{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T05:27:42Z","timestamp":1730266062785,"version":"3.28.0"},"reference-count":50,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,7]]},"DOI":"10.1109\/ijcnn.2018.8489227","type":"proceedings-article","created":{"date-parts":[[2018,10,19]],"date-time":"2018-10-19T22:25:09Z","timestamp":1539987909000},"page":"1-8","source":"Crossref","is-referenced-by-count":9,"title":["Multi-granularity Hierarchical Attention Siamese Network for Visual Tracking"],"prefix":"10.1109","author":[{"given":"Xing","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huibin","family":"Tan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Long","family":"Lan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhigang","family":"Luo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuhui","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2014.2333151"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2017.8019422"},{"key":"ref33","article-title":"Action recognition using visual attention","author":"sharma","year":"2015","journal-title":"arXiv preprint arXiv 1511 05271"},{"key":"ref32","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref31","article-title":"Abcnn: Attention-based convolutional neural network for modeling sentence pairs","author":"yin","year":"2015","journal-title":"arXiv preprint arXiv 1512 05193"},{"key":"ref30","article-title":"Dcfnet: Discriminant correlation filters network for visual tracking","author":"wang","year":"2017","journal-title":"arXiv preprint arXiv 1704 04057"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.161"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.206"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.396"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-68612-7_65"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2388226"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.465"},{"key":"ref2","first-page":"864","article-title":"Real-time compressive tracking","author":"zhang","year":"2012","journal-title":"European Conference on Computer Vision"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.230"},{"key":"ref20","first-page":"621","article-title":"Convolutional features for correlation filter based visual tracking","author":"danelljan","year":"2016","journal-title":"IEEE International Conference on Computer Vision Workshop"},{"key":"ref22","first-page":"472","article-title":"Beyond correlation filters: Learning continuous convolution operators for visual tracking","author":"danelljan","year":"2016","journal-title":"European Conference on Computer Vision"},{"key":"ref21","first-page":"597","article-title":"Online tracking by learning discriminative saliency map with convolutional neural network","author":"hong","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.158"},{"key":"ref23","article-title":"Eco: Efficient convolution operators for tracking","author":"danelljan","year":"2016","journal-title":"arXiv preprint arXiv 1611 09224"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.312"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.156"},{"key":"ref10","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref11","article-title":"Once for all: a two-flow convolutional neural network for visual tracking","author":"chen","year":"2016","journal-title":"arXiv preprint arXiv 1604 07507"},{"key":"ref40","article-title":"Sca-cnn: Spatial and channel-wise attention in convolutional networks for image captioning","author":"chen","year":"2016","journal-title":"arXiv preprint arXiv 1611 05594"},{"key":"ref12","first-page":"3","article-title":"Deeptrack: Learning discriminative feature representations by convolutional neural networks for visual tracking","volume":"1","author":"li","year":"2014","journal-title":"The British Machine Vision Conference"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2656628"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2016.2601691"},{"key":"ref15","first-page":"850","article-title":"Fully-convolutional siamese networks for object tracking","author":"bertinetto","year":"2016","journal-title":"European Conference on Computer Vision"},{"key":"ref16","first-page":"749","article-title":"Learning to track at 100 fps with deep regression networks","author":"held","year":"2016","journal-title":"European Conference on Computer Vision"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.531"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.352"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.357"},{"key":"ref4","first-page":"1830","article-title":"Real time robust l1 tracker using accelerated proximal gradient approach","author":"ji","year":"2012","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref3","first-page":"662","article-title":"Real-time visual tracking: Promoting the robustness of correlation filter learning","author":"sui","year":"2016","journal-title":"European Conference on Computer Vision"},{"key":"ref6","first-page":"1822","article-title":"Visual tracking via adaptive structural local sparse appearance model","author":"jia","year":"2012","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"470","DOI":"10.1007\/978-3-540-24671-8_37","article-title":"Adaptive probabilistic visual tracking with incremental subspace update","volume":"3022","author":"ross","year":"2004","journal-title":"Lecture Notes in Computer Science"},{"key":"ref8","first-page":"263","article-title":"Struck: Structured output tracking with kernels","author":"hare","year":"2012","journal-title":"IEEE International Conference on Computer Vision"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.226"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.466"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.462"},{"key":"ref46","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.196"},{"key":"ref48","first-page":"65.1","article-title":"Accurate scale estimation for robust visual tracking","author":"danelljan","year":"2014","journal-title":"British Machine Vision Conference"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2345390"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref41","article-title":"Squeeze-and-excitation networks","author":"hu","year":"2017","journal-title":"arXiv preprint arXiv 1709 04396"},{"key":"ref44","first-page":"12","article-title":"Inception-v4, inception-resnet and the impact of residual connections on learning","volume":"4","author":"szegedy","year":"2017","journal-title":"AAAI"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"}],"event":{"name":"2018 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2018,7,8]]},"location":"Rio de Janeiro","end":{"date-parts":[[2018,7,13]]}},"container-title":["2018 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8465565\/8488986\/08489227.pdf?arnumber=8489227","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,23]],"date-time":"2020-08-23T22:11:35Z","timestamp":1598220695000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8489227\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,7]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/ijcnn.2018.8489227","relation":{},"subject":[],"published":{"date-parts":[[2018,7]]}}}