{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T00:47:30Z","timestamp":1768524450120,"version":"3.49.0"},"reference-count":52,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2022,12,5]],"date-time":"2022-12-05T00:00:00Z","timestamp":1670198400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,12,5]],"date-time":"2022-12-05T00:00:00Z","timestamp":1670198400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61866016"],"award-info":[{"award-number":["61866016"]}],"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":["62061019"],"award-info":[{"award-number":["62061019"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004479","name":"Natural Science Foundation of Jiangxi Province","doi-asserted-by":"publisher","award":["20212BAB202013"],"award-info":[{"award-number":["20212BAB202013"]}],"id":[{"id":"10.13039\/501100004479","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004479","name":"Natural Science Foundation of Jiangxi Province","doi-asserted-by":"publisher","award":["20202BABL202014"],"award-info":[{"award-number":["20202BABL202014"]}],"id":[{"id":"10.13039\/501100004479","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100009102","name":"Education Department of Jiangxi Province","doi-asserted-by":"publisher","award":["GJJ201107"],"award-info":[{"award-number":["GJJ201107"]}],"id":[{"id":"10.13039\/501100009102","id-type":"DOI","asserted-by":"publisher"}]},{"name":"the Youth Top Talent Foundation of Jiangxi Science and Technology Normal University","award":["2018QNBJRC002"],"award-info":[{"award-number":["2018QNBJRC002"]}]},{"DOI":"10.13039\/501100011343","name":"Key Laboratory of System Control and Information Processing","doi-asserted-by":"publisher","award":["Scip202106"],"award-info":[{"award-number":["Scip202106"]}],"id":[{"id":"10.13039\/501100011343","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Machine Vision and Applications"],"published-print":{"date-parts":[[2023,1]]},"DOI":"10.1007\/s00138-022-01354-2","type":"journal-article","created":{"date-parts":[[2022,12,5]],"date-time":"2022-12-05T05:05:31Z","timestamp":1670216731000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["SiamMMF: multi-modal multi-level fusion object tracking based on Siamese networks"],"prefix":"10.1007","volume":"34","author":[{"given":"Zhen","family":"Yang","sequence":"first","affiliation":[]},{"given":"Peng","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Dunyun","family":"He","sequence":"additional","affiliation":[]},{"given":"Zhongwang","family":"Cai","sequence":"additional","affiliation":[]},{"given":"Zhijian","family":"Yin","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,12,5]]},"reference":[{"key":"1354_CR1","doi-asserted-by":"crossref","unstructured":"Grabner, H., Grabner, M., Bischof, H.: Real-time tracking via on-line boosting. In: Proceedings of the 2006 British Machine Vision, pp. 47\u201356 (2006)","DOI":"10.5244\/C.20.6"},{"issue":"2","key":"1354_CR2","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1109\/TPAMI.2007.35","volume":"29","author":"S Avidan","year":"2007","unstructured":"Avidan, S.: Ensemble tracking. IEEE Trans. Pattern Anal. Mach. Intell. 29(2), 261\u2013271 (2007)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1354_CR3","doi-asserted-by":"crossref","unstructured":"Grabner, H., Leistner, C., Bischof, H.: Semi-supervised on-line boosting for robust tracking. In: European Conference on Computer Vision, pp. 234\u2013247 (2008)","DOI":"10.1007\/978-3-540-88682-2_19"},{"key":"1354_CR4","doi-asserted-by":"crossref","unstructured":"Zhang, J. M., Ma, S.G., Sclaroff, S.: MEEM: robust tracking via multiple experts using entropy minimization. In: European Conference on Computer Vision, pp. 188\u2013203 (2014)","DOI":"10.1007\/978-3-319-10599-4_13"},{"issue":"10","key":"1354_CR5","doi-asserted-by":"publisher","first-page":"2096","DOI":"10.1109\/TPAMI.2015.2509974","volume":"38","author":"S Hare","year":"2015","unstructured":"Hare, S., Golodetz, S., Saffari, A.: Struck: structured output tracking with kernels. IEEE Trans. Pattern Anal. Mach. Intell. 