{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T05:32:48Z","timestamp":1730266368756,"version":"3.28.0"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,18]],"date-time":"2023-06-18T00:00:00Z","timestamp":1687046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,18]],"date-time":"2023-06-18T00:00:00Z","timestamp":1687046400000},"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":[[2023,6,18]]},"DOI":"10.1109\/ijcnn54540.2023.10192000","type":"proceedings-article","created":{"date-parts":[[2023,8,2]],"date-time":"2023-08-02T13:30:03Z","timestamp":1690983003000},"page":"1-7","source":"Crossref","is-referenced-by-count":0,"title":["Weighted Keywords-Guided feature Extraction and Reasoning Network for Visual Grounding"],"prefix":"10.1109","author":[{"given":"Guangqi","family":"Zhu","sequence":"first","affiliation":[{"name":"Beijing University of Posts and Telecommunications,Beijing,China"}]},{"given":"Jian","family":"Xu","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,Beijing,China"}]},{"given":"Xingxian","family":"Liu","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,Beijing,China"}]},{"given":"Yunling","family":"Feng","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,Beijing,China"}]},{"given":"Yajing","family":"Xu","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,Beijing,China"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01089"},{"key":"ref35","first-page":"455","article-title":"Parsing with compositional vector grammars","author":"socher","year":"0","journal-title":"Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1 Long Papers)"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00478"},{"journal-title":"An image is worth 16×16 words Transformers for image recognition at scale","year":"2020","author":"dosovitskiy","key":"ref34"},{"journal-title":"Real-time referring expression comprehension by single-stage grounding network","year":"2018","author":"chen","key":"ref15"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00437"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_23"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref31","first-page":"5583","article-title":"Vilt: Vision-and-language transformer without convolution or region supervision","author":"kim","year":"2021","journal-title":"International Conference on Machine Learning"},{"key":"ref30","first-page":"121","article-title":"Oscar: Object-semantics aligned pre-training for vision-language tasks","author":"li","year":"2020","journal-title":"European Conference on Computer Vision"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00468"},{"key":"ref33","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"radford","year":"2021","journal-title":"International Conference on Machine Learning"},{"key":"ref10","first-page":"2758","article-title":"Tgifqa: Toward spatiotemporal reasoning in visual question answering","author":"jang","year":"0","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref32","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume":"34","author":"li","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.538"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00205"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00206"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01661"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00447"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00477"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00179"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref26","doi-asserted-by":"crossref","first-page":"13 587","DOI":"10.1609\/aaai.v35i15.17602","article-title":"Disentangled motifaware graph learning for phrase grounding","volume":"35","author":"mu","year":"0","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00997"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.470"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475313"},{"key":"ref22","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","volume":"28","author":"ren","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref21","article-title":"Learning to compose and reason with language tree structures for visual grounding","author":"hong","year":"2019","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"journal-title":"Lxmert Learning cross-modality encoder representations from transformers","year":"2019","author":"tan","key":"ref28"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_23"},{"key":"ref29","article-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume":"32","author":"lu","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00475"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01093"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"journal-title":"Deep captioning with multimodal recurrent neural networks (m-rnn)","year":"2014","author":"mao","key":"ref4"},{"journal-title":"Show ask attend and answer A strong baseline for visual question answering","year":"2017","author":"kazemi","key":"ref3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.323"},{"key":"ref5","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref40","first-page":"4644","article-title":"r39 for referring expression comprehension","author":"yang","year":"0","journal-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision"}],"event":{"name":"2023 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2023,6,18]]},"location":"Gold Coast, Australia","end":{"date-parts":[[2023,6,23]]}},"container-title":["2023 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10190990\/10190992\/10192000.pdf?arnumber=10192000","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T13:43:52Z","timestamp":1692625432000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10192000\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,18]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/ijcnn54540.2023.10192000","relation":{},"subject":[],"published":{"date-parts":[[2023,6,18]]}}}