{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:07:02Z","timestamp":1777655222862,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":51,"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":"the National Natural Science Foundation of China","award":["U21B2024, 62202327"],"award-info":[{"award-number":["U21B2024, 62202327"]}]},{"name":"the China Postdoctoral Science Foundation","award":["2022M712369"],"award-info":[{"award-number":["2022M712369"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3612472","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:30Z","timestamp":1698391650000},"page":"6264-6273","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":13,"title":["Towards Deconfounded Image-Text Matching with Causal Inference"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9609-6120","authenticated-orcid":false,"given":"Wenhui","family":"Li","sequence":"first","affiliation":[{"name":"Tianjin University & Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Tianjin & Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4581-1807","authenticated-orcid":false,"given":"Xinqi","family":"Su","sequence":"additional","affiliation":[{"name":"Tianjin University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5864-0276","authenticated-orcid":false,"given":"Dan","family":"Song","sequence":"additional","affiliation":[{"name":"Tianjin University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7696-5330","authenticated-orcid":false,"given":"Lanjun","family":"Wang","sequence":"additional","affiliation":[{"name":"Tianjin University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6311-0840","authenticated-orcid":false,"given":"Kun","family":"Zhang","sequence":"additional","affiliation":[{"name":"Meituan, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5755-9145","authenticated-orcid":false,"given":"An-An","family":"Liu","sequence":"additional","affiliation":[{"name":"Tianjin University & Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Tianjin & Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Causal feature learning: an overview","author":"Chalupka Krzysztof","year":"2017","unstructured":"Krzysztof Chalupka, Frederick Eberhardt, and Pietro Perona. 2017. Causal feature learning: an overview., Vol. 44 (2017), 137--164."},{"key":"e_1_3_2_1_2_1","volume-title":"IMRAM: Iterative Matching With Recurrent Attention Memory for Cross-Modal Image-Text Retrieval. In 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR","author":"Chen Hui","year":"2020","unstructured":"Hui Chen, Guiguang Ding, Xudong Liu, Zijia Lin, Ji Liu, and Jungong Han. 2020. IMRAM: Iterative Matching With Recurrent Attention Memory for Cross-Modal Image-Text Retrieval. In 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020. 12652--12660."},{"key":"e_1_3_2_1_3_1","volume-title":"Learning the Best Pooling Strategy for Visual Semantic Embedding. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR. 15789--15798","author":"Chen Jiacheng","year":"2021","unstructured":"Jiacheng Chen, Hexiang Hu, Hao Wu, Yuning Jiang, and Changhu Wang. 2021a. Learning the Best Pooling Strategy for Visual Semantic Embedding. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR. 15789--15798."},{"key":"e_1_3_2_1_4_1","volume-title":"Adapted Graph Reasoning and Filtration for Description-Image Retrieval. In SIGIR '21: The 44th International ACM SIGIR Conference on Research and Development in Information Retrieval. 1839--1843","author":"Chen Shiqian","year":"2021","unstructured":"Shiqian Chen, Zhiling Luo, Yingqi Gao, Wei Zhou, Chenliang Li, and Haiqing Chen. 2021b. Adapted Graph Reasoning and Filtration for Description-Image Retrieval. In SIGIR '21: The 44th International ACM SIGIR Conference on Research and Development in Information Retrieval. 1839--1843."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547936"},{"key":"e_1_3_2_1_6_1","volume-title":"More Than Just Attention: Improving Cross-Modal Attentions with Contrastive Constraints for Image-Text Matching. In IEEE\/CVF Winter Conference on Applications of Computer Vision, WACV. 4421--4429","author":"Chen Yuxiao","unstructured":"Yuxiao Chen, Jianbo Yuan, Long Zhao, Tianlang Chen, Rui Luo, Larry Davis, and Dimitris N. Metaxas. 2023. More Than Just Attention: Improving Cross-Modal Attentions with Contrastive Constraints for Image-Text Matching. In IEEE\/CVF Winter Conference on Applications of Computer Vision, WACV. 4421--4429."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_8_1","volume-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding.","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. (2019), 4171--4186."