{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,2]],"date-time":"2025-11-02T15:24:32Z","timestamp":1762097072751,"version":"build-2065373602"},"publisher-location":"New York, NY, USA","reference-count":27,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,12,7]],"date-time":"2023-12-07T00:00:00Z","timestamp":1701907200000},"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":[[2023,12,7]]},"DOI":"10.1145\/3628797.3628957","type":"proceedings-article","created":{"date-parts":[[2023,12,6]],"date-time":"2023-12-06T15:25:34Z","timestamp":1701876334000},"page":"923-930","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Multi-User Video Search: Bridging the Gap Between Text and Embedding Queries"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-3415-5382","authenticated-orcid":false,"given":"Khai","family":"Trinh Xuan","sequence":"first","affiliation":[{"name":"Ho Chi Minh City University of Technology, Viet Nam"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-9978-053X","authenticated-orcid":false,"given":"Nguyen","family":"Nguyen Khoi","sequence":"additional","affiliation":[{"name":"Ho Chi Minh City University of Technology, Viet Nam"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7302-6095","authenticated-orcid":false,"given":"Huy","family":"Luong-Quang","sequence":"additional","affiliation":[{"name":"FPT University, Viet Nam"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-0240-0223","authenticated-orcid":false,"given":"Sang","family":"Hoa-Xuan","sequence":"additional","affiliation":[{"name":"Industrial University Of Ho Chi Minh City, Viet Nam"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6313-3435","authenticated-orcid":false,"given":"Anh","family":"Nguyen-Luong-Nam","sequence":"additional","affiliation":[{"name":"Hanoi University of Industry, Viet Nam"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0394-4731","authenticated-orcid":false,"given":"Minh-Hung","family":"An","sequence":"additional","affiliation":[{"name":"FPT Telecom, Viet Nam"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0717-1254","authenticated-orcid":false,"given":"Hong-Phuc","family":"Nguyen","sequence":"additional","affiliation":[{"name":"Eastern International University, Viet Nam"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,12,7]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3591106.3592226"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00959"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-560"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","unstructured":"Fabio Carrara Lucia Vadicamo Claudio Gennaro and Giuseppe Amato. 2022. Approximate Nearest Neighbor Search on\u00a0Standard Search Engines. (2022) 214\u2013221. https:\/\/doi.org\/10.1007\/978-3-031-17849-8_17","DOI":"10.1007\/978-3-031-17849-8_17"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3460426.3470945"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3372278.3388043"},{"key":"e_1_3_2_1_7_1","volume-title":"CoRR abs\/1703.06870","author":"He Kaiming","year":"2017","unstructured":"Kaiming He, Georgia Gkioxari, Piotr Doll\u00e1r, and Ross\u00a0B. Girshick. 