{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T18:04:24Z","timestamp":1784138664874,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":80,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T00:00:00Z","timestamp":1784419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,20]]},"DOI":"10.1145\/3805712.3809742","type":"proceedings-article","created":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T14:28:19Z","timestamp":1783693699000},"page":"857-868","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Generation-Augmented Video Corpus Moment Retrieval"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-0230-4595","authenticated-orcid":false,"given":"Mingjin","family":"Kuai","sequence":"first","affiliation":[{"name":"Nanjing University, Suzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8189-8279","authenticated-orcid":false,"given":"Qianyin","family":"Xiao","sequence":"additional","affiliation":[{"name":"Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2258-1291","authenticated-orcid":false,"given":"Juncheng","family":"Li","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2401-1931","authenticated-orcid":false,"given":"Jin","family":"Peng","sequence":"additional","affiliation":[{"name":"Nanjing University, Suzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9973-3305","authenticated-orcid":false,"given":"Lizi","family":"Liao","sequence":"additional","affiliation":[{"name":"Singapore Management University, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8106-9768","authenticated-orcid":false,"given":"Wei","family":"Ji","sequence":"additional","affiliation":[{"name":"Nanjing University, Suzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,19]]},"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":"10.1109\/CVPR.2017.502"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-025-02597-y"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1278"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3316025"},{"key":"e_1_3_2_1_6_1","volume-title":"PRVR: Partially Relevant Video Retrieval","author":"Chen Xianke","year":"2025","unstructured":"Xianke Chen, Daizong Liu, Xun Yang, Xirong Li, Jianfeng Dong, Meng Wang, and Xu Wang. 2025. PRVR: Partially Relevant Video Retrieval. IEEE Transactions on Pattern Analysis and Machine Intelligence (2025)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2370"},{"key":"e_1_3_2_1_8_1","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","volume":"1","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. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). 4171-4186."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00957"},{"key":"e_1_3_2_1_10_1","volume-title":"Video-of-thought: Step-by-step video reasoning from perception to cognition. arXiv preprint arXiv:2501.03230","author":"Fei Hao","year":"2024","unstructured":"Hao Fei, Shengqiong Wu, Wei Ji, Hanwang Zhang, Meishan Zhang, Mong-Li Lee, and Wynne Hsu. 2024. Video-of-thought: Step-by-step video reasoning from perception to cognition. arXiv preprint arXiv:2501.03230 (2024)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_13"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.99"},{"key":"e_1_3_2_1_14_1","volume-title":"First Conference on Language Modeling.","author":"Gu Albert","year":"2024","unstructured":"Albert Gu and Tri Dao. 2024. Mamba: Linear-time sequence modeling with selective state spaces. In First Conference on Language Modeling."},{"key":"e_1_3_2_1_15_1","first-page":"1474","article-title":"Hippo: Recurrent memory with optimal polynomial projections","volume":"33","author":"Gu Albert","year":"2020","unstructured":"Albert Gu, Tri Dao, Stefano Ermon, Atri Rudra, and Christopher R\u00e9. 2020. Hippo: Recurrent memory with optimal polynomial projections. Advances in Neural Information Processing Systems, Vol. 33 (2020), 1474-1487.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_16_1","volume-title":"Efficiently Modeling Long Sequences with Structured State Spaces. In International Conference on Learning Representations.","author":"Gu Albert","year":"2022","unstructured":"Albert Gu, Karan Goel, and Christopher Re. 2022. Efficiently Modeling Long Sequences with Structured State Spaces. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3344097"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3726302.3730015"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3652583.3658088"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475281"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.77"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.530"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01280"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401075"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02706"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02249"},{"key":"e_1_3_2_1_28_1","volume-title":"European Conference on Computer Vision. 