{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:26:29Z","timestamp":1740122789722,"version":"3.37.3"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"19","license":[{"start":{"date-parts":[[2019,7,8]],"date-time":"2019-07-08T00:00:00Z","timestamp":1562544000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2019,7,8]],"date-time":"2019-07-08T00:00:00Z","timestamp":1562544000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2019,10]]},"DOI":"10.1007\/s11042-019-07933-2","type":"journal-article","created":{"date-parts":[[2019,7,8]],"date-time":"2019-07-08T23:17:42Z","timestamp":1562627862000},"page":"28209-28230","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Multi-Level Ensemble Network for Scene Recognition"],"prefix":"10.1007","volume":"78","author":[{"given":"Longhao","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Lingqiao","family":"Li","sequence":"additional","affiliation":[]},{"given":"Xipeng","family":"Pan","sequence":"additional","affiliation":[]},{"given":"Zhiwei","family":"Cao","sequence":"additional","affiliation":[]},{"given":"Qianyu","family":"Chen","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6334-4044","authenticated-orcid":false,"given":"Huihua","family":"Yang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,7,8]]},"reference":[{"key":"7933_CR1","unstructured":"Bertinetto L, Valmadre J, Henriques JF, et al. (2016) Fully-Convolutional Siamese Networks for Object Tracking[C]\/\/ European Conference on Computer Vision. Springer International Publishing, 850\u2013865"},{"key":"7933_CR2","unstructured":"Chen Y, Li J, Xiao H, et al. (2017) Dual Path Networks[J]"},{"key":"7933_CR3","doi-asserted-by":"crossref","unstructured":"Cheng Z, Shen J (2016) On very large scale test collection for landmark image search benchmarking[J]. Signal Processing, 124:13\u201326","DOI":"10.1016\/j.sigpro.2015.10.037"},{"key":"7933_CR4","doi-asserted-by":"crossref","unstructured":"Cheng Z, Chang X, et al. (2018) MMALFM: Explainable Recommendation by Leveraging Reviews and Images[J]. ACM Transactions on Information Systems","DOI":"10.1145\/3291060"},{"key":"7933_CR5","unstructured":"Danelljan M, Bhat G, Khan FS, et al. (2016) ECO: Efficient Convolution Operators for Tracking[J]. 6931\u20136939"},{"issue":"1","key":"7933_CR6","doi-asserted-by":"publisher","first-page":"140","DOI":"10.1109\/TITS.2017.2774778","volume":"19","author":"G Ding","year":"2018","unstructured":"Ding G, Chen W et al (2018) Real-Time Scalable Visual Tracking via Quadrangle Kernelized Correlation Filters[J]. IEEE Trans Intell Transp Syst 19(1):140\u2013150","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"7933_CR7","unstructured":"Fan H, SANet LH (2017) Structure-Aware Network for Visual Tracking[C]\/\/ Computer Vision and Pattern Recognition Workshops. IEEE, 2217\u20132224"},{"key":"7933_CR8","unstructured":"George M, Dixit M, Zogg G, et al. (2016) Semantic Clustering for Robust Fine-Grained Scene Recognition[M]\/\/ Computer Vision \u2013 ECCV 2016. Springer International Publishing, 783\u2013798."},{"key":"7933_CR9","first-page":"249","volume":"9","author":"X Glorot","year":"2010","unstructured":"Glorot X, Bengio Y (2010) Understanding the difficulty of training deep feedforward neural networks[J]. J Mach Learn Res 9:249\u2013256","journal-title":"J Mach Learn Res"},{"key":"7933_CR10","first-page":"297","volume-title":"Simultaneous Detection and Segmentation[C]\/\/ European Conference on Computer Vision","author":"B Hariharan","year":"2014","unstructured":"Hariharan B, Arbel\u00e1ez P, Girshick R et al (2014) Simultaneous Detection and Segmentation[C]\/\/ European Conference on Computer Vision. Springer, Cham, pp 297\u2013312"},{"key":"7933_CR11","unstructured":"He K, Zhang X, Ren S, et al. (2016) Deep Residual Learning for Image Recognition[C]\/\/ IEEE Conference on Computer Vision and Pattern Recognition. IEEE Computer Society, :770\u2013778."},{"key":"7933_CR12","doi-asserted-by":"crossref","unstructured":"He K, Gkioxari G, Dollar P et al. (2017) Mask R-CNN[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, PP(99):1\u20131","DOI":"10.1109\/ICCV.2017.322"},{"key":"7933_CR13","unstructured":"Herranz L, Jiang S, Li X (2016) Scene Recognition with CNNs: Objects, Scales and Dataset Bias[C]\/\/ Computer Vision and Pattern Recognition. IEEE, 571\u2013579"},{"key":"7933_CR14","doi-asserted-by":"crossref","unstructured":"Hu J, Shen L, Sun G (2017) Squeeze-and-Excitation Networks[J]","DOI":"10.1109\/CVPR.2018.00745"},{"key":"7933_CR15","unstructured":"Huang G, Liu Z, Laurens VDM, et al. (2016) Densely Connected Convolutional Networks[J]. 2261\u20132269."},{"key":"7933_CR16","unstructured":"Ioffe S, Szegedy C (2015) Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift[J]. 448\u2013456"},{"key":"7933_CR17","doi-asserted-by":"crossref","unstructured":"Jia Y, Shelhamer E, Donahue J et al. (2014) Caffe: Convolutional Architecture for Fast Feature Embedding[J].","DOI":"10.1145\/2647868.2654889"},{"key":"7933_CR18","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2012) ImageNet classification with deep convolutional neural networks[C]\/\/ International Conference on Neural Information Processing Systems. Curran Associates Inc. 1097\u20131105."