{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T21:52:15Z","timestamp":1769550735545,"version":"3.49.0"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,9,19]],"date-time":"2021-09-19T00:00:00Z","timestamp":1632009600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,9,19]],"date-time":"2021-09-19T00:00:00Z","timestamp":1632009600000},"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":[[2021,9,19]]},"DOI":"10.1109\/icip42928.2021.9506177","type":"proceedings-article","created":{"date-parts":[[2021,8,23]],"date-time":"2021-08-23T21:08:41Z","timestamp":1629752921000},"page":"359-363","source":"Crossref","is-referenced-by-count":4,"title":["Two-Stream Hybrid Attention Network for Multimodal Classification"],"prefix":"10.1109","author":[{"given":"Qipin","family":"Chen","sequence":"first","affiliation":[{"name":"Pennsylvania State University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenyu","family":"Shi","sequence":"additional","affiliation":[{"name":"Amazon LLC"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhen","family":"Zuo","sequence":"additional","affiliation":[{"name":"Amazon LLC"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinmiao","family":"Fu","sequence":"additional","affiliation":[{"name":"Amazon LLC"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Sun","sequence":"additional","affiliation":[{"name":"Amazon LLC"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.497"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.629"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1115"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2753232"},{"key":"ref14","first-page":"2672","volume":"2","author":"goodfellow","year":"2014","journal-title":"Generative adversarial nets"},{"key":"ref15","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.232"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.450"},{"key":"ref18","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.12319","article-title":"Multimodal keyless attention fusion for video classification","author":"long","year":"2018","journal-title":"AAAI"},{"key":"ref19","article-title":"Memory fusion network for multi-view sequential learning","author":"zadeh","year":"2018","journal-title":"arXiv preprint arXiv 1802 00420"},{"key":"ref28","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"2017","journal-title":"arXiv preprint arXiv 1711 05847"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref27","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv preprint arXiv 1412 6980"},{"key":"ref3","first-page":"2048","article-title":"Show, at-tend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"ICML"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2916887"},{"key":"ref29","article-title":"An overview of gradient descent optimization algorithms","author":"ruder","year":"2016","journal-title":"arXiv preprint arXiv 1609 04802"},{"key":"ref5","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"NeurIPS"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1044"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2670560"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2015.01.001"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2011.79"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2852503"},{"key":"ref20","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","author":"tan","year":"2019","journal-title":"arXiv preprint arXiv 1905 10520"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2015.01.095"},{"key":"ref21","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018","journal-title":"arXiv preprint arXiv 1810 04805"},{"key":"ref24","first-page":"2121","article-title":"Devise: A deep visual-semantic embedding model","author":"frome","year":"2013","journal-title":"NeurIPS"},{"key":"ref23","article-title":"Multimodal deep learning","author":"ngiam","year":"2011","journal-title":"ICML"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.11"},{"key":"ref25","article-title":"Is a picture worth a thousand words? a deep multi-modal fusion architecture for product classification in e-commerce","author":"zahavy","year":"2016","journal-title":"arXiv preprint arXiv 1611 09534"}],"event":{"name":"2021 IEEE International Conference on Image Processing (ICIP)","location":"Anchorage, AK, USA","start":{"date-parts":[[2021,9,19]]},"end":{"date-parts":[[2021,9,22]]}},"container-title":["2021 IEEE International Conference on Image Processing (ICIP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9506008\/9506009\/09506177.pdf?arnumber=9506177","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,7]],"date-time":"2023-01-07T22:29:46Z","timestamp":1673130586000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9506177\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,19]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icip42928.2021.9506177","relation":{},"subject":[],"published":{"date-parts":[[2021,9,19]]}}}