{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T16:57:22Z","timestamp":1779382642836,"version":"3.53.1"},"publisher-location":"New York, NY, USA","reference-count":47,"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":[{"name":"Guangdong Basic and Applied Basic Research Foundation","award":["2023A1515010688"],"award-info":[{"award-number":["2023A1515010688"]}]},{"DOI":"10.13039\/501100015805","name":"Shenzhen Municipal Science and Technology Innovation Council","doi-asserted-by":"publisher","award":["JCYJ20220531101412030"],"award-info":[{"award-number":["JCYJ20220531101412030"]}],"id":[{"id":"10.13039\/501100015805","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82261138629"],"award-info":[{"award-number":["82261138629"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3612148","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:26:54Z","timestamp":1698391614000},"page":"5572-5583","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":15,"title":["QA-CLIMS: Question-Answer Cross Language Image Matching for Weakly Supervised Semantic Segmentation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-9843-2083","authenticated-orcid":false,"given":"Songhe","family":"Deng","sequence":"first","affiliation":[{"name":"Computer Vision Institute, School of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5780-0364","authenticated-orcid":false,"given":"Wei","family":"Zhuo","sequence":"additional","affiliation":[{"name":"National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5678-4500","authenticated-orcid":false,"given":"Jinheng","family":"Xie","sequence":"additional","affiliation":[{"name":"Computer Vision Institute, School of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1420-0815","authenticated-orcid":false,"given":"Linlin","family":"Shen","sequence":"additional","affiliation":[{"name":"Computer Vision Institute, School of Computer Science and Software Engineering, Shenzhen University, Shenzhen, 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":"publisher","DOI":"10.1109\/CVPR.2019.00231"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00523"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00901"},{"key":"e_1_3_2_1_4_1","volume-title":"SemFormer: Semantic Guided Activation Transformer for Weakly Supervised Semantic Segmentation. arXiv preprint arXiv:2210.14618","author":"Chen Junliang","year":"2022","unstructured":"Junliang Chen, Xiaodong Zhao, Cheng Luo, and Linlin Shen. 2022d. SemFormer: Semantic Guided Activation Transformer for Weakly Supervised Semantic Segmentation. arXiv preprint arXiv:2210.14618 (2022)."},{"key":"e_1_3_2_1_5_1","volume-title":"Semantic image segmentation with deep convolutional nets and fully connected crfs. arXiv preprint arXiv:1412.7062","author":"Chen Liang-Chieh","year":"2014","unstructured":"Liang-Chieh Chen, George Papandreou, Iasonas Kokkinos, Kevin Murphy, and Alan L Yuille. 2014. Semantic image segmentation with deep convolutional nets and fully connected crfs. arXiv preprint arXiv:1412.7062 (2014)."},{"key":"e_1_3_2_1_6_1","volume-title":"Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs","author":"Chen Liang-Chieh","year":"2017","unstructured":"Liang-Chieh Chen, George Papandreou, Iasonas Kokkinos, Kevin Murphy, and Alan L Yuille. 2017. Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE transactions on pattern analysis and machine intelligence, Vol. 40, 4 (2017), 834--848."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00425"},{"key":"e_1_3_2_1_8_1","volume-title":"International conference on machine learning. PMLR, 1597--1607","author":"Chen Ting","year":"2020","unstructured":"Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey Hinton. 2020. A simple framework for contrastive learning of visual representations. In International conference on machine learning. PMLR, 1597--1607."},{"key":"e_1_3_2_1_9_1","volume-title":"Pali: A jointly-scaled multilingual language-image model. arXiv preprint arXiv:2209.06794","author":"Chen Xi","year":"2022","unstructured":"Xi Chen, Xiao Wang, Soravit Changpinyo, AJ Piergiovanni, Piotr Padlewski, Daniel Salz, Sebastian Goodman, Adam Grycner, Basil Mustafa, Lucas Beyer, et al. 2022a. Pali: A jointly-scaled multilingual language-image model. arXiv preprint arXiv:2209.06794 (2022)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00306"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00104"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_13_1","volume-title":"Christopher KI Williams, John Winn, and Andrew Zisserman.","author":"Everingham Mark","year":"2009","unstructured":"Mark Everingham, Luc Van Gool, Christopher KI Williams, John Winn, and Andrew Zisserman. 2009. The pascal visual object classes (voc) challenge. International journal of computer vision, Vol. 88 (2009), 303--308."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_16_1","volume-title":"International Conference on Machine Learning. PMLR, 4904--4916","author":"Jia Chao","year":"2021","unstructured":"Chao Jia, Yinfei Yang, Ye Xia, Yi-Ting Chen, Zarana Parekh, Hieu Pham, Quoc Le, Yun-Hsuan Sung, Zhen Li, and Tom Duerig. 