{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T01:40:05Z","timestamp":1750815605608,"version":"3.41.0"},"reference-count":44,"publisher":"Oxford University Press (OUP)","issue":"6","license":[{"start":{"date-parts":[[2024,12,16]],"date-time":"2024-12-16T00:00:00Z","timestamp":1734307200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62361027","62161011"],"award-info":[{"award-number":["62361027","62161011"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Research and Development Plan of Jiangxi Provincial Science and Technology Department","award":["20223BBE51036"],"award-info":[{"award-number":["20223BBE51036"]}]},{"name":"Humanity and Social Science Fund of Ministry of Education of China","award":["23YJA870005"],"award-info":[{"award-number":["23YJA870005"]}]},{"name":"Humanity and Social Science Foundation of the Jiangxi Province","award":["22TQ01"],"award-info":[{"award-number":["22TQ01"]}]},{"name":"Science and Technology Projects of Jiangxi Provincial Department of Education","award":["GJJ2200640","GJJ2200654"],"award-info":[{"award-number":["GJJ2200640","GJJ2200654"]}]},{"name":"Humanity and Social Science Foundation of Jiangxi University","award":["TQ22102"],"award-info":[{"award-number":["TQ22102"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,12]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Accurately identifying the emotions in images is crucial for sentiment content analysis. To detect local sentiment regions and acquire discriminative sentiment features, we propose a novel model named Distillation-guided and Contrastive-enhanced Sentiment Region Localization Network (DC-SRLN) to effectively complete image sentiment analysis. Two smart but heterogeneous SRLNs are designed first to pursue local sentiment regions. Then an innovative contrastive learning mode is implemented between global and local features to further enhance the discriminative ability of the sentiment features. Third, the enhanced global and local sentiment features are seamlessly integrated to guide each SRLN accurately capture local sentiment regions. Finally, an adaptive feature fusion module is created to fuse the heterogeneous features from the two SRLNs and generate a new multi-view multi-granularity sentiment semantics with more discriminative ability for image sentiment analysis. Extensive experimental results on three prevailing datasets, namely Twitter I, FI, and ArtPhoto, exhibit that DC-SRLN achieves satisfactory accuracies of 93.2%, 80.6%, and 78.7%, respectively, outperforming recent state-of-the-art baselines. Moreover, DC-SRLN needs less training time, demonstrating its high practicality. The code of DC-SRLN is freely available at https:\/\/github.com\/Riley6868\/DC-SRLN.<\/jats:p>","DOI":"10.1093\/comjnl\/bxae133","type":"journal-article","created":{"date-parts":[[2024,12,16]],"date-time":"2024-12-16T12:17:24Z","timestamp":1734351444000},"page":"577-590","source":"Crossref","is-referenced-by-count":0,"title":["Image sentiment analysis based on distillation and sentiment region localization network"],"prefix":"10.1093","volume":"68","author":[{"given":"Hongbin","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Information and Software Engineering , East China Jiaotong University, 808 Shuanggang East Street, Nanchang Economic and Technological Development Zone, Jiangxi Province,","place":["China"]}]},{"given":"Ya","family":"Feng","sequence":"additional","affiliation":[{"name":"School of Information and Software Engineering , East China Jiaotong University, 808 Shuanggang East Street, Nanchang Economic and Technological Development Zone, Jiangxi Province,","place":["China"]}]},{"given":"Meng","family":"Yuan","sequence":"additional","affiliation":[{"name":"School of Information and Software Engineering , East China Jiaotong University, 808 Shuanggang East Street, Nanchang Economic and Technological Development Zone, Jiangxi Province,","place":["China"]}]},{"given":"Jingyi","family":"Hou","sequence":"additional","affiliation":[{"name":"School of Information and Software Engineering , East China Jiaotong University, 808 Shuanggang East Street, Nanchang Economic and Technological Development Zone, Jiangxi Province,","place":["China"]}]},{"given":"Jin","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Information and Software Engineering , East China Jiaotong University, 808 Shuanggang East Street, Nanchang Economic and Technological Development