{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T17:23:49Z","timestamp":1764782629717,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":61,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12,7]]},"DOI":"10.1145\/3767695.3769480","type":"proceedings-article","created":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T17:14:58Z","timestamp":1764782098000},"page":"313-324","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["A Flexible and Scalable Framework for Video Moment Search"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1378-322X","authenticated-orcid":false,"given":"Chongzhi","family":"Zhang","sequence":"first","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5262-9713","authenticated-orcid":false,"given":"Xizhou","family":"Zhu","sequence":"additional","affiliation":[{"name":"SenseTime Research, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0764-4258","authenticated-orcid":false,"given":"Aixin","family":"Sun","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,12,6]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01257"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/1935826.1935849"},{"key":"e_1_3_2_1_3_1","unstructured":"Sebastian Borgeaud Arthur Mensch Jordan Hoffmann Trevor Cai Eliza Rutherford Katie Millican George van den Driessche Jean-Baptiste Lespiau Bogdan Damoc Aidan Clark Diego de Las Casas Aurelia Guy Jacob Menick Roman Ring Tom Hennigan Saffron Huang Loren Maggiore Chris Jones Albin Cassirer Andy Brock Michela Paganini Geoffrey Irving Oriol Vinyals Simon Osindero Karen Simonyan Jack W. Rae Erich Elsen and Laurent Sifre. 2022. Improving Language Models by Retrieving from Trillions of Tokens. In International Conference on Machine Learning ICML 2022 17-23 July 2022 Baltimore Maryland USA (Proceedings of Machine Learning Research Vol. 162) Kamalika Chaudhuri Stefanie Jegelka Le Song Csaba Szepesv\u00e1ri Gang Niu and Sivan Sabato (Eds.). PMLR 2206-2240. https:\/\/proceedings.mlr.press\/v162\/borgeaud22a.html"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102363"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2021.EMNLP-MAIN.773"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"e_1_3_2_1_7_1","volume-title":"Re-Imagen: Retrieval-Augmented Text-to-Image Generator. In The Eleventh International Conference on Learning Representations, ICLR 2023","author":"Chen Wenhu","year":"2023","unstructured":"Wenhu Chen, Hexiang Hu, Chitwan Saharia, and William W. Cohen. 2023. Re-Imagen: Retrieval-Augmented Text-to-Image Generator. In The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023. OpenReview.net. https:\/\/openreview.net\/forum?id=XSEBx0iSjFQ"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01034"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/1348246.1348248"},{"key":"e_1_3_2_1_10_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. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2401.08281"},{"key":"e_1_3_2_1_12_1","volume-title":"Russell","author":"Escorcia Victor","year":"2019","unstructured":"Victor Escorcia, Mattia Soldan, Josef Sivic, Bernard Ghanem, and Bryan C. Russell. 2019. Temporal Localization of Moments in Video Collections with Natural Language. CoRR abs\/1907.12763 (2019). arXiv:1907.12763 http:\/\/arxiv.org\/abs\/1907.12763"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2021.NAACL-MAIN.241"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2021.EMNLP-MAIN.552"},{"key":"e_1_3_2_1_16_1","first-page":"16399","volume-title":"Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation, LREC\/COLING 2024","author":"Gupta Deepak","year":"2024","unstructured":"Deepak Gupta, Kush Attal, and Dina Demner-Fushman. 2024. Towards Answering Health-related Questions from Medical Videos: Datasets and Approaches. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation, LREC\/COLING 2024, 20-25 May, 2024, Torino, Italy, Nicoletta Calzolari, Min-Yen Kan, V\u00e9ronique Hoste, Alessandro Lenci, Sakriani Sakti, and Nianwen Xue (Eds.). ELRA and ICCL, 16399-16411. https:\/\/aclanthology.org\/2024.lrec-main.1425"},{"key":"e_1_3_2_1_17_1","volume-title":"Thomas Seidl, and Gedas Bertasius.","author":"Hannan Tanveer","year":"2025","unstructured":"Tanveer Hannan, Md Mohaiminul Islam, Thomas Seidl, and Gedas Bertasius. 2025. RGNet: A Unified Clip Retrieval and\u00a0Grounding Network for\u00a0Long Videos. In Computer Vision - ECCV 2024, Ale\u0161 Leonardis, Elisa Ricci, Stefan Roth, Olga Russakovsky, Torsten Sattler, and G\u00fcl Varol (Eds.). Springer Nature Switzerland, Cham, 352-369."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.618"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475281"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2023.ACL-LONG.445"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/276698.276876"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.57"},{"key":"e_1_3_2_1_23_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning, ICML 2021","volume":"4916","author":"Jia Chao","year":"2021","unstructured":"Chao Jia, Yinfei Yang, Ye Xia, Yi-Ting Chen, Zarana Parekh, Hieu Pham, Quoc V. Le, Yun-Hsuan Sung, Zhen Li, and Tom Duerig. 2021. Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision. In Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18-24 July 2021, Virtual Event (Proceedings of Machine Learning Research, Vol. 139), Marina Meila and Tong Zhang (Eds.). PMLR, 4904-4916. http:\/\/proceedings.mlr.press\/v139\/jia21b.html"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2020.EMNLP-MAIN.550"},{"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\/ICCV.2017.83"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/383952.383970"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_27"},{"key":"e_1_3_2_1_29_1","volume-title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020","author":"Lewis Patrick S. H.","year":"2020","unstructured":"Patrick S. H. Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich K\u00fcttler, Mike Lewis, Wen-tau Yih, Tim Rockt\u00e4schel, Sebastian Riedel, and Douwe Kiela. 2020. Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual, Hugo Larochelle, Marc'Aurelio Ranzato, Raia Hadsell, Maria-Florina Balcan, and Hsuan-Tien Lin (Eds.). https:\/\/proceedings.neurips.cc\/paper\/2020\/hash\/6b493230205f780e1bc26945df7481e5-Abstract.html"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2020.EMNLP-MAIN.161"},{"key":"e_1_3_2_1_31_1","unstructured":"Renjie Liang Li Li Chongzhi Zhang Jing Wang Xizhou Zhu and Aixin Sun. 2024. TVR-Ranking: A Dataset for Ranked Video Moment Retrieval with Imprecise Queries. arXiv:2407.06597 [cs.AI] https:\/\/arxiv.org\/abs\/2407.06597"},{"key":"e_1_3_2_1_32_1","volume-title":"Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692","author":"Liu Yinhan","year":"2019","unstructured":"Yinhan Liu. 2019. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)."},{"key":"e_1_3_2_1_33_1","volume-title":"Universal Vision-Language Dense Retrieval: Learning A Unified Representation Space for Multi-Modal Retrieval. In The Eleventh International Conference on Learning Representations, ICLR 2023","author":"Liu Zhenghao","year":"2023","unstructured":"Zhenghao Liu, Chenyan Xiong, Yuanhuiyi Lv, Zhiyuan Liu, and Ge Yu. 2023. Universal Vision-Language Dense Retrieval: Learning A Unified Representation Space for Multi-Modal Retrieval. In The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023. OpenReview.net. https:\/\/openreview.net\/forum?id=PQOlkgsBsik"},{"key":"e_1_3_2_1_34_1","volume-title":"Decoupled Weight Decay Regularization. In 7th International Conference on Learning Representations, ICLR 2019","author":"Loshchilov Ilya","year":"2019","unstructured":"Ilya Loshchilov and Frank Hutter. 2019. Decoupled Weight Decay Regularization. In 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, May 6-9, 2019. OpenReview.net. https:\/\/openreview.net\/forum?id=Bkg6RiCqY7"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746786"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1016\/J.NEUCOM.2022.07.028"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1007\/S10791-012-9209-9"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889473"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00990"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3206025.3206064"},{"key":"e_1_3_2_1_41_1","volume-title":"Proceedings of the 32nd International Conference on Machine Learning, ICML 2015, Lille, France, 6-11 July 2015 (JMLR Workshop and Conference Proceedings","volume":"1934","author":"Neyshabur Behnam","year":"2015","unstructured":"Behnam Neyshabur and Nathan Srebro. 2015. On Symmetric and Asymmetric LSHs for Inner Product Search. In Proceedings of the 32nd International Conference on Machine Learning, ICML 2015, Lille, France, 6-11 July 2015 (JMLR Workshop and Conference Proceedings, Vol. 37), Francis R. Bach and David M. Blei (Eds.). JMLR.org, 1926-1934. http:\/\/proceedings.mlr.press\/v37\/neyshabur15.html"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01266"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3414053"},{"key":"e_1_3_2_1_44_1","volume-title":"International conference on machine learning. PMLR, 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. PMLR, 8748-8763."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1162\/TACL_A_00207"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/258525.258529"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1561\/1500000019"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_31"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00497"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2207.13443"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00695"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1609\/AAAI.V35I4.16406"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2021.EMNLP-MAIN.544"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1609\/AAAI.V33I01.33019062"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02082"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462874"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2021.FINDINGS-ACL.69"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2020.ACL-MAIN.585"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00040"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1609\/AAAI.V34I07.6984"}],"event":{"name":"SIGIR-AP 2025:Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region","location":"Xi'an China","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 2025 Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region"],"original-title":[],"deposited":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T17:17:50Z","timestamp":1764782270000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3767695.3769480"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":61,"alternative-id":["10.1145\/3767695.3769480","10.1145\/3767695"],"URL":"https:\/\/doi.org\/10.1145\/3767695.3769480","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]},"assertion":[{"value":"2025-12-06","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}