Sun, Jimin Xiao, Eng Gee Lim, and Yao Zhao. 2023. Fully and Weakly Supervised Referring Expression Segmentation with End-to-End Learning. IEEE Transactions on Circuits and Systems for Video Technology (2023)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00602"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"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","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01469"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02022"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3186410"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00270"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351074"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00556"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"crossref","unstructured":"Gen Luo Yiyi Zhou Minglang Huang Tianhe Ren Xiaoshuai Sun and Rongrong Ji. 2024. MoIL: Momentum Imitation Learning for Efficient Vision-Language Adaptation. IEEE Transactions on Pattern Analysis and Machine Intelligence (2024).","DOI":"10.1109\/TPAMI.2024.3435790"},{"key":"e_1_3_2_1_27_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Luo Gen","year":"2024","unstructured":"Gen Luo, Yiyi Zhou, Tianhe Ren, Shengxin Chen, Xiaoshuai Sun, and Rongrong Ji. 2024. Cheap and quick: Efficient vision-language instruction tuning for large language models. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3139234"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01871-1"},{"key":"e_1_3_2_1_30_1","volume-title":"2024 d. Feast Your Eyes: Mixture-of-Resolution Adaptation for Multimodal Large Language Models. arXiv preprint arXiv:2403.03003","author":"Luo Gen","year":"2024","unstructured":"Gen Luo, Yiyi Zhou, Yuxin Zhang, Xiawu Zheng, Xiaoshuai Sun, and Rongrong Ji. 2024 d. Feast Your Eyes: Mixture-of-Resolution Adaptation for Multimodal Large Language Models. arXiv preprint arXiv:2403.03003 (2024)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"e_1_3_2_1_32_1","first-page":"9564","article-title":"Multimodal contrastive learning with limoe: the language-image mixture of experts","volume":"35","author":"Mustafa Basil","year":"2022","unstructured":"Basil Mustafa, Carlos Riquelme, Joan Puigcerver, Rodolphe Jenatton, and Neil Houlsby. 2022. Multimodal contrastive learning with limoe: the language-image mixture of experts. Advances in Neural Information Processing Systems, Vol. 35 (2022), 9564--9576.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_48"},{"key":"e_1_3_2_1_34_1","volume-title":"Variational context: Exploiting visual and textual context for grounding referring expressions","author":"Niu Yulei","year":"2019","unstructured":"Yulei Niu, Hanwang Zhang, Zhiwu Lu, and Shih-Fu Chang. 2019. Variational context: Exploiting visual and textual context for grounding referring expressions. IEEE transactions on pattern analysis and machine intelligence, Vol. 43, 1 (2019), 347--359."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20108"},{"key":"e_1_3_2_1_36_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_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"e_1_3_2_1_38_1","volume-title":"Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767","author":"Redmon Joseph","year":"2018","unstructured":"Joseph Redmon and Ali Farhadi. 2018. Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767 (2018)."},{"key":"e_1_3_2_1_39_1","volume-title":"Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems","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. Advances in neural information processing systems, Vol. 28 (2015)."},{"key":"e_1_3_2_1_40_1","first-page":"28222","article-title":"What is where by looking: Weakly-supervised open-world phrase-grounding without text inputs","volume":"35","author":"Shaharabany Tal","year":"2022","unstructured":"Tal Shaharabany, Yoad Tewel, and Lior Wolf. 2022. What is where by looking: Weakly-supervised open-world phrase-grounding without text inputs. Advances in Neural Information Processing Systems, Vol. 35 (2022), 28222--28237.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_41_1","volume-title":"Weakly-supervised segmentation of referring expressions. arXiv preprint arXiv:2205.04725","author":"Strudel Robin","year":"2022","unstructured":"Robin Strudel, Ivan Laptev, and Cordelia Schmid. 2022. Weakly-supervised segmentation of referring expressions. arXiv preprint arXiv:2205.04725 (2022)."},{"key":"e_1_3_2_1_42_1","volume-title":"Si Liu, and John Y Goulermas.","author":"Sun Mingjie","year":"2021","unstructured":"Mingjie Sun, Jimin Xiao, Eng Gee Lim, Si Liu, and John Y Goulermas. 2021. Discriminative triad matching and reconstruction for weakly referring expression grounding. IEEE transactions on pattern analysis and machine intelligence, Vol. 43, 11 (2021), 4189--4195."},{"key":"e_1_3_2_1_43_1","volume-title":"Attention is all you need. Advances in neural information processing systems","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01387"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01139"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01760"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01762"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01075"},{"key":"e_1_3_2_1_49_1","first-page":"18123","article-title":"Counterfactual contrastive learning for weakly-supervised vision-language grounding","volume":"33","author":"Zhang Zhu","year":"2020","unstructured":"Zhu Zhang, Zhou Zhao, Zhijie Lin, Xiuqiang He, et al. 2020. Counterfactual contrastive learning for weakly-supervised vision-language grounding. Advances in Neural Information Processing Systems, Vol. 33 (2020), 18123--18134.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_50_1","volume-title":"Yelong Shen, Anlei Dong, Jingwen Lu, Rangan Majumder, Ji-Rong Wen, Nan Duan, et al.","author":"Zhou Kun","year":"2022","unstructured":"Kun Zhou, Yeyun Gong, Xiao Liu, Wayne Xin Zhao, Yelong Shen, Anlei Dong, Jingwen Lu, Rangan Majumder, Ji-Rong Wen, Nan Duan, et al. 2022. Simans: Simple ambiguous negatives sampling for dense text retrieval. arXiv preprint arXiv:2210.11773 (2022)."}],"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\/3664647.3681058","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681058","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:57:52Z","timestamp":1750294672000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681058"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":50,"alternative-id":["10.1145\/3664647.3681058","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681058","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"}}]}}