2017. Mask R-CNN. CoRR abs\/1703.06870 (2017). arXiv:1703.06870http:\/\/arxiv.org\/abs\/1703.06870"},{"key":"e_1_3_2_1_8_1","volume-title":"Deep Residual Learning for Image Recognition. CoRR abs\/1512.03385","author":"He Kaiming","year":"2015","unstructured":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2015. Deep Residual Learning for Image Recognition. CoRR abs\/1512.03385 (2015). arXiv:1512.03385http:\/\/arxiv.org\/abs\/1512.03385"},{"key":"e_1_3_2_1_9_1","volume-title":"Bidirectional LSTM-CRF Models for Sequence Tagging. CoRR abs\/1508.01991","author":"Huang Zhiheng","year":"2015","unstructured":"Zhiheng Huang, Wei Xu, and Kai Yu. 2015. Bidirectional LSTM-CRF Models for Sequence Tagging. CoRR abs\/1508.01991 (2015). arXiv:1508.01991http:\/\/arxiv.org\/abs\/1508.01991"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.7002879"},{"key":"e_1_3_2_1_11_1","unstructured":"Glenn Jocher Ayush Chaurasia and Jing Qiu. 2023. YOLO by Ultralytics. https:\/\/github.com\/ultralytics\/ultralytics"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2921572"},{"volume-title":"MultiMedia Modeling, Yong\u00a0Man Ro, Wen-Huang Cheng, Junmo Kim, Wei-Ta Chu, Peng Cui, Jung-Woo Choi, Min-Chun Hu, and Wesley De\u00a0Neve (Eds.)","author":"Kratochv\u00edl Miroslav","key":"e_1_3_2_1_13_1","unstructured":"Miroslav Kratochv\u00edl, Patrik Vesel\u00fd, Franti\u0161ek Mejzl\u00edk, and Jakub Loko\u010d. 2020. SOM-Hunter: Video Browsing with Relevance-to-SOM Feedback Loop. In MultiMedia Modeling, Yong\u00a0Man Ro, Wen-Huang Cheng, Junmo Kim, Wei-Ta Chu, Peng Cui, Jung-Woo Choi, Min-Chun Hu, and Wesley De\u00a0Neve (Eds.). Springer International Publishing, Cham, 790\u2013795."},{"volume-title":"MultiMedia Modeling, Bj\u00f6rn \u00de\u00f3r J\u00f3nsson, Cathal Gurrin, Minh-Triet Tran, Duc-Tien Dang-Nguyen, Anita Min-Chun Hu, Binh Huynh Thi\u00a0Thanh","author":"Loko\u010d Jakub","key":"e_1_3_2_1_14_1","unstructured":"Jakub Loko\u010d, Franti\u0161ek Mejzl\u00edk, Tom\u00e1\u0161 Sou\u010dek, Patrik Dokoupil, and Ladislav Pe\u0161ka. 2022. Video Search with\u00a0Context-Aware Ranker and\u00a0Relevance Feedback. In MultiMedia Modeling, Bj\u00f6rn \u00de\u00f3r J\u00f3nsson, Cathal Gurrin, Minh-Triet Tran, Duc-Tien Dang-Nguyen, Anita Min-Chun Hu, Binh Huynh Thi\u00a0Thanh, and Benoit Huet (Eds.). Springer International Publishing, Cham, 505\u2013510."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","unstructured":"Jakub Loko\u010d Zuzana Vop\u00e1lkov\u00e1 Patrik Dokoupil and Ladislav Pe\u0161ka. 2023. Video Search with\u00a0CLIP and\u00a0Interactive Text Query Reformulation. (2023) 628\u2013633. https:\/\/doi.org\/10.1007\/978-3-031-27077-2_50","DOI":"10.1007\/978-3-031-27077-2_50"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-27077-2_51"},{"key":"e_1_3_2_1_17_1","volume-title":"ALADIN: Distilling Fine-grained Alignment Scores for Efficient Image-Text Matching and Retrieval. In International Conference on Content-based Multimedia Indexing. 64\u201370","author":"Messina Nicola","year":"2022","unstructured":"Nicola Messina, Matteo Stefanini, Marcella Cornia, Lorenzo Baraldi, Fabrizio Falchi, Giuseppe Amato, and Rita Cucchiara. 2022. ALADIN: Distilling Fine-grained Alignment Scores for Efficient Image-Text Matching and Retrieval. In International Conference on Content-based Multimedia Indexing. 64\u201370."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","unstructured":"Thai\u00a0Binh Nguyen. 2021. Vietnamese end-to-end speech recognition using wav2vec 2.0. https:\/\/doi.org\/10.5281\/zenodo.5356039","DOI":"10.5281\/zenodo.5356039"},{"key":"e_1_3_2_1_19_1","volume-title":"Learning Transferable Visual Models From Natural Language Supervision. CoRR abs\/2103.00020","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong\u00a0Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. CoRR abs\/2103.00020 (2021). arXiv:2103.00020https:\/\/arxiv.org\/abs\/2103.00020"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1108\/00220410410560582"},{"volume-title":"Deep Learning-Based Concept Detection in vitrivr","author":"Rossetto Luca","key":"e_1_3_2_1_22_1","unstructured":"Luca Rossetto, Mahnaz Amiri\u00a0Parian, Ralph Gasser, Ivan Giangreco, Silvan Heller, and Heiko Schuldt. 