{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T08:46:30Z","timestamp":1771663590729,"version":"3.50.1"},"reference-count":80,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100012245","name":"Science and Technology Planning Project of Guangdong Province","doi-asserted-by":"publisher","award":["2022B0701180001"],"award-info":[{"award-number":["2022B0701180001"]}],"id":[{"id":"10.13039\/501100012245","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61273270"],"award-info":[{"award-number":["61273270"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["60802069"],"award-info":[{"award-number":["60802069"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61673402"],"award-info":[{"award-number":["61673402"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62076262"],"award-info":[{"award-number":["62076262"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1016\/j.neunet.2025.107309","type":"journal-article","created":{"date-parts":[[2025,3,3]],"date-time":"2025-03-03T16:58:07Z","timestamp":1741021087000},"page":"107309","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":6,"special_numbering":"C","title":["DRTN: Dual Relation Transformer Network with feature erasure and contrastive learning for multi-label image classification"],"prefix":"10.1016","volume":"187","author":[{"given":"Wei","family":"Zhou","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6716-9226","authenticated-orcid":false,"given":"Kang","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhijie","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dihu","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Su","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4884-323X","authenticated-orcid":false,"given":"Haifeng","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2025.107309_b1","doi-asserted-by":"crossref","unstructured":"Arandjelovic, R., Gronat, P., Torii, A., Pajdla, T., & Sivic, J. (2016). NetVLAD: CNN architecture for weakly supervised place recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 5297\u20135307).","DOI":"10.1109\/CVPR.2016.572"},{"key":"10.1016\/j.neunet.2025.107309_b2","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2019.107164","article-title":"Semi-supervised robust deep neural networks for multi-label image classification","volume":"100","author":"Cevikalp","year":"2020","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.neunet.2025.107309_b3","unstructured":"Chen, T., Kornblith, S., Norouzi, M., & Hinton, G. (2020). A simple framework for contrastive learning of visual representations. In International conference on machine learning (pp. 1597\u20131607)."},{"issue":"3","key":"10.1016\/j.neunet.2025.107309_b4","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":"2022","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2025.107309_b5","doi-asserted-by":"crossref","unstructured":"Chen, Z.-M., Wei, X.-S., Wang, P., & Guo, Y. (2019). Multi-label image recognition with graph convolutional networks. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 5177\u20135186).","DOI":"10.1109\/CVPR.2019.00532"},{"key":"10.1016\/j.neunet.2025.107309_b6","doi-asserted-by":"crossref","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 international conference on computer vision (pp. 522\u2013531).","DOI":"10.1109\/ICCV.2019.00061"},{"key":"10.1016\/j.neunet.2025.107309_b7","article-title":"MSFA: Multi-stage feature aggregation network for multi-label image recognition","author":"Chen","year":"2024","journal-title":"IET Image Processing"},{"key":"10.1016\/j.neunet.2025.107309_b8","doi-asserted-by":"crossref","unstructured":"Choe, J., & Shim, H. (2019). Attention-based dropout layer for weakly supervised object localization. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 2219\u20132228).","DOI":"10.1109\/CVPR.2019.00232"},{"key":"10.1016\/j.neunet.2025.107309_b9","doi-asserted-by":"crossref","unstructured":"Chua, T.-S., Tang, J., Hong, R., Li, H., Luo, Z., & Zheng, Y. (2009). NUS-WIDE: a real-world web image database from National University of Singapore. In Proceedings of the ACM international conference on image and video retrieval (pp. 1\u20139).","DOI":"10.1145\/1646396.1646452"},{"key":"10.1016\/j.neunet.2025.107309_b10","doi-asserted-by":"crossref","unstructured":"Dai, Z., Chen, M., Gu, X., Zhu, S., & Tan, P. (2019). Batch dropblock network for person re-identification and beyond. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 3691\u20133701).","DOI":"10.1109\/ICCV.2019.00379"},{"key":"10.1016\/j.neunet.2025.107309_b11","series-title":"Multi-label image classification with contrastive learning","author":"Dao","year":"2021"},{"key":"10.1016\/j.neunet.2025.107309_b12","series-title":"Improved regularization of convolutional neural networks with cutout","author":"DeVries","year":"2017"},{"key":"10.1016\/j.neunet.2025.107309_b13","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., et al. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In International conference on learning representations."},{"issue":"2","key":"10.1016\/j.neunet.2025.107309_b14","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","article-title":"The pascal visual object classes (voc) challenge","volume":"88","author":"Everingham","year":"2010","journal-title":"International Journal of Computer Vision"},{"key":"10.1016\/j.neunet.2025.107309_b15","doi-asserted-by":"crossref","unstructured":"Fu, J., Liu, J., Tian, H., Li, Y., Bao, Y., Fang, Z., et al. (2019). Dual attention network for scene segmentation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 3146\u20133154).","DOI":"10.1109\/CVPR.2019.00326"},{"key":"10.1016\/j.neunet.2025.107309_b16","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 Transactions on Image Processing"},{"key":"10.1016\/j.neunet.2025.107309_b17","article-title":"Dropblock: A regularization method for convolutional networks","volume":"vol. 31","author":"Ghiasi","year":"2018"},{"key":"10.1016\/j.neunet.2025.107309_b18","series-title":"Deep convolutional ranking for multilabel image annotation","author":"Gong","year":"2013"},{"key":"10.1016\/j.neunet.2025.107309_b19","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. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 729\u2013739).","DOI":"10.1109\/CVPR.2019.00082"},{"key":"10.1016\/j.neunet.2025.107309_b20","doi-asserted-by":"crossref","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":"Journal of Visual Communication and Image Representation"},{"key":"10.1016\/j.neunet.2025.107309_b21","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., & Girshick, R. (2020). Momentum contrast for unsupervised visual representation learning. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 9729\u20139738).","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"10.1016\/j.neunet.2025.107309_b22","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 770\u2013778).","DOI":"10.1109\/CVPR.2016.90"},{"key":"10.1016\/j.neunet.2025.107309_b23","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1016\/j.neunet.2023.04.009","article-title":"Co-attention enabled content-based image retrieval","volume":"164","author":"Hu","year":"2023","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2025.107309_b24","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., & Sun, G. (2018). Squeeze-and-excitation networks. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 7132\u20137141).","DOI":"10.1109\/CVPR.2018.00745"},{"key":"10.1016\/j.neunet.2025.107309_b25","article-title":"Theme-aware aesthetic distribution prediction with full-resolution photographs","author":"Jia","year":"2022","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"10.1016\/j.neunet.2025.107309_b26","doi-asserted-by":"crossref","unstructured":"Jin, J., & Nakayama, H. (2016). Annotation order matters: Recurrent image annotator for arbitrary length image tagging. In IEEE 23rd international conference on pattern recognition (pp. 2452\u20132457).","DOI":"10.1109\/ICPR.2016.7900004"},{"key":"10.1016\/j.neunet.2025.107309_b27","series-title":"Semi-supervised classification with graph convolutional networks","author":"Kipf","year":"2016"},{"key":"10.1016\/j.neunet.2025.107309_b28","doi-asserted-by":"crossref","unstructured":"Lanchantin, J., Wang, T., Ordonez, V., & Qi, Y. (2021). General multi-label image classification with transformers. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 16478\u201316488).","DOI":"10.1109\/CVPR46437.2021.01621"},{"key":"10.1016\/j.neunet.2025.107309_b29","series-title":"Learning category correlations for multi-label image recognition with graph networks","author":"Li","year":"2019"},{"key":"10.1016\/j.neunet.2025.107309_b30","doi-asserted-by":"crossref","unstructured":"Li, J., Zhang, C., Wang, X., & Du, L. (2020). Multi-Scale Cross-Modal Spatial Attention Fusion for Multi-label Image Recognition. In International conference on artificial neural networks (pp. 736\u2013747).","DOI":"10.1007\/978-3-030-61609-0_58"},{"key":"10.1016\/j.neunet.2025.107309_b31","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"},{"key":"10.1016\/j.neunet.2025.107309_b32","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., et al. (2014). Microsoft coco: Common objects in context. In European conference on computer vision (pp. 740\u2013755).","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"10.1016\/j.neunet.2025.107309_b33","doi-asserted-by":"crossref","unstructured":"Liu, R., Liu, H., Li, G., Hou, H., Yu, T., & Yang, T. (2022). Contextual debiasing for visual recognition with causal mechanisms. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 12755\u201312765).","DOI":"10.1109\/CVPR52688.2022.01242"},{"key":"10.1016\/j.neunet.2025.107309_b34","series-title":"Query2Label: A simple transformer way to multi-label classification","author":"Liu","year":"2021"},{"key":"10.1016\/j.neunet.2025.107309_b35","doi-asserted-by":"crossref","unstructured":"Meng, Q., & Zhang, W. (2019). Multi-Label Image Classification with Attention Mechanism and Graph Convolutional Networks. In Proceedings of the ACM multimedia Asia (MM Asia) (pp. 1\u20136).","DOI":"10.1145\/3338533.3366589"},{"key":"10.1016\/j.neunet.2025.107309_b36","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":"10.1016\/j.neunet.2025.107309_b37","series-title":"Multi-layered semantic representation network for multi-label image classification","author":"Qu","year":"2021"},{"key":"10.1016\/j.neunet.2025.107309_b38","series-title":"International conference on machine learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.neunet.2025.107309_b39","doi-asserted-by":"crossref","unstructured":"Ridnik, T., Ben-Baruch, E., Zamir, N., Noy, A., Friedman, I., Protter, M., et al. (2021). Asymmetric loss for multi-label classification. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 82\u201391).","DOI":"10.1109\/ICCV48922.2021.00015"},{"key":"10.1016\/j.neunet.2025.107309_b40","doi-asserted-by":"crossref","unstructured":"Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., & Batra, D. (2017). Grad-cam: Visual explanations from deep networks via gradient-based localization. In Proceedings of the IEEE international conference on computer vision (pp. 618\u2013626).","DOI":"10.1109\/ICCV.2017.74"},{"key":"10.1016\/j.neunet.2025.107309_b41","article-title":"Region-object relation-aware dense captioning via transformer","author":"Shao","year":"2022","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"10.1016\/j.neunet.2025.107309_b42","doi-asserted-by":"crossref","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":"Computer Vision and Image Understanding"},{"key":"10.1016\/j.neunet.2025.107309_b43","doi-asserted-by":"crossref","unstructured":"Singh, K. K., & Lee, Y. J. (2017). Hide-and-seek: Forcing a network to be meticulous for weakly-supervised object and action localization. In IEEE international conference on computer vision (pp. 3544\u20133553).","DOI":"10.1109\/ICCV.2017.381"},{"key":"10.1016\/j.neunet.2025.107309_b44","series-title":"Advances in neural information processing systems (neurIPS)","first-page":"5998","article-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"key":"10.1016\/j.neunet.2025.107309_b45","doi-asserted-by":"crossref","unstructured":"Wang, Z., Chen, T., Li, G., Xu, R., & Lin, L. (2017). Multi-label image recognition by recurrently discovering attentional regions. In Proceedings of the IEEE international conference on computer vision (pp. 464\u2013472).","DOI":"10.1109\/ICCV.2017.58"},{"issue":"4","key":"10.1016\/j.neunet.2025.107309_b46","doi-asserted-by":"crossref","first-page":"1848","DOI":"10.1109\/TCSVT.2021.3083978","article-title":"Semantic supplementary network with prior information for multi-label image classification","volume":"32","author":"Wang","year":"2021","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10.1016\/j.neunet.2025.107309_b47","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., & He, K. (2018). Non-local neural networks. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 7794\u20137803).","DOI":"10.1109\/CVPR.2018.00813"},{"key":"10.1016\/j.neunet.2025.107309_b48","doi-asserted-by":"crossref","unstructured":"Wang, X., Li, Y., Luo, T., Guo, Y., Fu, Y., & Xue, X. (2021). Distance Restricted Transformer Encoder for Multi-Label Classification. In IEEE international conference on multimedia and expo (pp. 1\u20136).","DOI":"10.1109\/ICME51207.2021.9428164"},{"key":"10.1016\/j.neunet.2025.107309_b49","first-page":"1","article-title":"STMG: Swin transformer for multi-label image recognition with graph convolution network","author":"Wang","year":"2022","journal-title":"Neural Computing and Applications"},{"key":"10.1016\/j.neunet.2025.107309_b50","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. In Proceedings of the 29th ACM international conference on information & knowledge management (pp. 1575\u20131584).","DOI":"10.1145\/3340531.3411880"},{"key":"10.1016\/j.neunet.2025.107309_b51","doi-asserted-by":"crossref","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).","DOI":"10.1109\/CVPR.2016.251"},{"issue":"9","key":"10.1016\/j.neunet.2025.107309_b52","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 Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2025.107309_b53","article-title":"Multilabel image classification via feature\/label co-projection","author":"Wen","year":"2020","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics: Systems"},{"key":"10.1016\/j.neunet.2025.107309_b54","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.