{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,3]],"date-time":"2025-06-03T06:25:09Z","timestamp":1748931909179,"version":"3.28.0"},"reference-count":43,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,7,18]]},"DOI":"10.1109\/ijcnn55064.2022.9892164","type":"proceedings-article","created":{"date-parts":[[2022,9,30]],"date-time":"2022-09-30T15:56:04Z","timestamp":1664553364000},"page":"1-8","source":"Crossref","is-referenced-by-count":1,"title":["TRICAN: Multi-Modal Hateful Memes Detection with Triplet-Relation Information Cross-Attention Network"],"prefix":"10.1109","author":[{"given":"Xiaolin","family":"Liang","sequence":"first","affiliation":[{"name":"School of Mathematics and Statistics, Changsha University of Science and Technology,Changsha,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yajuan","family":"Huang","sequence":"additional","affiliation":[{"name":"Changsha University of Science and Technology, Institute of Information Engineering, Chinese Academy of Sciences,Changsha,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wen","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"He","family":"Zhu","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhao","family":"Liang","sequence":"additional","affiliation":[{"name":"School of Mathematics and Statistics, Changsha University of Science and Technology,Changsha,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Libo","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Mathematics and Statistics, Changsha University of Science and Technology,Changsha,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"journal-title":"Detectron2","year":"2019","author":"lo","key":"ref39"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1317"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref32","article-title":"Hateful memes detection via complementary visual and linguistic networks","author":"zhang","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref31","article-title":"Detecting hate speech in multi-modal memes","author":"das","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3097180"},{"journal-title":"Structured attention networks","year":"0","author":"kim","key":"ref37"},{"key":"ref36","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014","journal-title":"ArXiv Preprint"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref40","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"ICLR (Poster)"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16431"},{"key":"ref12","first-page":"4373","article-title":"Devlbert: Learning decon-founded visio-linguistic representations","author":"zhang","year":"0","journal-title":"Proceedings of the 28th ACM International Conference on Multimedia"},{"key":"ref13","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"},{"journal-title":"Hadamard product for low-rank bilinear pooling","year":"2017","author":"kim","key":"ref14"},{"key":"ref15","article-title":"Bilinear attention networks","volume":"31","author":"kim","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018102"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2817340"},{"key":"ref18","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref19","first-page":"91","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":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-1062"},{"key":"ref27","article-title":"Pixel-bert: Aligning image pixels with text by deep multi-modal transformers","author":"huang","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/1126004.1126005","article-title":"Content-based multimedia information retrieval: State of the art and challenges","volume":"2","author":"michael","year":"2006","journal-title":"ACM Transactions on Multimedia Computing Communications and Applications (TOMM)"},{"key":"ref6","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"journal-title":"Learning phrase representations using RNN encoder-decoder for statistical machine translation","year":"2014","author":"cho","key":"ref5"},{"key":"ref8","first-page":"121","article-title":"Oscar: Object-semantics aligned pre-training for vision-language tasks","author":"li","year":"0","journal-title":"European Conference on Computer Vision"},{"journal-title":"Visualbert A simple and performant baseline for vision and language","year":"0","author":"li","key":"ref7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00688"},{"journal-title":"Uniter Learning universal image-text representations","year":"2019","author":"chen","key":"ref9"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref22","first-page":"603","article-title":"Natural language processing","year":"2020","journal-title":"Fundamentals of Artificial Intelligence"},{"journal-title":"Computer Vision Algorithms and Applications","year":"2010","author":"szeliski","key":"ref21"},{"key":"ref42","first-page":"876","article-title":"Averaging weights leads to wider optima and better generalization","author":"izmailov","year":"0","journal-title":"34th Conference on Uncertainty in Artificial Intelligence 2018 UAI 2018"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_44"},{"journal-title":"On the adequacy of untuned warmup for adaptive optimization","year":"2020","author":"ma","key":"ref41"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref26","first-page":"2611","article-title":"The hateful memes challenge: Detecting hate speech in multimodal memes","volume":"33","author":"kiela","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref43","doi-asserted-by":"crossref","first-page":"1145","DOI":"10.1016\/S0031-3203(96)00142-2","article-title":"The use of the area under the roc curve in the evaluation of machine learning algorithms","volume":"30","author":"andrew","year":"1997","journal-title":"Pattern Recognition"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_25"}],"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\/09892164.pdf?arnumber=9892164","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T18:59:23Z","timestamp":1667501963000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9892164\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,18]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/ijcnn55064.2022.9892164","relation":{},"subject":[],"published":{"date-parts":[[2022,7,18]]}}}