{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T05:01:01Z","timestamp":1785474061976,"version":"3.56.0"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"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":[[2026,6]]},"DOI":"10.1109\/ivworkshops71735.2026.11624065","type":"proceedings-article","created":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T19:09:50Z","timestamp":1785438590000},"page":"2167-2173","source":"Crossref","is-referenced-by-count":0,"title":["AutoVDC: Automated Vision Data Cleaning Using Vision-Language Models"],"prefix":"10.1109","author":[{"given":"Santosh","family":"Vasa","sequence":"first","affiliation":[{"name":"Mercedes-Benz Research & Development North America","place":["San Jose, CA, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aditi","family":"Ramadwar","sequence":"additional","affiliation":[{"name":"Mercedes-Benz Research & Development North America","place":["San Jose, CA, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jnana Rama Krishna","family":"Darabattula","sequence":"additional","affiliation":[{"name":"Mercedes-Benz Research & Development North America","place":["San Jose, CA, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Md Zafar","family":"Anwar","sequence":"additional","affiliation":[{"name":"Mercedes-Benz Research & Development North America","place":["San Jose, CA, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stanislaw","family":"Antol","sequence":"additional","affiliation":[{"name":"Mercedes-Benz Research & Development North America","place":["San Jose, CA, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrei","family":"Vatavu","sequence":"additional","affiliation":[{"name":"Mercedes-Benz Research & Development North America","place":["San Jose, CA, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thomas","family":"Monninger","sequence":"additional","affiliation":[{"name":"Mercedes-Benz Research & Development North America","place":["San Jose, CA, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sihao","family":"Ding","sequence":"additional","affiliation":[{"name":"Mercedes-Benz Research & Development North America","place":["San Jose, CA, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3166544"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"ref3","article-title":"Argoverse 2: Next generation datasets for self-driving perception and forecasting","author":"Wilson","year":"2021","journal-title":"NeurIPS Datasets and Benchmarks"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-45528-0"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/335191.335437"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-28818-3"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295387"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4471-2099-5_1"},{"key":"ref12","article-title":"Active learning literature survey","volume-title":"Tech. Rep. TR 1648","author":"Settles","year":"2009"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CAIN58948.2023.00011"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2024.3394735"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2020"},{"key":"ref16","article-title":"Llms-as-judges: A comprehensive survey on llm-based evaluation methods","author":"Li","year":"2024"},{"key":"ref17","article-title":"Generative AI for synthetic data generation: Methods, challenges and the future","author":"Guo","year":"2024"},{"key":"ref18","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00461"},{"key":"ref20","article-title":"SAM 2: Segment anything in images and videos","author":"Ravi","year":"2024"},{"key":"ref21","article-title":"Pixtral 12b","author":"Agrawal","year":"2024"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref23","article-title":"Phi-3 technical report: A highly capable language model locally on your phone","author":"Abdin","year":"2024"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1833"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01227"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00420"},{"key":"ref27","article-title":"Vision-language models as pseudo-label validators in semi-supervised learning: Geolocating medium voltage cabins from google street view imagery","author":"Diab","year":"2025"},{"key":"ref28","article-title":"ClipGrader: Leveraging vision-language models for robust label quality assessment in object detection","author":"Lu","year":"2025"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref30","article-title":"Deepseek-vl2: Mixture-of-experts vision-language models for advanced multimodal understanding","author":"Wu","year":"2024"},{"key":"ref31","article-title":"Gemini flash 2.0"},{"key":"ref32","article-title":"Chatgpt (gpt-4.1)"},{"key":"ref33","article-title":"The llama 3 herd of models","author":"G","year":"2024"},{"key":"ref34","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"ICLR","author":"Hu"}],"event":{"name":"2026 IEEE Intelligent Vehicles Symposium Workshops (IV Workshops)","location":"Ann Arbor, MI, USA","start":{"date-parts":[[2026,6,22]]},"end":{"date-parts":[[2026,6,22]]}},"container-title":["2026 IEEE Intelligent Vehicles Symposium Workshops (IV Workshops)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11623814\/11623822\/11624065.pdf?arnumber=11624065","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T04:52:04Z","timestamp":1785473524000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11624065\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/ivworkshops71735.2026.11624065","relation":{},"subject":[],"published":{"date-parts":[[2026,6]]}}}