{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T04:24:18Z","timestamp":1764995058607,"version":"3.46.0"},"reference-count":30,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"12","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Inf. & Syst."],"published-print":{"date-parts":[[2025,12,1]]},"DOI":"10.1587\/transinf.2024edp7313","type":"journal-article","created":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T18:07:34Z","timestamp":1750183654000},"page":"1612-1621","source":"Crossref","is-referenced-by-count":0,"title":["Entity Knowledge-Guided Image-Text Alignment for Joint Multimodal Aspect-Based Sentiment Analysis"],"prefix":"10.1587","volume":"E108.D","author":[{"given":"Yan","family":"XIANG","sequence":"first","affiliation":[{"name":"Faculty of Information Engineering and Automation, Kunming University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Di","family":"WU","sequence":"additional","affiliation":[{"name":"Faculty of Information Engineering and Automation, Kunming University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunjia","family":"CAI","sequence":"additional","affiliation":[{"name":"Faculty of Information Engineering and Automation, Kunming University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yantuan","family":"XIAN","sequence":"additional","affiliation":[{"name":"Faculty of Information Engineering and Automation, Kunming University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"532","reference":[{"key":"1","doi-asserted-by":"crossref","unstructured":"[1] X. Ju, D. Zhang, R. Xiao, J. Li, S. Li, M. Zhang, and G. Zhou, \u201cJoint multi-modal aspect-sentiment analysis with auxiliary cross-modal relation detection,\u201d Proc. 2021 Conference on Empirical Methods in Natural Language Processing, pp.4395-4405, 2021. 10.18653\/v1\/2021.emnlp-main.360","DOI":"10.18653\/v1\/2021.emnlp-main.360"},{"key":"2","doi-asserted-by":"crossref","unstructured":"[2] K. He, X. Zhang, S. Ren, and J. Sun, \u201cDeep residual learning for image recognition,\u201d Proc. IEEE conference on computer vision and pattern recognition, pp.770-778, 2016. 10.1109\/cvpr.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"3","unstructured":"[3] A. Dosovitskiy, L. Beyer, A. Kolesnikov, et al., \u201cAn image is worth 16x16 words: Transformers for image recognition at scale,\u201d arXiv preprint arXiv:2010.11929, 2020."},{"key":"4","doi-asserted-by":"crossref","unstructured":"[4] P. Anderson, X. He, C. Buehler, D. Teney, M. Johnson, S. Gould, and L. Zhang, \u201cBottom-up and top-down attention for image captioning and visual question answering,\u201d Proc. IEEE conference on computer vision and pattern recognition, pp.6077-6086, 2018. 10.1109\/cvpr.2018.00636","DOI":"10.1109\/CVPR.2018.00636"},{"key":"5","unstructured":"[5] J. Devlin, M.W. Chang, K. Lee, et al., \u201cBert: Pre-training of deep bidirectional transformers for language understanding,\u201d arXiv preprint arXiv:1810.04805, 2018."},{"key":"6","unstructured":"[6] Y. Liu, M. Ott, N. Goyal, et al., \u201cRoberta: A robustly optimized bert pretraining approach,\u201d arXiv preprint arXiv:1907.11692, 2019."},{"key":"7","doi-asserted-by":"crossref","unstructured":"[7] Z. Khan and Y. Fu, \u201cExploiting BERT for multimodal target sentiment classification through input space translation,\u201d Proc. 29th ACM International Conference on Multimedia, pp.3034-3042, 2021. 