{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T23:17:13Z","timestamp":1784330233867,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":53,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,7,10]],"date-time":"2024-07-10T00:00:00Z","timestamp":1720569600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100006374","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2023YFC3310700"],"award-info":[{"award-number":["2023YFC3310700"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,7,10]]},"DOI":"10.1145\/3626772.3657740","type":"proceedings-article","created":{"date-parts":[[2024,7,11]],"date-time":"2024-07-11T12:40:05Z","timestamp":1720701605000},"page":"80-90","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":50,"title":["LDRE: LLM-based Divergent Reasoning and Ensemble for Zero-Shot Composed Image Retrieval"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-5298-0543","authenticated-orcid":false,"given":"Zhenyu","family":"Yang","sequence":"first","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences &amp; University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0173-1556","authenticated-orcid":false,"given":"Dizhan","family":"Xue","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences &amp; University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9488-2208","authenticated-orcid":false,"given":"Shengsheng","family":"Qian","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences &amp; University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6502-145X","authenticated-orcid":false,"given":"Weiming","family":"Dong","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences &amp; University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8343-9665","authenticated-orcid":false,"given":"Changsheng","family":"Xu","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, University of Chinese Academy of Sciences &amp; Peng Cheng Laboratory, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,7,11]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al.","author":"Achiam Josh","year":"2023","unstructured":"Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al. 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"e_1_3_2_1_3_1","volume-title":"Zero-Shot Composed Image Retrieval with Textual Inversion. arXiv preprint arXiv:2303.15247","author":"Baldrati Alberto","year":"2023","unstructured":"Alberto Baldrati, Lorenzo Agnolucci, Marco Bertini, and Alberto Del Bimbo. 2023. Zero-Shot Composed Image Retrieval with Textual Inversion. arXiv preprint arXiv:2303.15247 (2023)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00543"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02080"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1097-4571(199303)44:2<70::AID-ASI2>3.0.CO;2-I"},{"key":"e_1_3_2_1_7_1","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et al. 2020. Language models are few-shot learners. Advances in neural information processing systems 33 (2020) 1877--1901."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00307"},{"key":"e_1_3_2_1_9_1","volume-title":"A region-based fuzzy feature matching approach to content-based image retrieval","author":"Chen Yixin","year":"2002","unstructured":"Yixin Chen and James Ze Wang. 2002. A region-based fuzzy feature matching approach to content-based image retrieval. IEEE transactions on pattern analysis and machine intelligence 24, 9 (2002), 1252--1267."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20044-1_32"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1038\/215671a0"},{"key":"e_1_3_2_1_12_1","volume-title":"Gabriela Csurka, and Diane Larlus.","author":"Delmas Ginger","year":"2022","unstructured":"Ginger Delmas, Rafael Sampaio de Rezende, Gabriela Csurka, and Diane Larlus. 2022. Artemis: Attention-based retrieval with text-explicit matching and implicit similarity. arXiv preprint arXiv:2203.08101 (2022)."