Zone, Jiangxi Province,","place":["China"]}]},{"given":"Guangli","family":"Li","sequence":"additional","affiliation":[{"name":"School of Information and Software Engineering , East China Jiaotong University, 808 Shuanggang East Street, Nanchang Economic and Technological Development Zone, Jiangxi Province,","place":["China"]}]}],"member":"286","published-online":{"date-parts":[[2024,12,16]]},"reference":[{"key":"2025062421055272400_ref1","article-title":"Visual-textual sentiment analysis in product reviews","author":"Ye","year":"2019","journal-title":"Processing of IEEE International Confe rence on Image"},{"key":"2025062421055272400_ref2","first-page":"2003","article-title":"Survey of expression action unit recognition based on deep learning","volume":"50","author":"Shao","year":"2022","journal-title":"Acta Electron Sin"},{"key":"2025062421055272400_ref3","doi-asserted-by":"crossref","first-page":"2945","DOI":"10.1145\/3394171.3413776","article-title":"Emotion-based end-to-end matching between image and music in valence-arousal space","volume-title":"Proceedings of the 28th ACM International Conference on Multimedia","author":"Zhao","year":"2020"},{"key":"2025062421055272400_ref4","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1145\/3065386","article-title":"Imagenet classification with deep convolutional neural networks","volume":"60","author":"Krizhevsky","year":"2017","journal-title":"Commun ACM"},{"article-title":"Very deep convolutional networks for large-scale image recognition","year":"2015","author":"Simonyan","key":"2025062421055272400_ref5"},{"key":"2025062421055272400_ref6","first-page":"770","article-title":"Deep residual learning for image recognition","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"He","year":"2016"},{"key":"2025062421055272400_ref7","doi-asserted-by":"publisher","first-page":"1440","DOI":"10.1049\/iet-ipr.2019.1270","article-title":"Survey on visual sentiment analysis","volume":"14","author":"Ortis","year":"2020","journal-title":"IET Image Process"},{"key":"2025062421055272400_ref8","doi-asserted-by":"publisher","first-page":"576","DOI":"10.1016\/j.jvcir.2018.12.032","article-title":"Affective image classification by jointly using interpretable art features and semantic annotations","volume":"58","author":"Liu","year":"2019","journal-title":"J Vis Commun Image Represent"},{"key":"2025062421055272400_ref9","doi-asserted-by":"publisher","first-page":"429","DOI":"10.1016\/j.neucom.2018.12.053","article-title":"Multi-level region-based convolutional neural network for image emotion classification","volume":"333","author":"Rao","year":"2019","journal-title":"Neurocomputing"},{"key":"2025062421055272400_ref10","doi-asserted-by":"publisher","first-page":"105245","DOI":"10.1016\/j.knosys.2019.105245","article-title":"Object semantics sentiment correlation analysis enhanced image sentiment classification","volume":"191","author":"Zhang","year":"2020","journal-title":"Knowl-Based Syst"},{"key":"2025062421055272400_ref11","doi-asserted-by":"publisher","first-page":"2043","DOI":"10.1007\/s11063-019-10033-9","article-title":"Learning multi-level deep representations for image emotion classification","volume":"51","author":"Rao","year":"2020","journal-title":"Neural Process Lett"},{"key":"2025062421055272400_ref12","doi-asserted-by":"publisher","first-page":"1358","DOI":"10.1109\/TMM.2019.2939744","article-title":"WSCNet: weakly supervised coupled networks for visual sentiment classification and detection","volume":"22","author":"She","year":"2019","journal-title":"IEEE Trans Multimed"},{"key":"2025062421055272400_ref13","doi-asserted-by":"publisher","first-page":"7432","DOI":"10.1109\/TIP.2021.3106813","article-title":"Stimuli-aware visual emotion analysis","volume":"30","author":"Yang","year":"2021","journal-title":"IEEE Trans Image Process"},{"key":"2025062421055272400_ref14","doi-asserted-by":"publisher","first-page":"818","DOI":"10.1093\/comjnl\/bxaa112","article-title":"Weakly supervised sentiment-specific region discovery for VSA","volume":"65","author":"Xue","year":"2022","journal-title":"Comput J"},{"key":"2025062421055272400_ref15","article-title":"Image sentiment analysis via multi-head data augmentation and multi-granularity semantics mining","volume":"39","author":"Hongbin","year":"2024","journal-title":"Control Decision"},{"key":"2025062421055272400_ref16","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1016\/j.neucom.2021.10.062","article-title":"Image