{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T13:04:39Z","timestamp":1775567079823,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":52,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,7,6]],"date-time":"2022-07-06T00:00:00Z","timestamp":1657065600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,7,6]]},"DOI":"10.1145\/3477495.3532078","type":"proceedings-article","created":{"date-parts":[[2022,7,7]],"date-time":"2022-07-07T15:12:08Z","timestamp":1657206728000},"page":"1033-1043","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":40,"title":["Video Moment Retrieval from Text Queries via Single Frame Annotation"],"prefix":"10.1145","author":[{"given":"Ran","family":"Cui","sequence":"first","affiliation":[{"name":"The Australian National University, Canberra, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianwen","family":"Qian","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pai","family":"Peng","sequence":"additional","affiliation":[{"name":"bilibili, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Elena","family":"Daskalaki","sequence":"additional","affiliation":[{"name":"The Australian National University, Canberra, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingjing","family":"Chen","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaowei","family":"Guo","sequence":"additional","affiliation":[{"name":"bilibili, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huyang","family":"Sun","sequence":"additional","affiliation":[{"name":"bilibili, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu-Gang","family":"Jiang","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,7,7]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.618"},{"key":"e_1_3_2_2_2_1","volume-title":"Jamie Ryan Kiros, and Geoffrey E Hinton","author":"Ba Jimmy Lei","year":"2016","unstructured":"Jimmy Lei Ba , Jamie Ryan Kiros, and Geoffrey E Hinton . 2016 . Layer normalization. arXiv preprint arXiv:1607.06450 (2016). Jimmy Lei Ba, Jamie Ryan Kiros, and Geoffrey E Hinton. 2016. Layer normalization. arXiv preprint arXiv:1607.06450 (2016)."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"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.v33i01.33018175"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_20"},{"key":"e_1_3_2_2_8_1","volume-title":"End-to-end Multimodal Video Temporal Grounding. Advances in Neural Information Processing Systems 34","author":"Chen Yi-Wen","year":"2021","unstructured":"Yi-Wen Chen , Yi-Hsuan Tsai , and Ming-Hsuan Yang . 2021. End-to-end Multimodal Video Temporal Grounding. Advances in Neural Information Processing Systems 34 ( 2021 ). Yi-Wen Chen, Yi-Hsuan Tsai, and Ming-Hsuan Yang. 2021. End-to-end Multimodal Video Temporal Grounding. Advances in Neural Information Processing Systems 34 (2021)."},{"key":"e_1_3_2_2_9_1","volume-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin , Ming-Wei Chang , Kenton Lee , and Kristina Toutanova . 2018 . BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. arXiv preprint arXiv:1810.04805 (2018). Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_2_10_1","volume-title":"Weakly supervised dense event captioning in videos. arXiv preprint arXiv:1812.03849","author":"Duan Xuguang","year":"2018","unstructured":"Xuguang Duan , Wenbing Huang , Chuang Gan , Jingdong Wang , Wenwu Zhu , and Junzhou Huang . 2018. Weakly supervised dense event captioning in videos. arXiv preprint arXiv:1812.03849 ( 2018 ). Xuguang Duan, Wenbing Huang, Chuang Gan, Jingdong Wang, Wenwu Zhu, and Junzhou Huang. 2018. Weakly supervised dense event captioning in videos. arXiv preprint arXiv:1812.03849 (2018)."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_47"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"e_1_3_2_2_13_1","volume-title":"Wslln: Weakly supervised natural language localization networks. arXiv preprint arXiv:1909.00239","author":"Gao Mingfei","year":"2019","unstructured":"Mingfei Gao , Larry S Davis , Richard Socher , and Caiming Xiong . 2019 . Wslln: Weakly supervised natural language localization networks. arXiv preprint arXiv:1909.00239 (2019). Mingfei Gao, Larry S Davis, Richard Socher, and Caiming Xiong. 2019. Wslln: Weakly supervised natural language localization networks. arXiv preprint arXiv:1909.00239 (2019)."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00032"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00711"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3323873.3325019"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2815998"},{"key":"e_1_3_2_2_20_1","volume-title":"Dense-Captioning Events in Videos. In International Conference on Computer Vision (ICCV).","author":"Krishna Ranjay","year":"2017","unstructured":"Ranjay Krishna , Kenji Hata , Frederic Ren , Li Fei-Fei , and Juan Carlos Niebles . 2017 . Dense-Captioning Events in Videos. In International Conference on Computer Vision (ICCV). Ranjay Krishna, Kenji Hata, Frederic Ren, Li Fei-Fei, and Juan Carlos Niebles. 2017. Dense-Captioning Events in Videos. In International Conference on Computer Vision (ICCV)."},{"key":"e_1_3_2_2_21_1","volume-title":"Proceedings, Part XXI 16","author":"Lei Jie","year":"2020","unstructured":"Jie Lei , Licheng Yu , Tamara L Berg , and Mohit Bansal . 2020 . Tvr: A large-scale dataset for video-subtitle moment retrieval. In Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020 , Proceedings, Part XXI 16 . Springer, 447--463. Jie Lei, Licheng Yu, Tamara L Berg, and Mohit Bansal. 2020. Tvr: A large-scale dataset for video-subtitle moment retrieval. In Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020, Proceedings, Part XXI 16. Springer, 447--463."