{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T02:43:43Z","timestamp":1783737823225,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":36,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100006374","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62302140"],"award-info":[{"award-number":["62302140"]}],"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":[[2025,7,13]]},"DOI":"10.1145\/3726302.3729902","type":"proceedings-article","created":{"date-parts":[[2025,7,14]],"date-time":"2025-07-14T01:18:36Z","timestamp":1752455916000},"page":"792-802","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Beyond General Alignment: Fine-Grained Entity-Centric Image-Text Matching with Multimodal Attentive Experts"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6596-8117","authenticated-orcid":false,"given":"Yaxiong","family":"Wang","sequence":"first","affiliation":[{"name":"Hefei University of Technology, Hefei, Anhui, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1451-9295","authenticated-orcid":false,"given":"Lianwei","family":"Wu","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University, Xi'an, Sha'xi Province, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7546-9052","authenticated-orcid":false,"given":"Lechao","family":"Cheng","sequence":"additional","affiliation":[{"name":"Hefei University of Technology, Hefei, Anhui, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8202-0544","authenticated-orcid":false,"given":"Zhun","family":"Zhong","sequence":"additional","affiliation":[{"name":"Hefei University of Technology, Hefei, Anhui, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6366-9834","authenticated-orcid":false,"given":"Yujiao","family":"Wu","sequence":"additional","affiliation":[{"name":"CSIRO, Hobart, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3094-7735","authenticated-orcid":false,"given":"Meng","family":"Wang","sequence":"additional","affiliation":[{"name":"Hefei University of Technology, Hefei, Anhui, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,7,13]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Qwen-VL: A Frontier Large Vision-Language Model with Versatile Abilities. CoRR abs\/2308.12966","author":"Bai Jinze","year":"2023","unstructured":"Jinze Bai, Shuai Bai, Shusheng Yang, Shijie Wang, Sinan Tan, PengWang, Junyang Lin, Chang Zhou, and Jingren Zhou. 2023. Qwen-VL: A Frontier Large Vision-Language Model with Versatile Abilities. CoRR abs\/2308.12966 (2023). doi:10. 48550\/ARXIV.2308.12966 arXiv:2308.12966"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01275"},{"key":"e_1_3_2_1_3_1","unstructured":"Tom B. Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell Sandhini Agarwal Ariel Herbert-Voss Gretchen Krueger Tom Henighan Rewon Child Aditya Ramesh Daniel M. Ziegler Jeffrey Wu Clemens Winter Christopher Hesse Mark Chen Eric Sigler Mateusz Litwin Scott Gray Benjamin Chess Jack Clark Christopher Berner Sam McCandlish Alec Radford Ilya Sutskever and Dario Amodei. 2020. Language Models are Few-Shot Learners. In Advances in Neural Information Processing Systems Hugo Larochelle Marc'Aurelio Ranzato Raia Hadsell Maria-Florina Balcan and Hsuan-Tien Lin (Eds.). https:\/\/proceedings.neurips.cc\/paper\/2020\/hash\/1457c0d6bfcb4967418bfb8ac142f64a-Abstract.html"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3372278.3390719"},{"key":"e_1_3_2_1_5_1","volume-title":"9th International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=YicbFdNTTy","author":"Dosovitskiy Alexey","year":"2021","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby. 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In 9th International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=YicbFdNTTy"},{"key":"e_1_3_2_1_6_1","volume-title":"VSE: Improving Visual-Semantic Embeddings with Hard Negatives. In British Machine Vision Conference. 12","author":"Faghri Fartash","year":"2018","unstructured":"Fartash Faghri, David J. Fleet, Jamie Ryan Kiros, and Sanja Fidler. 2018. VSE: Improving Visual-Semantic Embeddings with Hard Negatives. In British Machine Vision Conference. 