{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T10:55:21Z","timestamp":1773658521858,"version":"3.50.1"},"reference-count":47,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T00:00:00Z","timestamp":1769644800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T00:00:00Z","timestamp":1769644800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"S&T Program of Hebei","award":["Nos.20375001D and 236Z7725G"],"award-info":[{"award-number":["Nos.20375001D and 236Z7725G"]}]},{"name":"Project of Hebei Key Laboratory of Software Engineering","award":["Nos.22567637H and ZZYB2302"],"award-info":[{"award-number":["Nos.22567637H and ZZYB2302"]}]},{"DOI":"10.13039\/501100003787","name":"Natural Science Foundation of Hebei Province","doi-asserted-by":"publisher","award":["No.F2025203033"],"award-info":[{"award-number":["No.F2025203033"]}],"id":[{"id":"10.13039\/501100003787","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int. J. Mach. Learn. & Cyber."],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1007\/s13042-025-02821-8","type":"journal-article","created":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T14:41:00Z","timestamp":1769697660000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A multi-label image classification method via graph attention network with dynamic and static label correlations"],"prefix":"10.1007","volume":"17","author":[{"given":"Zhiming","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kai","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bingnan","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuchen","family":"Lv","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yihao","family":"He","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dianlong","family":"You","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,1,29]]},"reference":[{"issue":"14","key":"2821_CR1","doi-asserted-by":"publisher","first-page":"4758","DOI":"10.3390\/s21144758","volume":"21","author":"D Ahmedt-Aristizabal","year":"2021","unstructured":"Ahmedt-Aristizabal D, Armin MA, Denman S, Fookes C, Petersson L (2021) Graph-based deep learning for medical diagnosis and analysis: past, present and future. Sensors 21(14):4758. https:\/\/doi.org\/10.3390\/s21144758","journal-title":"Sensors"},{"key":"2821_CR2","doi-asserted-by":"crossref","unstructured":"Guo H, Zheng K, Fan X, Yu H, Wang S (2019) Visual attention consistency under image transforms for multi-label image classification. pp 729\u2013739","DOI":"10.1109\/CVPR.2019.00082"},{"key":"2821_CR3","doi-asserted-by":"publisher","unstructured":"Jia J, Chen X, Huang K (2021) Spatial and semantic consistency regularizations for pedestrian attribute recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 962\u2013971. https:\/\/doi.org\/10.48550\/arXiv.2109.05686","DOI":"10.48550\/arXiv.2109.05686"},{"key":"2821_CR4","doi-asserted-by":"publisher","unstructured":"Tang C, Sheng L, Zhang Z, Hu X (2019) Improving pedestrian attribute recognition with weakly-supervised multi-scale attribute-specific localization. pp 4997\u20135006. https:\/\/doi.org\/10.1109\/ICCV.2019.00510","DOI":"10.1109\/ICCV.2019.00510"},{"key":"2821_CR5","doi-asserted-by":"crossref","unstructured":"Papadopoulos K, Ghorbel E, Aouada D, Ottersten B (2021). Vertex feature encoding and hierarchical temporal modeling in a spatio-temporal graph convolutional network for action recognition. IEEE, pp 452\u2013458","DOI":"10.1109\/ICPR48806.2021.9413189"},{"issue":"9","key":"2821_CR6","doi-asserted-by":"publisher","first-page":"5866","DOI":"10.1109\/TPAMI.2021.3074313","volume":"44","author":"D Zhang","year":"2021","unstructured":"Zhang D, Han J, Cheng G, Yang M-H (2021) Weakly supervised object localization and detection: A survey. IEEE Trans Pattern Anal Mach Intell 44(9):5866\u20135885. https:\/\/doi.org\/10.1109\/TPAMI.2021.3074313","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2821_CR7","doi-asserted-by":"publisher","unstructured":"Wei X-S, Cui Q, Yang L, Wang P, Liu L (2019) Rpc: A large-scale retail product checkout dataset. arXiv preprint arXiv:1901.07249, https:\/\/doi.org\/10.48550\/arXiv.1901.07249","DOI":"10.48550\/arXiv.1901.07249"},{"issue":"5","key":"2821_CR8","doi-asserted-by":"publisher","first-page":"2871","DOI":"10.3390\/app13052871","volume":"13","author":"V