{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T09:05:03Z","timestamp":1771923903661,"version":"3.50.1"},"reference-count":27,"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\/501100006465","name":"Korea Creative Content Agency","doi-asserted-by":"publisher","award":["RS-2024-00396700"],"award-info":[{"award-number":["RS-2024-00396700"]}],"id":[{"id":"10.13039\/501100006465","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\/iccvw69036.2025.00452","type":"proceedings-article","created":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T20:44:02Z","timestamp":1771879442000},"page":"4360-4368","source":"Crossref","is-referenced-by-count":0,"title":["CoT-Pose: Chain-of-Thought Reasoning for 3D Pose Generation from Abstract Prompts"],"prefix":"10.1109","author":[{"given":"Junuk","family":"Cha","sequence":"first","affiliation":[{"name":"KAIST,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jihyeon","family":"Kim","sequence":"additional","affiliation":[{"name":"KT,South Korea"}],"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","article-title":"Towards better adversarial synthesis of human images from text","author":"Briq","year":"2021","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27888"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20068-7_20"},{"key":"ref5","article-title":"Emerging properties in unified multimodal pretraining","author":"Deng","year":"2025","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00132"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00204"},{"key":"ref8","article-title":"Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning","author":"Guo","year":"2025","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530094"},{"key":"ref10","article-title":"Lora: Low-rank adaptation of large language models","volume-title":"ICLR","author":"Hu","year":"2022"},{"key":"ref11","article-title":"Openai o1 system card","author":"Jaech","year":"2024","journal-title":"arXiv preprint"},{"key":"ref12","article-title":"Large language models are zero-shot reasoners","volume-title":"NIPS","author":"Kojima","year":"2022"},{"key":"ref13","article-title":"Flux. 1 kontext: Flow matching for in-context image generation and editing in latent space","author":"Labs","year":"2025","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02589"},{"key":"ref15","article-title":"Visual instruction tuning","volume-title":"NIPS","author":"Liu","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3596711.3596800"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00554"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01326"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01123"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00078"},{"key":"ref21","article-title":"Cogcom: A visual language model with chain-of-manipulations reasoning","volume-title":"ICLR","author":"Qi","year":"2025"},{"key":"ref22","volume-title":"Flux-lora-dlc","author":"Prithiv","year":"2024"},{"key":"ref23","article-title":"Neural discrete representation learning","volume-title":"NIPS","author":"Van Den Oord","year":"2017"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.492"},{"key":"ref25","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume-title":"NIPS","author":"Wei","year":"2022"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3618174"},{"key":"ref27","article-title":"Least-to-most prompting enables complex reasoning in large language models","author":"Zhou","year":"2022","journal-title":"arXiv preprint"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision Workshops (ICCVW)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,20]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision Workshops (ICCVW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11373940\/11374285\/11375593.pdf?arnumber=11375593","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T08:06:15Z","timestamp":1771920375000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11375593\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/iccvw69036.2025.00452","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}