{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T01:25:20Z","timestamp":1784165120283,"version":"3.55.0"},"reference-count":73,"publisher":"Association for Computing Machinery (ACM)","issue":"3","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62276155 and 62576195"],"award-info":[{"award-number":["62276155 and 62576195"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Inf. Syst."],"published-print":{"date-parts":[[2026,3,31]]},"abstract":"<jats:p>Video Moment Retrieval (VMR) aims to retrieve temporal moments in videos that align with natural language queries, a task requiring cross-modal reasoning between video and text. Among various supervision paradigms, point-supervised VMR has emerged as a practical solution, leveraging single-frame annotations to significantly reduce annotation costs while maintaining competitive retrieval performance. However, this sparse supervision approach induces cross-modal representation shift. This shift complicates the model\u2019s ability to accurately capture action sequences and associate text with visual content. To tackle this, we propose a novel framework called pseuDo fRame-based tempOral and semaNtic rEfinement (DRONE) with two key modules: (1) Pseudo-Frame Temporal Alignment (PTA), which embeds textual queries as pseudo-frames to enhance temporal coherence, and (2) Curriculum-Guided Semantic Refinement (CSR), which uses a progressive contrastive learning strategy to refine semantic representations from easy to hard cases. Extensive experiments show that DRONE achieves effective retrieval performance while keeping annotation costs low.<\/jats:p>","DOI":"10.1145\/3786606","type":"journal-article","created":{"date-parts":[[2025,12,24]],"date-time":"2025-12-24T13:57:22Z","timestamp":1766584642000},"page":"1-30","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Cross-modal Representation Shift Refinement for Point-supervised Video Moment Retrieval"],"prefix":"10.1145","volume":"44","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-4856-8806","authenticated-orcid":false,"given":"Kun","family":"Wang","sequence":"first","affiliation":[{"name":"School of Software, Shandong University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5653-8286","authenticated-orcid":false,"given":"Yupeng","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Software, Shandong University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1026-4499","authenticated-orcid":false,"given":"Hao","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Software, Shandong University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1789-0935","authenticated-orcid":false,"given":"Jiang","family":"Shao","sequence":"additional","affiliation":[{"name":"School of Software, Shandong University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1476-0273","authenticated-orcid":false,"given":"Liqiang","family":"Nie","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,2,16]]},"reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27832"},{"key":"e_1_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27831"},{"key":"e_1_3_1_4_2","first-page":"549","volume-title":"Proceedings of the European Conference on Computer Vision","author":"Bearman Amy","year":"2016","unstructured":"Amy Bearman, Olga Russakovsky, Vittorio Ferrari, and Li Fei-Fei. 2016. What\u2019s the point: Semantic segmentation with point supervision. In Proceedings of the European Conference on Computer Vision, 549\u2013565."},{"key":"e_1_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"e_1_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00631"},{"key":"e_1_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"e_1_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612504"},{"key":"e_1_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/3652600"},{"key":"e_1_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611696"},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3532078"},{"key":"e_1_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/3688570"},{"key":"e_1_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1016\/0010-0277(93)90058-4"},{"key":"e_1_3_1_14_2","first-page":"482","volume-title":"Proceedings of the Conference on Robot Learning","author":"Florensa Carlos","year":"2017","unstructured":"Carlos Florensa, David Held, Markus Wulfmeier, Michael Zhang, and Pieter Abbeel. 2017. Reverse curriculum generation for reinforcement learning. In Proceedings of the Conference on Robot Learning, 482\u2013495."},{"key":"e_1_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"e_1_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00155"},{"key":"e_1_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_9"},{"key":"e_1_3_1_18_2","first-page":"2535","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Hacohen Guy","year":"2019","unstructured":"Guy Hacohen and Daphna Weinshall. 2019. On the power of curriculum learning in training deep networks. In Proceedings of the International Conference on Machine Learning, 2535\u20132544."},{"key":"e_1_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3632403"},{"key":"e_1_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3073867"},{"key":"e_1_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3090521"},{"key":"e_1_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/3620669"},{"key":"e_1_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00711"},{"key":"e_1_3_1_24_2","first-page":"2304","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Jiang Lu","year":"2018","unstructured":"Lu Jiang, Zhengyuan Zhou, Thomas Leung, Li-Jia Li, and Li Fei-Fei. 2018. MentorNet: Learning data-driven curriculum for very deep neural networks on corrupted labels. In Proceedings of the International Conference on Machine Learning, 2304\u20132313."},{"key":"e_1_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612394"},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/3627158"},{"key":"e_1_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"e_1_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29812"},{"key":"e_1_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01263"},{"key":"e_1_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0321"},{"key":"e_1_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6820"},{"key":"e_1_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3726302.3729984"},{"key":"e_1_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10890877"},{"key":"e_1_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240549"},{"key":"e_1_3_1_35_2","unstructured":"Ilya Loshchilov and Frank Hutter. 