Abstract
Graph neural networks’ application in automatic image annotation is becoming more mature. However, there are still several problems. First, the feature data of the original image obtained by the feature extraction algorithm, such as color features and gradient features, all have the problem of slight intra-class variance and significant inter-class variance. Second, merely utilize the graph convolution neural networks to construct samples or labeled graphs, limiting multimodality’s fusion and expansion. This paper uses a parallel graph convolution network based on feature fusion for automatic image annotation. By fusing the sample features, the inherent defects of the features extracted by a single model are reduced, and the annotation performance under the condition of semi-supervised learning is improved. Experiments on three benchmark image annotation datasets show that this method is superior to the existing methods.
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11063-022-11131-x/MediaObjects/11063_2022_11131_Fig1_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11063-022-11131-x/MediaObjects/11063_2022_11131_Fig2_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11063-022-11131-x/MediaObjects/11063_2022_11131_Fig3_HTML.png)
Similar content being viewed by others
References
Chen M, Zheng A, Weinberger KQ (2013) Fast image tagging. In Proceedings of the 30th international conference on international conference on machine learning - Volume 28, ICML’13, page III-1274-III-1282. JMLR.org,
Chen T, Xu M, Hui X, Wu H, Lin L (2019) Learning semantic-specific graph representation for multi-label image recognition. In 2019 IEEE/CVF International conference on computer vision (ICCV), pages 522–531,
Chen Z-M, Wei X-S, Wang P, Guo Y (2019) Multi-label image recognition with graph convolutional networks. In 2019 IEEE/CVF conference on computer vision and pattern recognition (CVPR), pages 5172–5181,
Dai Y, Gieseke F, Oehmcke S, Wu Y, Barnard K (2021) Attentional feature fusion. In 2021 IEEE winter conference on applications of computer vision (WACV), pages 3559–3568,
Feng D, Zhongcheng W, Zhang J, Ren T (2021) Multi-scale spatial temporal graph neural network for skeleton-based action recognition. IEEE Access 9:58256–58265
Gibert D, Mateu C, Planes J (2020) The rise of machine learning for detection and classification of malware: research developments, trends and challenges. J Netw Comput Appl 153:102526
Gunes H, Piccardi M (2005) Affect recognition from face and body: early fusion vs. late fusion. In 2005 IEEE international conference on systems, man and cybernetics, volume 4, pages 3437–3443 Vol. 4,
Huang Z, Shen X, Tian X, Li H, Huang J, Hua X-S (2020) Spatio-temporal inception graph convolutional networks for skeleton-based action recognition, page 2122–2130. Association for Computing Machinery, New York, NY, USA
Kalayeh MM, Idrees H, Shah M (2014) Nmf-knn: image annotation using weighted multi-view non-negative matrix factorization. In 2014 IEEE conference on computer vision and pattern recognition, pages 184–191,
Ke X, Zou J, Niu Y (2019) End-to-end automatic image annotation based on deep cnn and multi-label data augmentation. IEEE Trans Multimed 21(8):2093–2106
Kipf T, Welling M (2017) Semi-supervised classification with graph convolutional networks. Ar**v:1609.02907
Li C, Qin X, **aodong X, Yang D, Wei G (2020) Scalable graph convolutional networks with fast localized spectral filter for directed graphs. IEEE Access 8:105634–105644
Li C, Qin X, **aodong X, Yang D, Wei G (2020) Scalable graph convolutional networks with fast localized spectral filter for directed graphs. IEEE Access 8:105634–105644
Li X, Shen B, Liu B-D, Zhang Y-J (2018) Ranking-preserving low-rank factorization for image annotation with missing labels. IEEE Trans Multimed 20(5):1169–1178
Li X, Shen B, Liu B-D, Zhang Y-J (2018) Ranking-preserving low-rank factorization for image annotation with missing labels. IEEE Trans Multimed 20(5):1169–1178
Lin T-Y, Dollár P, Girshick R, He K, Hariharan B, Belongie S (2017) Feature pyramid networks for object detection. In 2017 IEEE conference on computer vision and pattern recognition (CVPR), pages 936–944,
Liu WB, Zou ZY, **ng WW (2017) Feature fusion methods in pattern classification. J Bei**g Univ of Posts Telecommun
Liu W, Ma X, Zhou Y, Tao D, Cheng J (2019) \(p\) -laplacian regularization for scene recognition. IEEE Transact Cybernet 49(8):2927–2940
Liu W, Ma X, Zhou Y, Tao D, Cheng J (2019) \(p\) -laplacian regularization for scene recognition. IEEE Transact Cybernet 49(8):2927–2940
Ma Y, Hao J, Yang Y, Li H, ** J, Chen G (2019) Spectral-based graph convolutional network for directed graphs. Ar**v:1907.08990
Niu Y, Zhiwu L, Wen J-R, **ang T, Chang S-F (2019) Multi-modal multi-scale deep learning for large-scale image annotation. IEEE Trans Image Process 28:1720–1731
Ravindraiah R, Chandra Mohan Reddy S (2018) Exudates detection in diabetic retinopathy images using possibilistic c-means clustering algorithm with induced spatial constraint. pages 455–463,
Shao Q, Liu B-D (2019) Laplacian eigenmaps regularized feature map** for image annotation. In 2019 IEEE international conference on systems, man and cybernetics (SMC), pages 3901–3906,
Shao Q, Wang M, Li J, Liu W, Zhang K, Liu B (2021) Semi-supervised image annotation with parallel graph convolutional networks. In 2021 40th Chinese control conference (CCC), pages 7415–7420,
Snoek CGM, Worring M, Smeulders AWM (2005) Early versus late fusion in semantic video analysis. In MULTIMEDIA ’05
Song H, Wang P, Yun J, Li W, Xue B, Gang W (2020) A weighted topic model learned from local semantic space for automatic image annotation. IEEE Access 8:76411–76422
Tang P, Jiang M, ** for multi-label image annotation. Multimed Tools Appl 78(10):13149–13168
Jiahao X, Tian H, Wang Z, Wang Y, Kang W, Chen F (2021) Joint input and output space learning for multi-label image classification. IEEE Trans Multimed 23:1696–1707
Yang J, Yang J, Zhang D, feng Lu J (2003) Feature fusion: parallel strategy vs. serial strategy. Pattern Recogn 36(6):1369–1381
Yang J, Wang L (2019) Feature fusion and enhancement for single shot multibox detector. In 2019 Chinese automation congress (CAC), pages 2766–2770
Zeng Y, Li Y, Liu J, Ma J, Liu Z (2021) Pri-pgd: forging privacy-preserving graph towards spectral-based graph neural network. In 2021 IEEE global communications conference (GLOBECOM), pages 01–06,
Zhang Y, Jia W, Cai Z, Philip SY (2020) Multi-view multi-label learning with sparse feature selection for image annotation. IEEE Trans Multimed 22(11):2844–2857
Zhu P, Tan Y, Zhang L, Wang Y, Mei J, Liu H, Mengfan W (2020) Deep learning for multilabel remote sensing image annotation with dual-level semantic concepts. IEEE Trans Geosci Remote Sens 58:4047–4060
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Wang, M., Liu, Y., Liu, W. et al. Feature Fusion Based Parallel Graph Convolutional Neural Network for Image Annotation. Neural Process Lett 55, 6153–6164 (2023). https://doi.org/10.1007/s11063-022-11131-x
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11063-022-11131-x