2021. Scaling up visual and vision-language representation learning with noisy text supervision. In International Conference on Machine Learning. PMLR, 4904--4916."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01638"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.181"},{"key":"e_1_3_2_1_19_1","first-page":"27408","article-title":"Reducing information bottleneck for weakly supervised semantic segmentation","volume":"34","author":"Lee Jungbeom","year":"2021","unstructured":"Jungbeom Lee, Jooyoung Choi, Jisoo Mok, and Sungroh Yoon. 2021a. Reducing information bottleneck for weakly supervised semantic segmentation. Advances in Neural Information Processing Systems, Vol. 34 (2021), 27408--27421.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00406"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01639"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00429"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00545"},{"key":"e_1_3_2_1_24_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. 2022b. 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_25_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20034"},{"key":"e_1_3_2_1_26_1","volume-title":"Supervision exists everywhere: A data efficient contrastive language-image pre-training paradigm. arXiv preprint arXiv:2110.05208","author":"Li Yangguang","year":"2021","unstructured":"Yangguang Li, Feng Liang, Lichen Zhao, Yufeng Cui, Wanli Ouyang, Jing Shao, Fengwei Yu, and Junjie Yan. 2021. Supervision exists everywhere: A data efficient contrastive language-image pre-training paradigm. arXiv preprint arXiv:2110.05208 (2021)."},{"key":"e_1_3_2_1_27_1","volume-title":"Open-vocabulary semantic segmentation with mask-adapted clip. arXiv preprint arXiv:2210.04150","author":"Liang Feng","year":"2022","unstructured":"Feng Liang, Bichen Wu, Xiaoliang Dai, Kunpeng Li, Yinan Zhao, Hang Zhang, Peizhao Zhang, Peter Vajda, and Diana Marculescu. 2022. Open-vocabulary semantic segmentation with mask-adapted clip. arXiv preprint arXiv:2210.04150 (2022)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.344"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_1_30_1","volume-title":"CLIP is Also an Efficient Segmenter: A Text-Driven Approach for Weakly Supervised Semantic Segmentation. arXiv preprint arXiv:2212.09506","author":"Lin Yuqi","year":"2022","unstructured":"Yuqi Lin, Minghao Chen, Wenxiao Wang, Boxi Wu, Ke Li, Binbin Lin, Haifeng Liu, and Xiaofei He. 2022. CLIP is Also an Efficient Segmenter: A Text-Driven Approach for Weakly Supervised Semantic Segmentation. arXiv preprint arXiv:2212.09506 (2022)."},{"key":"e_1_3_2_1_31_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_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240542"},{"key":"e_1_3_2_1_33_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_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.315"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01229"},{"key":"e_1_3_2_1_36_1","volume-title":"Zihang Dai, Yulia Tsvetkov, and Yuan Cao.","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. arXiv preprint arXiv:2108.10904 (2021)."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.01.006"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00444"},{"key":"e_1_3_2_1_39_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 989--998","author":"Xie Jinheng","year":"2022","unstructured":"Jinheng Xie, Jianfeng Xiang, Junliang Chen, Xianxu Hou, Xiaodong Zhao, and Linlin Shen. 2022b. C2AM: Contrastive Learning of Class-Agnostic Activation Map for Weakly Supervised Object Localization and Semantic Segmentation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 989--998."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548201"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00427"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01877"},{"key":"e_1_3_2_1_43_1","first-page":"655","article-title":"Causal intervention for weakly-supervised semantic segmentation","volume":"33","author":"Zhang Dong","year":"2020","unstructured":"Dong Zhang, Hanwang Zhang, Jinhui Tang, Xian-Sheng Hua, and Qianru Sun. 2020. Causal intervention for weakly-supervised semantic segmentation. Advances in Neural Information Processing Systems, Vol. 33 (2020), 655--666.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547919"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475675"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00426"}],"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\/3581783.3612148","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3612148","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T23:55:37Z","timestamp":1755820537000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612148"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":47,"alternative-id":["10.1145\/3581783.3612148","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3612148","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"}}]}}