{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,8]],"date-time":"2025-07-08T19:40:10Z","timestamp":1752003610151,"version":"3.41.2"},"publisher-location":"New York, NY, USA","reference-count":41,"publisher":"ACM","funder":[{"name":"NSF","award":["2211133"],"award-info":[{"award-number":["2211133"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,22]]},"DOI":"10.1145\/3736733.3736738","type":"proceedings-article","created":{"date-parts":[[2025,7,8]],"date-time":"2025-07-08T19:03:51Z","timestamp":1752001431000},"page":"1-7","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Bootstrapping Compositional Video Query Synthesis with Natural Language and Previous Queries from Users"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-8213-7286","authenticated-orcid":false,"given":"Manasi","family":"Ganti","sequence":"first","affiliation":[{"name":"University of Washington, Seattle, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-2477-6594","authenticated-orcid":false,"given":"Enhao","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Washington, Seattle, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6805-0325","authenticated-orcid":false,"given":"Magdalena","family":"Balazinska","sequence":"additional","affiliation":[{"name":"University of Washington, Seattle, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,7,8]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Jinze Bai Shuai Bai Shusheng Yang Shijie Wang Sinan Tan Peng Wang Junyang Lin Chang Zhou and Jingren Zhou. 2023. Qwen-VL: A Versatile Vision-Language Model for Understanding Localization Text Reading and Beyond. arXiv:2308.12966 [cs.CV]"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.14778\/3415478.3415498"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"Daren Chao Nick Koudas and Ioannis Xarchakos. 2020. SVQ++: Querying for Object Interactions in Video Streams. In SIGMOD. 2769\u20132772.","DOI":"10.1145\/3318464.3384701"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.14778\/3551793.3551865"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Kayhan Dursun Carsten Binnig Ugur Cetintemel and TIm Kraska. 2017. Revisiting Reuse in Main Memory Database Systems. In SIGMOD. 1275\u20131289.","DOI":"10.1145\/3035918.3035957"},{"key":"e_1_3_2_1_6_1","volume-title":"Brandon Chow, Kai Deng, Katherine Lin, Marcos Campos, K. Venkatesh Emani, Vivek Pandit, Victor Shnayder, Wenjing Wang, and Carlo Curino.","author":"Floratou Avrilia","year":"2024","unstructured":"Avrilia Floratou, Fotis Psallidas, Fuheng Zhao, Shaleen Deep, Gunther Hagleither, Wangda Tan, Joyce Cahoon, Rana Alotaibi, Jordan Henkel, Abhik Singla, Alex Van Grootel, Brandon Chow, Kai Deng, Katherine Lin, Marcos Campos, K. Venkatesh Emani, Vivek Pandit, Victor Shnayder, Wenjing Wang, and Carlo Curino. 2024. NL2SQL is a solved problem... Not!. In CIDR."},{"key":"e_1_3_2_1_7_1","volume-title":"Rekall: Specifying Video Events using Compositions of Spatiotemporal Labels. arXiv:1910.02993 [cs.DB]","author":"Fu Daniel Y.","year":"2019","unstructured":"Daniel Y. Fu, Will Crichton, James Hong, Xinwei Yao, Haotian Zhang, Anh Truong, Avanika Narayan, Maneesh Agrawala, Christopher R\u00e9, and Kayvon Fatahalian. 2019. Rekall: Specifying Video Events using Compositions of Spatiotemporal Labels. arXiv:1910.02993 [cs.DB]"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.14778\/3115404.3115418"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"crossref","unstructured":"Jonathan Goldstein and Per-\u00c5ke Larson. 2001. Optimizing Queries Using Materialized Views: A practical scalable solution. In SIGMOD. 331\u2013342.","DOI":"10.1145\/375663.375706"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1061\/(ASCE)CP.1943-5487.0000027"},{"key":"e_1_3_2_1_11_1","volume-title":"IntelliSys (AISC","volume":"159","author":"Hammer Patrick","year":"2020","unstructured":"Patrick Hammer, Tony Lofthouse, Enzo Fenoglio, Hugo Latapie, and Pei Wang. 2020. A Reasoning Based Model for Anomaly Detection in the Smart City Domain. In IntelliSys (AISC, Vol. 1251). 144\u2013159."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"crossref","unstructured":"Moshe Hazoom Vibhor Malik and Ben Bogin. 