10.1145\/3474085.3475692","DOI":"10.1145\/3474085.3475692"},{"key":"8","doi-asserted-by":"crossref","unstructured":"[8] Y. Ling and R. Xia, \u201cVision-language pre-training for multimodal aspect-based sentiment analysis,\u201d arXiv preprint arXiv:2204.07955, 2022.","DOI":"10.18653\/v1\/2022.acl-long.152"},{"key":"9","unstructured":"[9] T. Chen, D. Borth, T. Darrell, et al., \u201cDeepsentibank: Visual sentiment concept classification with deep convolutional neural networks,\u201d arXiv preprint arXiv:1410.8586, 2014."},{"key":"10","unstructured":"[10] D. Tang, B. Qin, X. Feng, et al., \u201cEffective LSTMs for target-dependent sentiment classification,\u201d arXiv preprint arXiv:1512.01100, 2015."},{"key":"11","unstructured":"[11] A. Vaswani, N. Shazeer, N. Parmar, et al., \u201cAttention is all you need,\u201d Advances in neural information processing systems, 30, 2017."},{"key":"12","doi-asserted-by":"crossref","unstructured":"[12] D. Ma, S. Li, X. Zhang, et al., \u201cInteractive attention networks for aspect-level sentiment classification,\u201d arXiv preprint arXiv:1709.00893, 2017.","DOI":"10.24963\/ijcai.2017\/568"},{"key":"13","doi-asserted-by":"crossref","unstructured":"[13] F. Fan, Y. Feng, and D. Zhao, \u201cMulti-grained attention network for aspect-level sentiment classification,\u201d Proc. 2018 conference on empirical methods in natural language processing, pp.3433-3442, 2018. 10.18653\/v1\/d18-1380","DOI":"10.18653\/v1\/D18-1380"},{"key":"14","doi-asserted-by":"crossref","unstructured":"[14] X. Li, L. Bing, and W. Zhang, et al., \u201cExploiting BERT for end-to-end aspect-based sentiment analysis,\u201d arXiv preprint arXiv:1910.00883, 2019.","DOI":"10.18653\/v1\/D19-5505"},{"key":"15","unstructured":"[15] C. Sun, L. Huang, and X. Qiu, \u201cUtilizing BERT for aspect-based sentiment analysis via constructing auxiliary sentence,\u201d Proc. 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pp.380-385, 2019."},{"key":"16","doi-asserted-by":"crossref","unstructured":"[16] S. Liang, W. Wei, X.L. Mao, et al., \u201cBiSyn-GAT+: Bi-syntax aware graph attention network for aspect-based sentiment analysis,\u201d arXiv preprint arXiv:2204.03117, 2022.","DOI":"10.18653\/v1\/2022.findings-acl.144"},{"key":"17","doi-asserted-by":"crossref","unstructured":"[17] H. Chen, Z. Zhai, F. Feng, et al., \u201cEnhanced multi-channel graph convolutional network for aspect sentiment triplet extraction,\u201d Proc. 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp.2974-2985, 2022. 10.18653\/v1\/2022.acl-long.212","DOI":"10.18653\/v1\/2022.acl-long.212"},{"key":"18","doi-asserted-by":"crossref","unstructured":"[18] Q. You, J. Luo, H. Jin, and J. Yang, \u201cJoint visual-textual sentiment analysis with deep neural networks,\u201d Proc. 23rd ACM international conference on Multimedia, pp.1071-1074, 2015. 10.1145\/2733373.2806284","DOI":"10.1145\/2733373.2806284"},{"key":"19","doi-asserted-by":"crossref","unstructured":"[19] A. Zadeh, M. Chen, S. Poria, E. Cambria, and L.-P. Morency, \u201cTensor Fusion Network for Multimodal Sentiment Analysis,\u201d EMNLP 2017, 2017. 10.18653\/v1\/d17-1115","DOI":"10.18653\/v1\/D17-1115"},{"key":"20","doi-asserted-by":"crossref","unstructured":"[20] A. Zadeh, P.P. Liang, S. Poria, E. Cambria, and L.P. Morency, \u201cMemory fusion network for multimodal sentiment analysis,\u201d AAAI 2018, 2018.","DOI":"10.1609\/aaai.v32i1.12021"},{"key":"21","doi-asserted-by":"crossref","unstructured":"[21] Y.-H.H. Tsai, S. Bai, P.P. Liang, J.Z. Kolter, L.