Guimar\u00e3es","year":"2023","unstructured":"Guimar\u00e3es V, Nascimento J, Viana P, Carvalho P (2023) A review of recent advances and challenges in grocery label detection and recognition. Appl Sci 13(5):2871","journal-title":"Appl Sci"},{"key":"2821_CR9","doi-asserted-by":"publisher","unstructured":"Chen ZM, Wei XS, Wang P, Guo Yw (2019) Multi-label image recognition with graph convolutional networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5177\u20135186 . https:\/\/doi.org\/10.48550\/arXiv.1904.03582","DOI":"10.48550\/arXiv.1904.03582"},{"key":"2821_CR10","doi-asserted-by":"publisher","first-page":"5920","DOI":"10.1109\/TIP.2021.3088605","volume":"30","author":"B-B Gao","year":"2021","unstructured":"Gao B-B, Zhou H-Y (2021) Learning to discover multi-class attentional regions for multi-label image recognition. IEEE Trans Image Process 30:5920\u20135932. https:\/\/doi.org\/10.1109\/TIP.2021.3088605","journal-title":"IEEE Trans Image Process"},{"key":"2821_CR11","doi-asserted-by":"publisher","unstructured":"Wang Z, Chen T, Li G, Xu R, Lin L (2017) Multi-label image recognition by recurrently discovering attentional regions. pp 464\u2013472. https:\/\/doi.org\/10.1109\/ICCV.2017.58","DOI":"10.1109\/ICCV.2017.58"},{"key":"2821_CR12","doi-asserted-by":"publisher","unstructured":"Wang J, Yang Y, Mao J, Huang Z, Huang C, Xu W (2016) Cnn-rnn: A unified framework for multi-label image classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2285\u20132294. https:\/\/doi.org\/10.48550\/arXiv.1604.04573","DOI":"10.48550\/arXiv.1604.04573"},{"key":"2821_CR13","doi-asserted-by":"publisher","unstructured":"Chen S-F, Chen Y-C, Yeh C-K, Wang Y-C (2018) Order-free rnn with visual attention for multi-label classification. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32. https:\/\/doi.org\/10.48550\/arXiv.1707.05495","DOI":"10.48550\/arXiv.1707.05495"},{"key":"2821_CR14","doi-asserted-by":"publisher","unstructured":"Chen T, Xu M, Hui X, Wu H, Lin L (2019) Learning semantic-specific graph representation for multi-label image recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 522\u2013531 . https:\/\/doi.org\/10.48550\/arXiv.1908.07325","DOI":"10.48550\/arXiv.1908.07325"},{"key":"2821_CR15","doi-asserted-by":"publisher","unstructured":"Wang Y, He D, Li F, Long X, Zhou Z, Ma J, Wen S (2020) Multi-label classification with label graph superimposing. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 12265\u201312272. https:\/\/doi.org\/10.48550\/arXiv.1911.09243","DOI":"10.48550\/arXiv.1911.09243"},{"key":"2821_CR16","doi-asserted-by":"crossref","unstructured":"Ye J, He J, Peng X, Wu W, Qiao Y (2020) Attention-driven dynamic graph convolutional network for multi-label image recognition. In: Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XXI 16, pp. 649\u2013665. Springer","DOI":"10.1007\/978-3-030-58589-1_39"},{"key":"2821_CR17","unstructured":"Veli\u010dkovi\u0107 P, Cucurull G, Casanova A, Romero A, Lio P, Bengio Y (2017) Graph attention networks. arXiv preprint arXiv:1710.10903"},{"key":"2821_CR18","doi-asserted-by":"publisher","unstructured":"Ridnik T, Lawen H, Noy A, Ben\u00a0Baruch E, Sharir G, Friedman I (2021) Tresnet: High performance gpu-dedicated architecture. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 1400\u20131409. https:\/\/doi.org\/10.48550\/arXiv.2003.13630","DOI":"10.48550\/arXiv.2003.13630"},{"issue":"1","key":"2821_CR19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40649-019-0069-y","volume":"6","author":"S Zhang","year":"2019","unstructured":"Zhang S, Tong H, Xu J, Maciejewski R (2019) Graph convolutional networks: a comprehensive review. Comput Soc Netw 6(1):1\u201323. https:\/\/doi.org\/10.1186\/s40649-019-0069-y","journal-title":"Comput Soc Netw"},{"key":"2821_CR20","first-page":"9092","volume":"35","author":"HD Nguyen","year":"2021","unstructured":"Nguyen HD, Vu X-S, Le D-T (2021) Modular graph transformer networks for multi-label image classification. Proc AAAI Conf Artif Intell 35:9092\u20139100","journal-title":"Proc AAAI Conf Artif Intell"},{"issue":"12","key":"2821_CR21","doi-asserted-by":"publisher","first-page":"10051","DOI":"10.1007\/s00521-022-06990-3","volume":"34","author":"Y