},{"issue":"11","key":"7933_CR19","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y L\u00e9cun","year":"1998","unstructured":"L\u00e9cun Y, Bottou L, Bengio Y et al (1998) Gradient-based learning applied to document recognition[J]. Proc IEEE 86(11):2278\u20132324","journal-title":"Proc IEEE"},{"key":"7933_CR20","unstructured":"Li Y, Qi H, Dai J, et al. (2016) Fully Convolutional Instance-aware Semantic Segmentation[J]. 4438\u20134446"},{"key":"7933_CR21","unstructured":"Romera-Paredes B, Torr PHS (2016) Recurrent Instance Segmentation[C]\/\/ European Conference on Computer Vision. Springer International Publishing, 312\u2013329"},{"key":"7933_CR22","unstructured":"Shen L, Lin Z, Huang Q (2016) Relay Backpropagation for Effective Learning of Deep Convolutional Neural Networks[C]\/\/ European Conference on Computer Vision. Springer International Publishing, 467\u2013482"},{"key":"7933_CR23","unstructured":"Szegedy C, Liu W, Jia Y, et al. (2015) Going deeper with convolutions[C]\/\/ IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 1\u20139"},{"key":"7933_CR24","unstructured":"Szegedy C, Vanhoucke V, Ioffe S, et al. (2016) Rethinking the Inception Architecture for Computer Vision[C]\/\/ IEEE Conference on Computer Vision and Pattern Recognition. IEEE Computer Society, 2818\u20132826"},{"key":"7933_CR25","doi-asserted-by":"crossref","unstructured":"Szegedy C, Ioffe S, Vanhoucke V, et al. (2016) Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning[J]","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"7933_CR26","unstructured":"Wang L, Ouyang W, Wang X et al. (2016) Visual Tracking with Fully Convolutional Networks[C]\/\/ IEEE International Conference on Computer Vision. IEEE, 3119\u20133127"},{"key":"7933_CR27","unstructured":"Xie S, Girshick R, Dollar P, et al. (2017) Aggregated Residual Transformations for Deep Neural Networks[C]\/\/ IEEE Conference on Computer Vision and Pattern Recognition. IEEE Computer Society, 5987\u20135995"},{"key":"7933_CR28","doi-asserted-by":"crossref","unstructured":"Yan C, Tu Y, Wang X, et al. (2019) STAT: Spatial-Temporal Attention Mechanism for Video Captioning, IEEE Transactions on Multimedia","DOI":"10.1109\/TMM.2020.2966830"},{"key":"7933_CR29","doi-asserted-by":"crossref","unstructured":"Yan C, Li L, Zhang C, et al. (2019) Cross-modality Bridging and Knowledge Transferring for Image Understanding, IEEE Transactions on Multimedia","DOI":"10.1109\/TMM.2019.2903448"},{"key":"7933_CR30","doi-asserted-by":"crossref","unstructured":"Zagoruyko S, Komodakis N (2016) Wide Residual Networks[J]","DOI":"10.5244\/C.30.87"},{"key":"7933_CR31","unstructured":"Zeiler MD, Fergus R (2014) Visualizing and Understanding Convolutional Networks[J]. 8689:818\u2013833"},{"key":"7933_CR32","unstructured":"Zhao S, Yao H et al. (2016) Continuous Probability Distribution Prediction of Image Emotions via Multi-Task Shared Sparse Regression[J]. IEEE Transactions on Multimedia, PP(99):1\u20131"},{"key":"7933_CR33","unstructured":"Zhao S, Yao H, et al. (2016) Predicting Personalized Image Emotion Perceptions in Social Networks[J]. IEEE Transactions on Affective Computing, 1\u20131"},{"key":"7933_CR34","unstructured":"Zhao S, Gao Y, et al. (2017) Real-Time Multimedia Social Event Detection in Microblog[J]. IEEE Transactions on Cybernetics, 1\u201314"},{"key":"7933_CR35","unstructured":"Zhou B, Lapedriza A, Xiao J, et al. (2014) Learning deep features for scene recognition using places database[C]\/\/ International Conference on Neural Information Processing Systems. MIT Press, 487\u2013495"},{"key":"7933_CR36","doi-asserted-by":"crossref","unstructured":"Zhou B, Lapedriza A, Khosla A, et al. (2018) Places: A 10 million Image Database for Scene Recognition.[J]. IEEE Trans Pattern Anal Mach Intell, PP(99):1\u20131","DOI":"10.1109\/TPAMI.2017.2723009"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-019-07933-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-019-07933-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-019-07933-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,23]],"date-time":"2022-09-23T06:32:05Z","timestamp":1663914725000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-019-07933-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7,8]]},"references-count":36,"journal-issue":{"issue":"19","published-print":{"date-parts":[[2019,10]]}},"alternative-id":["7933"],"URL":"https:\/\/doi.org\/10.1007\/s11042-019-07933-2","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"type":"print","value":"1380-7501"},{"type":"electronic","value":"1573-7721"}],"subject":[],"published":{"date-parts":[[2019,7,8]]},"assertion":[{"value":"25 October 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 June 2019","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 June 2019","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 July 2019","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Compliance with Ethical Standards"}},{"value":"The authors declared that they have no conflicts of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of Interest"}}]}}