220-238","author":"Lee Pilhyeon","year":"2024","unstructured":"Pilhyeon Lee and Hyeran Byun. 2024. Bam-detr: Boundary-aligned moment detection transformer for temporal sentence grounding in videos. In European Conference on Computer Vision. 220-238."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_27"},{"key":"e_1_3_2_1_30_1","volume-title":"International Conference on Machine Learning. 12888-12900","author":"Li Junnan","year":"2022","unstructured":"Junnan Li, Dongxu Li, Caiming Xiong, and Steven Hoi. 2022. Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In International Conference on Machine Learning. 12888-12900."},{"key":"e_1_3_2_1_31_1","volume-title":"European Conference on Computer Vision. 237-255","author":"Li Kunchang","year":"2024","unstructured":"Kunchang Li, Xinhao Li, Yi Wang, Yinan He, Yali Wang, Limin Wang, and Yu Qiao. 2024. Videomamba: State space model for efficient video understanding. In European Conference on Computer Vision. 237-255."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.161"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3722552"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6820"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"crossref","unstructured":"Haoyu Liu Shaohan Huang Jianfeng Liu Yuefeng Zhan Hao Sun Weiwei Deng Feng Sun Furu Wei and Qi Zhang. 2025a. GeAR: Generation Augmented Retrieval. arXiv preprint arXiv:2501.02772 (2025).","DOI":"10.32388\/GWQ6LR"},{"key":"e_1_3_2_1_36_1","volume-title":"Aggregate and Discriminate: Pseudo Clips-Guided Boundary Perception for Video Moment Retrieval","author":"Liu Jin","year":"2025","unstructured":"Jin Liu, Zongbing Zhang, Yuting Su, Bing Yang, Xiongkuo Min, and Guangtao Zhai. 2025c. Aggregate and Discriminate: Pseudo Clips-Guided Boundary Perception for Video Moment Retrieval. IEEE Transactions on Multimedia (2025)."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00826"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3581797"},{"key":"e_1_3_2_1_39_1","volume-title":"CAST: Modeling Visual State Transitions for Consistent Video Retrieval. arXiv preprint arXiv:2603.08648","author":"Liu Yanqing","year":"2026","unstructured":"Yanqing Liu, Yingcheng Liu, Fanghong Dong, Budianto Budianto, Cihang Xie, and Yan Jiao. 2026. CAST: Modeling Visual State Transitions for Consistent Video Retrieval. arXiv preprint arXiv:2603.08648 (2026)."},{"key":"e_1_3_2_1_40_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. 2019. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3273"},{"key":"e_1_3_2_1_42_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_43_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547910"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.316"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3206025.3206064"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i6.32666"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW67362.2025.00356"},{"key":"e_1_3_2_1_49_1","volume-title":"Document expansion by query prediction. arXiv preprint arXiv:1904.08375","author":"Nogueira Rodrigo","year":"2019","unstructured":"Rodrigo Nogueira, Wei Yang, Jimmy Lin, and Kyunghyun Cho. 2019. Document expansion by query prediction. arXiv preprint arXiv:1904.08375 (2019)."},{"key":"e_1_3_2_1_50_1","first-page":"413","volume-title":"Generative Retrieval and Alignment Model: A New Paradigm for E-commerce Retrieval. In Companion Proceedings of the ACM on Web Conference","author":"Pang Ming","year":"2025","unstructured":"Ming Pang, Chunyuan Yuan, Xiaoyu He, Zheng Fang, Donghao Xie, Fanyi Qu, Xue Jiang, Changping Peng, Zhangang Lin, Zheng Luo, et al., 2025. Generative Retrieval and Alignment Model: A New Paradigm for E-commerce Retrieval. In Companion Proceedings of the ACM on Web Conference 2025. 413-421."},{"key":"e_1_3_2_1_51_1","volume-title":"Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics. 311-318","author":"Papineni Kishore","year":"2002","unstructured":"Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. Bleu: a method for automatic evaluation of machine translation. In Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics. 311-318."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.83"},{"key":"e_1_3_2_1_53_1","volume-title":"Generalized Video Moment Retrieval. In The Thirteenth International Conference on Learning Representations.","author":"Qin You","year":"2025","unstructured":"You Qin, Qilong Wu, Yicong Li, Wei Ji, Li Li, Pengcheng Cai, Lina Wei, and Roger Zimmermann. 