},{"key":"e_1_3_2_1_9_1","volume-title":"Similarity Reasoning and Filtration for Image-Text Matching. In Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI","author":"Diao Haiwen","year":"2021","unstructured":"Haiwen Diao, Ying Zhang, Lin Ma, and Huchuan Lu. 2021. Similarity Reasoning and Filtration for Image-Text Matching. In Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI 2021. 1218--1226."},{"key":"e_1_3_2_1_10_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_11_1","volume-title":"MKVSE: Multimodal Knowledge Enhanced Visual-Semantic Embedding for Image-Text Retrieval. ACM Transactions on Multimedia Computing, Communications and Applications","author":"Feng Duoduo","year":"2023","unstructured":"Duoduo Feng, Xiangteng He, and Yuxin Peng. 2023. MKVSE: Multimodal Knowledge Enhanced Visual-Semantic Embedding for Image-Text Retrieval. ACM Transactions on Multimedia Computing, Communications and Applications (2023)."},{"key":"e_1_3_2_1_12_1","volume-title":"Cross-modal Semantic Enhanced Interaction for Image-Sentence Retrieval. In IEEE\/CVF Winter Conference on Applications of Computer Vision, WACV. 1022--1031","author":"Ge Xuri","unstructured":"Xuri Ge, Fuhai Chen, Songpei Xu, Fuxiang Tao, and Joemon M. Jose. 2023. Cross-modal Semantic Enhanced Interaction for Image-Sentence Retrieval. In IEEE\/CVF Winter Conference on Applications of Computer Vision, WACV. 1022--1031."},{"key":"e_1_3_2_1_13_1","volume-title":"Causal inference in statistics: A primer","author":"Glymour Madelyn","unstructured":"Madelyn Glymour, Judea Pearl, and Nicholas P Jewell. 2016. Causal inference in statistics: A primer. John Wiley & Sons."},{"key":"e_1_3_2_1_14_1","volume-title":"Deep Residual Learning for Image Recognition. In 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR","author":"He Kaiming","year":"2016","unstructured":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep Residual Learning for Image Recognition. In 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016. 770--778."},{"key":"e_1_3_2_1_15_1","first-page":"7892","article-title":"MACK: Multimodal Aligned Conceptual Knowledge for Unpaired Image-text Matching","volume":"35","author":"Huang Yan","year":"2022","unstructured":"Yan Huang, Yuming Wang, Yunan Zeng, and Liang Wang. 2022. MACK: Multimodal Aligned Conceptual Knowledge for Unpaired Image-text Matching. Advances in Neural Information Processing Systems, Vol. 35 (2022), 7892--7904.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"e_1_3_2_1_17_1","volume-title":"Deep Fragment Embeddings for Bidirectional Image Sentence Mapping. (2014)","author":"Karpathy Andrej","year":"1889","unstructured":"Andrej Karpathy, Armand Joulin, and Li Fei-Fei. 2014. Deep Fragment Embeddings for Bidirectional Image Sentence Mapping. (2014), 1889--1897."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299073"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"e_1_3_2_1_20_1","volume-title":"Computer Vision - ECCV 2018 - 15th European Conference","author":"Lee Kuang-Huei","unstructured":"Kuang-Huei Lee, Xi Chen, Gang Hua, Houdong Hu, and Xiaodong He. 2018. Stacked Cross Attention for Image-Text Matching. In Computer Vision - ECCV 2018 - 15th European Conference, Vol. 11208. 212--228."},{"key":"e_1_3_2_1_21_1","volume-title":"Visual Semantic Reasoning for Image-Text Matching. In IEEE\/CVF International Conference on Computer Vision, ICCV. 4653--4661","author":"Li Kunpeng","year":"2019","unstructured":"Kunpeng Li, Yulun Zhang, Kai Li, Yuanyuan Li, and Yun Fu. 2019. Visual Semantic Reasoning for Image-Text Matching. In IEEE\/CVF International Conference on Computer Vision, ICCV. 4653--4661."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3148470"},{"key":"e_1_3_2_1_23_1","first-page":"7","article-title":"Multi-view visual semantic embedding","volume":"2","author":"Li Zheng","year":"2022","unstructured":"Zheng Li, Caili Guo, Zerun Feng, Jenq-Neng Hwang, and Xijun Xue. 2022. Multi-view visual semantic embedding. In IJCAI, Vol. 2. 7.","journal-title":"IJCAI"},{"key":"e_1_3_2_1_24_1","volume-title":"Computer Vision - ECCV 2014 - 13th European Conference","author":"Lin Tsung-Yi","unstructured":"Tsung-Yi Lin, Michael Maire, Serge J. Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Doll\u00e1r, and C. Lawrence Zitnick. 2014. Microsoft COCO: Common Objects in Context. In Computer Vision - ECCV 2014 - 13th European Conference, Vol. 8693. 740--755."