2021. Text-to-SQL in the Wild: A Naturally-Occurring Dataset Based on Stack Exchange Data. arXiv:2106.05006 [cs.CL]","DOI":"10.18653\/v1\/2021.nlp4prog-1.9"},{"key":"e_1_3_2_1_13_1","unstructured":"Zijin Hong Zheng Yuan Qinggang Zhang Hao Chen Junnan Dong Feiran Huang and Xiao Huang. 2024. Next-Generation Database Interfaces: A Survey of LLM-based Text-to-SQL. arXiv:2406.08426 [cs.CL]"},{"key":"e_1_3_2_1_14_1","unstructured":"Cheng-Yu Hsieh Jieyu Zhang Zixian Ma Aniruddha Kembhavi and Ranjay Krishna. 2023. SugarCrepe: Fixing Hackable Benchmarks for Vision-Language Compositionality. In NeurIPS."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"crossref","unstructured":"Milena Ivanova Martin L. Kersten Niels J. Nes and Romulo Goncalves. 2009. An architecture for recycling intermediates in a column-store. In SIGMOD. 309\u2013320.","DOI":"10.1145\/1559845.1559879"},{"key":"e_1_3_2_1_16_1","volume-title":"Action Genome: Actions As Compositions of Spatio-Temporal Scene Graphs. In CVPR. 10233\u201310244.","author":"Ji Jingwei","year":"2020","unstructured":"Jingwei Ji, Ranjay Krishna, Li Fei-Fei, and Juan Carlos Niebles. 2020. Action Genome: Actions As Compositions of Spatio-Temporal Scene Graphs. In CVPR. 10233\u201310244."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"crossref","unstructured":"Ranjay Krishna Vincent S. Chen Paroma Varma Michael S. Bernstein Christopher R\u00e9 and Li Fei-Fei. 2019. Scene Graph Prediction With Limited Labels. In ICCV. 2580\u20132590.","DOI":"10.1109\/ICCV.2019.00267"},{"key":"e_1_3_2_1_18_1","volume-title":"Fei Huang, Reynold Cheng, and Yongbin Li.","author":"Li Jinyang","year":"2023","unstructured":"Jinyang Li, Binyuan Hui, Ge Qu, Jiaxi Yang, Binhua Li, Bowen Li, Bailin Wang, Bowen Qin, Ruiying Geng, Nan Huo, Xuanhe Zhou, Chenhao Ma, Guoliang Li, Kevin Chen-Chuan Chang, Fei Huang, Reynold Cheng, and Yongbin Li. 2023. Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs. In NeurIPS."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"crossref","unstructured":"Yilin Li and Deddy Jobson. 2024. LLMs as an Interactive Database Interface for Designing Large Queries. In HILDA. 1\u20137.","DOI":"10.1145\/3665939.3665969"},{"key":"e_1_3_2_1_20_1","unstructured":"Haotian Liu Chunyuan Li Qingyang Wu and Yong Jae Lee. 2023. Visual Instruction Tuning. In NeurIPS."},{"key":"e_1_3_2_1_21_1","unstructured":"Haoyu Lu Wen Liu Bo Zhang Bingxuan Wang Kai Dong Bo Liu Jingxiang Sun Tongzheng Ren Zhuoshu Li Hao Yang Yaofeng Sun Chengqi Deng Hanwei Xu Zhenda Xie and Chong Ruan. 2024. DeepSeek-VL: Towards Real-World Vision-Language Understanding. arXiv:2403.05525 [cs.AI]"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/1121949.1121979"},{"key":"e_1_3_2_1_23_1","first-page":"459","article-title":"Synthesizing Trajectory Queries from Examples","volume":"13964","author":"Mell Stephen","year":"2023","unstructured":"Stephen Mell, Favyen Bastani, Steve Zdancewic, and Osbert Bastani. 2023. Synthesizing Trajectory Queries from Examples. In CAV, Vol. 13964. 459\u2013484.","journal-title":"CAV"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"crossref","unstructured":"Fabian Nagel Peter A. Boncz and Stratis Viglas. 2013. Recycling in pipelined query evaluation. In ICDE. 338\u2013349.","DOI":"10.1109\/ICDE.2013.6544837"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"crossref","unstructured":"Simone Papicchio Paolo Papotti and Luca Cagliero. 2024. Evaluating Ambiguous Questions in Semantic Parsing. In ICDEW. 338\u2013342.","DOI":"10.1109\/ICDEW61823.2024.00050"},{"key":"e_1_3_2_1_26_1","volume-title":"Jermaine","author":"Perez Luis Leopoldo","year":"2014","unstructured":"Luis Leopoldo Perez and Christopher M. Jermaine. 2014. History-aware query optimization with materialized intermediate views. In ICDE. 520\u2013531."},{"key":"e_1_3_2_1_27_1","volume-title":"Zelda: Video Analytics using Vision-Language Models. arXiv:2305.03785 [cs.DB]","author":"Romero Francisco","year":"2023","unstructured":"Francisco Romero, Caleb Winston, Johann Hauswald, Matei Zaharia, and Christos Kozyrakis. 2023. Zelda: Video Analytics using Vision-Language Models. arXiv:2305.03785 [cs.DB]"},{"key":"e_1_3_2_1_28_1","volume-title":"Dragan","author":"Sadigh Dorsa","year":"2016","unstructured":"Dorsa Sadigh, Shankar Sastry, Sanjit A. Seshia, and Anca D. Dragan. 