{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T12:27:28Z","timestamp":1776083248699,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":58,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,5,11]],"date-time":"2024-05-11T00:00:00Z","timestamp":1715385600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["CCF-1762299, CCF-1918889, CNS-1908304, CCF-1901376, CNS-2120696, CCF- 2210831, and CCF-2319471"],"award-info":[{"award-number":["CCF-1762299, CCF-1918889, CNS-1908304, CCF-1901376, CNS-2120696, CCF- 2210831, and CCF-2319471"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,5,11]]},"DOI":"10.1145\/3613904.3642319","type":"proceedings-article","created":{"date-parts":[[2024,5,11]],"date-time":"2024-05-11T08:37:41Z","timestamp":1715416661000},"page":"1-15","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["PhotoScout: Synthesis-Powered Multi-Modal Image Search"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7688-6133","authenticated-orcid":false,"given":"Celeste","family":"Barnaby","sequence":"first","affiliation":[{"name":"University of Texas at Austin, United States"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4680-5157","authenticated-orcid":false,"given":"Qiaochu","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Texas at Austin, United States"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5933-6620","authenticated-orcid":false,"given":"Chenglong","family":"Wang","sequence":"additional","affiliation":[{"name":"Microsoft Research, United States"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8006-1230","authenticated-orcid":false,"given":"Isil","family":"Dillig","sequence":"additional","affiliation":[{"name":"University of Texas at Austin, United States"}]}],"member":"320","published-online":{"date-parts":[[2024,5,11]]},"reference":[{"key":"e_1_3_3_3_1_1","unstructured":"2021. Essential Planning: Your Wedding Photo Checklist. https:\/\/onefabday.com\/wedding-photo-checklist\/"},{"key":"e_1_3_3_3_2_1","volume-title":"https:\/\/photos.google.com\/. Accessed","author":"Photos Google","year":"2023","unstructured":"2023. Google Photos. https:\/\/photos.google.com\/. Accessed: Dec 1, 2023."},{"key":"e_1_3_3_3_3_1","volume-title":"https:\/\/support.apple.com\/photos. Accessed","author":"Support Photos","year":"2023","unstructured":"2023. Photos Support. https:\/\/support.apple.com\/photos. Accessed: Dec 1, 2023."},{"key":"e_1_3_3_3_4_1","volume-title":"Piktures - Beautiful Gallery. https:\/\/www.piktures.app\/. Accessed","year":"2023","unstructured":"2023. Piktures - Beautiful Gallery. https:\/\/www.piktures.app\/. Accessed: Dec 1, 2023."},{"key":"e_1_3_3_3_5_1","volume-title":"https:\/\/docs.aws.amazon.com\/rekognition\/latest\/dg\/what-is.html. Accessed","author":"Rekognition Amazon","year":"2024","unstructured":"2024. Amazon Rekognition. https:\/\/docs.aws.amazon.com\/rekognition\/latest\/dg\/what-is.html. Accessed: Jan 22, 2024."},{"key":"e_1_3_3_3_6_1","volume-title":"Advances in Neural Information Processing Systems, S.\u00a0Koyejo, S.\u00a0Mohamed, A.\u00a0Agarwal, D.\u00a0Belgrave, K.\u00a0Cho, and A.\u00a0Oh (Eds.). Vol.\u00a035. Curran Associates","author":"Alayrac Jean-Baptiste","year":"2022","unstructured":"Jean-Baptiste Alayrac, Jeff Donahue, Pauline Luc, Antoine Miech, Iain Barr, Yana Hasson, Karel Lenc, Arthur Mensch, Katherine Millican, Malcolm Reynolds, Roman Ring, Eliza Rutherford, Serkan Cabi, Tengda Han, Zhitao Gong, Sina Samangooei, Marianne Monteiro, Jacob\u00a0L Menick, Sebastian Borgeaud, Andy Brock, Aida Nematzadeh, Sahand Sharifzadeh, Miko\u0142\u00a0aj Bi\u0144kowski, Ricardo Barreira, Oriol Vinyals, Andrew Zisserman, and Kar\u00e9n Simonyan. 2022. Flamingo: a Visual Language Model for Few-Shot Learning. In Advances in Neural Information Processing Systems, S.\u00a0Koyejo, S.\u00a0Mohamed, A.\u00a0Agarwal, D.\u00a0Belgrave, K.