Wang","year":"2022","unstructured":"Wang Y, Xie Y, Fan L, Hu G (2022) Stmg: Swin transformer for multi-label image recognition with graph convolution network. Neural Comput Appl 34(12):10051\u201310063","journal-title":"Neural Comput Appl"},{"issue":"4","key":"2821_CR22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3578518","volume":"19","author":"J Yuan","year":"2023","unstructured":"Yuan J, Chen S, Zhang Y, Shi Z, Geng X, Fan J, Rui Y (2023) Graph attention transformer network for multi-label image classification. ACM Trans Multimed Comput Commun Appl 19(4):1\u201316","journal-title":"ACM Trans Multimed Comput Commun Appl"},{"key":"2821_CR23","doi-asserted-by":"publisher","unstructured":"Zhang J, Zhang Q, Ren J, Zhao Y, Liu J (2022) Spatial-context-aware deep neural network for multi-class image classification. In: ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1960\u20131964. IEEE. https:\/\/doi.org\/10.48550\/arXiv.2111.12296","DOI":"10.48550\/arXiv.2111.12296"},{"key":"2821_CR24","doi-asserted-by":"publisher","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. pp 770\u2013778. https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"2821_CR25","doi-asserted-by":"crossref","unstructured":"Wang Y, Xie Y, Liu Y, Zhou K, Li X (2020) Fast graph convolution network based multi-label image recognition via cross-modal fusion. pp 1575\u20131584","DOI":"10.1145\/3340531.3411880"},{"key":"2821_CR26","doi-asserted-by":"crossref","unstructured":"Ghosh A, Bhattacharya B, Chowdhury SBR (2018) Adgap: Advanced global average pooling. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32","DOI":"10.1609\/aaai.v32i1.12154"},{"key":"2821_CR27","doi-asserted-by":"crossref","unstructured":"Wu T, Huang Q, Liu Z, Wang Y, Lin D (2020) Distribution-balanced loss for multi-label classification in long-tailed datasets. In: Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part IV 16, pp. 162\u2013178. Springer","DOI":"10.1007\/978-3-030-58548-8_10"},{"key":"2821_CR28","doi-asserted-by":"crossref","unstructured":"Durand T, Mehrasa N, Mori G (2019) Learning a deep convnet for multi-label classification with partial labels. pp 647\u2013657","DOI":"10.1109\/CVPR.2019.00074"},{"key":"2821_CR29","doi-asserted-by":"crossref","unstructured":"Zhu F, Li H, Ouyang W, Yu N, Wang X (2017) Learning spatial regularization with image-level supervisions for multi-label image classification. pp. 5513\u20135522","DOI":"10.1109\/CVPR.2017.219"},{"key":"2821_CR30","doi-asserted-by":"publisher","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser \u0141, Polosukhin I (2017) Attention is all you need. Adv Neural Inf Process Syst 30https:\/\/doi.org\/10.48550\/arXiv.1706.03762","DOI":"10.48550\/arXiv.1706.03762"},{"key":"2821_CR31","doi-asserted-by":"publisher","unstructured":"Cheng X, Lin H, Wu X, Shen D, Yang F, Liu H, Shi N (2022) Mltr: Multi-label classification with transformer. In: 2022 IEEE International Conference on Multimedia and Expo (ICME), pp. 1\u20136. IEEE. https:\/\/doi.org\/10.48550\/arXiv.2106.06195","DOI":"10.48550\/arXiv.2106.06195"},{"key":"2821_CR32","doi-asserted-by":"publisher","unstructured":"Ridnik T, Sharir G, Ben-Cohen A, Ben-Baruch E, Noy A (2023) Ml-decoder: Scalable and versatile classification head. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 32\u201341 . https:\/\/doi.org\/10.48550\/arXiv.2111.12933","DOI":"10.48550\/arXiv.2111.12933"},{"key":"2821_CR33","doi-asserted-by":"publisher","unstructured":"Liu S, Zhang L, Yang X, Su H, Zhu J (2021) Query2label: A simple transformer way to multi-label classification. arXiv:2107.10834. https:\/\/doi.org\/10.48550\/arXiv.2107.10834","DOI":"10.48550\/arXiv.2107.10834"},{"key":"2821_CR34","doi-asserted-by":"crossref","unstructured":"Ridnik T, Ben-Baruch E, Zamir N, Noy A, Friedman I, Protter M, Zelnik-Manor L (2021) Asymmetric loss for multi-label classification. pp 82\u201391","DOI":"10.1109\/ICCV48922.2021.00015"},{"key":"2821_CR35","unstructured":"Loshchilov I, Hutter F (2017) Decoupled weight decay regularization. arXiv:1711.05101"},{"key":"2821_CR36","doi-asserted-by":"crossref","unstructured":"Lin T-Y, Goyal P, Girshick R, He