{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T09:04:24Z","timestamp":1765357464474,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":44,"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":"Natural Science Foundation of Hunan Province","award":["2022JJ30159 and 2023JJ20013"],"award-info":[{"award-number":["2022JJ30159 and 2023JJ20013"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61802121"],"award-info":[{"award-number":["61802121"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Fundamental Research Funds for the Central Universities"},{"DOI":"10.13039\/501100012226","name":"China Scholarship Council","doi-asserted-by":"publisher","award":["202206130103"],"award-info":[{"award-number":["202206130103"]}],"id":[{"id":"10.13039\/501100012226","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\/3581783.3613822","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:12Z","timestamp":1698391632000},"page":"7521-7529","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Deconfounded Multimodal Learning for Spatio-temporal Video Grounding"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6601-2958","authenticated-orcid":false,"given":"Jiawei","family":"Wang","sequence":"first","affiliation":[{"name":"Hunan University, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-7705-3639","authenticated-orcid":false,"given":"Zhanchang","family":"Ma","sequence":"additional","affiliation":[{"name":"Hunan University, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2611-2559","authenticated-orcid":false,"given":"Da","family":"Cao","sequence":"additional","affiliation":[{"name":"Hunan University, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6283-9037","authenticated-orcid":false,"given":"Yuquan","family":"Le","sequence":"additional","affiliation":[{"name":"Hunan University, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5573-6195","authenticated-orcid":false,"given":"Junbin","family":"Xiao","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6097-7807","authenticated-orcid":false,"given":"Tat-Seng","family":"Chua","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"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\/ICCV.2017.618"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413840"},{"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":"10.1145\/3394171.3413614"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1183"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3481539"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"crossref","unstructured":"Dedre Gentner and Linsey A Smith. 2013. Analogical Learning and Reasoning. In The Oxford Handbook of Cognitive Psychology.","DOI":"10.1093\/oxfordhb\/9780195376746.013.0042"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.493"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19983"},{"key":"e_1_3_2_1_12_1","volume-title":"Embracing Consistency: A One-Stage Approach for Spatio-Temporal Video Grounding. arXiv preprint arXiv:2209.13306","author":"Jin Yang","year":"2022","unstructured":"Yang Jin, Yongzhi Li, Zehuan Yuan, and Yadong Mu. 2022. Embracing Consistency: A One-Stage Approach for Spatio-Temporal Video Grounding. arXiv preprint arXiv:2209.13306 (2022)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548333"},{"key":"e_1_3_2_1_15_1","volume-title":"Be causal: Debiasing social network confounding in recommendation. ACM Transactions on Knowledge Discovery from Data","author":"Li Qian","year":"2023","unstructured":"Qian Li, Xiangmeng Wang, Zhichao Wang, and Guandong Xu. 2023. Be causal: Debiasing social network confounding in recommendation. ACM Transactions on Knowledge Discovery from Data, Vol. 17, 1 (2023), 1--23."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00294"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01089"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547969"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00477"},{"key":"e_1_3_2_1_20_1","volume-title":"Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692","author":"Liu Yinhan","year":"2019","unstructured":"Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019a. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)."},{"key":"e_1_3_2_1_21_1","volume-title":"Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101","author":"Loshchilov Ilya","year":"2017","unstructured":"Ilya Loshchilov and Frank Hutter. 2017. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01005"},{"key":"e_1_3_2_1_23_1","volume-title":"Rethinking the Role of Demonstrations: What Makes In-Context Learning Work? arXiv preprint arXiv:2202.12837","author":"Min Sewon","year":"2022","unstructured":"Sewon Min, Xinxi Lyu, Ari Holtzman, Mikel Artetxe, Mike Lewis, Hannaneh Hajishirzi, and Luke Zettlemoyer. 2022. Rethinking the Role of Demonstrations: What Makes In-Context Learning Work? arXiv preprint arXiv:2202.12837 (2022)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_48"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00279"},{"key":"e_1_3_2_1_26_1","volume-title":"Cambridge University Press","volume":"19","author":"Judea","year":"2000","unstructured":"Judea Pearl et al. 2000. Models, reasoning and inference. Cambridge University Press, Vol. 19, 2 (2000)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475266"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3323873.3325056"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475485"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00156"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3085907"},{"volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. IEEE","author":"Wang Peng","key":"e_1_3_2_1_33_1","unstructured":"Peng Wang, Qi Wu, Jiewei Cao, Chunhua Shen, Lianli Gao, and Anton van den Hengel. 2019. Neighbourhood watch: Referring expression comprehension via language-guided graph attention networks. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. IEEE, 1960--1968."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548014"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.162"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01595"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00427"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00474"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462823"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413610"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00972"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_23"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00478"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01068"}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Ottawa ON Canada","acronym":"MM '23"},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3613822","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3613822","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T23:59:57Z","timestamp":1755820797000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3613822"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":44,"alternative-id":["10.1145\/3581783.3613822","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3613822","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"}}]}}