12. http:\/\/bmvc2018.org\/contents\/papers\/0344.pdf"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2404.00934"},{"key":"e_1_3_2_1_9_1","unstructured":"Albert Q. Jiang Alexandre Sablayrolles Arthur Mensch Chris Bamford Devendra Singh Chaplot Diego de Las Casas Florian Bressand Gianna Lengyel Guillaume Lample Lucile Saulnier L\u00e9lio Renard Lavaud Marie-Anne Lachaux Pierre Stock Teven Le Scao Thibaut Lavril Thomas Wang Timoth\u00e9e Lacroix and William El Sayed. 2023. Mistral 7B. CoRR abs\/2310.06825 (2023). doi:10. 48550\/ARXIV.2310.06825 arXiv:2310.06825"},{"key":"e_1_3_2_1_10_1","volume-title":"CaLa: Complementary Association Learning for Augmenting Composed Image Retrieval. SIGIR","author":"Jiang Xintong","year":"2024","unstructured":"Xintong Jiang, Yaxiong Wang, Yujiao Wu, Bingwen Hu, and Xueming Qian. 2024. CaLa: Complementary Association Learning for Augmenting Composed Image Retrieval. SIGIR (2024)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"e_1_3_2_1_12_1","volume-title":"International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"19742","author":"Li Junnan","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven C. H. Hoi. 2023. BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models. In International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 202), Andreas Krause, Emma Brunskill, Kyunghyun Cho, Barbara Engelhardt, Sivan Sabato, and Jonathan Scarlett (Eds.). 19730-19742. https:\/\/proceedings.mlr.press\/v202\/li23q.html"},{"key":"e_1_3_2_1_13_1","volume-title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation. In International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"12900","author":"Li Junnan","unstructured":"Junnan Li, Dongxu Li, Caiming Xiong, and Steven C. H. Hoi. 2022. BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation. In International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 162), Kamalika Chaudhuri, Stefanie Jegelka, Le Song, Csaba Szepesv\u00e1ri, Gang Niu, and Sivan Sabato (Eds.). 12888-12900. https:\/\/proceedings.mlr.press\/v162\/li22n.html"},{"key":"e_1_3_2_1_14_1","volume-title":"Advances in Neural Information Processing Systems, Marc'Aurelio Ranzato, Alina Beygelzimer, Yann N","author":"Li Junnan","year":"2021","unstructured":"Junnan Li, Ramprasaath R. Selvaraju, Akhilesh Gotmare, Shafiq R. Joty, Caiming Xiong, and Steven Chu-Hong Hoi. 2021. Align before Fuse: Vision and Language Representation Learning with Momentum Distillation. In Advances in Neural Information Processing Systems, Marc'Aurelio Ranzato, Alina Beygelzimer, Yann N. Dauphin, Percy Liang, and Jennifer Wortman Vaughan (Eds.). 9694-9705. https:\/\/proceedings.neurips.cc\/paper\/2021\/hash\/505259756244493872b7709a8a01b536-Abstract.html"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/J.CVIU.2023.103623"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2021.EMNLP-MAIN.542"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2023.EMNLP-MAIN.297"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2304.01852"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2699623"},{"key":"e_1_3_2_1_21_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"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, Gretchen Krueger, and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. In Proceedings of the 38th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 139), Marina Meila and Tong Zhang (Eds.). 8748-8763. http:\/\/proceedings.mlr.press\/v139\/radford21a.html"},{"key":"e_1_3_2_1_22_1","unstructured":"Alec Radford Karthik Narasimhan Tim Salimans Ilya Sutskever et al. 2018. Improving language understanding by generative pre-training. (2018)."},{"key":"e_1_3_2_1_23_1","unstructured":"Alec Radford JeffreyWu Rewon Child David Luan Dario Amodei Ilya Sutskever et al. 2019. Language models are unsupervised multitask learners. OpenAI blog 1 8 (2019) 9."