K, Doll\u00e1r P (2017) Focal loss for dense object detection pp. 2980\u20132988","DOI":"10.1109\/ICCV.2017.324"},{"key":"2821_CR37","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham M, Van Gool L, Williams CK, Winn J, Zisserman A (2010) The pascal visual object classes (voc) challenge. Int J Comput Vision 88:303\u2013338","journal-title":"Int J Comput Vision"},{"key":"2821_CR38","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1007\/s11263-014-0733-5","volume":"111","author":"M Everingham","year":"2015","unstructured":"Everingham M, Eslami SA, Van Gool L, Williams CK, Winn J, Zisserman A (2015) The pascal visual object classes challenge: A retrospective. Int J Comput Vision 111:98\u2013136","journal-title":"Int J Comput Vision"},{"key":"2821_CR39","doi-asserted-by":"crossref","unstructured":"Lin T-Y, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Doll\u00e1r P, Zitnick CL (2014) Microsoft coco: Common objects in context. In: Computer Vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13, pp. 740\u2013755. Springer","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"2821_CR40","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2025.107309","volume":"187","author":"W Zhou","year":"2025","unstructured":"Zhou W, Lin K, Zheng Z, Chen D, Su T, Hu H (2025) Drtn: Dual relation transformer network with feature erasure and contrastive learning for multi-label image classification. Neural Netw 187:107309","journal-title":"Neural Netw"},{"key":"2821_CR41","doi-asserted-by":"crossref","unstructured":"Liu X, Hu Y (2024) Multi-label image classification based on object detection and dynamic graph convolutional networks. Comput Mater Continua 80(3)","DOI":"10.32604\/cmc.2024.053938"},{"key":"2821_CR42","doi-asserted-by":"crossref","unstructured":"Deng J, Dong W, Socher R, Li L-J, Li K, Fei-Fei L (2009) Imagenet: A large-scale hierarchical image database. Ieee. pp. 248\u2013255","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"2821_CR43","unstructured":"DeVries T, Taylor GW (2017) Improved regularization of convolutional neural networks with cutout. arXiv:1708.04552"},{"key":"2821_CR44","unstructured":"Loshchilov I, Hutter F (2017) Decoupled weight decay regularization arXiv:1711.05101"},{"key":"2821_CR45","doi-asserted-by":"crossref","unstructured":"Cubuk ED, Zoph B, Shlens J, Le QV (2020) Randaugment, Practical automated data augmentation with a reduced search space. pp. 702\u2013703","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"2821_CR46","unstructured":"Sun Y, Dong L, Huang S, Ma S, Xia Y, Xue J, Wang J, Wei F (2023) Retentive network: A successor to transformer for large language models. arXiv:2307.08621"},{"key":"2821_CR47","doi-asserted-by":"crossref","unstructured":"Ding X, Zhang Y, Ge Y, Zhao S, Song L, Yue X, Shan Y (2023) Unireplknet: A universal perception large-kernel convnet for audio, video, point cloud, time-series and image recognition. arXiv:2311.15599","DOI":"10.1109\/CVPR52733.2024.00527"}],"container-title":["International Journal of Machine Learning and Cybernetics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-025-02821-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s13042-025-02821-8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-025-02821-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T09:56:26Z","timestamp":1773654986000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s13042-025-02821-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,29]]},"references-count":47,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,2]]}},"alternative-id":["2821"],"URL":"https:\/\/doi.org\/10.1007\/s13042-025-02821-8","relation":{},"ISSN":["1868-8071","1868-808X"],"issn-type":[{"value":"1868-8071","type":"print"},{"value":"1868-808X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,29]]},"assertion":[{"value":"20 February 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 December 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 January 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no Conflict of interest in this work.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"The authors declare no Conflict of interest.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"46"}}