{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T02:19:37Z","timestamp":1773886777460,"version":"3.50.1"},"reference-count":48,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2019,8,1]],"date-time":"2019-08-01T00:00:00Z","timestamp":1564617600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2019,8,1]],"date-time":"2019-08-01T00:00:00Z","timestamp":1564617600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61672202"],"award-info":[{"award-number":["61672202"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"State Key Program of NSFC-Shenzhen Joint Foundation","award":["U1613217"],"award-info":[{"award-number":["U1613217"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2020,7]]},"DOI":"10.1007\/s00371-019-01731-5","type":"journal-article","created":{"date-parts":[[2019,8,1]],"date-time":"2019-08-01T13:02:32Z","timestamp":1564664552000},"page":"1325-1335","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Learning semantic dependencies with channel correlation for multi-label classification"],"prefix":"10.1007","volume":"36","author":[{"given":"Lixia","family":"Xue","sequence":"first","affiliation":[]},{"given":"Di","family":"Jiang","sequence":"additional","affiliation":[]},{"given":"Ronggui","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Juan","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Min","family":"Hu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,8,1]]},"reference":[{"key":"1731_CR1","doi-asserted-by":"crossref","unstructured":"Sivic, J., Zisserman, A.: Video Google: a text retrieval approach to object matching in videos. In: Proceedings of IEEE International Conference on Computer Vision, pp. 1470\u20131477. IEEE (2003)","DOI":"10.1109\/ICCV.2003.1238663"},{"issue":"3","key":"1731_CR2","first-page":"27","volume":"2","author":"CC Chang","year":"2011","unstructured":"Chang, C.C., Lin, C.J.: LIBSVM: a library for support vector machines. ACM Trans. Intell. Syst. Technol. TIST 2(3), 27 (2011)","journal-title":"ACM Trans. Intell. Syst. Technol. TIST"},{"issue":"1","key":"1731_CR3","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","volume":"45","author":"L Breiman","year":"2001","unstructured":"Breiman, L.: Random forests. Mach. Learn. 45(1), 5\u201332 (2001)","journal-title":"Mach. Learn."},{"key":"1731_CR4","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.: Imagenet classification with deep convolutional neural networks. In: Neural Information Processing Systems, pp. 1106\u20131114 (2012)"},{"key":"1731_CR5","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1\u20139 (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"1731_CR6","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770-778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"1731_CR7","unstructured":"Huang, G., Liu, Z., Weinberger, K.Q., Maaten, L.: Densely connected convolutional networks. In: IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 2261\u20132269. IEEE Computer Society (2017)"},{"key":"1731_CR8","unstructured":"Gong, Y., Jia, Y., Leung, T., Toshev, A., Ioffe, S.: dee8p convolutional ranking for multi-label image annotation. In: International Conference on Learning Representations (2014)"},{"key":"1731_CR9","doi-asserted-by":"crossref","unstructured":"Harzallah, H., Jurie, F., Schmid, C.: Combining efficient object localization and image classification. In: International Conference on Computer Vision, pp. 237\u2013244 (2009)","DOI":"10.1109\/ICCV.2009.5459257"},{"issue":"3","key":"1731_CR10","doi-asserted-by":"publisher","first-page":"222","DOI":"10.1007\/s11263-013-0636-x","volume":"105","author":"J Sanchez","year":"2013","unstructured":"Sanchez, J., Perronnin, F., Mensink, T., Verbeek, J.J.: Image classification with the fisher vector: theory and practice. Int. J. Comput. Vis. 105(3), 222\u2013245 (2013)","journal-title":"Int. J. Comput. Vis."},{"key":"1731_CR11","doi-asserted-by":"crossref","unstructured":"Razavian, A.S., Azizpour, H., Sullivan, J., Carlsson, S.: CNN features off-the-shelf: an astounding baseline for recognition. In: Computer Vision and Pattern Recognition, pp. 512\u2013519 (2014)","DOI":"10.1109\/CVPRW.2014.131"},{"issue":"9","key":"1731_CR12","doi-asserted-by":"publisher","first-page":"1901","DOI":"10.1109\/TPAMI.2015.2491929","volume":"38","author":"Y Wei","year":"2016","unstructured":"Wei, Y., Xia, W., Lin, M., Huang, J., Ni, B., Dong, J., Yan, S.: HCP: a flexible CNN framework for multi-label image classification. IEEE Trans. Pattern Anal. Mach. Intell. 38(9), 1901\u20131907 (2016)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"2","key":"1731_CR13","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, C.K., Winn, J., Zisserman, A.: The pascal visual object classes (VOC) challenge. Int. J. Comput. Vis. 88(2), 303\u2013338 (2010)","journal-title":"Int. J. Comput. Vis."},{"key":"1731_CR14","doi-asserted-by":"crossref","unstructured":"Cheng, M.-M., Zhang, Z., Lin, W.