{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T21:26:42Z","timestamp":1770845202053,"version":"3.50.1"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,5]],"date-time":"2025-10-05T00:00:00Z","timestamp":1759622400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,5]],"date-time":"2025-10-05T00:00:00Z","timestamp":1759622400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,5]]},"DOI":"10.1109\/smc58881.2025.11342511","type":"proceedings-article","created":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T20:54:44Z","timestamp":1769633684000},"page":"1270-1276","source":"Crossref","is-referenced-by-count":0,"title":["Snap, Segment, Deploy: A Visual Data and Detection Pipeline for Wearable Industrial Assistants"],"prefix":"10.1109","author":[{"given":"Di","family":"Wen","sequence":"first","affiliation":[{"name":"Karlsruhe Institute of Technology,Computer Vision for Human-Computer Interaction Lab (CV:HCI), Institute for Anthropomatics and Robotics (IAR),Karlsruhe,Germany,76131"}]},{"given":"Junwei","family":"Zheng","sequence":"additional","affiliation":[{"name":"Karlsruhe Institute of Technology,Computer Vision for Human-Computer Interaction Lab (CV:HCI), Institute for Anthropomatics and Robotics (IAR),Karlsruhe,Germany,76131"}]},{"given":"Ruiping","family":"Liu","sequence":"additional","affiliation":[{"name":"Karlsruhe Institute of Technology,Computer Vision for Human-Computer Interaction Lab (CV:HCI), Institute for Anthropomatics and Robotics (IAR),Karlsruhe,Germany,76131"}]},{"given":"Yi","family":"Xu","sequence":"additional","affiliation":[{"name":"Karlsruhe Institute of Technology,Computer Vision for Human-Computer Interaction Lab (CV:HCI), Institute for Anthropomatics and Robotics (IAR),Karlsruhe,Germany,76131"}]},{"given":"Kunyu","family":"Peng","sequence":"additional","affiliation":[{"name":"Karlsruhe Institute of Technology,Computer Vision for Human-Computer Interaction Lab (CV:HCI), Institute for Anthropomatics and Robotics (IAR),Karlsruhe,Germany,76131"}]},{"given":"Rainer","family":"Stiefelhagen","sequence":"additional","affiliation":[{"name":"Karlsruhe Institute of Technology,Computer Vision for Human-Computer Interaction Lab (CV:HCI), Institute for Anthropomatics and Robotics (IAR),Karlsruhe,Germany,76131"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.rcim.2024.102789"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2024.110478"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1177\/00187208221105135"},{"key":"ref4","article-title":"Sam 2: Segment anything in images and videos","author":"Ravi","year":"2024"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.107272"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s00170-024-12989-y"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2024.3379075"},{"key":"ref8","article-title":"Retrieval-augmented generation for knowledge-intensive nlp tasks","author":"Lewis","year":"2020","journal-title":"NeurIPS"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.151"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_7"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569519"},{"key":"ref12","article-title":"Procsy: Procedural synthetic dataset generation towards influence factor studies of semantic segmentation networks","volume-title":"CVPR workshops","author":"Khan"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00143"},{"key":"ref15","article-title":"Object detection using domain randomization and generative adversarial refinement of synthetic images","author":"Nogues","year":"2018"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3390\/math11224588"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01339"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.146"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.352"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00025"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00352"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00387"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00200"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3390\/app14072942"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6501\/ac7cbd"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.5220\/0008877901650172"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.120065"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00147"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00328"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.20517\/ir.2023.24"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3135024"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.isci.2024.109479"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610333"},{"key":"ref34","article-title":"Objectfinder: Open-vocabulary assistive system for interactive object search by blind people","author":"Liu","year":"2024"},{"key":"ref35","article-title":"Yolov11: An overview of the key architectural enhancements","author":"Khanam","year":"2024"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/tbdata.2025.3618474"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"ref39","article-title":"Phi-3 technical report: A highly capable language model locally on your phone","author":"Abdin","year":"2024"},{"key":"ref40","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"ICML","author":"Radford"},{"key":"ref41","volume-title":"pyttsx3","year":"2024"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP46576.2022.9897990"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/S0166-4115(08)62386-9"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1177\/1541931215591373"}],"event":{"name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","location":"Vienna, Austria","start":{"date-parts":[[2025,10,5]]},"end":{"date-parts":[[2025,10,8]]}},"container-title":["2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11342430\/11342431\/11342511.pdf?arnumber=11342511","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T20:50:11Z","timestamp":1770843011000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11342511\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,5]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/smc58881.2025.11342511","relation":{},"subject":[],"published":{"date-parts":[[2025,10,5]]}}}