{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,25]],"date-time":"2025-08-25T21:10:02Z","timestamp":1756156202360,"version":"3.44.0"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"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":[[2019,5]]},"DOI":"10.1109\/icassp.2019.8683464","type":"proceedings-article","created":{"date-parts":[[2019,4,17]],"date-time":"2019-04-17T16:01:56Z","timestamp":1555516916000},"page":"2097-2101","source":"Crossref","is-referenced-by-count":7,"title":["Visual Relationship Recognition via Language and Position Guided Attention"],"prefix":"10.1109","author":[{"given":"Hao","family":"Zhou","sequence":"first","affiliation":[{"name":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, 200240, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chuanping","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, 200240, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chongyang","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, 200240, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shengyang","family":"Shen","sequence":"additional","affiliation":[{"name":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, 200240, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.121"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.331"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.352"},{"article-title":"Very deep convolutional networks for large-scale image recognition","year":"2014","author":"simonyan","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref15","article-title":"Distributed representations of words and phrases and their compo-sitionality","author":"yin","year":"2016","journal-title":"EMNLP"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.71"},{"article-title":"A method for stochastic optimization. cornell university library","year":"2017","author":"kingma","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995711"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.554"},{"key":"ref4","first-page":"4995","article-title":"Visual7w: Grounded question answering in images","author":"zhu","year":"2016","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref3","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":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.683"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_28"},{"key":"ref8","first-page":"2017","article-title":"Spatial transformer networks","author":"jaderberg","year":"2015","journal-title":"Advances in neural information processing systems"},{"article-title":"Scacnn: Spatial and channel-wise attention in convolutional networks for image captioning","year":"2016","author":"chen","key":"ref7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_51"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.396"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_20"}],"event":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2019,5,12]]},"location":"Brighton, UK","end":{"date-parts":[[2019,5,17]]}},"container-title":["ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8671773\/8682151\/08683464.pdf?arnumber=8683464","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,25]],"date-time":"2025-08-25T20:29:06Z","timestamp":1756153746000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8683464\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8683464","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}