},{"key":"e_1_3_2_1_13_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, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475619"},{"key":"e_1_3_2_1_15_1","volume-title":"CompoDiff: Versatile Composed Image Retrieval With Latent Diffusion. arXiv preprint arXiv:2303.11916","author":"Gu Geonmo","year":"2023","unstructured":"Geonmo Gu, Sanghyuk Chun, Wonjae Kim, HeeJae Jun, Yoohoon Kang, and Sangdoo Yun. 2023. CompoDiff: Versatile Composed Image Retrieval With Latent Diffusion. arXiv preprint arXiv:2303.11916 (2023)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00262"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_18_1","volume-title":"Long short-term memory. Neural computation 9, 8","author":"Hochreiter Sepp","year":"1997","unstructured":"Sepp Hochreiter and J\u00fcrgen Schmidhuber. 1997. Long short-term memory. Neural computation 9, 8 (1997), 1735--1780."},{"key":"e_1_3_2_1_19_1","volume-title":"The curious case of neural text degeneration. arXiv preprint arXiv:1904.09751","author":"Holtzman Ari","year":"2019","unstructured":"Ari Holtzman, Jan Buys, Li Du, Maxwell Forbes, and Yejin Choi. 2019. The curious case of neural text degeneration. arXiv preprint arXiv:1904.09751 (2019)."},{"key":"e_1_3_2_1_20_1","volume-title":"Proceedings, Part XV 16","author":"Hou Zhi","year":"2020","unstructured":"Zhi Hou, Xiaojiang Peng, Yu Qiao, and Dacheng Tao. 2020. Visual compositional learning for human-object interaction detection. In Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020, Proceedings, Part XV 16. Springer, 584--600."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","unstructured":"Gabriel Ilharco Mitchell Wortsman Ross Wightman Cade Gordon Nicholas Carlini Rohan Taori Achal Dave Vaishaal Shankar Hongseok Namkoong John Miller Hannaneh Hajishirzi Ali Farhadi and Ludwig Schmidt. 2021. OpenCLIP. https:\/\/doi.org\/10.5281\/zenodo.5143773","DOI":"10.5281\/zenodo.5143773"},{"key":"e_1_3_2_1_22_1","volume-title":"Vision-by-Language for Training-Free Compositional Image Retrieval. arXiv preprint arXiv:2310.09291","author":"Karthik Shyamgopal","year":"2023","unstructured":"Shyamgopal Karthik, Karsten Roth, Massimiliano Mancini, and Zeynep Akata. 2023. Vision-by-Language for Training-Free Compositional Image Retrieval. arXiv preprint arXiv:2310.09291 (2023)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16271"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00086"},{"key":"e_1_3_2_1_25_1","volume-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.12597","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023. Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.12597 (2023)."},{"key":"e_1_3_2_1_26_1","volume-title":"International Conference on Machine Learning. PMLR, 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. PMLR, 12888--12900."},{"key":"e_1_3_2_1_27_1","volume-title":"Visualbert: A simple and performant baseline for vision and language. arXiv preprint arXiv:1908.03557","author":"Li Liunian Harold","year":"2019","unstructured":"Liunian Harold Li, Mark Yatskar, Da Yin, Cho-Jui Hsieh, and Kai-Wei Chang. 2019. Visualbert: A simple and performant baseline for vision and language. arXiv preprint arXiv:1908.03557 (2019)."},{"key":"e_1_3_2_1_28_1","volume-title":"Piotr Doll'a r, and C. Lawrence Zitnick","author":"Lin Tsung-Yi","year":"2014","unstructured":"Tsung-Yi Lin, Michael Maire, Serge J. Belongie, Lubomir D. Bourdev, Ross B. Girshick, James Hays, Pietro Perona, Deva Ramanan, Piotr Doll'a r, and C. Lawrence Zitnick. 2014. Microsoft COCO: Common Objects in Context. CoRR abs\/1405.0312 (2014). arXiv:1405.0312 http:\/\/arxiv.org\/abs\/1405.0312"},{"key":"e_1_3_2_1_29_1","volume-title":"Zeroshot Composed Text-Image Retrieval. arXiv preprint arXiv:2306.07272","author":"Liu Yikun","year":"2023","unstructured":"Yikun Liu, Jiangchao Yao, Ya Zhang, Yanfeng Wang, and Weidi Xie. 2023. Zeroshot Composed Text-Image Retrieval. arXiv preprint arXiv:2306.07272 (2023)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00213"},{"key":"e_1_3_2_1_31_1","volume-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. Advances in neural information processing systems 32","author":"Lu Jiasen","year":"2019","unstructured":"Jiasen Lu, Dhruv Batra, Devi Parikh, and Stefan Lee. 2019. Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1037\/0022-3514.52.6.1258"},{"key":"e_1_3_2_1_33_1","volume-title":"Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems 32","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et al. 2019. