{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:23:47Z","timestamp":1777890227909,"version":"3.51.4"},"reference-count":53,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00695","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"7409-7418","source":"Crossref","is-referenced-by-count":0,"title":["Autocompose: Automatic Generation of Pose Transition Descriptions for Composed Pose Retrieval Using Multimodal LLMs"],"prefix":"10.1109","author":[{"given":"Yi-Ting","family":"Shen","sequence":"first","affiliation":[{"name":"University of Maryland, College Park"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sungmin","family":"Eum","sequence":"additional","affiliation":[{"name":"DEVCOM Army Research Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Doheon","family":"Lee","sequence":"additional","affiliation":[{"name":"University of Maryland, College Park"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rohit","family":"Shete","sequence":"additional","affiliation":[{"name":"University of Maryland, College Park"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chiao-Yi","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Maryland, College Park"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Heesung","family":"Kwon","sequence":"additional","affiliation":[{"name":"DEVCOM Army Research Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuvra S.","family":"Bhattacharyy","sequence":"additional","affiliation":[{"name":"University of Maryland, College Park"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Unreal Engine 5","year":"2025"},{"key":"ref2","article-title":"Hallucination of multimodal large language models: A survey","author":"Bai","year":"2024","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3617597"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01407"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00843"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.143"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2353"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29730"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20068-7_20"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01379"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00204"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206495"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00762"},{"key":"ref14","volume-title":"\u2013","author":"Haven","year":"2025"},{"key":"ref15","first-page":"1989","article-title":"Cycada: Cycle-consistent adversarial domain adaptation","volume-title":"In International conference on machine learning","author":"Hoffman","year":"2018"},{"issue":"2","key":"ref16","article-title":"Lora: Low-rank adaptation of large language models","volume":"1","author":"Edward","year":"2022","journal-title":"ICLR"},{"key":"ref17","article-title":"Gpt-4o system card","author":"Hurst","year":"2024","journal-title":"arXiv preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01590"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00216"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i14.17555"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00086"},{"key":"ref22","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"In International conference on machine learning","author":"Li"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01315"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00213"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00213"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818013"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00554"},{"key":"ref29","volume-title":"Tubingen","author":"Meshcapade GmbH","year":"2025"},{"key":"ref30","author":"Mori","year":"2015","journal-title":"Pose embeddings: A deep architecture for learning to match human poses"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01326"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00763"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01123"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.01080"},{"key":"ref35","article-title":"Learning transferable visual models from natural language supervision","volume-title":"In Proceedings of the International Conference on Machine Learning (ICML)","author":"Radford"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01850"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/icip55913.2025.11084750"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-019-0197-0"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3767328"},{"key":"ref40","article-title":"Selective annotation makes language models better few-shot learners","author":"Su","year":"2023","journal-title":"In ICLR"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.54"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00660"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28101"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_1"},{"key":"ref45","first-page":"229","article-title":"Simple but effective rawdata level multimodal fusion for composed image retrieval","volume-title":"In Proceedings of the International ACM SIGIR Conference on Research and Development in Information Retrieval","author":"Wen"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01115"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/BigData59044.2023.10386743"},{"key":"ref48","article-title":"Visionllm v2: An end-to-end generalist multimodal large language model for hundreds of visionlanguage tasks","author":"Wu","year":"2024","journal-title":"NEURIPS"},{"key":"ref49","article-title":"Next-gpt: Any-to-any multimodal 11 m","volume-title":"In Forty-first International Conference on Machine Learning","author":"Wu"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2795"},{"key":"ref51","article-title":"Motiongpt: Large language model for human motion generation","author":"Zhang","year":"2023","journal-title":"In Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref52","first-page":"47","article-title":"Neucore: Neural concept reasoning for composed image retrieval","volume-title":"In Proceedings of UniReps: the First Workshop on Unifying Representations in Neural Models","author":"Zhao"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2017.244"}],"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\/11445367.pdf?arnumber=11445367","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:32:08Z","timestamp":1777613528000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445367\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00695","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}