{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:15:55Z","timestamp":1777889755459,"version":"3.51.4"},"reference-count":49,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62422605,92370132"],"award-info":[{"award-number":["62422605,92370132"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2024YFE0210900"],"award-info":[{"award-number":["2024YFE0210900"]}],"id":[{"id":"10.13039\/501100012166","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\/iccv51701.2025.00964","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"10353-10363","source":"Crossref","is-referenced-by-count":0,"title":["RoboAnnotatorX: A Comprehensive and Universal Annotation Framework for Accurate Understanding of Long-Horizon Robot Demonstration"],"prefix":"10.1109","author":[{"given":"Longxin","family":"Kou","sequence":"first","affiliation":[{"name":"Tianjin University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fei","family":"Ni","sequence":"additional","affiliation":[{"name":"Tianjin University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Zheng","sequence":"additional","affiliation":[{"name":"Tianjin University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peilong","family":"Han","sequence":"additional","affiliation":[{"name":"Tianjin University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinyi","family":"Liu","sequence":"additional","affiliation":[{"name":"Tianjin University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haiqin","family":"Cui","sequence":"additional","affiliation":[{"name":"Tianjin University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Liu","sequence":"additional","affiliation":[{"name":"Tianjin University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianye","family":"Hao","sequence":"additional","affiliation":[{"name":"Tianjin University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref2","article-title":"Scaling robot policy learning via zero-shot labeling with foundation models","volume-title":"8th Annual Conference on Robot Learning","author":"Blank","year":"2024"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.025"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01370"},{"key":"ref5","first-page":"2012","article-title":"Playfusion: Skill acquisition via diffusion from language-annotated play","volume-title":"Conference on Robot Learning","author":"Chen","year":"2023"},{"key":"ref6","article-title":"Plan-seq-learn: Language model guided rl for solving long horizon robotics tasks","author":"Dalal","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref7","article-title":"Bridge data: Boosting generalization of robotic skills with cross-domain datasets","author":"Ebert","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref8","article-title":"Rh20t: A robotic dataset for learning diverse skills in one-shot","volume-title":"RSS 2023 Workshop on Learning for Task and Motion Planning","author":"Fang","year":"2023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1578"},{"key":"ref10","volume-title":"Gensim2: Scaling robot data generation with multi-modal and reasoning 1 lms","author":"Hua","year":"2024"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801993"},{"key":"ref12","article-title":"Victor: Learning hierarchical vision-instruction correlation rewards for longhorizon manipulation","author":"Hung","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref13","first-page":"991","article-title":"Bc-z: Zero-shot task generalization with robotic imitation learning","volume-title":"Conference on Robot Learning","author":"Jang","year":"2022"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.120"},{"key":"ref15","article-title":"Subtask-aware visual reward learning from segmented demonstrations","volume-title":"CoRL 2024 Workshop on Mastering Robot Manipulation in a World of Abundant Data","author":"Kim"},{"key":"ref16","article-title":"Kisa: A unified keyframe identifier and skill annotator for long-horizon robotics demonstrations","volume-title":"Forty-first International Conference on Machine Learning","author":"Kou"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_19"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02484"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref21","volume-title":"Llava-next: Improved reasoning, ocr, and world knowledge","author":"Liu","year":"2024"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref23","article-title":"Vip: Towards universal visual reward and representation via value-implicit pre-training","author":"Jason Ma","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref24","article-title":"Liv: Language-image representations and rewards for robotic control","author":"Jason Ma","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref25","article-title":"Videogpt+: Integrating image and video encoders for enhanced video understanding","author":"Maaz","year":"2024","journal-title":"arxiv"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2020.xvi.061"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3180108"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2024.xx.050"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01327"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0558"},{"key":"ref31","article-title":"Open x-embodiment: Robotic learning datasets and rt-x models","author":"O\u2019Neill","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref32","volume-title":"Understanding long videos in one multimodal language model pass","author":"Ranasinghe","year":"2024"},{"key":"ref33","article-title":"Timechat: A time-sensitive multimodal large language model for long video understanding","author":"Ren","year":"2023","journal-title":"ArXiv"},{"key":"ref34","article-title":"Robovqa: Multimodal long-horizon reasoning for robotics","author":"Sermanet","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref35","article-title":"Maniskill3: Gpu parallelized robotics simulation and rendering for generalizable embodied ai","author":"Tao","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref36","article-title":"Bridgedata v2: A dataset for robot learning at scale","volume-title":"Conference on Robot Learning (CoRL)","author":"Walke","year":"2023"},{"key":"ref37","article-title":"Mimicplay: Long-horizon imitation learning by watching human play","author":"Wang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref38","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref39","article-title":"Robogen: Towards unleashing infinite data for automated robot learning via generative simulation","author":"Wang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref40","article-title":"Internvideo2: Scaling video foundation models for multimodal video understanding","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref41","volume-title":"Pllava: Parameter-free llava extension from images to videos for video dense captioning","author":"Xu","year":"2024"},{"key":"ref42","first-page":"3536","article-title":"Xskill: Cross embodiment skill discovery","volume-title":"Conference on Robot Learning","author":"Xu","year":"2023"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"ref44","article-title":"Minicpm-v: A gpt-4v level mllm on your phone","author":"Yao","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610606"},{"key":"ref47","article-title":"Lohoravens: A long-horizon language-conditioned benchmark for robotic tabletop manipulation","author":"Zhang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref48","article-title":"Universal visual decomposer: Long-horizon manipulation made easy","author":"Zhang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref49","article-title":"robosuite: A modular simulation framework and benchmark for robot learning","author":"Zhu","year":"2020","journal-title":"arXiv preprint arXiv"}],"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\/11445474.pdf?arnumber=11445474","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:18:09Z","timestamp":1777612689000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445474\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00964","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}