{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:21:36Z","timestamp":1792786896022,"version":"4.5.0"},"reference-count":92,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2024YFB4708900"],"award-info":[{"award-number":["2024YFB4708900"]}]},{"name":"National Natural Science Foundation of China","award":["62225309"],"award-info":[{"award-number":["62225309"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"crossref"}]},{"name":"Explorers Program of Shanghai","award":["25TS1415100"],"award-info":[{"award-number":["25TS1415100"]}]},{"name":"Shanghai Municipal Special Program for Basic Research on General AI Foundation Models","award":["2025SHZDZX025G01"],"award-info":[{"award-number":["2025SHZDZX025G01"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1109\/tpami.2026.3717912","type":"journal-article","created":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T19:07:01Z","timestamp":1785352021000},"page":"14795-14812","source":"Crossref","is-referenced-by-count":0,"title":["EgoLoc: A Generalizable Solution for Temporal Interaction Localization in Egocentric Videos"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2453-0001","authenticated-orcid":false,"given":"Junyi","family":"Ma","sequence":"first","affiliation":[{"name":"Shanghai Key Laboratory of Navigation and Location Based Services","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-4172-4935","authenticated-orcid":false,"given":"Erhang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai Key Laboratory of Navigation and Location Based Services","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2437-9807","authenticated-orcid":false,"given":"Yin-Dong","family":"Zheng","sequence":"additional","affiliation":[{"name":"Shanghai Key Laboratory of Navigation and Location Based Services","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5520-5900","authenticated-orcid":false,"given":"Yuchen","family":"Xie","sequence":"additional","affiliation":[{"name":"Shanghai Key Laboratory of Navigation and Location Based Services","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0808-5593","authenticated-orcid":false,"given":"Yixuan","family":"Zhou","sequence":"additional","affiliation":[{"name":"Shanghai Key Laboratory of Navigation and Location Based Services","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9959-1634","authenticated-orcid":false,"given":"Hesheng","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai Key Laboratory of Navigation and Location Based Services","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2015.2409731"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02095-7"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2986648"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01625"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00660"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01806"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00814"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01950"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00938"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3247907"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3369646"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00068"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3298850"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_8"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02033"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i8.32883"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00660"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3058688"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3090167"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3311447"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00299"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3395778"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3538675"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00566"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2025.3555167"},{"key":"ref26","article-title":"Open-vocabulary temporal action localization using multimodal guidance","author":"Gupta","year":"2024"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11128834"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2475"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IROS60139.2025.11246682"},{"key":"ref30","article-title":"Grounded SAM: Assembling open-world models for diverse visual tasks","author":"Ren","year":"2024"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/IROS60139.2025.11246527"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00719"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00689"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01253"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3193611"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3007826"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01310"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00641"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3466212"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72655-2_10"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3330794"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_7"},{"key":"ref43","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20062-5_39"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3414275"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01771"},{"key":"ref47","article-title":"Multi-modal prompting for low-shot temporal action localization","author":"Ju","year":"2023"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02095"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00538"},{"key":"ref50","article-title":"GPT-4 technical report","author":"Achiam","year":"2023"},{"key":"ref51","first-page":"37321","article-title":"PIVOT: Iterative visual prompting elicits actionable knowledge for VLMs","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"51","author":"Nasiriany","year":"2024"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-11015-4_12"},{"key":"ref53","first-page":"720","article-title":"Scaling egocentric vision: The epic-kitchens dataset","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Damen","year":"2018"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00989"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3068645"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00569"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02153"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2454"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73229-4_11"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01260"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/IROS60139.2025.11247704"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3633453"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01758"},{"key":"ref64","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2023"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00178"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01355"},{"key":"ref67","article-title":"EgoVLM: Policy optimization for egocentric video understanding","author":"Vinod","year":"2025"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1021\/ac60214a047"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.4693-06.2007"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.3390\/app12083863"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1800"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.52202\/085713-1207"},{"key":"ref73","first-page":"141261","article-title":"Depth anything 3: Recovering the visual space from any views","volume-title":"Proc. Int. Conf. Learn. Representations","volume":"2026","author":"Lin","year":"2026"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02126"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref76","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Brown","year":"2020"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4321-9"},{"key":"ref79","first-page":"1825","article-title":"Point policy: Unifying observations and actions with key points for robot manipulation","volume-title":"Proc. 9th Conf. Robot Learn.","author":"Haldar","year":"2025"},{"key":"ref80","article-title":"EgoZero: Robot learning from smart glasses","author":"Liu","year":"2025"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0491"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1145\/3711896.3736569"},{"key":"ref83","article-title":"Gemini 2.5: Pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities","author":"Comanici","year":"2025"},{"key":"ref84","article-title":"Grok 4 model card","year":"2025"},{"key":"ref85","article-title":"Qwen3-VL technical report","author":"Bai","year":"2025"},{"key":"ref86","article-title":"Internvl3: Exploring advanced training and test-time recipes for open-source multimodal models","author":"Zhu","year":"2025"},{"key":"ref87","article-title":"Janus-Pro: Unified multimodal understanding and generation with data and model scaling","author":"Chen","year":"2025"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/IROS60139.2025.11246803"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11128322"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01111"},{"key":"ref91","first-page":"3828","article-title":"Articulated object estimation in the wild","volume-title":"Proc. 1st Workshop Egocentric Percep. Action Robot Learn.","author":"Werby","year":"2025"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2992889"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11723300\/11627683.pdf?arnumber=11627683","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T19:10:30Z","timestamp":1791486630000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11627683\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":92,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3717912","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,11]]}}}