\u00a0Cho, and A.\u00a0Oh (Eds.). Vol.\u00a035. Curran Associates, Inc., 23716\u201323736. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2022\/file\/960a172bc7fbf0177ccccbb411a7d800-Paper-Conference.pdf"},{"key":"e_1_3_3_3_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412419"},{"key":"e_1_3_3_3_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.572"},{"key":"e_1_3_3_3_9_1","doi-asserted-by":"crossref","unstructured":"Alberto Baldrati Marco Bertini Tiberio Uricchio and A. Bimbo. 2023. Composed Image Retrieval using Contrastive Learning and Task-oriented CLIP-based Features. ACM Transactions on Multimedia Computing Communications and Applications (2023). https:\/\/api.semanticscholar.org\/CorpusID:261065158","DOI":"10.1145\/3617597"},{"key":"e_1_3_3_3_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3591248"},{"key":"e_1_3_3_3_11_1","volume-title":"Learning visual similarity for product design with convolutional neural networks. ACM transactions on graphics (TOG) 34, 4","author":"Bell Sean","year":"2015","unstructured":"Sean Bell and Kavita Bala. 2015. Learning visual similarity for product design with convolutional neural networks. ACM transactions on graphics (TOG) 34, 4 (2015), 1\u201310."},{"key":"e_1_3_3_3_12_1","volume-title":"Language models are few-shot learners. Advances in neural information processing systems 33","author":"Brown Tom","year":"2020","unstructured":"Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared\u00a0D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, 2020. Language models are few-shot learners. Advances in neural information processing systems 33 (2020), 1877\u20131901."},{"key":"e_1_3_3_3_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCA.2004.838464"},{"key":"e_1_3_3_3_14_1","unstructured":"Qiaochu Chen Arko Banerjee \u00c7a\u011fatay Demiralp Greg Durrett and Isil Dillig. 2023. Data Extraction via Semantic Regular Expression Synthesis. arxiv:2305.10401\u00a0[cs.PL] https:\/\/arxiv.org\/abs\/2305.10401"},{"key":"e_1_3_3_3_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00307"},{"key":"e_1_3_3_3_16_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2021204164"},{"key":"e_1_3_3_3_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.1998.698660"},{"key":"e_1_3_3_3_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/1348246.1348248"},{"key":"e_1_3_3_3_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3080920"},{"key":"e_1_3_3_3_20_1","volume-title":"Advances in Neural Information Processing Systems, S.\u00a0Bengio, H.\u00a0Wallach, H.\u00a0Larochelle, K.\u00a0Grauman, N.\u00a0Cesa-Bianchi, and R.\u00a0Garnett (Eds.). Vol.\u00a031. Curran Associates","author":"Ellis Kevin","year":"2018","unstructured":"Kevin Ellis, Daniel Ritchie, Armando Solar-Lezama, and Josh Tenenbaum. 2018. Learning to Infer Graphics Programs from Hand-Drawn Images. In Advances in Neural Information Processing Systems, S.\u00a0Bengio, H.\u00a0Wallach, H.\u00a0Larochelle, K.\u00a0Grauman, N.\u00a0Cesa-Bianchi, and R.\u00a0Garnett (Eds.). Vol.\u00a031. Curran Associates, Inc.https:\/\/proceedings.neurips.cc\/paper\/2018\/file\/6788076842014c83cedadbe6b0ba0314-Paper.pdf"},{"key":"e_1_3_3_3_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/1101826.1101858"},{"key":"e_1_3_3_3_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01436"},{"key":"e_1_3_3_3_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_3_3_24_1","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525356"},{"key":"e_1_3_3_3_25_1","volume-title":"SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and < 0.5 MB model size. arXiv preprint arXiv:1602.07360","author":"Iandola N","year":"2016","unstructured":"Forrest\u00a0N Iandola, Song Han, Matthew\u00a0W Moskewicz, Khalid Ashraf, William\u00a0J Dally, and Kurt Keutzer. 2016. SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and < 0.5 MB model size. arXiv preprint arXiv:1602.07360 (2016)."