-Y., Torr, P.H.S.: BING: binarized normed gradients for objectness estimation at 300\u00a0fps. In: Computer Vision and Pattern Recognition, pp. 3286\u20133293 (2014)","DOI":"10.1109\/CVPR.2014.414"},{"key":"1731_CR15","doi-asserted-by":"crossref","unstructured":"Wang, J., Yang, Y., Mao, J., Huang, Z., Huang, C., Xu, W.: CNN-RNN: a unified framework for multi-label image classification. In: Computer Vision and Pattern Recognition (CVPR), pp. 2285\u20132294 (2016)","DOI":"10.1109\/CVPR.2016.251"},{"issue":"8","key":"1731_CR16","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"1731_CR17","unstructured":"Srivastava, N., Salakhutdinov, R.: Learning representations for multimodal data with deep belief nets. In: International Conference on Machine Learning Workshop, vol. 79 (2012)"},{"key":"1731_CR18","unstructured":"Xue, X., Zhang, W., Zhang, J., Wu, B., Fan, J., Lu, Y.: Correlative multi-label multi-instance image annotation. In: International Conference on Computer Vision, 2011. IEEE Computer Society, pp. 651\u2013658 (2011)"},{"key":"1731_CR19","unstructured":"Guo, Y., Gu, S.: Multi-label classification using conditional dependency networks. In: International Joint Conference on Artificial Intelligence, pp. 1300\u20132011 (2011)"},{"issue":"10","key":"1731_CR20","doi-asserted-by":"publisher","first-page":"2801","DOI":"10.1109\/TMM.2018.2812605","volume":"20","author":"J Zhang","year":"2018","unstructured":"Zhang, J., Wu, Q., Shen, C., et al.: Multilabel image classification with regional latent semantic dependencies. IEEE Trans. Multimedia 20(10), 2801\u20132813 (2018)","journal-title":"IEEE Trans. Multimedia"},{"key":"1731_CR21","unstructured":"Glorot, X., Bordes, A., Bengio, Y.: Deep sparse rectifier neural networks. In: International Conference on Artificial Intelligence and Statistics, pp. 315\u2013323 (2011)"},{"key":"1731_CR22","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: Computer Science (2014)"},{"key":"1731_CR23","doi-asserted-by":"crossref","unstructured":"Yang, H., Tianyi Zhou, J., Zhang, Y., Gao, B.-B., Wu, J., Cai, J.: Exploit bounding box annotations for multi-label object recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 280\u2013288 (2016)","DOI":"10.1109\/CVPR.2016.37"},{"key":"1731_CR24","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Computer Vision and Pattern Recognition (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"1731_CR25","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1016\/j.jvcir.2017.07.004","volume":"49","author":"R Wang","year":"2017","unstructured":"Wang, R., Xie, Y., Yang, J., Xue, L., Hu, M., Zhang, Q.: Large scale automatic image annotation based on convolutional neural network. J. Vis. Commun. Image Represent. 49, 213\u2013224 (2017)","journal-title":"J. Vis. Commun. Image Represent."},{"issue":"2","key":"1731_CR26","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"DG Lowe","year":"2004","unstructured":"Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60(2), 91\u2013110 (2004)","journal-title":"Int. J. Comput. Vis."},{"key":"1731_CR27","unstructured":"Ba, J., Mnih, V., Kavukcuoglu, K.: Multiple object recognition with visual attention. In: International Conference on Learning Representations (2015)"},{"key":"1731_CR28","unstructured":"Mnih, V., Heess, N., Graves, A., Kavukcuoglu, K.: Recurrent models of visual attention. In: Neural Information Processing Systems, pp. 2204\u20132212 (2014)"},{"key":"1731_CR29","unstructured":"Wang, Y., Deng, Z., Hu, X., Zhu, L., Ni, D.: Deep attentional features for prostate segmentation in ultrasound. In: International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), 2018. Springer, Cham (2018)"},{"key":"1731_CR30","doi-asserted-by":"crossref","unstructured":"Hu, X., Yu, L., Chen, H., Qin, J., Heng, P.A.: AGNet: attention-guided network for surgical tool presence detection. In: Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support, pp. 186\u2013194. Springer, Cham (2017)","DOI":"10.1007\/978-3-319-67558-9_22"},{"key":"1731_CR31","unstructured":"Xu, K., Ba, J., Kiros, R., Cho, K., Courville, A., Salakhutdinov, R., Zemel, R.S., Bengio, Y.: Show, attend and tell: neural image caption generation with visual attention. In: International Conference on Machine Learning, pp. 2048\u20132057 (2015)"},{"key":"1731_CR32","unstructured":"Dalal, N., Triggs, B: Histograms of oriented gradients for human detection, In: Computer Vision and Pattern Recognition, pp. 886\u2013893 (2005)"},{"key":"1731_CR33","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., FeiFei, L.: Imagenet: a large-scale hierarchical image database. In: Computer Vision and Pattern Recognition, pp. 248\u2013255 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"issue":"1","key":"1731_CR34","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1016\/0031-3203(95)00067-4","volume":"29","author":"T Ojala","year":"1996","unstructured":"Ojala, T., Pietikainen, M., Harwood, D.: A comparative study of texture measures with classification based on featured distributions. Pattern Recognit. 