sentiment classification via multi-level sentiment region correlation analysis","volume":"469","author":"Zhang","year":"2022","journal-title":"Neurocomputing"},{"key":"2025062421055272400_ref17","doi-asserted-by":"publisher","first-page":"2403","DOI":"10.1093\/comjnl\/bxae061","article-title":"Thematic editorial: Sentiment analysis","volume":"67","author":"Manolopoulos","year":"2024","journal-title":"Comput J"},{"key":"2025062421055272400_ref18","doi-asserted-by":"publisher","first-page":"2230","DOI":"10.1093\/comjnl\/bxae002","article-title":"Multimodal sentiment analysis based on composite hierarchical fusion","volume":"67","author":"Lei","year":"2024","journal-title":"Comput J"},{"key":"2025062421055272400_ref19","doi-asserted-by":"publisher","first-page":"4014","DOI":"10.1109\/TMM.2020.3035277","article-title":"Image-text multimodal emotion classification via multi-view attentional network","volume":"23","author":"Yang","year":"2020","journal-title":"IEEE Trans Multimed"},{"key":"2025062421055272400_ref20","first-page":"569","article-title":"Image-text aspect emotion recognition based on joint aspect attention interaction","volume":"50","author":"Zhao","year":"2022","journal-title":"J Beijing Univ Aeronaut Astronaut"},{"key":"2025062421055272400_ref21","article-title":"Image-text fusion sentiment analysis method based on image semantic translation","volume":"59","author":"Jian","year":"2023","journal-title":"J Comput Eng Appl"},{"key":"2025062421055272400_ref22","doi-asserted-by":"publisher","first-page":"296","DOI":"10.1016\/j.inffus.2022.07.006","article-title":"Deep emotional arousal network for multimodal sentiment analysis and emotion recognition","volume":"88","author":"Zhang","year":"2022","journal-title":"Inf Fusion"},{"key":"2025062421055272400_ref23","doi-asserted-by":"publisher","first-page":"108598","DOI":"10.1016\/j.compeleceng.2023.108598","article-title":"Cross-modal dynamic sentiment annotation for speech sentiment analysis","volume":"106","author":"Chen","year":"2023","journal-title":"Comput Electr Eng"},{"key":"2025062421055272400_ref24","doi-asserted-by":"publisher","first-page":"1169","DOI":"10.1007\/s41095-023-0389-6","article-title":"Learning to compose diversified prompts for image emotion classification","volume":"10","author":"Deng","year":"2024","journal-title":"Comput Vis Media"},{"key":"2025062421055272400_ref25","doi-asserted-by":"publisher","DOI":"10.14569\/IJACSA.2024.0150290","article-title":"Cross-modal sentiment analysis based on clip image-text attention interaction","volume":"15","author":"Lu","year":"2024","journal-title":"Int J Adv Comput Sci Appl"},{"key":"2025062421055272400_ref26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1609\/aaai.v29i1.9179","article-title":"Robust image sentiment analysis using progressively trained and domain transferred deep networks","volume":"29","author":"You","year":"2015","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"2025062421055272400_ref27","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1016\/j.asoc.2019.03.017","article-title":"Novel framework for image attribute annotation with gene selection xgboost algorithm and relative attribute model","volume":"80","author":"Zhang","year":"2019","journal-title":"Appl Soft Comput"},{"key":"2025062421055272400_ref28","doi-asserted-by":"publisher","first-page":"1984","DOI":"10.1109\/TIFS.2016.2569061","article-title":"Discriminant correlation analysis: real-time feature level fusion for multimodal biometric recognition","volume":"11","author":"Haghighat","year":"2016","journal-title":"IEEE Trans Inf Forensics Secur"},{"key":"2025062421055272400_ref29","first-page":"6383","article-title":"Large-scale sparse kernel canonical correlation analysis","volume-title":"International Conference on Machine Learning","author":"Uurtio","year":"2019"},{"key":"2025062421055272400_ref30","first-page":"642","article-title":"Wildcat: Weakly supervised learning of deep convnets for image classification, pointwise localization and segmentation","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Durand","year":"2017"},{"key":"2025062421055272400_ref31","first-page":"1","article-title":"Smile, be happy: emoji embedding for visual sentiment analysis","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops","author":"Al-Halah","year":"2019"},{"key":"2025062421055272400_ref32","doi-asserted-by":"publisher","first-page":"14107","DOI":"10.1007\/s00521-022-07139-y","article-title":"Learning