{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,1,11]],"date-time":"2025-01-11T05:34:24Z","timestamp":1736573664270,"version":"3.32.0"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T00:00:00Z","timestamp":1732233600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T00:00:00Z","timestamp":1732233600000},"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":[[2024,11,22]]},"DOI":"10.1109\/humanoids58906.2024.10769848","type":"proceedings-article","created":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T18:54:29Z","timestamp":1733252069000},"page":"934-940","source":"Crossref","is-referenced-by-count":0,"title":["Robotic State Recognition with Image-to-Text Retrieval Task of Pre-Trained Vision-Language Model and Black-Box Optimization"],"prefix":"10.1109","author":[{"given":"Kento","family":"Kawaharazuka","sequence":"first","affiliation":[{"name":"The University of Tokyo 7-3-1 Hongo, Bunkyo-ku,Graduate School of Information Science and Technology,Department of Mechano-Informatics,Tokyo,Japan,113-8656"}]},{"given":"Yoshiki","family":"Obinata","sequence":"additional","affiliation":[{"name":"The University of Tokyo 7-3-1 Hongo, Bunkyo-ku,Graduate School of Information Science and Technology,Department of Mechano-Informatics,Tokyo,Japan,113-8656"}]},{"given":"Naoaki","family":"Kanazawa","sequence":"additional","affiliation":[{"name":"The University of Tokyo 7-3-1 Hongo, Bunkyo-ku,Graduate School of Information Science and Technology,Department of Mechano-Informatics,Tokyo,Japan,113-8656"}]},{"given":"Kei","family":"Okada","sequence":"additional","affiliation":[{"name":"The University of Tokyo 7-3-1 Hongo, Bunkyo-ku,Graduate School of Information Science and Technology,Department of Mechano-Informatics,Tokyo,Japan,113-8656"}]},{"given":"Masayuki","family":"Inaba","sequence":"additional","affiliation":[{"name":"The University of Tokyo 7-3-1 Hongo, Bunkyo-ku,Graduate School of Information Science and Technology,Department of Mechano-Informatics,Tokyo,Japan,113-8656"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICMA.2005.1626828"},{"article-title":"Semantic Object Search in Large-scale Indoor Environments","volume-title":"IEEE\/RSJ International Conference on Intelligent Robots and Systems, Workshop on Active Semantic Perception and Object Search in the Real World","author":"Saito","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8594509"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CRV.2014.44"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.autcon.2017.10.016"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1177\/1729881420932715"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3390\/s20205753"},{"key":"ref8","article-title":"Vision-Language Intelligence: Tasks, Representation Learning, and Large Models","author":"Li","year":"2022","journal-title":"arXiv:2203.01922"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/Humanoids57100.2023.10375211"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1080\/01691864.2024.2408593"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref12","first-page":"23 318","article-title":"OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework","volume-title":"Proceedings of the 39th International Conference on Machine Learning","author":"Wang"},{"key":"ref13","first-page":"8748","article-title":"Learning Transferable Visual Models From Natural Language Supervision","volume-title":"Proceedings of the 38th International Conference on Machine Learning","author":"Radford"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"ref15","first-page":"1","article-title":"Open-vocabulary Object Detection via Vision and Language Knowledge Distillation","volume-title":"Proceedings of the 10th International Conference on Learning Representations","author":"Gu"},{"key":"ref16","first-page":"893","article-title":"Can Foundation Models Perform Zero-Shot Task Specification For Robot Manipulation?","volume-title":"Proceedings of the 4th Annual Learning for Dynamics and Control Conference","author":"Cui"},{"article-title":"Open X-Embodiment: Robotic Learning Datasets and RT-X Models","volume-title":"Proceedings of the 2024 IEEE International Conference on Robotics and Automation","author":"Collaboration","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160390"},{"key":"ref19","first-page":"547","article-title":"A simple zero-shot prompt weighting technique to improve prompt ensembling in text-image models","volume-title":"Proceedings of the 40th International Conference on Machine Learning","author":"Allingham"},{"key":"ref20","first-page":"2171","article-title":"DEAP: Evolutionary Algorithms Made Easy","volume":"13","author":"Fortin","year":"2012","journal-title":"Journal of Machine Learning Research"}],"event":{"name":"2024 IEEE-RAS 23rd International Conference on Humanoid Robots (Humanoids)","start":{"date-parts":[[2024,11,22]]},"location":"Nancy, France","end":{"date-parts":[[2024,11,24]]}},"container-title":["2024 IEEE-RAS 23rd International Conference on Humanoid Robots (Humanoids)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10769770\/10769590\/10769848.pdf?arnumber=10769848","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,10]],"date-time":"2025-01-10T19:57:05Z","timestamp":1736539025000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10769848\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,22]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/humanoids58906.2024.10769848","relation":{},"subject":[],"published":{"date-parts":[[2024,11,22]]}}}