2025. Generalized Video Moment Retrieval. In The Thirteenth International Conference on Learning Representations."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW67362.2025.00355"},{"key":"e_1_3_2_1_55_1","volume-title":"International Conference on Machine Learning. 8748-8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al., 2021. Learning transferable visual models from natural language supervision. In International Conference on Machine Learning. 8748-8763."},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3402613"},{"key":"e_1_3_2_1_57_1","volume-title":"Simplified State Space Layers for Sequence Modeling. In The Eleventh International Conference on Learning Representations.","author":"Smith Jimmy TH","year":"2023","unstructured":"Jimmy TH Smith, Andrew Warrington, and Scott Linderman. 2023. Simplified State Space Layers for Sequence Modeling. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i7.32778"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/3726302.3729907"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1587"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"e_1_3_2_1_62_1","volume-title":"Advances in Neural Information Processing Systems","volume":"30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in Neural Information Processing Systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01566"},{"key":"e_1_3_2_1_64_1","unstructured":"Qiyi Wang Senda Chen and Ying Shen. 2025a. CausalVTG: Towards Robust Video Temporal Grounding via Causal Inference. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"crossref","unstructured":"Ye Wang Ziheng Wang Boshen Xu Yang Du Kejun Lin Zihan Xiao Zihao Yue Jianzhong Ju Liang Zhang Dingyi Yang et al. 2025b. Time-R1: Post-Training Large Vision Language Model for Temporal Video Grounding. arXiv preprint arXiv:2503.13377 (2025).","DOI":"10.1109\/ICASSP49660.2025.10888314"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i9.32971"},{"key":"e_1_3_2_1_67_1","volume-title":"FILIP: Fine-grained Interactive Language-Image Pre-Training. In International Conference on Learning Representations.","author":"Yao Lewei","year":"2022","unstructured":"Lewei Yao, Runhui Huang, Lu Hou, Guansong Lu, Minzhe Niu, Hang Xu, Xiaodan Liang, Zhenguo Li, Xin Jiang, and Chunjing Xu. 2022. FILIP: Fine-grained Interactive Language-Image Pre-Training. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_11"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01959"},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547963"},{"key":"e_1_3_2_1_71_1","volume-title":"Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: System Demonstrations. 543-553","author":"Zhang Hang","year":"2023","unstructured":"Hang Zhang, Xin Li, and Lidong Bing. 2023a. Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: System Demonstrations. 543-553."},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462874"},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3530570"},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657797"},{"key":"e_1_3_2_1_76_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3120745"},{"key":"e_1_3_2_1_77_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3294567"},{"key":"e_1_3_2_1_78_1","volume-title":"European Conference on Computer Vision. 20-37","author":"Zheng Minghang","year":"2024","unstructured":"Minghang Zheng, Xinhao Cai, Qingchao Chen, Yuxin Peng, and Yang Liu. 2024. Training-free video temporal grounding using large-scale pre-trained models. In European Conference on Computer Vision. 20-37."},{"key":"e_1_3_2_1_79_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.02005"},{"key":"e_1_3_2_1_80_1","volume-title":"Proceedings of the 41st International Conference on Machine Learning. 62429-62442","author":"Zhu Lianghui","year":"2024","unstructured":"Lianghui Zhu, Bencheng Liao, Qian Zhang, Xinlong Wang, Wenyu Liu, and Xinggang Wang. 2024. Vision mamba: efficient visual representation learning with bidirectional state space model. In Proceedings of the 41st International Conference on Machine Learning. 62429-62442."}],"event":{"name":"SIGIR '26: The 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Melbourne VIC Australia","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"deposited":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T17:13:24Z","timestamp":1784135604000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805712.3809742"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"references-count":80,"alternative-id":["10.1145\/3805712.3809742","10.1145\/3805712"],"URL":"https:\/\/doi.org\/10.1145\/3805712.3809742","relation":{},"subject":[],"published":{"date-parts":[[2026,7,19]]},"assertion":[{"value":"2026-07-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}