{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T06:34:10Z","timestamp":1763102050831,"version":"3.45.0"},"reference-count":58,"publisher":"Tech Science Press","issue":"3","license":[{"start":{"date-parts":[[2025,3,16]],"date-time":"2025-03-16T00:00:00Z","timestamp":1742083200000},"content-version":"vor","delay-in-days":74,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.32604\/TSP-CROSSMARKPOLICY"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["CMC"],"published-print":{"date-parts":[[2025]]},"DOI":"10.32604\/cmc.2025.059102","type":"journal-article","created":{"date-parts":[[2025,2,18]],"date-time":"2025-02-18T02:51:42Z","timestamp":1739847102000},"page":"5285-5306","update-policy":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.32604\/tsp-crossmarkpolicy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-Scale Feature Fusion and Advanced Representation Learning for Multi Label Image Classification"],"prefix":"10.32604","volume":"82","author":[{"given":"Naikang","family":"Zhong","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiao","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wen","family":"Du","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jin","family":"Shi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"17807","published-online":{"date-parts":[[2025]]},"reference":[{"key":"ref1","doi-asserted-by":"crossref","first-page":"1081","DOI":"10.32604\/csse.2023.026128","article-title":"Deep learning with optimal hierarchical spiking neural network for medical image classification","volume":"44","author":"Jenifer","year":"2023","journal-title":"Comput Syst Sci Eng"},{"key":"ref2","first-page":"5313","article-title":"Research on multi-scale feature fusion network algorithm based on brain tumor medical image classification","volume":"79","author":"Zhou","year":"2024","journal-title":"Comput Mater Contin"},{"key":"ref3","series-title":"2018 IEEE International Conference on Multimedia and Expo (ICME)","first-page":"1","article-title":"MSGC: a new bottom-up model for salient object detection","author":"Wang","year":"2018"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"287","DOI":"10.1007\/s11390-019-1911-2","article-title":"CATIRI: an efficient method for content-and-text based image retrieval","volume":"34","author":"Zeng","year":"2019","journal-title":"J Comput Sci Tech"},{"key":"ref5","first-page":"3489","article-title":"Fusion of hash-based hard and soft biometrics for enhancing face image database search and retrieval","volume":"77","author":"Alshahrani","year":"2023","journal-title":"Comput Mater Contin"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1016\/j.cag.2023.08.010","article-title":"Image deraining based on dual-channel component decomposition","volume":"116","author":"Lin","year":"2023","journal-title":"Comput Graph"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"1901","DOI":"10.1109\/TPAMI.2015.2491929","article-title":"HCP: a flexible CNN framework for multi-label image classification","volume":"38","author":"Wei","year":"2015","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref8","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"280","article-title":"Exploit bounding box annotations for multi-label object recognition","author":"Yang","year":"2016 Jun 27\u201330"},{"key":"ref9","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"729","article-title":"Visual attention consistency under image transforms for multi-label image classification","author":"Guo","year":"2019 Jun 15\u201320"},{"key":"ref10","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"12755","article-title":"Contextual debiasing for visual recognition with causal mechanisms","author":"Liu","year":"2022 Jun 18\u201324"},{"key":"ref11","series-title":"Computer Vision\u2014ECCV 2020, 16th European Conference on Computer Vision","first-page":"649","article-title":"Attention-driven dynamic graph convolutional network for multi-label image recognition","author":"Ye","year":"2020 Aug 23\u201328"},{"key":"ref12","first-page":"9092","article-title":"Modular graph transformer networks for multi-label image classification","volume":"35","author":"Nguyen","year":"2021","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref13","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"5177","article-title":"Multi-label image recognition with graph convolutional networks","author":"Chen","year":"2019 Jun 15\u201320"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"109203","DOI":"10.1016\/j.patcog.2022.109203","article-title":"Feature learning network with transformer for multi-label image classification","volume":"136","author":"Zhou","year":"2023","journal-title":"Pattern Recognit"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"342","DOI":"10.1109\/TCSVT.2023.3284812","article-title":"DATran: dual attention transformer for multi-label image classification","volume":"34","author":"Zhou","year":"2024","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"ref16","first-page":"12709","article-title":"Cross-modality attention with semantic graph embedding for multi-label classification","volume":"34","author":"You","year":"2020","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref17","unstructured":"Liu S, Zhang L, Yang X, Su H, Zhu J. Query2label: a simple transformer way to multi-label classification. arXiv:2107.10834. 