38(10), 2096\u20132109 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1354_CR6","doi-asserted-by":"crossref","unstructured":"Bertinetto, L., Valmadre, J., Henriques, J. F., Vedaldi, A., Torr, P. H. S.: Fully-convolutional siamese networks for object tracking, Computer Vision - ECCV 2016 Workshops, pp. 850\u2013865 (2016)","DOI":"10.1007\/978-3-319-48881-3_56"},{"key":"1354_CR7","doi-asserted-by":"crossref","unstructured":"Li, B., Yan, J.J., Wu, W., Zhu, Z., Hu, X.L.: High performance visual tracking with siamese region proposal network. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2018), pp. 8971\u20138980(2018)","DOI":"10.1109\/CVPR.2018.00935"},{"key":"1354_CR8","doi-asserted-by":"crossref","unstructured":"Li, B., Wu, W., Wang, Q., Zhang, F. Y., Xing, J. L., Yan, J. J.: SiamRPN++: evolution of siamese visual tracking with very deep networks. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2019), pp. 4277\u20134286 (2019)","DOI":"10.1109\/CVPR.2019.00441"},{"key":"1354_CR9","doi-asserted-by":"crossref","unstructured":"Guo, D.Y., Wang, J., Cui, Y., Wang, Z.H., Chen, S.Y.: SiamCAR: siamese fully convolutional classification and regression for visual tracking. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00630"},{"key":"1354_CR10","doi-asserted-by":"crossref","unstructured":"Liu, H.P., Sun, F.C.: Fusion tracking in color and infrared images using joint sparse representation, Science China: Information Sciences, pp. 104\u2013113 (2012)","DOI":"10.1007\/s11432-011-4536-9"},{"key":"1354_CR11","doi-asserted-by":"crossref","unstructured":"Zhang, X.C., Ye, P., Leung, H., Gong, K., Xiao, G.: Object fusion tracking based on visible and infrared images: A comprehensive review, Information Fusion, pp. 166\u2013187 (2020)","DOI":"10.1016\/j.inffus.2020.05.002"},{"key":"1354_CR12","doi-asserted-by":"crossref","unstructured":"Li, C.L., Liang, X.Y., Lu, Y.J.: RGB-T object tracking: benchmark and baseline, Pattern Recognition (2018)","DOI":"10.1016\/j.patcog.2019.106977"},{"key":"1354_CR13","unstructured":"Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection, In CVPR (2005)"},{"key":"1354_CR14","doi-asserted-by":"crossref","unstructured":"Lowe, D.: Distinctive image features from scale-invariant keypoints, IJCV (2004)","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"1354_CR15","unstructured":"Wu, Y., Blasch, E., Chen, G.S.: Multiple source data fusion via sparse representation for robust visual tracking. In: 14th International Conference on Information Fusion, pp. 1\u20138 (2011)"},{"key":"1354_CR16","doi-asserted-by":"crossref","unstructured":"Lan, X.Y., Ma, A.J., Yuen, P.C.: Multi-cue visual tracking using robust feature-level fusion based on joint sparse representation. In: IEEE Conference on Computer Vision and Pattern Recognition(CVPR), pp. 1194\u20131201 (2014)","DOI":"10.1109\/CVPR.2014.156"},{"issue":"12","key":"1354_CR17","doi-asserted-by":"publisher","first-page":"5743","DOI":"10.1109\/TIP.2016.2614135","volume":"25","author":"CL Li","year":"2016","unstructured":"Li, C.L., Cheng, H., Hu, S.Y.: Learning collaborative sparse representation for grayscale-thermal tracking. IEEE Trans. Image Process. 25(12), 5743\u20135756 (2016)","journal-title":"IEEE Trans. Image Process."