2016. Planning for Autonomous Cars that Leverage Effects on Human Actions. In Robotics: Science and Systems."},{"key":"e_1_3_2_1_29_1","first-page":"202","article-title":"Find and Focus: Retrieve and Localize Video Events with Natural Language Queries","volume":"11213","author":"Shao Dian","year":"2018","unstructured":"Dian Shao, Yu Xiong, Yue Zhao, Qingqiu Huang, Yu Qiao, and Dahua Lin. 2018. Find and Focus: Retrieve and Localize Video Events with Natural Language Queries. In ECCV, Vol. 11213. 202\u2013218.","journal-title":"ECCV"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"crossref","unstructured":"Liang Shi Zhengju Tang Nan Zhang Xiaotong Zhang and Zhi Yang. 2024. A Survey on Employing Large Language Models for Text-to-SQL Tasks. arXiv:2407.15186 [cs.CL]","DOI":"10.1145\/3737873"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"crossref","unstructured":"Ruoxi Sun Sercan Arik Rajarishi Sinha Hootan Nakhost Hanjun Dai Pengcheng Yin and Tomas Pfister. 2023. SQLPrompt: In-Context Text-to-SQL with Minimal Labeled Data. In EMNLP (Findings). 542\u2013550.","DOI":"10.18653\/v1\/2023.findings-emnlp.39"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"crossref","unstructured":"David Tweed and Andrew Calway. 2002. Tracking Multiple Animals in Wildlife Footage. In ICPR. 24.","DOI":"10.1109\/ICPR.2002.1048227"},{"key":"e_1_3_2_1_33_1","unstructured":"Dominique Verdejo and Eunika Mercier-Laurent. 2022. Video Intelligence as a component of a Global Security system. arXiv:2201.04349 [cs.AI]"},{"key":"e_1_3_2_1_34_1","unstructured":"Jiayu Wang Yifei Ming Zhenmei Shi Vibhav Vineet Xin Wang Sharon Li and Neel Joshi. 2024. Is A Picture Worth A Thousand Words? Delving Into Spatial Reasoning for Vision Language Models. In NeurIPS."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3677140"},{"key":"e_1_3_2_1_36_1","volume-title":"Joy Arulraj, and Umakishore Ramachandran.","author":"Xu Zhuangdi","year":"2022","unstructured":"Zhuangdi Xu, Gaurav Tarlok Kakkar, Joy Arulraj, and Umakishore Ramachandran. 2022. EVA: A Symbolic Approach to Accelerating Exploratory Video Analytics with Materialized Views. In SIGMOD. 602\u2013616."},{"key":"e_1_3_2_1_37_1","volume-title":"Tenenbaum","author":"Yi Kexin","year":"2020","unstructured":"Kexin Yi, Chuang Gan, Yunzhu Li, Pushmeet Kohli, Jiajun Wu, Antonio Torralba, and Joshua B. Tenenbaum. 2020. CLEVRER: Collision Events for Video Representation and Reasoning. In ICLR."},{"key":"e_1_3_2_1_38_1","volume-title":"Radev","author":"Yu Tao","year":"2018","unstructured":"Tao Yu, Rui Zhang, Kai Yang, Michihiro Yasunaga, Dongxu Wang, Zifan Li, James Ma, Irene Li, Qingning Yao, Shanelle Roman, Zilin Zhang, and Dragomir R. Radev. 2018. Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task. In EMNLP. 3911\u20133921."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.14778\/3611540.3611600"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.14778\/3611479.3611482"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"crossref","unstructured":"Enhao Zhang Nicole Sullivan Brandon Haynes Ranjay Krishna and Magdalena Balazinska. 2025. Self-Enhancing Video Data Management System for Compositional Events with Large Language Models [Technical Report]. arXiv:2408.02243 [cs.DB]","DOI":"10.1145\/3725352"}],"event":{"name":"HILDA '25: Workshop on Human-In-the-Loop Data Analytics","location":"Intercontinental Berlin Berlin Germany","acronym":"HILDA '25","sponsor":["SIGMOD ACM Special Interest Group on Management of Data"]},"container-title":["Proceedings of the Workshop on Human-In-the-Loop Data Analytics"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3736733.3736738","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,8]],"date-time":"2025-07-08T19:04:46Z","timestamp":1752001486000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3736733.3736738"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,22]]},"references-count":41,"alternative-id":["10.1145\/3736733.3736738","10.1145\/3736733"],"URL":"https:\/\/doi.org\/10.1145\/3736733.3736738","relation":{},"subject":[],"published":{"date-parts":[[2025,6,22]]},"assertion":[{"value":"2025-07-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}