multi-level representations for affective image recognition","volume":"34","author":"Zhang","year":"2022","journal-title":"Neural Comput Appl"},{"key":"2025062421055272400_ref33","first-page":"203","article-title":"Hierarchical graph convolutional network for image sentiment analysis","volume":"50","author":"Tan","year":"2023","journal-title":"Comput Sci"},{"key":"2025062421055272400_ref34","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1609\/aaai.v30i1.9987","article-title":"Building a large scale dataset for image emotion recognition: the fine print and the benchmark","volume":"30","author":"You","year":"2016","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"2025062421055272400_ref35","article-title":"Image sentiment analysis via active sample refinement and cross-modal semantics mining","volume":"37","author":"Hongbing","year":"2022","journal-title":"Control Decision"},{"key":"2025062421055272400_ref36","doi-asserted-by":"publisher","first-page":"1691","DOI":"10.1587\/transinf.2020EDP7218","article-title":"Image emotion recognition using visual and semantic features reflecting emotional and similar objects","volume":"E104.D","author":"Yamamoto","year":"2021","journal-title":"IEICE Trans Inf Syst"},{"key":"2025062421055272400_ref37","first-page":"9479","article-title":"Mdan: Multi-level dependent attention network for visual emotion analysis","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Xu","year":"2022"},{"key":"2025062421055272400_ref38","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1145\/1873951.1873965","article-title":"Affective image classification using features inspired by psychology and art theory","volume-title":"Proceedings of the 18th ACM International Conference on Multimedia","author":"Machajdik","year":"2010"},{"key":"2025062421055272400_ref39","doi-asserted-by":"crossref","first-page":"192","DOI":"10.1145\/3343031.3351062","article-title":"PDANet: polarity-consistent deep attention network for fine-grained visual emotion regression","volume-title":"Proceedings of the 27th ACM International Conference on Multimedia","author":"Zhao","year":"2019"},{"key":"2025062421055272400_ref40","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13640-019-0433-8","article-title":"Region-based convolutional neural network using group sparse regularization for image sentiment classification","volume":"2019","author":"Xiong","year":"2019","journal-title":"EURASIP J Image Video Process"},{"key":"2025062421055272400_ref41","doi-asserted-by":"publisher","first-page":"103619","DOI":"10.1109\/ACCESS.2020.2999128","article-title":"Multidimensional extra evidence mining for image sentiment analysis","volume":"8","author":"Zhang","year":"2020","journal-title":"IEEE Access"},{"key":"2025062421055272400_ref42","doi-asserted-by":"crossref","first-page":"459","DOI":"10.1145\/2502081.2502268","article-title":"SentiBank: large-scale ontology and classifiers for detecting sentiment and emotions in visual content","volume-title":"Proceedings of the 21st ACM International Conference on Multimedia","author":"Borth","year":"2013"},{"key":"2025062421055272400_ref43","first-page":"3595","article-title":"Dependency exploitation: a unified cnn-rnn approach for visual emotion recognition","volume-title":"IJCAI","author":"Zhu","year":"2017"},{"article-title":"DeepSentiBank: visual sentiment concept classification with deep convolutional neural networks","year":"2014","author":"Chen","key":"2025062421055272400_ref44"}],"container-title":["The Computer Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/comjnl\/article-pdf\/68\/6\/577\/61196077\/bxae133.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/comjnl\/article-pdf\/68\/6\/577\/61196077\/bxae133.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T01:06:01Z","timestamp":1750813561000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/comjnl\/article\/68\/6\/577\/7925233"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,16]]},"references-count":44,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2024,12,16]]},"published-print":{"date-parts":[[2025,6,12]]}},"URL":"https:\/\/doi.org\/10.1093\/comjnl\/bxae133","relation":{},"ISSN":["0010-4620","1460-2067"],"issn-type":[{"type":"print","value":"0010-4620"},{"type":"electronic","value":"1460-2067"}],"subject":[],"published-other":{"date-parts":[[2025,6]]},"published":{"date-parts":[[2024,12,16]]}}}