2021."},{"key":"ref18","series-title":"Proceedings of the IEEE International Conference on Computer Vision","first-page":"464","article-title":"Multi-label image recognition by recurrently discovering attentional regions","author":"Wang","year":"2017 Oct 22\u201329"},{"key":"ref19","series-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision","first-page":"32","article-title":"Ml-decoder: scalable and versatile classification head","author":"Ridnik","year":"2023 Jan 2\u20137"},{"key":"ref20","unstructured":"Kipf TN, Welling M. Semi-supervised classification with graph convolutional networks. arXiv:1609.02907. 2016."},{"key":"ref21","first-page":"1","article-title":"Multi-label image classification model based on multiscale fusion and adaptive label correlation","volume":"34","author":"Ye","year":"2024","journal-title":"J Shanghai Jiaotong Univ"},{"key":"ref22","series-title":"Proceedings of NAACL-HLT","first-page":"2","article-title":"Bert: pre-training of deep bidirectional transformers for language understanding","volume":"1","author":"Kenton","year":"2019 Jun 2\u20137"},{"key":"ref23","unstructured":"Yang Z. XLNet: generalized autoregressive pretraining for language understanding. arXiv:1906.08237. 2019."},{"key":"ref24","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J Mach Learn Res"},{"key":"ref25","unstructured":"Alexey D. An image is worth 16 \u00d7 16 words: transformers for image recognition at scale. arXiv:2010.11929. 2020."},{"key":"ref26","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"10012","article-title":"Swin transformer: hierarchical vision transformer using shifted windows","author":"Liu","year":"2021 Oct 11\u201317"},{"key":"ref27","series-title":"Proceedings of the 38th International Conference on Machine Learning","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","author":"Touvron","year":"2021 Jul 18\u201324"},{"key":"ref28","first-page":"12077","article-title":"SegFormer: simple and efficient design for semantic segmentation with transformers","volume":"34","author":"Xie","year":"2021","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref29","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016 Jun 27\u201330"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"1862","DOI":"10.1049\/ipr2.13068","article-title":"MSFA: multi-stage feature aggregation network for multi-label image recognition","volume":"18","author":"Chen","year":"2024","journal-title":"IET Image Process"},{"key":"ref31","doi-asserted-by":"crossref","first-page":"1143","DOI":"10.1109\/TMM.2023.3277279","article-title":"Mining semantic information with dual relation graph network for multi-label image classification","volume":"26","author":"Zhou","year":"2023","journal-title":"IEEE Trans Multimed"},{"key":"ref32","doi-asserted-by":"crossref","first-page":"924","DOI":"10.1109\/TCSVT.2023.3288205","article-title":"Transformer driven matching selection mechanism for multi-label image classification","volume":"34","author":"Wu","year":"2024","journal-title":"IEEE Trans Circ Syst Video Technol"},{"key":"ref33","doi-asserted-by":"crossref","first-page":"104062","DOI":"10.1016\/j.cviu.2024.104062","article-title":"Multi-label image classification using adaptive graph convolutional networks: from a single domain to multiple domains","volume":"247","author":"Singh","year":"2024","journal-title":"Comput Vis Image Underst"},{"key":"ref34","series-title":"11th International Conference on Learning Representations","article-title":"Causality compensated attention for contextual biased visual recognition","author":"Liu","year":"2023 May 1\u20135"},{"key":"ref35","first-page":"1","article-title":"Double attention based on graph attention network for image multi-label classification","volume":"19","author":"Zhou","year":"2023","journal-title":"ACM Trans Multimed Comput Commun Appl"},{"key":"ref36","doi-asserted-by":"crossref","first-page":"126605","DOI":"10.1016\/j.neucom.2023.126605","article-title":"Contrastively enforcing distinctiveness for multi-label image classification","volume":"555","author":"Dao","year":"2023","journal-title":"Neurocomputing"},{"key":"ref37","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"5513","article-title":"Learning spatial regularization with image-level supervisions for multi-label image classification","author":"Zhu","year":"2017 Jul 21\u201326"},{"key":"ref38","series-title":"Proceedings of the 26th ACM International Conference on Multimedia","first-page":"700","article-title":"Multi-label image classification via knowledge distillation from weakly-supervised detection","author":"Liu","year":"2018 Oct"},{"key":"ref39","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1016\/j.neucom.2023.01.018","article-title":"Semantic representation and dependency learning for multi-label image recognition","volume":"526","author":"Pu","year":"2023","journal-title":"Neurocomputing"},{"key":"ref40","first-page":"6730","article-title":"Recurrent attentional reinforcement learning for multi-label image recognition","volume":"32","author":"Chen","year":"2018","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref41","unstructured":"Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556. 