2019. Deep Learning-Based Concept Detection in vitrivr. In MultiMedia Modeling, Ioannis Kompatsiaris, Benoit Huet, Vasileios Mezaris, Cathal Gurrin, Wen-Huang Cheng, and Stefanos Vrochidis (Eds.). Springer International Publishing, Cham, 616\u2013621."},{"key":"e_1_3_2_1_23_1","volume-title":"Vibro: Video Browsing with\u00a0Semantic and\u00a0Visual Image Embeddings","author":"Schall Konstantin","year":"2023","unstructured":"Konstantin Schall, Nico Hezel, Klaus Jung, and Kai\u00a0Uwe Barthel. 2023. Vibro: Video Browsing with\u00a0Semantic and\u00a0Visual Image Embeddings. In MultiMedia Modeling, Duc-Tien Dang-Nguyen, Cathal Gurrin, Martha Larson, Alan\u00a0F. Smeaton, Stevan Rudinac, Minh-Son Dao, Christoph Trattner, and Phoebe Chen (Eds.). Springer International Publishing, Cham, 665\u2013670."},{"key":"e_1_3_2_1_24_1","volume-title":"QIVISE: A Quantum-Inspired Interactive Video Search Engine in VBS2023","author":"Song Weixi","year":"2023","unstructured":"Weixi Song, Jiangshan He, Xinghan Li, Shiwei Feng, and Chao Liang. 2023. QIVISE: A Quantum-Inspired Interactive Video Search Engine in VBS2023. In MultiMedia Modeling, Duc-Tien Dang-Nguyen, Cathal Gurrin, Martha Larson, Alan\u00a0F. Smeaton, Stevan Rudinac, Minh-Son Dao, Christoph Trattner, and Phoebe Chen (Eds.). Springer International Publishing, Cham, 640\u2013645."},{"key":"e_1_3_2_1_25_1","volume-title":"TransNet V2: An effective deep network architecture for fast shot transition detection. arXiv preprint arXiv:2008.04838","author":"Sou\u010dek Tom\u00e1\u0161","year":"2020","unstructured":"Tom\u00e1\u0161 Sou\u010dek and Jakub Loko\u010d. 2020. TransNet V2: An effective deep network architecture for fast shot transition detection. arXiv preprint arXiv:2008.04838 (2020)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"crossref","unstructured":"Haoyang Zhang Ying Wang Feras Dayoub and Niko S\u00fcnderhauf. 2021. VarifocalNet: An IoU-aware Dense Object Detector. In CVPR.","DOI":"10.1109\/CVPR46437.2021.00841"},{"key":"e_1_3_2_1_27_1","volume-title":"Recognize Anything: A Strong Image Tagging Model. arXiv preprint arXiv:2306.03514","author":"Zhang Youcai","year":"2023","unstructured":"Youcai Zhang, Xinyu Huang, Jinyu Ma, Zhaoyang Li, Zhaochuan Luo, Yanchun Xie, Yuzhuo Qin, Tong Luo, Yaqian Li, Shilong Liu, 2023. Recognize Anything: A Strong Image Tagging Model. arXiv preprint arXiv:2306.03514 (2023)."}],"event":{"name":"SOICT 2023: The 12th International Symposium on Information and Communication Technology","acronym":"SOICT 2023","location":"Ho Chi Minh Vietnam"},"container-title":["Proceedings of the 12th International Symposium on Information and Communication Technology"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3628797.3628957","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3628797.3628957","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T12:24:39Z","timestamp":1755779079000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3628797.3628957"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,7]]},"references-count":27,"alternative-id":["10.1145\/3628797.3628957","10.1145\/3628797"],"URL":"https:\/\/doi.org\/10.1145\/3628797.3628957","relation":{},"subject":[],"published":{"date-parts":[[2023,12,7]]},"assertion":[{"value":"2023-12-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}