29(1), 51\u201359 (1996)","journal-title":"Pattern Recognit."},{"key":"1731_CR35","unstructured":"Huang, G., Chen, D., Li, T., Wu, F., Laurens, V.D.M., Weinberger, K.Q.: Multi-scale dense networks for resource efficient image classification. International Conference on Learning Representations (2018)"},{"key":"1731_CR36","doi-asserted-by":"crossref","unstructured":"Shen, Z., Liu, Z., Li, J., Jiang, Y. G., Chen, Y., Xue, X.: DSOD: learning deeply supervised object detectors from scratch. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1919\u20131927 (2017)","DOI":"10.1109\/ICCV.2017.212"},{"key":"1731_CR37","unstructured":"Chen, Y., Li, J., Xiao, H., Jin, X., Yan, S., Feng, J.: Dual path networks. In: Neural Information Processing Systems, pp. 4467\u20134475 (2017)"},{"key":"1731_CR38","first-page":"1","volume":"27","author":"W Wang","year":"2017","unstructured":"Wang, W., Shen, J., Shao, L.: Video salient object detection via fully convolutional networks. IEEE Trans. Image Process. 27, 1 (2017)","journal-title":"IEEE Trans. Image Process."},{"key":"1731_CR39","doi-asserted-by":"crossref","unstructured":"Dong, X., Shen, J., Wang, W., Liu, Y., Shao, L., Porikli, F.: Hyperparameter optimization for tracking with continuous deep Q-learning. In: Computer Vision and Pattern Recognition (CVPR), pp. 518\u2013527 (2018)","DOI":"10.1109\/CVPR.2018.00061"},{"key":"1731_CR40","doi-asserted-by":"crossref","unstructured":"Dong, X., Shen, J.: Triplet loss in siamese network for object tracking. In: European Conference on Computer Vision (2018)","DOI":"10.1007\/978-3-030-01261-8_28"},{"key":"1731_CR41","doi-asserted-by":"crossref","unstructured":"Zhu, L., Deng, Z., Hu, X., Fu, C. W., Xu, X., Qin, J., Heng, P.A.: Bidirectional feature pyramid network with recurrent attention residual modules for shadow detection. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 121\u2013136 (2018)","DOI":"10.1007\/978-3-030-01231-1_8"},{"key":"1731_CR42","first-page":"1","volume":"41","author":"W Wenguan","year":"2018","unstructured":"Wenguan, W., Jianbing, S., Haibin, L.: A deep network solution for attention and aesthetics aware photo cropping. IEEE Trans. Pattern Anal. Mach. Intell. 41, 1 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"5","key":"1731_CR43","doi-asserted-by":"publisher","first-page":"2368","DOI":"10.1109\/TIP.2017.2787612","volume":"27","author":"W Wang","year":"2018","unstructured":"Wang, W., Shen, J.: Deep visual attention prediction. IEEE Trans. Image Process. 27(5), 2368\u20132378 (2018)","journal-title":"IEEE Trans. Image Process."},{"issue":"7","key":"1731_CR44","doi-asserted-by":"publisher","first-page":"3516","DOI":"10.1109\/TIP.2019.2898567","volume":"28","author":"X Dong","year":"2019","unstructured":"Dong, X., Shen, J., Wu, D., et al.: Quadruplet network with one-shot learning for fast visual object tracking. IEEE Trans. Image Process. 28(7), 3516\u20133527 (2019)","journal-title":"IEEE Trans. Image Process."},{"key":"1731_CR45","doi-asserted-by":"crossref","unstructured":"Wang, J., Li, X., Yang, J., et al.: Stacked conditional generative adversarial networks for jointly learning shadow detection and shadow removal. In: Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1788\u20131797 (2018)","DOI":"10.1109\/CVPR.2018.00192"},{"key":"1731_CR46","doi-asserted-by":"crossref","unstructured":"Hu, X., Zhu, L., Fu, C., et al.: Direction-aware spatial context features for shadow detection. In: Conference Computer Vision and Pattern Recognition (CVPR), pp. 7454\u20137462 (2018)","DOI":"10.1109\/CVPR.2018.00778"},{"issue":"3","key":"1731_CR47","doi-asserted-by":"publisher","first-page":"431","DOI":"10.1109\/TPAMI.2015.2462355","volume":"38","author":"SH Khan","year":"2016","unstructured":"Khan, S.H., Bennamoun, M., Sohel, F.A., et al.: Automatic shadow detection and removal from a single image. IEEE Trans. Pattern Anal. Mach. Intell. 38(3), 431\u2013446 (2016)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1731_CR48","doi-asserted-by":"crossref","unstructured":"Hu, X., Fu, C., Zhu, L., et al.: Direction-aware spatial context features for shadow detection and removal. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7454\u20137462 (2018)","DOI":"10.1109\/CVPR.2018.00778"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-019-01731-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00371-019-01731-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-019-01731-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,7,30]],"date-time":"2020-07-30T23:48:22Z","timestamp":1596152902000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00371-019-01731-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,8,1]]},"references-count":48,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2020,7]]}},"alternative-id":["1731"],"URL":"https:\/\/doi.org\/10.1007\/s00371-019-01731-5","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,8,1]]},"assertion":[{"value":"1 August 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}