2014."},{"key":"ref42","doi-asserted-by":"crossref","first-page":"5920","DOI":"10.1109\/TIP.2021.3088605","article-title":"Learning to discover multi-class attentional regions for multi-label image recognition","volume":"30","author":"Gao","year":"2021","journal-title":"IEEE Trans Image Process"},{"key":"ref43","series-title":"2019 IEEE International Conference on Multimedia and Expo (ICME)","first-page":"622","article-title":"Multi-label image recognition with joint class-aware map disentangling and label correlation embedding","author":"Chen","year":"2019 Jul 8\u201312"},{"key":"ref44","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"522","article-title":"Learning semantic-specific graph representation for multi-label image recognition","author":"Chen","year":"2019 Oct 27\u2013Nov 2"},{"key":"ref45","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"16478","article-title":"General multi-label image classification with transformers","author":"Lanchantin","year":"2021 Jun 20\u201325"},{"key":"ref46","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"163","article-title":"Transformer-based dual relation graph for multi-label image recognition","author":"Zhao","year":"2021 Oct 11\u201317"},{"key":"ref47","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"2285","article-title":"Cnn-rnn: a unified framework for multi-label image classification","author":"Wang","year":"2016 Jun 27\u201330"},{"key":"ref48","doi-asserted-by":"crossref","first-page":"1371","DOI":"10.1109\/TPAMI.2020.3025814","article-title":"Knowledge-guided multi-label few-shot learning for general image recognition","volume":"44","author":"Chen","year":"2020","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref49","doi-asserted-by":"crossref","first-page":"6969","DOI":"10.1109\/TPAMI.2021.3063496","article-title":"Learning graph convolutional networks for multi-label recognition and applications","volume":"45","author":"Chen","year":"2021","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref50","doi-asserted-by":"crossref","first-page":"103448","DOI":"10.1016\/j.jvcir.2022.103448","article-title":"Learning discriminative representations for multi-label image recognition","volume":"83","author":"Hassanin","year":"2022","journal-title":"J Vis Commun Image Rep"},{"key":"ref51","doi-asserted-by":"crossref","unstructured":"Xu J, Huang S, Zhou F, Huangfu L, Zeng D, Liu B. Boosting multi-label image classification with complementary parallel self-distillation. arXiv:2205.10986. 2022.","DOI":"10.24963\/ijcai.2022\/208"},{"key":"ref52","doi-asserted-by":"crossref","first-page":"1308","DOI":"10.1007\/s12559-021-09977-9","article-title":"An attention-driven multi-label image classification with semantic embedding and graph convolutional networks","volume":"15","author":"Sun","year":"2023","journal-title":"Cognit Comput"},{"key":"ref53","first-page":"3572","article-title":"Deep semantic dictionary learning for multi-label image classification","volume":"35","author":"Zhou","year":"2021","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref54","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1016\/j.neucom.2022.03.057","article-title":"A multi-scale semantic attention representation for multi-label image recognition with graph networks","volume":"491","author":"Liang","year":"2022","journal-title":"Neurocomputing"},{"journal-title":"Advances in neural information processing systems","year":"2019","author":"Paszke","key":"ref55"},{"key":"ref56","unstructured":"Loshchilov I. Decoupled weight decay regularization. arXiv:1711.05101. 2017."},{"key":"ref57","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops","first-page":"702","article-title":"Randaugment: practical automated data augmentation with a reduced search space","author":"Cubuk","year":"2020 Jun 14\u201319"},{"key":"ref58","unstructured":"DeVries T. Improved regularization of convolutional neural networks with cutout. arXiv:1708.04552. 2017."}],"container-title":["Computers, Materials & Continua"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/cdn.techscience.cn\/files\/cmc\/2025\/TSP_CMC-82-3\/TSP_CMC_59102\/TSP_CMC_59102.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T06:29:39Z","timestamp":1763101779000},"score":1,"resource":{"primary":{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/www.techscience.com\/cmc\/v82n3\/59887"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":58,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2025]]},"published-print":{"date-parts":[[2025]]}},"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.32604\/cmc.2025.059102","relation":{},"ISSN":["1546-2226"],"issn-type":[{"type":"electronic","value":"1546-2226"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"2024-09-28","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-01-10","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-03-06","order":2,"name":"published","label":"Published Online","group":{"name":"publication_history","label":"Publication History"}}]}}