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3101642"},{"key":"e_1_3_2_1_35_1","first-page":"4794","article-title":"Integrating multi-label contrastive learning with dual adversarial graph neural networks for cross-modal retrieval","volume":"45","author":"Qian Shengsheng","year":"2022","unstructured":"Shengsheng Qian, Dizhan Xue, Quan Fang, and Changsheng Xu. 2022. Integrating multi-label contrastive learning with dual adversarial graph neural networks for cross-modal retrieval. IEEE Transactions on Pattern Analysis and Machine Intelligence 45, 4 (2022), 4794--4811.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16345"},{"key":"e_1_3_2_1_37_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_38_1","volume-title":"Divergent thinking","author":"Runco Mark A","unstructured":"Mark A Runco. 1991. Divergent thinking. Ablex Publishing Corporation Norwood, NJ."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01850"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1016\/0306-4573(76)90004-2"},{"key":"e_1_3_2_1_41_1","volume-title":"Lxmert: Learning cross-modality encoder representations from transformers. arXiv preprint arXiv:1908.07490","author":"Tan Hao","year":"2019","unstructured":"Hao Tan and Mohit Bansal. 2019. Lxmert: Learning cross-modality encoder representations from transformers. arXiv preprint arXiv:1908.07490 (2019)."},{"key":"e_1_3_2_1_42_1","volume-title":"Context-I2W: Mapping Images to Context-dependent Words for Accurate Zero-Shot Composed Image Retrieval. arXiv preprint arXiv:2309.16137","author":"Tang Yuanmin","year":"2023","unstructured":"Yuanmin Tang, Jing Yu, Keke Gai, Zhuang Jiamin, Gang Xiong, Yue Hu, and Qi Wu. 2023. Context-I2W: Mapping Images to Context-dependent Words for Accurate Zero-Shot Composed Image Retrieval. arXiv preprint arXiv:2309.16137 (2023)."},{"key":"e_1_3_2_1_43_1","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale et al. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)."},{"key":"e_1_3_2_1_44_1","volume-title":"Attention is all you need. Advances in neural information processing systems 30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_45_1","volume-title":"Show and tell: Lessons learned from the 2015 mscoco image captioning challenge","author":"Vinyals Oriol","year":"2016","unstructured":"Oriol Vinyals, Alexander Toshev, Samy Bengio, and Dumitru Erhan. 2016. Show and tell: Lessons learned from the 2015 mscoco image captioning challenge. IEEE transactions on pattern analysis and machine intelligence 39, 4 (2016), 652--663."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00660"},{"key":"e_1_3_2_1_47_1","volume-title":"Git: A generative image-to-text transformer for vision and language. arXiv preprint arXiv:2205.14100","author":"Wang Jianfeng","year":"2022","unstructured":"Jianfeng Wang, Zhengyuan Yang, Xiaowei Hu, Linjie Li, Kevin Lin, Zhe Gan, Zicheng Liu, Ce Liu, and Lijuan Wang. 2022. Git: A generative image-to-text transformer for vision and language. arXiv preprint arXiv:2205.14100 (2022)."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611817"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01115"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548022"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00238"},{"key":"e_1_3_2_1_52_1","volume-title":"Coca: Contrastive captioners are image-text foundation models. arXiv preprint arXiv:2205.01917","author":"Yu Jiahui","year":"2022","unstructured":"Jiahui Yu, Zirui Wang, Vijay Vasudevan, Legg Yeung, Mojtaba Seyedhosseini, and Yonghui Wu. 2022. Coca: Contrastive captioners are image-text foundation models. arXiv preprint arXiv:2205.01917 (2022)."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475659"}],"event":{"name":"SIGIR 2024: The 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Washington DC USA","acronym":"SIGIR 2024","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626772.3657740","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3626772.3657740","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T05:29:05Z","timestamp":1755840545000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626772.3657740"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,10]]},"references-count":53,"alternative-id":["10.1145\/3626772.3657740","10.1145\/3626772"],"URL":"https:\/\/doi.org\/10.1145\/3626772.3657740","relation":{},"subject":[],"published":{"date-parts":[[2024,7,10]]},"assertion":[{"value":"2024-07-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}