2017. Decoupled weight decay regularization. arXiv:1711.05101. Retrieved from https:\/\/arxiv.org\/abs\/1711.05101"},{"key":"e_1_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/3233773"},{"key":"e_1_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_10"},{"key":"e_1_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01082"},{"key":"e_1_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"e_1_3_1_40_2","doi-asserted-by":"crossref","unstructured":"Emmanouil Antonios Platanios Otilia Stretcu Graham Neubig Barnabas Poczos and Tom M. Mitchell. 2019. Competence-based curriculum learning for neural machine translation. arXiv:1903.09848. Retrieved from https:\/\/arxiv.org\/abs\/1903.09848","DOI":"10.18653\/v1\/N19-1119"},{"key":"e_1_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00207"},{"key":"e_1_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33718-5_11"},{"key":"e_1_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_31"},{"key":"e_1_3_1_44_2","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556. Retrieved from https:\/\/arxiv.org\/abs\/1409.1556"},{"key":"e_1_3_1_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00213"},{"key":"e_1_3_1_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"e_1_3_1_47_2","doi-asserted-by":"publisher","DOI":"10.1145\/3561971"},{"key":"e_1_3_1_48_2","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten Laurens","year":"2008","unstructured":"Laurens Van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. Journal of Machine Learning Research 9 (2008), 2579\u20132605.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_1_49_2","doi-asserted-by":"publisher","DOI":"10.1145\/3528667"},{"key":"e_1_3_1_50_2","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680774"},{"issue":"9","key":"e_1_3_1_51_2","first-page":"4555","article-title":"A survey on curriculum learning","volume":"44","author":"Wang Xin","year":"2021","unstructured":"Xin Wang, Yudong Chen, and Wenwu Zhu. 2021. A survey on curriculum learning. IEEE Transactions on Pattern Analysis and Machine Intelligence 44, 9 (2021), 4555\u20134576.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_1_52_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20163"},{"key":"e_1_3_1_53_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00281"},{"key":"e_1_3_1_54_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16406"},{"key":"e_1_3_1_55_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3191841"},{"key":"e_1_3_1_56_2","doi-asserted-by":"publisher","DOI":"10.1145\/3652854"},{"key":"e_1_3_1_57_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3368919"},{"key":"e_1_3_1_58_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019159"},{"key":"e_1_3_1_59_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01030"},{"key":"e_1_3_1_60_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00134"},{"key":"e_1_3_1_61_2","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475234"},{"key":"e_1_3_1_62_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3312302"},{"key":"e_1_3_1_63_2","first-page":"1","article-title":"Spatial understanding from videos: Structured prompts meet simulation data","volume":"39","author":"Zhang Haoyu","year":"2025","unstructured":"Haoyu Zhang, Meng Liu, Zaijing Li, Haokun Wen, Weili Guan, Yaowei Wang, and Liqiang Nie. 2025. Spatial understanding from videos: Structured prompts meet simulation data. In Advances in Neural Information Processing Systems, Vol. 39, 1\u201316.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_64_2","first-page":"59310","volume-title":"Proceedings of the 41st International Conference on Machine Learning","volume":"235","author":"Zhang Haoyu","year":"2024","unstructured":"Haoyu Zhang, Meng Liu, Zixin Liu, Xuemeng Song, Yaowei Wang, and Liqiang Nie. 2024. Multi-factor adaptive vision selection for egocentric video question answering. In Proceedings of the 41st International Conference on Machine Learning, Vol. 235. PMLR, 59310\u201359328."},{"issue":"8","key":"e_1_3_1_65_2","first-page":"4252","article-title":"Natural language video localization: A revisit in span-based question answering framework","volume":"44","author":"Zhang Hao","year":"2021","unstructured":"Hao Zhang, Aixin Sun, Wei Jing, Liangli Zhen, Joey Tianyi Zhou, and Rick Siow Mong Goh. 2021. Natural language video localization: A revisit in span-based question answering framework. IEEE Transactions on Pattern Analysis and Machine Intelligence 44, 8 (2021), 4252\u20134266.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_1_66_2","doi-asserted-by":"crossref","unstructured":"Hao Zhang Aixin Sun Wei Jing and Joey Tianyi Zhou. 2020. Span-based localizing network for natural language video localization. arXiv:2004.13931. Retrieved from https:\/\/arxiv.org\/abs\/2004.13931","DOI":"10.18653\/v1\/2020.acl-main.585"},{"key":"e_1_3_1_67_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3258628"},{"key":"e_1_3_1_68_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6984"},{"key":"e_1_3_1_69_2","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, and Xiuqiang He. 2020. Counterfactual contrastive learning for weakly-supervised vision-language grounding. In Advances in Neural Information Processing Systems, Vol. 33, 18123\u201318134.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_70_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6513"},{"key":"e_1_3_1_71_2","doi-asserted-by":"publisher","DOI":"10.1145\/3637870"},{"key":"e_1_3_1_72_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20263"},{"key":"e_1_3_1_73_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01511"},{"key":"e_1_3_1_74_2","first-page":"8602","article-title":"Curriculum learning by dynamic instance hardness","volume":"33","author":"Zhou Tianyi","year":"2020","unstructured":"Tianyi Zhou, Shengjie Wang, and Jeffrey Bilmes. 2020. Curriculum learning by dynamic instance hardness. In Advances in Neural Information Processing Systems, Vol. 33, 8602\u20138613.","journal-title":"Advances in Neural Information Processing Systems"}],"container-title":["ACM Transactions on Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3786606","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T12:16:05Z","timestamp":1773317765000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3786606"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,16]]},"references-count":73,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,3,31]]}},"alternative-id":["10.1145\/3786606"],"URL":"https:\/\/doi.org\/10.1145\/3786606","relation":{},"ISSN":["1046-8188","1558-2868"],"issn-type":[{"value":"1046-8188","type":"print"},{"value":"1558-2868","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,16]]},"assertion":[{"value":"2025-03-27","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-11-03","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-02-16","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}