{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T15:55:18Z","timestamp":1774713318510,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":82,"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":"open research fund of The State Key Laboratory of Multimodal Artificial Intelligence Systems"},{"name":"Young Elite Scientists Sponsorship Program by CAST","award":["2022ONRC001"],"award-info":[{"award-number":["2022ONRC001"]}]},{"name":"Fundamental Research Funds for the Provincial Universities of Zhejiang"},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61972448,62172068,62202293,61831007"],"award-info":[{"award-number":["61972448,62172068,62202293,61831007"]}],"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\/3581783.3612038","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:12Z","timestamp":1698391632000},"page":"4190-4199","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["Filling the Information Gap between Video and Query for Language-Driven Moment Retrieval"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8179-4508","authenticated-orcid":false,"given":"Daizong","family":"Liu","sequence":"first","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4907-3978","authenticated-orcid":false,"given":"Xiaoye","family":"Qu","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5244-3274","authenticated-orcid":false,"given":"Jianfeng","family":"Dong","sequence":"additional","affiliation":[{"name":"Zhejiang Gongshang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1987-2736","authenticated-orcid":false,"given":"Guoshun","family":"Nan","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8629-4622","authenticated-orcid":false,"given":"Pan","family":"Zhou","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5438-1468","authenticated-orcid":false,"given":"Zichuan","family":"Xu","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1805-0183","authenticated-orcid":false,"given":"Lixing","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai Jiaotong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8948-3544","authenticated-orcid":false,"given":"He","family":"Yan","sequence":"additional","affiliation":[{"name":"ProtagoLabs, Vienna, VA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9830-0081","authenticated-orcid":false,"given":"Yu","family":"Cheng","sequence":"additional","affiliation":[{"name":"Microsoft Research, Richmond, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_2_1_1","first-page":"12980","article-title":"Compress: Self-supervised learning by compressing representations","volume":"33","author":"Koohpayegani Soroush Abbasi","year":"2020","unstructured":"Soroush Abbasi Koohpayegani, Ajinkya Tejankar, and Hamed Pirsiavash. 2020. Compress: Self-supervised learning by compressing representations. Advances in Neural Information Processing Systems, Vol. 33 (2020), 12980--12992.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.618"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.773"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1015"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6627"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01138"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01137"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547976"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2832602"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3059295"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591690"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25127"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3150959"},{"key":"e_1_3_2_2_15_1","volume-title":"Learning Linguistic Association Towards Efficient Text-Video Retrieval. In European Conference on Computer Vision. Springer, 254--270","author":"Fang Sheng","year":"2022","unstructured":"Sheng Fang, Shuhui Wang, Junbao Zhuo, Xinzhe Han, and Qingming Huang. 2022c. Learning Linguistic Association Towards Efficient Text-Video Retrieval. In European Conference on Computer Vision. Springer, 254--270."},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3222965"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00242"},{"key":"e_1_3_2_2_18_1","volume-title":"Hierarchical local-global transformer for temporal sentence grounding. arXiv preprint arXiv:2208.14882","author":"Fang Xiang","year":"2022","unstructured":"Xiang Fang, Daizong Liu, Pan Zhou, Zichuan Xu, and Ruixuan Li. 2022b. Hierarchical local-global transformer for temporal sentence grounding. arXiv preprint arXiv:2208.14882 (2022)."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00155"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00032"},{"key":"e_1_3_2_2_22_1","volume-title":"Zhaohan Guo, Mohammad Gheshlaghi Azar, et al.","author":"Grill Jean-Bastien","year":"2020","unstructured":"Jean-Bastien Grill, Florian Strub, Florent Altch\u00e9, Corentin Tallec, Pierre Richemond, Elena Buchatskaya, Carl Doersch, Bernardo Avila Pires, Zhaohan Guo, Mohammad Gheshlaghi Azar, et al. 2020. Bootstrap your own latent-a new approach to self-supervised learning. Advances in neural information processing systems, Vol. 33 (2020), 21271--21284."