},{"key":"1354_CR18","doi-asserted-by":"crossref","unstructured":"Lan, X.Y., Ye, M., Zhang, S.P.: Robust collaborative discriminative learning for RGB-infrared tracking. In: 32nd AAAI Conference on Artificial Intelligence, pp. 7008\u20137015 (2018)","DOI":"10.1609\/aaai.v32i1.12307"},{"key":"1354_CR19","doi-asserted-by":"crossref","unstructured":"Bolme, D.S., Beveridge, J.R., Draper, B.A.: Visual object tracking using adaptive correlation filters. In: The 23rd IEEE Conference on Computer Vision and Pattern Recognition (2010)","DOI":"10.1109\/CVPR.2010.5539960"},{"key":"1354_CR20","first-page":"1","volume":"19","author":"S Zhao","year":"2022","unstructured":"Zhao, S., Zhang, Z., Zhang, T., Guo, W., Luo, Y.: Transferable SAR image classification crossing different satellites under open set condition. IEEE Geosci. Remote Sens. Lett. 19, 1\u20135 (2022)","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"1354_CR21","first-page":"1","volume":"99","author":"T Zhang","year":"2022","unstructured":"Zhang, T., Quan, S.N., Yang, Z., Guo, W.W., Zhang, Z.H., Gan, H.P.: A two-stage method for ship detection using PolSAR image. IEEE Trans. Geosci. Remote Sens. 99, 1\u201319 (2022)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"1354_CR22","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1016\/j.neucom.2018.01.068","volume":"286","author":"B Bai","year":"2018","unstructured":"Bai, B., Zhong, B.N., Ouyang, G.: Kernel correlation filters for visual tracking with adaptive fusion of heterogeneous cues. Neurocomputing 286, 109\u2013120 (2018)","journal-title":"Neurocomputing"},{"key":"1354_CR23","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1016\/j.neucom.2019.01.022","volume":"334","author":"SY Zhai","year":"2019","unstructured":"Zhai, S.Y., Shao, P.P., Liang, X.Y.: Fast RGB-T tracking via cross-modal correlation filters. Neurocomputing 334, 172\u2013181 (2019)","journal-title":"Neurocomputing"},{"key":"1354_CR24","doi-asserted-by":"crossref","unstructured":"Wang, Y. L., Li, C.L., Tang, J.: Learning soft-consistent correlation filters for RGB-T object tracking. In: Chinese Conference on Pattern Recognition and Computer Vision (PRCV), pp. 295\u2013306 (2018)","DOI":"10.1007\/978-3-030-03341-5_25"},{"key":"1354_CR25","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1016\/j.neucom.2017.11.068","volume":"281","author":"CL Li","year":"2018","unstructured":"Li, C.L., Wu, X.H., Zhao, N.: Fusing two-stream convolutional neural networks for RGB-T object tracking. Neurocomputing 281, 78\u201385 (2018)","journal-title":"Neurocomputing"},{"key":"1354_CR26","doi-asserted-by":"crossref","unstructured":"Zhu, Y.B., Li, C.L., Luo, B.: Dense feature aggregation and pruning for RGBT tracking. In: Proceedings of the 27th ACM Intermational Conference on Multimedia, pp. 465\u2013472 (2019)","DOI":"10.1145\/3343031.3350928"},{"key":"1354_CR27","doi-asserted-by":"crossref","unstructured":"Li, C.L., Lu, A.D., Zheng, A.H.: Multi-adapter RGBT tracking, arXiv Preprint, (2019)","DOI":"10.1109\/ICCVW.2019.00279"},{"key":"1354_CR28","doi-asserted-by":"crossref","unstructured":"Yang, R., Zhu, Y.B., Wang, X.: Learning target-oriented dual attention for robust RGB-T tracking. In: 2019 IEEE International Conference on Image Processing (ICIP) (2019)","DOI":"10.1109\/ICIP.2019.8803528"},{"key":"1354_CR29","doi-asserted-by":"crossref","unstructured":"Ma, J., Chen, C., Li, C.: Infrared and visible image fusion via gradient transfer and total variation minimization, Information Fusion, pp. 100\u2013109 (2016)","DOI":"10.1016\/j.inffus.2016.02.001"},{"key":"1354_CR30","doi-asserted-by":"crossref","unstructured":"Liu, C.H., Qi, Y., Ding, W.R.: Infrared and visible image fusion method