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2302.13971"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale Dan Bikel Lukas Blecher Cristian Canton-Ferrer Moya Chen Guillem Cucurull David Esiobu Jude Fernandes Jeremy Fu Wenyin Fu Brian Fuller Cynthia Gao Vedanuj Goswami Naman Goyal Anthony Hartshorn Saghar Hosseini Rui Hou Hakan Inan Marcin Kardas Viktor Kerkez Madian Khabsa Isabel Kloumann Artem Korenev Punit Singh Koura Marie-Anne Lachaux Thibaut Lavril Jenya Lee Diana Liskovich Yinghai Lu Yuning Mao Xavier Martinet Todor Mihaylov Pushkar Mishra Igor Molybog Yixin Nie Andrew Poulton Jeremy Reizenstein Rashi Rungta Kalyan Saladi Alan Schelten Ruan Silva Eric Michael Smith Ranjan Subramanian Xiaoqing Ellen Tan Binh Tang Ross Taylor Adina Williams Jian Xiang Kuan Puxin Xu Zheng Yan Iliyan Zarov Yuchen Zhang Angela Fan Melanie Kambadur Sharan Narang Aur\u00e9lien Rodriguez Robert Stojnic Sergey Edunov and Thomas Scialom. 2023. Llama 2: Open Foundation and Fine-Tuned Chat Models. CoRR abs\/2307.09288 (2023). doi:10.48550\/ARXIV.2307.09288 arXiv:2307.09288","DOI":"10.48550\/ARXIV.2307.09288"},{"key":"e_1_3_2_1_26_1","volume-title":"Advances in Neural Information Processing Systems, Isabelle Guyon, Ulrike von Luxburg, Samy Bengio, Hanna M","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. In Advances in Neural Information Processing Systems, Isabelle Guyon, Ulrike von Luxburg, Samy Bengio, Hanna M. Wallach, Rob Fergus, S. V. N. Vishwanathan, and Roman Garnett (Eds.). 5998-6008. https:\/\/proceedings.neurips. cc\/paper\/2017\/hash\/3f5ee243547dee91fbd053c1c4a845aa-Abstract.html"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3024822"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.24963\/IJCAI.2019\/526"},{"key":"e_1_3_2_1_29_1","unstructured":"Zhen Wang Xu Shan Xiangxie Zhang and Jie Yang. 2022. N24News: A New Dataset for Multimodal News Classification. In Proceedings of the Thirteenth Language Resources and Evaluation Conference Nicoletta Calzolari Fr\u00e9d\u00e9ric B\u00e9chet Philippe Blache Khalid Choukri Christopher Cieri Thierry Declerck Sara Goggi Hitoshi Isahara Bente Maegaard Joseph Mariani H\u00e9l\u00e8ne Mazo Jan Odijk and Stelios Piperidis (Eds.). 6768-6775. https:\/\/aclanthology.org\/2022.lrec-1.729"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611709"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1162\/TACL_A_00166"},{"key":"e_1_3_2_1_32_1","volume-title":"Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts. In International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"26009","author":"Zeng Yan","year":"2022","unstructured":"Yan Zeng, Xinsong Zhang, and Hang Li. 2022. Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts. In International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 162), Kamalika Chaudhuri, Stefanie Jegelka, Le Song, Csaba Szepesv\u00e1ri, Gang Niu, and Sivan Sabato (Eds.). 25994-26009. https:\/\/proceedings.mlr.press\/v162\/zeng22c.html"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3339661"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","unstructured":"Xinsong Zhang Yan Zeng Jipeng Zhang and Hang Li. 2023. Toward Building General Foundation Models for Language Vision and Vision-Language Understanding Tasks. In Findings of the Association for Computational Linguistics Houda Bouamor Juan Pino and Kalika Bali (Eds.). 551-568. doi:10.18653\/V1\/2023.FINDINGS-EMNLP.40","DOI":"10.18653\/V1\/2023.FINDINGS-EMNLP.40"},{"key":"e_1_3_2_1_35_1","unstructured":"Justin Zhao Timothy Wang Wael Abid Geoffrey Angus Arnav Garg Jeffery Kinnison Alex Sherstinsky Piero Molino Travis Addair and Devvret Rishi. 2024. LoRA Land: 310 Fine-tuned LLMs that Rival GPT-4 A Technical Report. CoRR abs\/2405.00732 (2024). doi:10.48550\/ARXIV.2405.00732 arXiv:2405.00732"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3383184"}],"event":{"name":"SIGIR '25: The 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Padua Italy","acronym":"SIGIR '25","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3726302.3729902","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T18:29:01Z","timestamp":1755887341000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3726302.3729902"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,13]]},"references-count":36,"alternative-id":["10.1145\/3726302.3729902","10.1145\/3726302"],"URL":"https:\/\/doi.org\/10.1145\/3726302.3729902","relation":{},"subject":[],"published":{"date-parts":[[2025,7,13]]},"assertion":[{"value":"2025-07-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}