{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,16]],"date-time":"2026-05-16T16:04:39Z","timestamp":1778947479796,"version":"3.51.4"},"reference-count":62,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["2320952,2117439,2112606,2117439"],"award-info":[{"award-number":["2320952,2117439,2112606,2117439"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,8]]},"DOI":"10.1109\/bigdata66926.2025.11401579","type":"proceedings-article","created":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T20:57:57Z","timestamp":1772830677000},"page":"142-151","source":"Crossref","is-referenced-by-count":1,"title":["Labeling Copilot: A Deep Research Agent for Automated Data Curation in Computer Vision"],"prefix":"10.1109","author":[{"given":"Debargha","family":"Ganguly","sequence":"first","affiliation":[{"name":"Microsoft Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sumit","family":"Kumar","sequence":"additional","affiliation":[{"name":"Microsoft Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ishwar","family":"Balappanawar","sequence":"additional","affiliation":[{"name":"Microsoft Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weicong","family":"Chen","sequence":"additional","affiliation":[{"name":"Case Western Reserve University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shashank","family":"Kambhatla","sequence":"additional","affiliation":[{"name":"Microsoft Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Srinivasan","family":"Iyengar","sequence":"additional","affiliation":[{"name":"Microsoft Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shivkumar","family":"Kalyanaraman","sequence":"additional","affiliation":[{"name":"Microsoft Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ponnurangam","family":"Kumaraguru","sequence":"additional","affiliation":[{"name":"IIIT Hyderabad"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vipin","family":"Chaudhary","sequence":"additional","affiliation":[{"name":"Case Western Reserve University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1405.0312"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01316-z"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2021.100336"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1280"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00461"},{"key":"ref7","article-title":"A survey of self-evolving agents: On path to artificial super intelligence","author":"Gao","year":"2025","journal-title":"arXiv preprint"},{"key":"ref8","article-title":"A comprehensive survey of self-evolving ai agents: A new paradigm bridging foundation models and lifelong agentic systems","author":"Fang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref11","article-title":"Cognitive architectures for language agents","author":"Sumers","year":"2023","journal-title":"Transactions on Machine Learning Research"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1833"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1179"},{"key":"ref14","article-title":"Multimodal datasets: misogyny, pornography, and malignant stereotypes","author":"Birhane","year":"2021","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"ref16","first-page":"5637","article-title":"Wilds: A benchmark of in-the-wild distribution shifts","volume-title":"International conference on machine learning","author":"Koh","year":"2021"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1919012117"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00982"},{"key":"ref19","article-title":"Crowdsourcing annotations for visual object detection","volume":"1","author":"Su","year":"2012","journal-title":"HCOMP@AAAI"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.27"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.12125"},{"key":"ref22","author":"Settles","year":"2009","journal-title":"Active learning literature survey"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02117-4"},{"key":"ref24","article-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","author":"Nichol","year":"2021","journal-title":"arXiv preprint"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45014-9_1"},{"key":"ref27","article-title":"Active learning for convolutional neural networks: A core-set approach","author":"Sener","year":"2017","journal-title":"arXiv preprint"},{"key":"ref28","article-title":"Deep batch active learning by diverse, uncertain gradient lower bounds","author":"Ash","year":"2019","journal-title":"arXiv preprint"},{"key":"ref29","article-title":"Forte: Finding outliers with representation typicality estimation","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Ganguly","year":"2025"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_21"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.593"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2019.00019"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2019.2946162"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.1710.09412"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00020"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01182"},{"key":"ref41","article-title":"Mixpro: Data augmentation with maskmix and progressive attention labeling for vision transformer","author":"Zhao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref43","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref44","first-page":"10684","article-title":"Highresolution image synthesis with latent diffusion models","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"Rombach","year":"2022"},{"key":"ref45","article-title":"Effective data augmentation with diffusion models","author":"Trabucco","year":"2023","journal-title":"arXiv preprint"},{"key":"ref46","article-title":"Image retrieval outperforms diffusion models on data augmentation","author":"Burg","year":"2023","journal-title":"arXiv preprint"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.3115\/981658.981684"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/279943.279962"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2005.186"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50026-X"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/130385.130417"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/wacv56688.2023.00016"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.14778\/3157794.3157797"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(96)00034-3"},{"key":"ref55","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning. PmLR","author":"Radford","year":"2021"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.14778\/3137628.3137631"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.14778\/2994509.2994514"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.14778\/3229863.3229867"},{"key":"ref59","article-title":"Characterizing deep research: A benchmark and formal definition","author":"Java","year":"2025","journal-title":"arXiv preprint"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/tbdata.2025.3618474"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0165"},{"key":"ref62","first-page":"7176","article-title":"Reliable fidelity and diversity metrics for generative models","volume-title":"International conference on machine learning","author":"Naeem","year":"2020"}],"event":{"name":"2025 IEEE International Conference on Big Data (BigData)","location":"Macau, China","start":{"date-parts":[[2025,12,8]]},"end":{"date-parts":[[2025,12,11]]}},"container-title":["2025 IEEE International Conference on Big Data (BigData)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11400704\/11400712\/11401579.pdf?arnumber=11401579","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T06:54:11Z","timestamp":1772866451000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11401579\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,8]]},"references-count":62,"URL":"https:\/\/doi.org\/10.1109\/bigdata66926.2025.11401579","relation":{},"subject":[],"published":{"date-parts":[[2025,12,8]]}}}