{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T16:27:06Z","timestamp":1790353626102,"version":"4.1.0"},"reference-count":65,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/tpami.2022.3187350","type":"journal-article","created":{"date-parts":[[2022,6,30]],"date-time":"2022-06-30T19:40:59Z","timestamp":1656618059000},"page":"1-18","source":"Crossref","is-referenced-by-count":6,"title":["Learning to Overcome Noise in Weak Caption Supervision for Object Detection"],"prefix":"10.1109","author":[{"given":"Mesut Erhan","family":"Unal","sequence":"first","affiliation":[{"name":"University of Pittsburgh, Google Research, Zurich"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Keren","family":"Ye","sequence":"additional","affiliation":[{"name":"University of Pittsburgh, Google Research, Zurich"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingda","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Pittsburgh, Google Research, Zurich"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christopher","family":"Thomas","sequence":"additional","affiliation":[{"name":"University of Pittsburgh, Google Research, Zurich"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1901-9660","authenticated-orcid":false,"given":"Adriana","family":"Kovashka","sequence":"additional","affiliation":[{"name":"University of Pittsburgh, Google Research, Zurich"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Li","sequence":"additional","affiliation":[{"name":"NewsBreak Seattle"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Danfeng","family":"Qin","sequence":"additional","affiliation":[{"name":"University of Pittsburgh, Google Research, Zurich"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jesse","family":"Berent","sequence":"additional","affiliation":[{"name":"University of Pittsburgh, Google Research, Zurich"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ren"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-66415-2_41"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00352"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20893-6_29"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.311"},{"key":"ref7","first-page":"434","article-title":"Ts2c: Tight box mining with surrounding segmentation context for weakly supervised object detection","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Wei"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.326"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01061"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00230"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00838"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01061"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298668"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2876304"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.545"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00141"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.412"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210036"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00208"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_28"},{"key":"ref25","first-page":"13","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lu"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_49"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58526-6_26"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_19"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.218"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00990"},{"key":"ref32","article-title":"COBE: Contextualized object embeddings from narrated instructional video","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Bertasius"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01101"},{"key":"ref34","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.124"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00978"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.320"},{"key":"ref38","article-title":"Equal but not the same: Understanding the implicit relationship between persuasive images and text","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Zhang"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.583"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1199"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00509"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.5555\/3044805.3045025"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00754"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0620-5"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4012"},{"key":"ref51","first-page":"45","article-title":"Software framework for topic modelling with large corpora","volume-title":"Proc. LREC Workshop New Challenges NLP Frameworks","author":"\u0158eh\u016f\u0159ek"},{"key":"ref52","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","volume-title":"Proc. 13th Int. Conf. Artif. Intell. Statist.","author":"Glorot"},{"key":"ref53","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889473"},{"key":"ref55","first-page":"2121","article-title":"Adaptive subgradient methods for online learning and stochastic optimization","volume":"12","author":"Duchi","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref56","first-page":"120","article-title":"The openCV library","volume":"25","author":"Bradski","year":"2000","journal-title":"Dr. Dobbs J. Softw. Tools"},{"key":"ref57","first-page":"265","article-title":"Tensorflow: A system for large-scale machine learning","volume-title":"Proc. USENIX Conf. Operating Syst. Des. Implementation","author":"Abadi"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.351"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref61","article-title":"Microsoft COCO captions: Data collection and evaluation server","author":"Chen","year":"2015"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/1743384.1743475"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01416"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/4359286\/09811398.pdf?arnumber=9811398","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T05:45:48Z","timestamp":1706766348000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9811398\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":65,"URL":"https:\/\/doi.org\/10.1109\/tpami.2022.3187350","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":[[2022]]}}}