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859675"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19781-9_26"},{"key":"e_1_3_2_2_26_1","volume-title":"Tel Aviv","author":"Huang Jiabo","year":"2022","unstructured":"Jiabo Huang, Hailin Jin, Shaogang Gong, and Yang Liu. 2022. Video Activity Localisation with Uncertainties in Temporal Boundary. In Computer Vision-ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23-27, 2022, Proceedings, Part XXXIV. Springer, 724--740."},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00129"},{"key":"e_1_3_2_2_28_1","volume-title":"Mrtnet: Multi-resolution temporal network for video sentence grounding. arXiv preprint arXiv:2212.13163","author":"Ji Wei","year":"2022","unstructured":"Wei Ji, Long Chen, Yinwei Wei, Yiming Wu, and Tat-Seng Chua. 2022. Mrtnet: Multi-resolution temporal network for video sentence grounding. arXiv preprint arXiv:2212.13163 (2022)."},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3002083"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2962216"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3479232"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02204"},{"key":"e_1_3_2_2_33_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_2_34_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16285"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00294"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403149"},{"key":"e_1_3_2_2_37_1","volume-title":"Pareto multi-task learning. Advances in neural information processing systems","author":"Lin Xi","year":"2019","unstructured":"Xi Lin, Hui-Ling Zhen, Zhenhua Li, Qing-Fu Zhang, and Sam Kwong. 2019. Pareto multi-task learning. Advances in neural information processing systems (2019)."},{"key":"e_1_3_2_2_38_1","volume-title":"2023 a. Exploring optical-flow-guided motion and detection-based appearance for temporal sentence grounding","author":"Liu Daizong","year":"2023","unstructured":"Daizong Liu, Xiang Fang, Wei Hu, and Pan Zhou. 2023 a. Exploring optical-flow-guided motion and detection-based appearance for temporal sentence grounding. IEEE Transactions on Multimedia (2023)."},{"key":"e_1_3_2_2_39_1","volume-title":"2023 b. Hypotheses tree building for one-shot temporal sentence localization. arXiv preprint arXiv:2301.01871","author":"Liu Daizong","year":"2023","unstructured":"Daizong Liu, Xiang Fang, Pan Zhou, Xing Di, Weining Lu, and Yu Cheng. 2023 b. Hypotheses tree building for one-shot temporal sentence localization. arXiv preprint arXiv:2301.01871 (2023)."},{"key":"e_1_3_2_2_40_1","volume-title":"Proceedings of the 29th International Conference on Computational Linguistics. 5532--5541","author":"Liu Daizong","year":"2022","unstructured":"Daizong Liu and Wei Hu. 2022a. Learning to focus on the foreground for temporal sentence grounding. In Proceedings of the 29th International Conference on Computational Linguistics. 5532--5541."},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547782"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20058"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.167"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.732"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01108"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547969"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3414026"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20060"},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.733"},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20059"},{"key":"e_1_3_2_2_51_1","volume-title":"2022 e. Few-shot temporal sentence grounding via memory-guided semantic learning","author":"Liu Daizong","year":"2022","unstructured":"Daizong Liu, Pan Zhou, Zichuan Xu, Haozhao Wang, and Ruixuan Li. 2022 e. Few-shot temporal sentence grounding via memory-guided semantic learning. IEEE Transactions on Circuits and Systems for Video Technology (2022)."},{"key":"e_1_3_2_2_52_1","volume-title":"Darts: Differentiable architecture search. arXiv preprint arXiv:1806.09055","author":"Liu Hanxiao","year":"2018","unstructured":"Hanxiao Liu, Karen Simonyan, and Yiming Yang. 2018a. Darts: Differentiable architecture search. arXiv preprint arXiv:1806.09055 (2018)."},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210003"},{"key":"e_1_3_2_2_54_1","volume-title":"Distantly-supervised named entity recognition with noise-robust learning and language model augmented self-training. arXiv preprint arXiv:2109.05003","author":"Meng Yu","year":"2021","unstructured":"Yu Meng, Yunyi Zhang, Jiaxin Huang, Xuan Wang, Yu Zhang, Heng Ji, and Jiawei Han. 2021. Distantly-supervised named entity recognition with noise-robust learning and language model augmented self-training. arXiv preprint arXiv:2109.05003 (2021)."