{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:23:29Z","timestamp":1777890209817,"version":"3.51.4"},"reference-count":43,"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\/iccv51701.2025.02125","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"22889-22898","source":"Crossref","is-referenced-by-count":0,"title":["CapeLLM: Support-Free Category-Agnostic Pose Estimation with Multimodal Large Language Models"],"prefix":"10.1109","author":[{"given":"Junho","family":"Kim","sequence":"first","affiliation":[{"name":"EverEx"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hyungjin","family":"Chung","sequence":"additional","affiliation":[{"name":"EverEx"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Byung-Hoon","family":"Kim","sequence":"additional","affiliation":[{"name":"EverEx"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Llama 3.2: Vision Edge for Mobile Devices","year":"2024"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.471"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02221"},{"key":"ref4","article-title":"Shikra: Unleashing Multimodal LLM\u2019s Referential Dialogue Magic","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref5","article-title":"Pix2seq: A Language Modeling Framework for Object Detection","volume-title":"International Conference on Learning Representations","author":"Chen","year":"2022"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref7","article-title":"Vision Transformers Need Registers","volume-title":"The Twelfth International Conference on Learning Representations","author":"Darcet","year":"2024"},{"key":"ref8","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73036-8_27"},{"key":"ref10","article-title":"LoRA: Low-Rank Adaptation of Large Language Models","volume-title":"International Conference on Learning Representations","author":"Hu","year":"2022"},{"key":"ref11","article-title":"Mistral 7B","author":"Jiang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.3389\/fnbeh.2020.581154"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"ref15","article-title":"Towards general text embeddings with multi-stage contrastive learning","author":"Li","year":"2023","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.52202\/079017"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01306"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02217"},{"key":"ref21","article-title":"DINOv2: Learning Robust Visual Features without Supervision","author":"Oquab","year":"2024","journal-title":"Transactions on Machine Learning Research"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01233"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00204"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00750"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00188"},{"key":"ref26","article-title":"CapeX: Category-Agnostic Pose Estimation from Textual Point Explanation","author":"Rusanovsky","year":"2024","journal-title":"arXiv preprint"},{"key":"ref27","first-page":"29441","article-title":"Hiera: A hierarchical vision transformer without the bells-andwhistles","volume-title":"International Conference on Machine Learning","author":"Ryali","year":"2023"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00706"},{"key":"ref29","article-title":"Decoding-based regression","author":"Song","year":"2025","journal-title":"arXiv preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00584"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00065"},{"key":"ref32","article-title":"Visionllm: Large language model is also an openended decoder for vision-centric tasks","volume":"36","author":"Wang","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10888428"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1800"},{"key":"ref35","article-title":"Commit: Coordinated instruction tuning for multimodal large language models","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref36","article-title":"VisionLLM v2: An End-to-End Generalist Multimodal Large Language Model for Hundreds of Vision-Language Tasks","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems","author":"Wu","year":"2024"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_29"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00202"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20068-7_23"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2795"},{"key":"ref41","article-title":"AP-10K: A Benchmark for Animal Pose Estimation in the Wild","volume-title":"Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2)","author":"Yu","year":"2021"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2020"},{"key":"ref43","article-title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","volume-title":"The Twelfth International Conference on Learning Representations","author":"Zhu","year":"2024"}],"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\/11445220.pdf?arnumber=11445220","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:31:42Z","timestamp":1777613502000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445220\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02125","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}