-Y., & Kweon, I. S. (2018). Cbam: Convolutional block attention module. In Proceedings of the European conference on computer vision (pp. 3\u201319).","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"10.1016\/j.neunet.2025.107309_b55","doi-asserted-by":"crossref","unstructured":"Wu, X., Chen, Q., Li, W., Xiao, Y., & Hu, B. (2020). AdaHGNN: Adaptive Hypergraph Neural Networks for Multi-Label Image Classification. In Proceedings of the 28th ACM international conference on multimedia (pp. 284\u2013293).","DOI":"10.1145\/3394171.3414046"},{"key":"10.1016\/j.neunet.2025.107309_b56","doi-asserted-by":"crossref","DOI":"10.1109\/TCSVT.2023.3268997","article-title":"Transformer driven matching selection mechanism for multi-label image classification","author":"Wu","year":"2023","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10.1016\/j.neunet.2025.107309_b57","first-page":"1","article-title":"A multi-label image classification method combining multi-stage image semantic information and label relevance","author":"Wu","year":"2024","journal-title":"International Journal of Machine Learning and Cybernetics"},{"key":"10.1016\/j.neunet.2025.107309_b58","doi-asserted-by":"crossref","first-page":"280","DOI":"10.1016\/j.neunet.2019.06.007","article-title":"Multi-perspective neural architecture for recommendation system","volume":"118","author":"Xiao","year":"2019","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2025.107309_b59","doi-asserted-by":"crossref","unstructured":"Xie, J., Xiang, J., Chen, J., Hou, X., Zhao, X., & Shen, L. (2022). C2AM: contrastive learning of class-agnostic activation map for weakly supervised object localization and semantic segmentation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 989\u2013998).","DOI":"10.1109\/CVPR52688.2022.00106"},{"key":"10.1016\/j.neunet.2025.107309_b60","doi-asserted-by":"crossref","first-page":"98005","DOI":"10.1109\/ACCESS.2019.2929512","article-title":"Multi-label image classification by feature attention network","volume":"7","author":"Yan","year":"2019","journal-title":"IEEE Access"},{"key":"10.1016\/j.neunet.2025.107309_b61","doi-asserted-by":"crossref","unstructured":"Yang, H., Tianyi Zhou, J., Zhang, Y., Gao, B.-B., Wu, J., & Cai, J. (2016). Exploit bounding box annotations for multi-label object recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 280\u2013288).","DOI":"10.1109\/CVPR.2016.37"},{"key":"10.1016\/j.neunet.2025.107309_b62","doi-asserted-by":"crossref","unstructured":"You, R., Guo, Z., Cui, L., Long, X., Bao, Y., & Wen, S. (2020). Cross-Modality Attention with Semantic Graph Embedding for Multi-Label Classification.. In Proceedings of the AAAI conference on artificialintelligence (pp. 12709\u201312716).","DOI":"10.1609\/aaai.v34i07.6964"},{"key":"10.1016\/j.neunet.2025.107309_b63","doi-asserted-by":"crossref","first-page":"322","DOI":"10.1016\/j.patcog.2019.03.006","article-title":"DELTA: A deep dual-stream network for multi-label image classification","volume":"91","author":"Yu","year":"2019","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.neunet.2025.107309_b64","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1016\/j.neucom.2016.12.051","article-title":"Combining local and global hypotheses in deep neural network for multi-label image classification","volume":"235","author":"Yu","year":"2017","journal-title":"Neurocomputing"},{"issue":"4","key":"10.1016\/j.neunet.2025.107309_b65","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3578518","article-title":"Graph attention transformer network for multi-label image classification","volume":"19","author":"Yuan","year":"2023","journal-title":"ACM Transactions on Multimedia Computing, Communications and Applications"},{"key":"10.1016\/j.neunet.2025.107309_b66","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1016\/j.neucom.2022.11.022","article-title":"Balanced masking strategy for multi-label image classification","volume":"522","author":"Yuan","year":"2023","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neunet.2025.107309_b67","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Lan, C., Zeng, W., Jin, X., & Chen, Z. (2020). Relation-aware global attention for person re-identification. In Proceedings of the ieee\/cvf conference on computer vision and pattern recognition (pp. 3186\u20133195).","DOI":"10.1109\/CVPR42600.2020.00325"},{"key":"10.1016\/j.neunet.2025.107309_b68","doi-asserted-by":"crossref","unstructured":"Zhang, X., Wei, Y., Feng, J., Yang, Y., & Huang, T. S. (2018). Adversarial complementary learning for weakly supervised object localization. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 1325\u20131334).","DOI":"10.1109\/CVPR.2018.00144"},{"issue":"10","key":"10.1016\/j.neunet.2025.107309_b69","doi-asserted-by":"crossref","first-page":"2801","DOI":"10.1109\/TMM.2018.2812605","article-title":"Multilabel image classification with regional latent semantic dependencies","volume":"20","author":"Zhang","year":"2018","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.1016\/j.neunet.2025.107309_b70","doi-asserted-by":"crossref","unstructured":"Zhao, J., Yan, K., Zhao, Y., Guo, X., Huang, F., & Li, J. (2021). Transformer-based dual relation graph for multi-label image recognition. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 163\u2013172).","DOI":"10.1109\/ICCV48922.2021.00023"},{"key":"10.1016\/j.neunet.2025.107309_b71","doi-asserted-by":"crossref","first-page":"225539","DOI":"10.1109\/ACCESS.2020.3044446","article-title":"Double attention for multi-label image classification","volume":"8","author":"Zhao","year":"2020","journal-title":"IEEE Access"},{"key":"10.1016\/j.neunet.2025.107309_b72","doi-asserted-by":"crossref","first-page":"428","DOI":"10.1016\/j.neunet.2021.03.022","article-title":"Learning to reweight examples in multi-label classification","volume":"142","author":"Zhong","year":"2021","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2025.107309_b73","doi-asserted-by":"crossref","unstructured":"Zhong, Z., Zheng, L., Kang, G., Li, S., & Yang, Y. (2020). Random erasing data augmentation. In Proceedings of the AAAI conference on artificial intelligence, Vol. 34, No. 07 (pp. 13001\u201313008).","DOI":"10.1609\/aaai.v34i07.7000"},{"key":"10.1016\/j.neunet.2025.107309_b74","doi-asserted-by":"crossref","unstructured":"Zhou, F., Huang, S., & Xing, Y. (2021). Deep semantic dictionary learning for multi-label image classification. In Proceedings of the AAAI conference on artificial intelligence (pp. 3572\u20133580).","DOI":"10.1609\/aaai.v35i4.16472"},{"issue":"2","key":"10.1016\/j.neunet.2025.107309_b75","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3550278","article-title":"Aligning image semantics and label concepts for image multi-label classification","volume":"19","author":"Zhou","year":"2023","journal-title":"ACM Transactions on Multimedia Computing, Communications and Applications"},{"issue":"1","key":"10.1016\/j.neunet.2025.107309_b76","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3519030","article-title":"Double attention based on graph attention network for image multi-label classification","volume":"19","author":"Zhou","year":"2023","journal-title":"ACM Transactions on Multimedia Computing, Communications and Applications"},{"key":"10.1016\/j.neunet.2025.107309_b77","doi-asserted-by":"crossref","unstructured":"Zhu, X., Cao, J., Ge, J., Liu, W., & Liu, B. (2022). Two-Stream Transformer for Multi-Label Image Classification. In Proceedings of the 30th ACM international conference on multimedia (pp. 3598\u20133607).","DOI":"10.1145\/3503161.3548343"},{"key":"10.1016\/j.neunet.2025.107309_b78","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. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 5513\u20135522).","DOI":"10.1109\/CVPR.2017.219"},{"key":"10.1016\/j.neunet.2025.107309_b79","doi-asserted-by":"crossref","unstructured":"Zhu, K., & Wu, J. (2021). Residual Attention: A Simple but Effective Method for Multi-Label Recognition. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 184\u2013193).","DOI":"10.1109\/ICCV48922.2021.00025"},{"key":"10.1016\/j.neunet.2025.107309_b80","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106241","article-title":"Adversarial pair-wise distribution matching for remote sensing image cross-scene classification","volume":"174","author":"Zhu","year":"2024","journal-title":"Neural Networks"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608025001881?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608025001881?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,6,9]],"date-time":"2025-06-09T14:39:32Z","timestamp":1749479972000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608025001881"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":80,"alternative-id":["S0893608025001881"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2025.107309","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2025,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"DRTN: Dual Relation Transformer Network with feature erasure and contrastive learning for multi-label image classification","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2025.107309","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"107309"}}