{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:31:09Z","timestamp":1777865469789,"version":"3.51.4"},"reference-count":58,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["2021R1A2C2007884,RS-2025-02263628"],"award-info":[{"award-number":["2021R1A2C2007884,RS-2025-02263628"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01982","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"21342-21352","source":"Crossref","is-referenced-by-count":0,"title":["MA-CIR: A Multimodal Arithmetic Benchmark for Composed Image Retrieval"],"prefix":"10.1109","author":[{"given":"Jaeseok","family":"Byun","sequence":"first","affiliation":[{"name":"Seoul National University,Department of ECE"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Young Kyun","family":"Jang","sequence":"additional","affiliation":[{"name":"Google Deepmind"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Seokhyeon","family":"Jeong","sequence":"additional","affiliation":[{"name":"Seoul National University,Department of ECE"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Donghyun","family":"Kim","sequence":"additional","affiliation":[{"name":"Korea University,Department of AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Taesup","family":"Moon","sequence":"additional","affiliation":[{"name":"Seoul National University,Department of ECE"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.4324\/9780080494562-78"},{"key":"ref3","article-title":"Sentence-level prompts benefit composed image retrieval","author":"Bai","year":"2024","journal-title":"ICLR"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02080"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00543"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01407"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref8","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"NeurIPS"},{"key":"ref9","article-title":"Reducing task discrepancy of text encoders for zero-shot composed image retrieval","author":"Byun","year":"2024","journal-title":"arXiv preprint"},{"key":"ref10","article-title":"Artemis: Attention-based retrieval with textexplicit matching and implicit similarity","author":"Delmas","year":"2022","journal-title":"ICLR"},{"key":"ref11","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0571"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.552"},{"key":"ref14","article-title":"Compodiff: Versatile composed image retrieval with latent diffusion","author":"Gu","year":"2023","journal-title":"TMLR"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01256"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1355"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00799"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72655-2_14"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01590"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.181"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.568"},{"key":"ref22","article-title":"Vision-by-language for training-free compositional image retrieval","author":"Karthik","year":"2024","journal-title":"ICLR"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01316-z"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00086"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28081"},{"key":"ref26","article-title":"Blip: Bootstrapping language-image pre-training for unified visionlanguage understanding and generation","author":"Li","year":"2022","journal-title":"ICML"},{"key":"ref27","article-title":"Blip2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"ICML"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01049"},{"key":"ref29","article-title":"Improving context understanding in multimodal large language models via multimodal composition learning","author":"Li","year":"2024","journal-title":"ICML"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657831"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00566"},{"key":"ref33","article-title":"Visual instruction tuning","author":"Liu","year":"2024","journal-title":"NeurIPS"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00213"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00565"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01050"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.1062"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.567"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01261"},{"key":"ref40","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","volume-title":"ICLR","author":"Podell","year":"2024"},{"key":"ref41","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01850"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.naacl-srw.29"},{"key":"ref44","article-title":"Laion-5b: An open large-scale dataset for training next generation image-text models","author":"Schuhmann","year":"2022","journal-title":"NeurIPS Dataset and Benchmark"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1644"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02545"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28324"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00517"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00663"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28334"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00574"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01115"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657740"},{"key":"ref54","article-title":"When and why vision-language models behave like bags-of-words, and what to do about it","author":"Yuksekgonul","year":"2023","journal-title":"ICLR"},{"key":"ref55","article-title":"Magiclens: Selfsupervised image retrieval with open-ended instructions","author":"Zhang","year":"2024","journal-title":"ICML"},{"key":"ref56","article-title":"Magicbrush: A manually annotated dataset for instructionguided image editing","author":"Zhang","year":"2024","journal-title":"NeurIPS"},{"key":"ref57","article-title":"X-paste: Revisiting scalable copy-paste for instance segmentation using clip and stablediffusion","author":"Zhao","year":"2023","journal-title":"ICML"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-demos.4"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11445432.pdf?arnumber=11445432","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:38:10Z","timestamp":1777531090000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445432\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01982","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}