},{"key":"e_1_3_3_3_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.325"},{"key":"e_1_3_3_3_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/872757.872829"},{"key":"e_1_3_3_3_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298810"},{"key":"e_1_3_3_3_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248026"},{"key":"e_1_3_3_3_30_1","volume-title":"Content-based image retrieval and feature extraction: a comprehensive review. Mathematical problems in engineering 2019","author":"Latif Afshan","year":"2019","unstructured":"Afshan Latif, Aqsa Rasheed, Umer Sajid, Jameel Ahmed, Nouman Ali, Naeem\u00a0Iqbal Ratyal, Bushra Zafar, Saadat\u00a0Hanif Dar, Muhammad Sajid, Tehmina Khalil, 2019. Content-based image retrieval and feature extraction: a comprehensive review. Mathematical problems in engineering 2019 (2019)."},{"key":"e_1_3_3_3_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00086"},{"key":"e_1_3_3_3_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00213"},{"key":"e_1_3_3_3_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/354384.354403"},{"key":"e_1_3_3_3_34_1","volume-title":"International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=rJgMlhRctm","author":"Mao Jiayuan","year":"2019","unstructured":"Jiayuan Mao, Chuang Gan, Pushmeet Kohli, Joshua\u00a0B. Tenenbaum, and Jiajun Wu. 2019. The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=rJgMlhRctm"},{"key":"e_1_3_3_3_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.1998.698659"},{"key":"e_1_3_3_3_36_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2017.05.025"},{"key":"e_1_3_3_3_37_1","volume-title":"International conference on machine learning. PMLR, 8748\u20138763","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, 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748\u20138763."},{"key":"e_1_3_3_3_38_1","volume-title":"Reed and Nando de Freitas","author":"E.","year":"2016","unstructured":"Scott\u00a0E. Reed and Nando de Freitas. 2016. Neural Programmer-Interpreters. In 4th International Conference on Learning Representations, ICLR 2016, San Juan, Puerto Rico, May 2-4, 2016, Conference Track Proceedings, Yoshua Bengio and Yann LeCun (Eds.). http:\/\/arxiv.org\/abs\/1511.06279"},{"key":"e_1_3_3_3_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/76.718510"},{"key":"e_1_3_3_3_40_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)."},{"key":"e_1_3_3_3_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161317"},{"key":"e_1_3_3_3_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/34.895972"},{"key":"e_1_3_3_3_43_1","doi-asserted-by":"crossref","unstructured":"D\u00eddac Sur\u00eds Sachit Menon and Carl Vondrick. 2023. ViperGPT: Visual Inference via Python Execution for Reasoning. arxiv:2303.08128\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2303.08128","DOI":"10.1109\/ICCV51070.2023.01092"},{"key":"e_1_3_3_3_44_1","volume-title":"International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=rylNH20qFQ","author":"Tian Yonglong","year":"2019","unstructured":"Yonglong Tian, Andrew Luo, Xingyuan Sun, Kevin Ellis, William\u00a0T. Freeman, Joshua\u00a0B. Tenenbaum, and Jiajun Wu. 2019. Learning to Infer and Execute 3D Shape Programs. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=rylNH20qFQ"},{"key":"e_1_3_3_3_45_1","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000004830.93820.78"},{"key":"e_1_3_3_3_46_1","volume-title":"Advances in Neural Information Processing Systems, S.\u00a0Solla, T.\u00a0Leen, and K.\u00a0M\u00fcller (Eds.). Vol.\u00a012","author":"Vasconcelos Nuno","year":"1999","unstructured":"Nuno Vasconcelos and Andrew Lippman. 1999. Learning from User Feedback in Image Retrieval Systems. In Advances in Neural Information Processing Systems, S.\u00a0Solla, T.\u00a0Leen, and K.\u00a0M\u00fcller (Eds.). Vol.