},{"key":"e_1_3_2_1_25_1","volume-title":"Deconfound and Tell: Image Captioning with Causal Inference. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR. 18020--18029","author":"Liu Bing","year":"2022","unstructured":"Bing Liu, Dong Wang, Xu Yang, Yong Zhou, Rui Yao, Zhiwen Shao, and Jiaqi Zhao. 2022. Show, Deconfound and Tell: Image Captioning with Causal Inference. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR. 18020--18029."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350869"},{"key":"e_1_3_2_1_27_1","volume-title":"Graph Structured Network for Image-Text Matching. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR. Computer Vision Foundation \/ IEEE, 10918--10927","author":"Liu Chunxiao","year":"2020","unstructured":"Chunxiao Liu, Zhendong Mao, Tianzhu Zhang, Hongtao Xie, Bin Wang, and Yongdong Zhang. 2020. Graph Structured Network for Image-Text Matching. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR. Computer Vision Foundation \/ IEEE, 10918--10927."},{"key":"e_1_3_2_1_28_1","volume-title":"Discovering Causal Signals in Images. In 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR. 58--66","author":"Lopez-Paz David","year":"2017","unstructured":"David Lopez-Paz, Robert Nishihara, Soumith Chintala, Bernhard Sch\u00f6lkopf, and L\u00e9on Bottou. 2017. Discovering Causal Signals in Images. In 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR. 58--66."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"crossref","unstructured":"Yonghua Pan Zechao Li Liyan Zhang and Jinhui Tang. 2020. Distilling knowledge in causal inference for unbiased visual question answering. In MMAsia 2020: ACM Multimedia Asia. 3:1--3:7.","DOI":"10.1145\/3444685.3446256"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3487042"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1515\/jci-2018-2001"},{"key":"e_1_3_2_1_32_1","volume-title":"Scene graph semantic inference for image and text matching. Transactions on Asian and Low-Resource Language Information Processing","author":"Pei Jiaming","year":"2022","unstructured":"Jiaming Pei, Kaiyang Zhong, Zhi Yu, Lukun Wang, and Kuruva Lakshmanna. 2022. Scene graph semantic inference for image and text matching. Transactions on Asian and Low-Resource Language Information Processing (2022)."},{"key":"e_1_3_2_1_33_1","volume-title":"Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, EMNLP 2014. 1532--1543","author":"Pennington Jeffrey","unstructured":"Jeffrey Pennington, Richard Socher, and Christopher D. Manning. 2014. Glove: Global Vectors for Word Representation. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, EMNLP 2014. 1532--1543."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"e_1_3_2_1_35_1","volume-title":"Context-Aware Multi-View Summarization Network for Image-Text Matching. In MM '20: The 28th ACM International Conference on Multimedia. 1047--1055","author":"Qu Leigang","year":"2020","unstructured":"Leigang Qu, Meng Liu, Da Cao, Liqiang Nie, and Qi Tian. 2020. Context-Aware Multi-View Summarization Network for Image-Text Matching. In MM '20: The 28th ACM International Conference on Multimedia. 1047--1055."},{"key":"e_1_3_2_1_36_1","unstructured":"Shaoqing Ren Kaiming He Ross B. Girshick and Jian Sun. 2015. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. (2015) 91--99."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/720"},{"key":"e_1_3_2_1_38_1","volume-title":"Computer Vision - ECCV 2020 - 16th European Conference","author":"Wang Haoran","unstructured":"Haoran Wang, Ying Zhang, Zhong Ji, Yanwei Pang, and Lin Ma. 2020b. Consensus-Aware Visual-Semantic Embedding for Image-Text Matching. In Computer Vision - ECCV 2020 - 16th European Conference, Vol. 12369. 18--34."},{"key":"e_1_3_2_1_39_1","volume-title":"Visual Commonsense R-CNN. In 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR. 10757--10767","author":"Wang Tan","year":"2020","unstructured":"Tan Wang, Jianqiang Huang, Hanwang Zhang, and Qianru Sun. 2020a. Visual Commonsense R-CNN. In 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR. 10757--10767."},{"key":"e_1_3_2_1_40_1","volume-title":"CAMP: Cross-Modal Adaptive Message Passing for Text-Image Retrieval. In IEEE\/CVF International Conference on Computer Vision, ICCV. 5763--5772","author":"Wang Zihao","year":"2019","unstructured":"Zihao Wang, Xihui Liu, Hongsheng Li, Lu Sheng, Junjie Yan, Xiaogang Wang, and Jing Shao. 2019. CAMP: Cross-Modal Adaptive Message Passing for Text-Image Retrieval. In IEEE\/CVF International Conference on Computer Vision, ICCV. 5763--5772."