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_1"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6820"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240549"},{"key":"e_1_3_2_2_25_1","volume-title":"A Survey on Natural Language Video Localization. arXiv preprint arXiv:2104.00234","author":"Liu Xinfang","year":"2021","unstructured":"Xinfang Liu , Xiushan Nie , Zhifang Tan , Jie Guo , and Yilong Yin . 2021. A Survey on Natural Language Video Localization. arXiv preprint arXiv:2104.00234 ( 2021 ). Xinfang Liu, Xiushan Nie, Zhifang Tan, Jie Guo, and Yilong Yin. 2021. A Survey on Natural Language Video Localization. arXiv preprint arXiv:2104.00234 (2021)."},{"key":"e_1_3_2_2_26_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 ). Ilya Loshchilov and Frank Hutter. 2017. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)."},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_10"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01186"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01082"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.5555\/3104322.3104425"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3414053"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00207"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33718-5_11"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_31"},{"key":"e_1_3_2_2_36_1","volume-title":"Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman . 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 ( 2014 ). Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)."},{"key":"e_1_3_2_2_37_1","volume-title":"Weakly-supervised multi-level attentional reconstruction network for grounding textual queries in videos. arXiv preprint arXiv:2003.07048","author":"Song Yijun","year":"2020","unstructured":"Yijun Song , Jingwen Wang , Lin Ma , Zhou Yu , and Jun Yu. 2020. Weakly-supervised multi-level attentional reconstruction network for grounding textual queries in videos. arXiv preprint arXiv:2003.07048 ( 2020 ). Yijun Song, Jingwen Wang, Lin Ma, Zhou Yu, and Jun Yu. 2020. Weakly-supervised multi-level attentional reconstruction network for grounding textual queries in videos. arXiv preprint arXiv:2003.07048 (2020)."},{"key":"e_1_3_2_2_38_1","volume-title":"Dropout: a simple way to prevent neural networks from overfitting. The journal of machine learning research 15, 1","author":"Srivastava Nitish","year":"2014","unstructured":"Nitish Srivastava , Geoffrey Hinton , Alex Krizhevsky , Ilya Sutskever , and Ruslan Salakhutdinov . 2014. Dropout: a simple way to prevent neural networks from overfitting. The journal of machine learning research 15, 1 ( 2014 ), 1929--1958. Nitish Srivastava, Geoffrey Hinton, Alex Krizhevsky, Ilya Sutskever, and Ruslan Salakhutdinov. 2014. Dropout: a simple way to prevent neural networks from overfitting. The journal of machine learning research 15, 1 (2014), 1929--1958."},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00213"},{"key":"e_1_3_2_2_40_1","volume-title":"C3D: generic features for video analysis. CoRR, abs\/1412.0767 2, 7","author":"Tran Du","year":"2014","unstructured":"Du Tran , Lubomir D Bourdev , Rob Fergus , Lorenzo Torresani , and Manohar Paluri . 2014. C3D: generic features for video analysis. CoRR, abs\/1412.0767 2, 7 ( 2014 ), 8. Du Tran, Lubomir D Bourdev, Rob Fergus, Lorenzo Torresani, and Manohar Paluri. 2014. C3D: generic features for video analysis. CoRR, abs\/1412.0767 2, 7 (2014), 8."},{"key":"e_1_3_2_2_41_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez \"ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In Advances in neural information processing systems. 5998--6008.  Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez \"ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In Advances in neural information processing systems. 5998--6008."},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00695"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6897"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413862"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019062"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019159"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00134"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.585"},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6984"},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331235"},{"key":"e_1_3_2_2_51_1","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 , Xiuqiang He , 2020 . Counterfactual contrastive learning for weakly-supervised vision-language grounding . Advances in Neural Information Processing Systems 33 (2020), 18123 -- 18134 . Zhu Zhang, Zhou Zhao, Zhijie Lin, Xiuqiang He, et al. 2020. Counterfactual contrastive learning for weakly-supervised vision-language grounding. Advances in Neural Information Processing Systems 33 (2020), 18123--18134.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.317"}],"event":{"name":"SIGIR '22: The 45th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Madrid Spain","acronym":"SIGIR '22","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3477495.3532078","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3477495.3532078","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T18:10:35Z","timestamp":1750183835000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3477495.3532078"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,6]]},"references-count":52,"alternative-id":["10.1145\/3477495.3532078","10.1145\/3477495"],"URL":"https:\/\/doi.org\/10.1145\/3477495.3532078","relation":{},"subject":[],"published":{"date-parts":[[2022,7,6]]},"assertion":[{"value":"2022-07-07","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}