\u00a012. MIT Press. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/1999\/file\/7283518d47a05a09d33779a17adf1707-Paper.pdf"},{"key":"e_1_3_3_3_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/34.955109"},{"key":"e_1_3_3_3_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2013.2279658"},{"key":"e_1_3_3_3_49_1","volume-title":"Rapid Image Labeling via Neuro-Symbolic Learning. arXiv preprint arXiv:2306.10490","author":"Wang Yifeng","year":"2023","unstructured":"Yifeng Wang, Zhi Tu, Yiwen Xiang, Shiyuan Zhou, Xiyuan Chen, Bingxuan Li, and Tianyi Zhang. 2023. Rapid Image Labeling via Neuro-Symbolic Learning. arXiv preprint arXiv:2306.10490 (2023)."},{"key":"e_1_3_3_3_50_1","unstructured":"Wedgewood Weddings. [n. d.]. Ultimate Wedding Shot List: Photography Guide. https:\/\/www.wedgewoodweddings.com\/blog\/ultimate-wedding-shot-list"},{"key":"e_1_3_3_3_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611817"},{"key":"e_1_3_3_3_52_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_3"},{"key":"e_1_3_3_3_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/1835449.1835497"},{"key":"e_1_3_3_3_54_1","volume-title":"Proceedings of the 36th International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol.\u00a097)","author":"Young Halley","year":"2019","unstructured":"Halley Young, Osbert Bastani, and Mayur Naik. 2019. Learning Neurosymbolic Generative Models via Program Synthesis. In Proceedings of the 36th International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol.\u00a097), Kamalika Chaudhuri and Ruslan Salakhutdinov (Eds.). PMLR, 7144\u20137153. https:\/\/proceedings.mlr.press\/v97\/young19a.html"},{"key":"e_1_3_3_3_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3567836"},{"key":"e_1_3_3_3_56_1","volume-title":"Content-based image retrieval with a Convolutional Siamese Neural Network: Distinguishing lung cancer and tuberculosis in CT images. Computers in biology and medicine 140","author":"Zhang Kai","year":"2022","unstructured":"Kai Zhang, Shouliang Qi, Jiumei Cai, Dan Zhao, Tao Yu, Yong Yue, Yudong Yao, and Wei Qian. 2022. Content-based image retrieval with a Convolutional Siamese Neural Network: Distinguishing lung cancer and tuberculosis in CT images. Computers in biology and medicine 140 (2022), 105096."},{"key":"e_1_3_3_3_57_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-002-0070-3"},{"key":"e_1_3_3_3_58_1","volume-title":"On robustness of prompt-based semantic parsing with large pre-trained language model: An empirical study on codex. arXiv preprint arXiv:2301.12868","author":"Zhuo Terry\u00a0Yue","year":"2023","unstructured":"Terry\u00a0Yue Zhuo, Zhuang Li, Yujin Huang, Yuan-Fang Li, Weiqing Wang, Gholamreza Haffari, and Fatemeh Shiri. 2023. On robustness of prompt-based semantic parsing with large pre-trained language model: An empirical study on codex. arXiv preprint arXiv:2301.12868 (2023)."}],"event":{"name":"CHI '24: CHI Conference on Human Factors in Computing Systems","location":"Honolulu HI USA","acronym":"CHI '24","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction","SIGACCESS ACM Special Interest Group on Accessible Computing"]},"container-title":["Proceedings of the CHI Conference on Human Factors in Computing Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3613904.3642319","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3613904.3642319","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T23:44:25Z","timestamp":1750290265000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3613904.3642319"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,11]]},"references-count":58,"alternative-id":["10.1145\/3613904.3642319","10.1145\/3613904"],"URL":"https:\/\/doi.org\/10.1145\/3613904.3642319","relation":{},"subject":[],"published":{"date-parts":[[2024,5,11]]},"assertion":[{"value":"2024-05-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}