{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T17:44:14Z","timestamp":1776879854434,"version":"3.51.2"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10887762","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["Triplet Synthesis for Enhancing Composed Image Retrieval via Counterfactual Image Generation"],"prefix":"10.1109","author":[{"given":"Kenta","family":"Uesugi","sequence":"first","affiliation":[{"name":"Hokkaido University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Naoki","family":"Saito","sequence":"additional","affiliation":[{"name":"Hokkaido University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Keisuke","family":"Maeda","sequence":"additional","affiliation":[{"name":"Hokkaido University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takahiro","family":"Ogawa","sequence":"additional","affiliation":[{"name":"Hokkaido University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Miki","family":"Haseyama","sequence":"additional","affiliation":[{"name":"Hokkaido University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Training vision transformers for image retrieval","author":"El-Nouby","year":"2021"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00019"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01850"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01407"},{"key":"ref5","article-title":"CompoDiff: Versatile composed image retrieval with latent diffusion","author":"Gu","year":"2024","journal-title":"Transactions on Machine Learning Research"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01256"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3617597"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP51287.2024.10648023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3640345"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612408"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00316"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01115"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00213"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28334"},{"key":"ref15","first-page":"25165","article-title":"LANCE: Stress-testing visual models by generating language-guided counterfactual images","volume-title":"Proceedings of the Neural Information Processing Systems","author":"Prabhu"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP51287.2024.10647654"},{"key":"ref17","first-page":"71195","article-title":"COCO-counterfactuals: Automatically constructed counterfactual examples for image-text pairs","volume":"36","author":"Le","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref18","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Li"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref20","article-title":"Prompt-to-prompt image editing with cross-attention control","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Hertz"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1644"},{"key":"ref23","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref24","article-title":"LoRA: Low-rank adaptation of large language models","author":"Hu","year":"2021"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10887762.pdf?arnumber=10887762","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:26:23Z","timestamp":1774416383000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10887762\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10887762","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}