{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T15:10:01Z","timestamp":1778166601052,"version":"3.51.4"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T00:00:00Z","timestamp":1685318400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T00:00:00Z","timestamp":1685318400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation","doi-asserted-by":"publisher","award":["92048205"],"award-info":[{"award-number":["92048205"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,5,29]]},"DOI":"10.1109\/icra48891.2023.10161294","type":"proceedings-article","created":{"date-parts":[[2023,7,4]],"date-time":"2023-07-04T17:20:56Z","timestamp":1688491256000},"page":"8299-8305","source":"Crossref","is-referenced-by-count":6,"title":["Weakly Supervised Referring Expression Grounding via Target-Guided Knowledge Distillation"],"prefix":"10.1109","author":[{"given":"Jinpeng","family":"Mi","sequence":"first","affiliation":[{"name":"Institute of Machine Intelligence (IMI), University of Shanghai for Science and Technology,China"}]},{"given":"Song","family":"Tang","sequence":"additional","affiliation":[{"name":"Institute of Machine Intelligence (IMI), University of Shanghai for Science and Technology,China"}]},{"given":"Zhiyuan","family":"Ma","sequence":"additional","affiliation":[{"name":"Institute of Machine Intelligence (IMI), University of Shanghai for Science and Technology,China"}]},{"given":"Dan","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Machine Intelligence (IMI), University of Shanghai for Science and Technology,China"}]},{"given":"Qingdu","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Machine Intelligence (IMI), University of Shanghai for Science and Technology,China"}]},{"given":"Jianwei","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Hamburg,Technical Aspects of Multimodal Systems (TAMS),Department of Informatics,Germany"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01039"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00409"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413850"},{"key":"ref34","article-title":"Fitnets: Hints for thin deep nets","author":"romero","year":"2015","journal-title":"ICLRE"},{"key":"ref15","first-page":"69","article-title":"Modeling context in referring expressions","author":"yu","year":"0","journal-title":"ECCV"},{"key":"ref37","article-title":"Improve object detection with feature-based knowledge distillation: Towards accurate and efficient detectors","author":"zhang","year":"2021","journal-title":"ICLRE"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00370"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00145"},{"key":"ref31","first-page":"18 123","article-title":"Counterfactual contrastive learning for weakly-supervised vision-language grounding","volume":"33","author":"zhang","year":"2020","journal-title":"NeurIPS"},{"key":"ref30","first-page":"347","article-title":"Variational context: Exploiting visual and textual context for grounding referring expressions","volume":"43","author":"niu","year":"2019","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"ref11","article-title":"Distilling the knowledge in a neural network","volume":"2","author":"hinton","year":"2015","journal-title":"ArXiv Preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3139467"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3058684"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3186410"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00640"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1162\/COLI_a_00088"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.470"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1192"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3203402"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00474"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00478"},{"key":"ref23","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","volume":"28","author":"ren","year":"2015","journal-title":"NeurIPS"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01089"},{"key":"ref25","article-title":"Yolov3: An incremental improvement","author":"redmon","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00206"},{"key":"ref42","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","volume":"30","author":"tarvainen","year":"2017","journal-title":"NeurIPS"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01509"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413902"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01005"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475313"},{"key":"ref29","article-title":"A proposal-free one-stage framework for referring expression comprehension and generation via dense cross-attention","author":"sun","year":"2022","journal-title":"IEEE Transactions on Multimedia"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00270"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.558"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351074"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919897133"},{"key":"ref3","first-page":"241","article-title":"Deep image retrieval: Learning global representations for image search","author":"gordo","year":"2016","journal-title":"ECCV"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_49"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2020.00043"},{"key":"ref40","first-page":"1532","article-title":"Glove: Global vectors for word representation","author":"pennington","year":"2014","journal-title":"EMNLP"}],"event":{"name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","location":"London, United Kingdom","start":{"date-parts":[[2023,5,29]]},"end":{"date-parts":[[2023,6,2]]}},"container-title":["2023 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10160211\/10160212\/10161294.pdf?arnumber=10161294","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,24]],"date-time":"2023-07-24T17:31:42Z","timestamp":1690219902000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10161294\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,29]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/icra48891.2023.10161294","relation":{},"subject":[],"published":{"date-parts":[[2023,5,29]]}}}