{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T13:50:04Z","timestamp":1765547404264,"version":"3.40.3"},"reference-count":65,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3555167","type":"journal-article","created":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T02:46:57Z","timestamp":1743043617000},"page":"56908-56917","source":"Crossref","is-referenced-by-count":1,"title":["Open-Vocabulary Action Localization With Iterative Visual Prompting"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8278-2373","authenticated-orcid":false,"given":"Naoki","family":"Wake","sequence":"first","affiliation":[{"name":"Applied Robotics Research, Microsoft, Redmond, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-0157-7500","authenticated-orcid":false,"given":"Atsushi","family":"Kanehira","sequence":"additional","affiliation":[{"name":"Applied Robotics Research, Microsoft, Redmond, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5408-3089","authenticated-orcid":false,"given":"Kazuhiro","family":"Sasabuchi","sequence":"additional","affiliation":[{"name":"Applied Robotics Research, Microsoft, Redmond, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7457-2878","authenticated-orcid":false,"given":"Jun","family":"Takamatsu","sequence":"additional","affiliation":[{"name":"Applied Robotics Research, Microsoft, Redmond, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9758-9357","authenticated-orcid":false,"given":"Katsushi","family":"Ikeuchi","sequence":"additional","affiliation":[{"name":"Applied Robotics Research, Microsoft, Redmond, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30301-5_60"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1992.219935"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/icra48506.2021.9562102"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IEEECONF49454.2021.9382750"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00055"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00399"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_1"},{"key":"ref8","article-title":"PIVOT: Iterative visual prompting elicits actionable knowledge for VLMs","author":"Nasiriany","year":"2024","journal-title":"arXiv:2402.07872"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28328"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/fg59268.2024.10581896"},{"key":"ref11","article-title":"Open-vocabulary spatiotemporal action detection","author":"Wu","year":"2024","journal-title":"arXiv:2405.10832"},{"key":"ref12","article-title":"Exploring scalability of self-training for open-vocabulary temporal action localization","author":"Hyun","year":"2024","journal-title":"arXiv:2407.07024"},{"key":"ref13","article-title":"Open-vocabulary temporal action localization using multimodal guidance","author":"Gupta","year":"2024","journal-title":"arXiv:2406.15556"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3395778"},{"journal-title":"Hello GPT-4o","year":"2025","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3310935"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3477090"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/SII52469.2022.9708836"},{"key":"ref19","first-page":"93.1","article-title":"End-to-end, singlestream temporal action detection in untrimmed videos","volume-title":"Proc. Brit. Mach. Vis. Conf. (BMVC)","author":"Buch"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.211"},{"key":"ref21","first-page":"768","article-title":"DAPs: Deep action proposals for action understanding","volume-title":"Proc. Eur. Conf. Comput. Vis. (ECCV)","author":"Escorcia"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.392"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.617"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00124"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.119"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2019.00224"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.317"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2922108"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00717"},{"key":"ref30","first-page":"6373","article-title":"SST: Singlestream temporal action proposals","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Buch"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6815"},{"issue":"3","key":"ref32","first-page":"2602","article-title":"BSN++: Complementary boundary regressor with scale-balanced relation modeling for temporal action proposal generation","volume-title":"Proc. AAAI Conf. Artif. Intell.","volume":"35","author":"Su"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00372"},{"key":"ref34","first-page":"988","article-title":"Single shot temporal action detection","volume-title":"Proc. 25th ACM Int. Conf. Multimedia","author":"Lin"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01327"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00520"},{"key":"ref37","first-page":"105","article-title":"Prompting visuallanguage models for efficient video understanding","volume-title":"Proc. Eur. Conf. Comput. Vis. (ECCV)","author":"Ju"},{"key":"ref38","article-title":"Open-vocabulary temporal action detection with Off-the-Shelf image-text features","author":"Rathod","year":"2022","journal-title":"arXiv:2212.10596"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3361862"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00539"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02640"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00375"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-091420-084139"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.105"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00034"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2991965"},{"issue":"1","key":"ref48","first-page":"1","article-title":"Human grasping database for activities of daily living with depth, color and kinematic data streams","volume":"5","author":"Saudabayev","year":"2018","journal-title":"Sci. Data"},{"journal-title":"Python Video Annotator","year":"2025","author":"Ribeiro","key":"ref49"},{"key":"ref50","article-title":"Related systems","volume-title":"Annals of Mathematic Studies","author":"Kuhn","year":"1956"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1177\/02783649231212929"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.3389\/fcomp.2024.1235239"},{"journal-title":"THUMOS Challenge: Action Recognition With a Large Number of Classes","year":"2014","author":"Jiang","key":"ref53"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00129"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00128"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3044448"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01107"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00332"},{"key":"ref59","article-title":"TemporalMaxer: Maximize temporal context with only max pooling for temporal action localization","author":"Tang","year":"2023","journal-title":"arXiv:2303.09055"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_29"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01808"},{"key":"ref62","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Radford"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20062-5_39"},{"journal-title":"Phi-3-Vision-128k-Instruct-Onnx-Cuda","year":"2025","key":"ref64"},{"key":"ref65","article-title":"Phi-3 technical report: A highly capable language model locally on your phone","volume-title":"arXiv:2404.14219","author":"Abdin","year":"2024"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/10942370.pdf?arnumber=10942370","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,5]],"date-time":"2025-04-05T08:16:44Z","timestamp":1743841004000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10942370\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":65,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3555167","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2025]]}}}