{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:22:52Z","timestamp":1740100972602,"version":"3.37.3"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"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 of China (NSFC)","doi-asserted-by":"publisher","award":["61906180,U21B2046"],"award-info":[{"award-number":["61906180,U21B2046"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,7,18]]},"DOI":"10.1109\/ijcnn55064.2022.9892139","type":"proceedings-article","created":{"date-parts":[[2022,9,30]],"date-time":"2022-09-30T19:56:04Z","timestamp":1664567764000},"page":"1-8","source":"Crossref","is-referenced-by-count":1,"title":["Region-based Cross-modal Retrieval"],"prefix":"10.1109","author":[{"given":"Danyang","family":"Hou","sequence":"first","affiliation":[{"name":"Data Intelligence System Research Center, Institute of Computing Technology, CAS,Beijing,China"}]},{"given":"Liang","family":"Pang","sequence":"additional","affiliation":[{"name":"Data Intelligence System Research Center, Institute of Computing Technology, CAS,Beijing,China"}]},{"given":"Yanyan","family":"Lan","sequence":"additional","affiliation":[{"name":"Institute for AI Industry Research, Tsinghua University,Beijing,China"}]},{"given":"Huawei","family":"Shen","sequence":"additional","affiliation":[{"name":"Data Intelligence System Research Center, Institute of Computing Technology, CAS,Beijing,China"}]},{"given":"Xueqi","family":"Cheng","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, CAS,CAS Key Lab of Network Data Science and Technology,Beijing,China"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1561\/1500000019"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref31","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Advances in Neural Infor-mation Processing Systems(Ne u rIPS)"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01192"},{"key":"ref35","article-title":"Deep residuallearning for image recognition","author":"he","year":"0","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition(CVPR)"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.552"},{"key":"ref10","article-title":"Vse++: Improving visual-semantic embeddings with hard negatives","author":"faghri","year":"0","journal-title":"Proceedings of the British Machine Vision Conference (BMVC)"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00645"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123326"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3383184"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00831"},{"key":"ref15","article-title":"Hierarchical mul-timodal lstm for dense visual-semantic embedding","author":"niu","year":"0","journal-title":"Proceedings of the IEEE International Conference on Computer Vision(ICCV)"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00586"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01095"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00359"},{"key":"ref19","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"0","journal-title":"International Conference on Learning Representations(ICLR)"},{"key":"ref28","article-title":"Microsoft coco: Common objects in context","author":"lin","year":"0","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"ref4","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref27","article-title":"Dense passage retrieval for open-domain question an-swering","author":"karpukhin","year":"0","journal-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00577"},{"key":"ref6","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"0","journal-title":"Pro-ceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics(NAACL)"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref7","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems(Ne u rIPS)"},{"key":"ref2","article-title":"Retrieve-gan: Image synthesis via differentiable patch retrieval","author":"tseng","year":"0","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_38"},{"key":"ref1","article-title":"Stacked cross attention for image-text matching","author":"lee","year":"0","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"ref20","article-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","author":"lu","year":"2019","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref22","article-title":"Uniter: Universal image-text representation learning","author":"chen","year":"0","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/69.166986"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.494"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413567"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"}],"event":{"name":"2022 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2022,7,18]]},"location":"Padua, Italy","end":{"date-parts":[[2022,7,23]]}},"container-title":["2022 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9891857\/9889787\/09892139.pdf?arnumber=9892139","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T23:00:16Z","timestamp":1667516416000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9892139\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,18]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/ijcnn55064.2022.9892139","relation":{},"subject":[],"published":{"date-parts":[[2022,7,18]]}}}