based on saliency detection in sparse domain, Infrared Physics and Technology, pp. 94\u2013102 (2017)","DOI":"10.1016\/j.infrared.2017.04.018"},{"key":"1354_CR31","unstructured":"Zhu, Y.B., Li, C. L., Lu, Y.: FANet: quality-aware feature aggregation network for RGB-T tracking, arXiv Preprint (2018)"},{"key":"1354_CR32","doi-asserted-by":"crossref","unstructured":"Zhang, X. C., Ye, P., Peng, S.Y., Liu, J., Gong, K., Xiao, G.: SiamFT: an RGB-infrared fusion tracking method via fully convolutional siamese networks, IEEE Access (2019)","DOI":"10.1109\/ACCESS.2019.2936914"},{"key":"1354_CR33","doi-asserted-by":"crossref","unstructured":"Zhang, X.C., Ye, P., Peng, S.Y., Liu, J., Xiao, G.: DSiamMFT: an RGB-T fusion tracking method via dynamic siamese networks using multi-layer feature fusion, Signal Process.-Image Commun. (2020)","DOI":"10.1016\/j.image.2019.115756"},{"key":"1354_CR34","doi-asserted-by":"crossref","unstructured":"Liu, J., Zhang, S., Wang, S., Metaxas, D.: Multispectral deep neural networks for pedestrian detection. In: British Machine Vision Conference 2016, pp. 73.1-73.13 (2016)","DOI":"10.5244\/C.30.73"},{"issue":"11","key":"1354_CR35","first-page":"2622","volume":"65","author":"H Yin","year":"2018","unstructured":"Yin, H.: Tensor sparse representation for 3-D medical image fusion using weighted average rule. IEEE Trans. 65(11), 2622\u20132633 (2018)","journal-title":"IEEE Trans."},{"issue":"3","key":"1354_CR36","first-page":"1076","volume":"26","author":"P Hill","year":"2017","unstructured":"Hill, P., Al-Mualla, M.E., Bull, D.: Perceptual image fusion using wavelets. IEEE Trans. 26(3), 1076\u20131088 (2017)","journal-title":"IEEE Trans."},{"key":"1354_CR37","doi-asserted-by":"crossref","unstructured":"Li, C.L., Lu, A.D., Zheng, A.H., Tu, Z.Z., Tang, J.: Multi-Adapter RGBT Tracking. In: 2019 IEEE\/CVF International Conference on Computer Vision Workshops (ICCVW), pp. 2262-2270 (2019)","DOI":"10.1109\/ICCVW.2019.00279"},{"key":"1354_CR38","doi-asserted-by":"crossref","unstructured":"Zhang, P., Zhao, J., Wang, D., Lu, H., Yang, X.: Jointly modeling motion and appearance cues for robust RGB-T tracking, arXiv preprint (2020)","DOI":"10.1109\/TIP.2021.3060862"},{"key":"1354_CR39","doi-asserted-by":"crossref","unstructured":"Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M.: Imagenet large scale visual recognition challenge, IJCV (2015)","DOI":"10.1007\/s11263-015-0816-y"},{"key":"1354_CR40","doi-asserted-by":"crossref","unstructured":"Ma, C., Huang, J.B., Yang, X.K., Yang, M.H.: Robust visual tracking via hierarchical convolutional features, TPAMI (2018)","DOI":"10.1109\/WCSP.2018.8555868"},{"key":"1354_CR41","doi-asserted-by":"crossref","unstructured":"Li, B., Wu, W., Wang, Q., Zhang, F.Y., Xing, J.L., Yan, J.J.: Siamrpn++: evolution of siamese visual tracking with very deep networks, In CVPR (2019)","DOI":"10.1109\/CVPR.2019.00441"},{"key":"1354_CR42","doi-asserted-by":"crossref","unstructured":"Danelljan, M., Robinson, A., Khan, F.S., Felsberg, M.: Beyond correlation filters: learning continuous convolution operators for visual tracking. In: Proc. Eur. Conf. pp. 472\u2013488 (2016)","DOI":"10.1007\/978-3-319-46454-1_29"},{"key":"1354_CR43","doi-asserted-by":"crossref","unstructured":"Danelljan, M., Khan, F.S., Felsberg, M., Weijer, J.V.: Adaptive color attributes for real-time visual tracking. In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit, pp. 1090-1097 (2014)","DOI":"10.1109\/CVPR.2014.143"},{"key":"1354_CR44","doi-asserted-by":"crossref","unstructured":"Henriques, J.F., Caseiro, R., Martins, P., Batista, J.: Exploiting the circulant structure of tracking-by-detection with kernels. In: Proc. Eur. Conf. Comput. Vis., pp. 702-715. Berlin, Germany, Springer (2012)","DOI":"10.1007\/978-3-642-33765-9_50"},{"key":"1354_CR45","doi-asserted-by":"crossref","unstructured":"Wang, D., Lu, H.: Visual tracking via probability continuous outlier model. In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit, pp. 3478\u20133485 (2014)","DOI":"10.1109\/CVPR.2014.445"},{"key":"1354_CR46","doi-asserted-by":"crossref","unstructured":"Danelljan, M., Bhat, G., Khan, F.S., Felsberg, M.: ECO: efficient convolution operators for tracking, inProc. IEEE Conf. Comput. Vis. Pattern Recognit, pp. 6638\u20136646 (2017)","DOI":"10.1109\/CVPR.2017.733"},{"key":"1354_CR47","unstructured":"Li, C., Zhu, C., Zhang, J., Luo, B., Wu, X., Tang, J.: Learning local-global multi-graph descriptors for RGB-T object tracking, IEEE Trans (to be published)"},{"issue":"8","key":"1354_CR48","doi-asserted-by":"publisher","first-page":"1619","DOI":"10.1109\/TPAMI.2010.226","volume":"33","author":"B Babenko","year":"2011","unstructured":"Babenko, B., Yang, M.-H., Belongie, S.: Robust object tracking with online multiple instance learning. IEEE Trans. Pattern Anal. Mach. Intell. 33(8), 1619\u20131632 (2011)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1354_CR49","doi-asserted-by":"crossref","unstructured":"Li, Y., Zhu, J., Hoi, S.C.: Reliable patch trackers: robust visual tracking by exploiting reliable patches, inProc. IEEE Conf. Comput. Vis. Pattern Recognit, pp. 353\u2013361 (2015)","DOI":"10.1109\/CVPR.2015.7298632"},{"issue":"7","key":"1354_CR50","doi-asserted-by":"publisher","first-page":"1409","DOI":"10.1109\/TPAMI.2011.239","volume":"34","author":"Z Kalal","year":"2012","unstructured":"Kalal, Z., Mikolajczyk, K., Matas, J.: Tracking-learning-detection. IEEE Trans. Pattern Anal. Mach. Intell. 34(7), 1409\u20131422 (2012)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"10","key":"1354_CR51","doi-asserted-by":"publisher","first-page":"2096","DOI":"10.1109\/TPAMI.2015.2509974","volume":"38","author":"S Hare","year":"2016","unstructured":"Hare, S., Golodetz, S., Saffari, A., Vineet, V., Cheng, M.-M., Hicks, S.L., Torr, P.H.: Struck: structured output tracking with kernels. IEEE Trans. Pattern Anal. Mach. Intell. 38(10), 2096\u20132109 (2016)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1354_CR52","doi-asserted-by":"crossref","unstructured":"Zhang, K., Zhang, L., Yang, M.-H.: Real-time compressive tracking. In: Proc. Eur. Conf. Comput. Vis. pp. 864-877, Berlin, Germany, Springer (2012)","DOI":"10.1007\/978-3-642-33712-3_62"}],"container-title":["Machine Vision and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-022-01354-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00138-022-01354-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-022-01354-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,17]],"date-time":"2023-01-17T16:08:45Z","timestamp":1673971725000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00138-022-01354-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,5]]},"references-count":52,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2023,1]]}},"alternative-id":["1354"],"URL":"https:\/\/doi.org\/10.1007\/s00138-022-01354-2","relation":{},"ISSN":["0932-8092","1432-1769"],"issn-type":[{"value":"0932-8092","type":"print"},{"value":"1432-1769","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,12,5]]},"assertion":[{"value":"7 January 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 September 2022","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 October 2022","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 December 2022","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"7"}}