},{"key":"e_1_3_2_2_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00970"},{"key":"e_1_3_2_2_56_1","volume-title":"Multi-scale self-contrastive learning with hard negative mining for weakly-supervised query-based video grounding. arXiv preprint arXiv:2203.03838","author":"Mo Shentong","year":"2022","unstructured":"Shentong Mo, Daizong Liu, and Wei Hu. 2022. Multi-scale self-contrastive learning with hard negative mining for weakly-supervised query-based video grounding. arXiv preprint arXiv:2203.03838 (2022)."},{"key":"e_1_3_2_2_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01082"},{"key":"e_1_3_2_2_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00279"},{"key":"e_1_3_2_2_59_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"e_1_3_2_2_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3414053"},{"key":"e_1_3_2_2_61_1","volume-title":"Grounding action descriptions in videos. Transactions of the Association for Computational Linguistics","author":"Regneri Michaela","year":"2013","unstructured":"Michaela Regneri, Marcus Rohrbach, Dominikus Wetzel, Stefan Thater, Bernt Schiele, and Manfred Pinkal. 2013. Grounding action descriptions in videos. Transactions of the Association for Computational Linguistics (2013)."},{"key":"e_1_3_2_2_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093328"},{"key":"e_1_3_2_2_63_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_49"},{"key":"e_1_3_2_2_64_1","volume-title":"Multi-task learning as multi-objective optimization. Advances in neural information processing systems","author":"Sener Ozan","year":"2018","unstructured":"Ozan Sener and Vladlen Koltun. 2018. Multi-task learning as multi-objective optimization. Advances in neural information processing systems, Vol. 31 (2018)."},{"key":"e_1_3_2_2_65_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_31"},{"key":"e_1_3_2_2_66_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6897"},{"key":"e_1_3_2_2_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00042"},{"key":"e_1_3_2_2_68_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20163"},{"key":"e_1_3_2_2_69_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16406"},{"key":"e_1_3_2_2_70_1","volume-title":"Tracking Objects and Activities with Attention for Temporal Sentence Grounding. In ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 1--5.","author":"Xiong Zeyu","year":"2023","unstructured":"Zeyu Xiong, Daizong Liu, Pan Zhou, and Jiahao Zhu. 2023. Tracking Objects and Activities with Attention for Temporal Sentence Grounding. In ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 1--5."},{"key":"e_1_3_2_2_71_1","volume-title":"Entity-aware and motion-aware transformers for language-driven action localization in videos. arXiv preprint arXiv:2205.05854","author":"Yang Shuo","year":"2022","unstructured":"Shuo Yang and Xinxiao Wu. 2022. Entity-aware and motion-aware transformers for language-driven action localization in videos. arXiv preprint arXiv:2205.05854 (2022)."},{"key":"e_1_3_2_2_72_1","unstructured":"Yitian Yuan Lin Ma Jingwen Wang Wei Liu and Wenwu Zhu. 2019a. Semantic Conditioned Dynamic Modulation for Temporal Sentence Grounding in Videos. In Advances in Neural Information Processing Systems (NIPS). 534--544."},{"key":"e_1_3_2_2_73_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019159"},{"key":"e_1_3_2_2_74_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01030"},{"key":"e_1_3_2_2_75_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00134"},{"key":"e_1_3_2_2_76_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.585"},{"key":"e_1_3_2_2_77_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6984"},{"key":"e_1_3_2_2_78_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331235"},{"key":"e_1_3_2_2_79_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00418"},{"key":"e_1_3_2_2_80_1","first-page":"1","article-title":"Progressive localization networks for language-based moment localization ACM Transactions on Multimedia Computing","volume":"19","author":"Zheng Qi","year":"2023","unstructured":"Qi Zheng, Jianfeng Dong, Xiaoye Qu, Xun Yang, Yabing Wang, Pan Zhou, Baolong Liu, and Xun Wang. 2023. Progressive localization networks for language-based moment localization ACM Transactions on Multimedia Computing, Communications and Applications, Vol. 19, 2 (2023), 1--21.","journal-title":"Communications and Applications"},{"key":"e_1_3_2_2_81_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01022"},{"key":"e_1_3_2_2_82_1","unstructured":"Jiahao Zhu Daizong Liu Pan Zhou Xing Di Yu Cheng Song Yang Wenzheng Xu Zichuan Xu Yao Wan Lichao Sun et al. 2023. Rethinking the video sampling and reasoning strategies for temporal sentence grounding. arXiv preprint arXiv:2301.00514 (2023)."}],"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\/3581783.3612038","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3612038","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:07:31Z","timestamp":1755821251000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612038"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":82,"alternative-id":["10.1145\/3581783.3612038","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3612038","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"}}]}}