-P. Morency, and R. Salakhutdinov, \u201cMultimodal Transformer for Unaligned Multimodal Language Sequences,\u201d ACL 2019, 2019. 10.18653\/v1\/p19-1656","DOI":"10.18653\/v1\/P19-1656"},{"key":"22","doi-asserted-by":"crossref","unstructured":"[22] H. Yan, J. Dai, X. Qiu, et al., \u201cA unified generative framework for aspect-based sentiment analysis,\u201d arXiv preprint arXiv:2106.04300, 2021.","DOI":"10.18653\/v1\/2021.acl-long.188"},{"key":"23","doi-asserted-by":"crossref","unstructured":"[23] M. Lewis, Y. Liu, N. Goyal, et al., \u201cBart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension,\u201d arXiv preprint arXiv:1910.13461, 2019.","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"24","doi-asserted-by":"crossref","unstructured":"[24] L. Yang, J.C. Na, and J. Yu, \u201cCross-modal multitask transformer for end-to-end multimodal aspect-based sentiment analysis,\u201d Information Processing & Management, vol.59, no.5, 103038, 2022.","DOI":"10.1016\/j.ipm.2022.103038"},{"key":"25","doi-asserted-by":"crossref","unstructured":"[25] J. Yu and J. Jiang, \u201cAdapting BERT for target-oriented multimodal sentiment classification,\u201d IJCAI, pp.5408-5414, 2019. 10.24963\/ijcai.2019\/751","DOI":"10.24963\/ijcai.2019\/751"},{"key":"26","doi-asserted-by":"crossref","unstructured":"[26] M. Hu, Y. Peng, Z. Huang, et al., \u201cOpen-domain targeted sentiment analysis via span-based extraction and classification,\u201d arXiv preprint arXiv:1906.03820, 2019.","DOI":"10.18653\/v1\/P19-1051"},{"key":"27","doi-asserted-by":"crossref","unstructured":"[27] G. Chen, Y. Tian, and Y. Song, \u201cJoint aspect extraction and sentiment analysis with directional graph convolutional networks,\u201d Proc. 28th international conference on computational linguistics, pp.272-279, 2020. 10.18653\/v1\/2020.coling-main.24","DOI":"10.18653\/v1\/2020.coling-main.24"},{"key":"28","unstructured":"[28] Y. Liu, M. Ott, N. Goyal, et al., \u201cRoberta: A robustly optimized bert pretraining approach,\u201d arXiv preprint arXiv:1907.11692, 2019."},{"key":"29","doi-asserted-by":"crossref","unstructured":"[29] J. Yu, J. Jiang, L. Yang, and R. Xia, \u201cImproving multimodal named entity recognition via entity span detection with unified multimodal transformer,\u201d Association for Computational Linguistics, 2020. 10.18653\/v1\/2020.acl-main.306","DOI":"10.18653\/v1\/2020.acl-main.306"},{"key":"30","doi-asserted-by":"crossref","unstructured":"[30] Z. Wu, C. Zheng, Y. Cai, J. Chen, H.-F. Leung, and Q. Li, \u201cMultimodal representation with embedded visual guiding objects for named entity recognition in social media posts,\u201d Proc. 28th ACM International Conference on Multimedia, pp.1038-1046, 2020. 10.1145\/3394171.3413650","DOI":"10.1145\/3394171.3413650"}],"container-title":["IEICE Transactions on Information and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E108.D\/12\/E108.D_2024EDP7313\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T03:27:33Z","timestamp":1764991653000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E108.D\/12\/E108.D_2024EDP7313\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,1]]},"references-count":30,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2025]]}},"URL":"https:\/\/doi.org\/10.1587\/transinf.2024edp7313","relation":{},"ISSN":["0916-8532","1745-1361"],"issn-type":[{"type":"print","value":"0916-8532"},{"type":"electronic","value":"1745-1361"}],"subject":[],"published":{"date-parts":[[2025,12,1]]},"article-number":"2024EDP7313"}}