{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,25]],"date-time":"2025-09-25T14:30:58Z","timestamp":1758810658420,"version":"3.37.3"},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2024,2,29]],"date-time":"2024-02-29T00:00:00Z","timestamp":1709164800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,2,29]],"date-time":"2024-02-29T00:00:00Z","timestamp":1709164800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Key Projects of Heilongjiang Provincial Natural Science Foundation","award":["No. ZD2022F001"],"award-info":[{"award-number":["No. ZD2022F001"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1007\/s00371-024-03282-w","type":"journal-article","created":{"date-parts":[[2024,2,29]],"date-time":"2024-02-29T17:02:42Z","timestamp":1709226162000},"page":"8895-8905","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Target-aware pooling combining global contexts for aerial tracking"],"prefix":"10.1007","volume":"40","author":[{"given":"Yue","family":"Wu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3475-6098","authenticated-orcid":false,"given":"Chengtao","family":"Cai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chai Kiat","family":"Yeo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kejun","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,2,29]]},"reference":[{"key":"3282_CR1","first-page":"1","volume":"66","author":"MH Junos","year":"2021","unstructured":"Junos, M.H., Mohd Khairuddin, A.S., Thannirmalai, S., Dahari, M.: Automatic detection of oil palm fruits from UAV images using an improved yolo model. Vis. Comput. 66, 1\u201315 (2021)","journal-title":"Vis. Comput."},{"issue":"1","key":"3282_CR2","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1007\/s00371-021-02331-y","volume":"39","author":"J Fan","year":"2023","unstructured":"Fan, J., Yang, X., Lu, R., Li, W., Huang, Y.: Long-term visual tracking algorithm for UAVs based on kernel correlation filtering and surf features. Vis. Comput. 39(1), 319\u2013333 (2023)","journal-title":"Vis. Comput."},{"key":"3282_CR3","doi-asserted-by":"publisher","first-page":"122772","DOI":"10.1109\/ACCESS.2020.3007261","volume":"8","author":"S Li","year":"2020","unstructured":"Li, S., Chu, J., Zhong, G., Leng, L., Miao, J.: Robust visual tracking with occlusion judgment and re-detection. IEEE Access 8, 122772\u2013122781 (2020)","journal-title":"IEEE Access"},{"key":"3282_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13640-020-0496-6","volume":"2020","author":"Y Yuan","year":"2020","unstructured":"Yuan, Y., Chu, J., Leng, L., Miao, J., Kim, B.-G.: A scale-adaptive object-tracking algorithm with occlusion detection. EURASIP J. Image Video Process. 2020, 1\u201315 (2020)","journal-title":"EURASIP J. Image Video Process."},{"issue":"3","key":"3282_CR5","doi-asserted-by":"publisher","first-page":"583","DOI":"10.1109\/TPAMI.2014.2345390","volume":"37","author":"JF Henriques","year":"2014","unstructured":"Henriques, J.F., Caseiro, R., Martins, P., Batista, J.: High-speed tracking with kernelized correlation filters. IEEE Trans. Pattern Anal. Mach. Intell. 37(3), 583\u2013596 (2014)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3282_CR6","doi-asserted-by":"crossref","unstructured":"Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR\u201905), vol. 1, pp. 886\u2013893. IEEE (2005)","DOI":"10.1109\/CVPR.2005.177"},{"key":"3282_CR7","doi-asserted-by":"crossref","unstructured":"Huang, Z., Fu, C., Li, Y., Lin, F., Lu, P.: Learning aberrance repressed correlation filters for real-time UAV tracking. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2891\u20132900 (2019)","DOI":"10.1109\/ICCV.2019.00298"},{"key":"3282_CR8","doi-asserted-by":"crossref","unstructured":"Li, Y., Fu, C., Ding, F., Huang, Z., Lu, G.: Autotrack: towards high-performance visual tracking for UAV with automatic spatio-temporal regularization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11923\u201311932 (2020)","DOI":"10.1109\/CVPR42600.2020.01194"},{"issue":"4","key":"3282_CR9","doi-asserted-by":"publisher","first-page":"1010","DOI":"10.3390\/s20041010","volume":"20","author":"Y Zhang","year":"2020","unstructured":"Zhang, Y., Chu, J., Leng, L., Miao, J.: Mask-refined r-cnn: a network for refining object details in instance segmentation. Sensors 20(4), 1010 (2020)","journal-title":"Sensors"},{"key":"3282_CR10","doi-asserted-by":"publisher","first-page":"19959","DOI":"10.1109\/ACCESS.2018.2815149","volume":"6","author":"J Chu","year":"2018","unstructured":"Chu, J., Guo, Z., Leng, L.: Object detection based on multi-layer convolution feature fusion and online hard example mining. IEEE Access 6, 19959\u201319967 (2018)","journal-title":"IEEE Access"},{"key":"3282_CR11","doi-asserted-by":"crossref","unstructured":"Chopra, S., Hadsell, R., LeCun, Y.: Learning a similarity metric discriminatively, with application to face verification. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR\u201905), vol. 1, pp. 539\u2013546. IEEE (2005)","DOI":"10.1109\/CVPR.2005.202"},{"key":"3282_CR12","doi-asserted-by":"crossref","unstructured":"Bertinetto, L., Valmadre, J., Henriques, J.F., Vedaldi, A., Torr, P.H.: Fully-convolutional SIAMESE networks for object tracking. In: European Conference on Computer Vision, pp. 850\u2013865. Springer (2016)","DOI":"10.1007\/978-3-319-48881-3_56"},{"key":"3282_CR13","doi-asserted-by":"crossref","unstructured":"Zhu, Z., Wang, Q., Li, B., Wu, W., Yan, J., Hu, W.: Distractor-aware siamese networks for visual object tracking. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 101\u2013117 (2018)","DOI":"10.1007\/978-3-030-01240-3_7"},{"key":"3282_CR14","first-page":"91","volume":"28","author":"S Ren","year":"2015","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: towards real-time object detection with region proposal networks. Adv. Neural Inf. Process. Syst. 28, 91\u201399 (2015)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"3282_CR15","doi-asserted-by":"crossref","unstructured":"Fu, C., Cao, Z., Li, Y., Ye, J., Feng, C.: Siamese anchor proposal network for high-speed aerial tracking. In: 2021 IEEE International Conference on Robotics and Automation (ICRA), pp. 510\u2013516. IEEE (2021)","DOI":"10.1109\/ICRA48506.2021.9560756"},{"issue":"6","key":"3282_CR16","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1145\/3065386","volume":"60","author":"A Krizhevsky","year":"2017","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. Commun. ACM 60(6), 84\u201390 (2017)","journal-title":"Commun. ACM"},{"key":"3282_CR17","first-page":"66","volume":"30","author":"A Vaswani","year":"2017","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141, Polosukhin, I.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30, 66 (2017)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"3282_CR18","unstructured":"Devlin, J., Chang, M.-W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"3282_CR19","doi-asserted-by":"crossref","unstructured":"L\u00fcscher, C., Beck, E., Irie, K., Kitza, M., Michel, W., Zeyer, A., Schl\u00fcter, R., Ney, H.: Rwth asr Systems for Librispeech: Hybrid vs Attention. INTERSPEECH (2019)","DOI":"10.21437\/Interspeech.2019-1780"},{"key":"3282_CR20","doi-asserted-by":"crossref","unstructured":"Cao, Z., Fu, C., Ye, J., Li, B., Li, Y.: Hift: hierarchical feature transformer for aerial tracking. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15457\u201315466 (2021)","DOI":"10.1109\/ICCV48922.2021.01517"},{"key":"3282_CR21","doi-asserted-by":"crossref","unstructured":"Cao, Z., Huang, Z., Pan, L., Zhang, S., Liu, Z., Fu, C.: Tctrack: temporal contexts for aerial tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14798\u201314808 (2022)","DOI":"10.1109\/CVPR52688.2022.01438"},{"key":"3282_CR22","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818\u20132826 (2016)","DOI":"10.1109\/CVPR.2016.308"},{"key":"3282_CR23","doi-asserted-by":"crossref","unstructured":"Mueller, M., Smith, N., Ghanem, B.: A benchmark and simulator for UAV tracking. In: European Conference on Computer Vision, pp. 445\u2013461. Springer (2016)","DOI":"10.1007\/978-3-319-46448-0_27"},{"key":"3282_CR24","doi-asserted-by":"crossref","unstructured":"Li, S., Yeung, D.-Y.: Visual object tracking for unmanned aerial vehicles: a benchmark and new motion models. In: Thirty-First AAAI Conference on Artificial Intelligence (2017)","DOI":"10.1609\/aaai.v31i1.11205"},{"key":"3282_CR25","doi-asserted-by":"crossref","unstructured":"Wu, Y., Lim, J., Yang, M.-H.: Online object tracking: a benchmark. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2411\u20132418 (2013)","DOI":"10.1109\/CVPR.2013.312"},{"issue":"8","key":"3282_CR26","doi-asserted-by":"publisher","first-page":"3931","DOI":"10.3390\/app12083931","volume":"12","author":"K Huang","year":"2022","unstructured":"Huang, K., Qin, P., Tu, X., Leng, L., Chu, J.: Siamcam: a real-time siamese network for object tracking with compensating attention mechanism. Appl. Sci. 12(8), 3931 (2022)","journal-title":"Appl. Sci."},{"key":"3282_CR27","doi-asserted-by":"crossref","unstructured":"Huang, K., Pan, C., Chu, J., Leng, L., Miao, J., Wu, J., Wang, L.: Siamorpn: enabling orthogonality between object and background in siamese object tracking. In: 2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI), pp. 644\u2013651. IEEE (2022)","DOI":"10.1109\/ICTAI56018.2022.00100"},{"key":"3282_CR28","doi-asserted-by":"crossref","unstructured":"Han, G., Ma, J., Huang, S., Chen, L., Chang, S.-F.: Few-shot object detection with fully cross-transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5321\u20135330 (2022)","DOI":"10.1109\/CVPR52688.2022.00525"},{"key":"3282_CR29","first-page":"1","volume":"66","author":"Q Zhang","year":"2022","unstructured":"Zhang, Q., Ge, Y., Zhang, C., Bi, H.: Tprnet: camouflaged object detection via transformer-induced progressive refinement network. Vis. Comput. 66, 1\u201315 (2022)","journal-title":"Vis. Comput."},{"key":"3282_CR30","doi-asserted-by":"crossref","unstructured":"Yang, F., Yang, H., Fu, J., Lu, H., Guo, B.: Learning texture transformer network for image super-resolution. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5791\u20135800 (2020)","DOI":"10.1109\/CVPR42600.2020.00583"},{"key":"3282_CR31","unstructured":"Lin, F., Wu, S., Ma, Y., Tian, S.: Full-scale selective transformer for semantic segmentation. In: Proceedings of the Asian Conference on Computer Vision, pp. 2663\u20132679 (2022)"},{"key":"3282_CR32","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: European Conference on Computer Vision, pp. 213\u2013229. Springer (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"3282_CR33","unstructured":"Huang, Z., Zhang, S., Pan, L., Qing, Z., Tang, M., Liu, Z., Ang\u00a0Jr, M.H.: Tada! Temporally-adaptive convolutions for video understanding. In: ICLR (2022)"},{"key":"3282_CR34","doi-asserted-by":"crossref","unstructured":"Chen, X., Yan, B., Zhu, J., Wang, D., Yang, X., Lu, H.: Transformer tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8126\u20138135 (2021)","DOI":"10.1109\/CVPR46437.2021.00803"},{"key":"3282_CR35","doi-asserted-by":"crossref","unstructured":"Yan, B., Peng, H., Fu, J., Wang, D., Lu, H.: Learning spatio-temporal transformer for visual tracking. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10448\u201310457 (2021)","DOI":"10.1109\/ICCV48922.2021.01028"},{"key":"3282_CR36","doi-asserted-by":"crossref","unstructured":"Jiang, B., Luo, R., Mao, J., Xiao, T., Jiang, Y.: Acquisition of localization confidence for accurate object detection. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 784\u2013799 (2018)","DOI":"10.1007\/978-3-030-01264-9_48"},{"key":"3282_CR37","first-page":"66","volume":"28","author":"M Jaderberg","year":"2015","unstructured":"Jaderberg, M., Simonyan, K., Zisserman, A., et al.: Spatial transformer networks. Adv. Neural Inf. Process. Syst. 28, 66 (2015)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"3282_CR38","unstructured":"Glorot, X., Bordes, A., Bengio, Y.: Deep sparse rectifier neural networks. In: Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, pp. 315\u2013323. JMLR Workshop and Conference Proceedings (2011)"},{"key":"3282_CR39","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., Zitnick, C.L.: Microsoft coco: common objects in context. In: European Conference on Computer Vision, pp. 740\u2013755. Springer(2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"issue":"5","key":"3282_CR40","doi-asserted-by":"publisher","first-page":"1562","DOI":"10.1109\/TPAMI.2019.2957464","volume":"43","author":"L Huang","year":"2021","unstructured":"Huang, L., Zhao, X., Huang, K.: Got-10k: a large high-diversity benchmark for generic object tracking in the wild. IEEE Trans. Pattern Anal. Mach. Intell. 43(5), 1562\u20131577 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"3","key":"3282_CR41","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al.: Imagenet large scale visual recognition challenge. Int. J. Comput. Vis. 115(3), 211\u2013252 (2015)","journal-title":"Int. J. Comput. Vis."},{"key":"3282_CR42","doi-asserted-by":"crossref","unstructured":"Real, E., Shlens, J., Mazzocchi, S., Pan, X., Vanhoucke, V.: Youtube-boundingboxes: a large high-precision human-annotated data set for object detection in video. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5296\u20135305 (2017)","DOI":"10.1109\/CVPR.2017.789"},{"issue":"2","key":"3282_CR43","doi-asserted-by":"publisher","first-page":"439","DOI":"10.1007\/s11263-020-01387-y","volume":"129","author":"H Fan","year":"2021","unstructured":"Fan, H., Bai, H., Lin, L., Yang, F., Chu, P., Deng, G., Yu, S., Huang, M., Liu, J., Xu, Y., et al.: Lasot: a high-quality large-scale single object tracking benchmark. Int. J. Comput. Vis. 129(2), 439\u2013461 (2021)","journal-title":"Int. J. Comput. Vis."},{"key":"3282_CR44","doi-asserted-by":"crossref","unstructured":"Yu, J., Jiang, Y., Wang, Z., Cao, Z., Huang, T.: Unitbox: an advanced object detection network. In: Proceedings of the 24th ACM International Conference on Multimedia, pp. 516\u2013520 (2016)","DOI":"10.1145\/2964284.2967274"},{"key":"3282_CR45","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\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-024-03282-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-024-03282-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-024-03282-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,12]],"date-time":"2024-11-12T09:19:46Z","timestamp":1731403186000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-024-03282-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,29]]},"references-count":45,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2024,12]]}},"alternative-id":["3282"],"URL":"https:\/\/doi.org\/10.1007\/s00371-024-03282-w","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"type":"print","value":"0178-2789"},{"type":"electronic","value":"1432-2315"}],"subject":[],"published":{"date-parts":[[2024,2,29]]},"assertion":[{"value":"15 January 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 February 2024","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"All the authors do not have any possible conflicts of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}