},{"key":"e_1_3_2_1_41_1","volume-title":"Synthesizing Counterfactual Samples for Effective Image-Text Matching. In MM '22: The 30th ACM International Conference on Multimedia. 4355--4364","author":"Wei Hao","year":"2022","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 MM '22: The 30th ACM International Conference on Multimedia. 4355--4364."},{"key":"e_1_3_2_1_42_1","volume-title":"Discrete-Continuous Action Space Policy Gradient-Based Attention for Image-Text Matching. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR. 8096--8105","author":"Yan Shiyang","year":"2021","unstructured":"Shiyang Yan, Li Yu, and Yuan Xie. 2021. Discrete-Continuous Action Space Policy Gradient-Based Attention for Image-Text Matching. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR. 8096--8105."},{"key":"e_1_3_2_1_43_1","volume-title":"Deconfounded image captioning: A causal retrospect","author":"Yang Xu","year":"2021","unstructured":"Xu Yang, Hanwang Zhang, and Jianfei Cai. 2021a. Deconfounded image captioning: A causal retrospect. IEEE Transactions on Pattern Analysis and Machine Intelligence (2021)."},{"key":"e_1_3_2_1_44_1","volume-title":"Causal Attention for Vision-Language Tasks. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR. 9847--9857","author":"Yang Xu","year":"2021","unstructured":"Xu Yang, Hanwang Zhang, Guojun Qi, and Jianfei Cai. 2021b. Causal Attention for Vision-Language Tasks. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR. 9847--9857."},{"key":"e_1_3_2_1_45_1","volume-title":"Electronics and Mobile Communication Conference (IEMCON). 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 2021 IEEE 12th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON). 0258--0265."},{"key":"e_1_3_2_1_46_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. 2020c. 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_47_1","volume-title":"Show Your Faith: Cross-Modal Confidence-Aware Network for Image-Text Matching. In Thirty-Sixth AAAI Conference on Artificial Intelligence, AAAI","volume":"36","author":"Zhang Huatian","year":"2022","unstructured":"Huatian Zhang, Zhendong Mao, Kun Zhang, and Yongdong Zhang. 2022b. Show Your Faith: Cross-Modal Confidence-Aware Network for Image-Text Matching. In Thirty-Sixth AAAI Conference on Artificial Intelligence, AAAI 2022, Vol. 36. 3262--3270."},{"key":"e_1_3_2_1_48_1","volume-title":"Negative-Aware Attention Framework for Image-Text Matching. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR. IEEE, 15640--15649","author":"Zhang Kun","year":"2022","unstructured":"Kun Zhang, Zhendong Mao, Quan Wang, and Yongdong Zhang. 2022a. Negative-Aware Attention Framework for Image-Text Matching. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR. IEEE, 15640--15649."},{"key":"e_1_3_2_1_49_1","volume-title":"Context-Aware Attention Network for Image-Text Retrieval. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR. 3533--3542","author":"Zhang Qi","unstructured":"Qi Zhang, Zhen Lei, Zhaoxiang Zhang, and Stan Z. Li. 2020b. Context-Aware Attention Network for Image-Text Retrieval. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR. 3533--3542."},{"key":"e_1_3_2_1_50_1","volume-title":"DeVLBert: Learning Deconfounded Visio-Linguistic Representations. In MM '20: The 28th ACM International Conference on Multimedia. 4373--4382","author":"Zhang Shengyu","year":"2020","unstructured":"Shengyu Zhang, Tan Jiang, Tan Wang, Kun Kuang, Zhou Zhao, Jianke Zhu, Jin Yu, Hongxia Yang, and Fei Wu. 2020a. DeVLBert: Learning Deconfounded Visio-Linguistic Representations. In MM '20: The 28th ACM International Conference on Multimedia. 4373--4382."},{"key":"e_1_3_2_1_51_1","volume-title":"Deep Stable Learning for Out-of-Distribution Generalization. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR. 5372--5382","author":"Zhang Xingxuan","year":"2021","unstructured":"Xingxuan Zhang, Peng Cui, Renzhe Xu, Linjun Zhou, Yue He, and Zheyan Shen. 2021. Deep Stable Learning for Out-of-Distribution Generalization. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR. 5372--5382."}],"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\/3581783.3612472","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3612472","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T23:57:02Z","timestamp":1755820622000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612472"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":51,"alternative-id":["10.1145\/3581783.3612472","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3612472","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"}}]}}