{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T07:24:33Z","timestamp":1763018673748,"version":"3.37.3"},"reference-count":87,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2023,9,19]],"date-time":"2023-09-19T00:00:00Z","timestamp":1695081600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,9,19]],"date-time":"2023-09-19T00:00:00Z","timestamp":1695081600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100004750","name":"Aeronautical Science Foundation of China","doi-asserted-by":"publisher","award":["20142057006"],"award-info":[{"award-number":["20142057006"]}],"id":[{"id":"10.13039\/501100004750","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62006152","61773262"],"award-info":[{"award-number":["62006152","61773262"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2024,6]]},"DOI":"10.1007\/s00371-023-03074-8","type":"journal-article","created":{"date-parts":[[2023,9,19]],"date-time":"2023-09-19T16:15:51Z","timestamp":1695140151000},"page":"4149-4166","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Multi-granularity attention in attention for person re-identification in aerial images"],"prefix":"10.1007","volume":"40","author":[{"given":"Simin","family":"Xu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lingkun","family":"Luo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haichao","family":"Hong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jilin","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9362-4642","authenticated-orcid":false,"given":"Shiqiang","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,9,19]]},"reference":[{"key":"3074_CR1","unstructured":"Zheng, L., Yang, Y., Hauptmann, A.G.: Person re-identification: past, present and future. arXiv preprint arXiv:1610.02984 (2016)"},{"issue":"9","key":"3074_CR2","doi-asserted-by":"publisher","first-page":"4192","DOI":"10.1109\/TIP.2019.2908062","volume":"28","author":"G Chen","year":"2019","unstructured":"Chen, G., Lu, J., Yang, M., Zhou, J.: Spatial-temporal attention-aware learning for video-based person re-identification. IEEE Trans. Image Process. 28(9), 4192\u20134205 (2019). https:\/\/doi.org\/10.1109\/TIP.2019.2908062","journal-title":"IEEE Trans. Image Process."},{"key":"3074_CR3","first-page":"1","volume":"10","author":"J Xie","year":"2021","unstructured":"Xie, J., Ge, Y., Zhang, J., Huang, S., Wang, H.: Low-resolution assisted three-stream network for person re-identification. Vis. Comput. 10, 1\u201311 (2021)","journal-title":"Vis. Comput."},{"key":"3074_CR4","doi-asserted-by":"crossref","unstructured":"Sun, Y., Zheng, L., Yang, Y., Tian, Q., Wang, S.: Beyond part models: Person retrieval with refined part pooling (and a strong convolutional baseline). In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 480\u2013496 (2018)","DOI":"10.1007\/978-3-030-01225-0_30"},{"key":"3074_CR5","doi-asserted-by":"crossref","unstructured":"Wang, P., Wang, M., He, D.: Multi-scale feature pyramid and multi-branch neural network for person re-identification. Vis. Comput. 1\u201313 (2022)","DOI":"10.1007\/s00371-022-02653-5"},{"key":"3074_CR6","doi-asserted-by":"crossref","unstructured":"Jia, Z., Li, Y., Tan, Z., Wang, W., Wang, Z., Yin, G.: Domain-invariant feature extraction and fusion for cross-domain person re-identification. Vis. Comput. 1\u201312 (2022)","DOI":"10.1007\/s00371-022-02398-1"},{"key":"3074_CR7","doi-asserted-by":"crossref","unstructured":"Zhou, P., Ni, B., Geng, C., Hu, J., Xu, Y.: Scale-transferrable object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 528\u2013537 (2018)","DOI":"10.1109\/CVPR.2018.00062"},{"key":"3074_CR8","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Bai, Y., Ding, M., Li, Y., Ghanem, B.: W2f: A weakly-supervised to fully-supervised framework for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 928\u2013936 (2018)","DOI":"10.1109\/CVPR.2018.00103"},{"key":"3074_CR9","doi-asserted-by":"crossref","unstructured":"Xiang, Y., Song, C., Mottaghi, R., Savarese, S.: Monocular multiview object tracking with 3d aspect parts. In: European Conference on Computer Vision, pp. 220\u2013235. Springer (2014)","DOI":"10.1007\/978-3-319-10599-4_15"},{"key":"3074_CR10","doi-asserted-by":"publisher","first-page":"281","DOI":"10.1109\/TMM.2020.2977528","volume":"23","author":"S Zhang","year":"2021","unstructured":"Zhang, S., Zhang, Q., Yang, Y., Wei, X., Wang, P., Jiao, B., Zhang, Y.: Person re-identification in aerial imagery. IEEE Trans. Multimedia 23, 281\u2013291 (2021). https:\/\/doi.org\/10.1109\/TMM.2020.2977528","journal-title":"IEEE Trans. Multimedia"},{"key":"3074_CR11","doi-asserted-by":"publisher","first-page":"1696","DOI":"10.1109\/TIFS.2020.3040881","volume":"16","author":"SVA Kumar","year":"2021","unstructured":"Kumar, S.V.A., Yaghoubi, E., Das, A., Harish, B.S., Proen\u00e7a, H.: The p-destre: a fully annotated dataset for pedestrian detection, tracking, and short\/long-term re-identification from aerial devices. IEEE Trans. Inf. Forensics Secur. 16, 1696\u20131708 (2021). https:\/\/doi.org\/10.1109\/TIFS.2020.3040881","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"3074_CR12","doi-asserted-by":"publisher","unstructured":"Zheng, Z., Zheng, L., Yang, Y.: A discriminatively learned CNN embedding for person reidentification. ACM Trans. Multimedia Comput. Commun. Appl. (TOMM) 14(1), 1\u201320 (2017). https:\/\/doi.org\/10.1145\/3159171","DOI":"10.1145\/3159171"},{"key":"3074_CR13","doi-asserted-by":"crossref","unstructured":"Xu, S., Luo, L., Hu, S.: Attention-based model with attribute classification for cross-domain person re-identification. In: 2020 25th International Conference on Pattern Recognition (ICPR), pp. 9149\u20139155. IEEE (2021)","DOI":"10.1109\/ICPR48806.2021.9413309"},{"key":"3074_CR14","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.109354","volume":"252","author":"S Xu","year":"2022","unstructured":"Xu, S., Luo, L., Hu, J., Yang, B., Hu, S.: Semantic driven attention network with attribute learning for unsupervised person re-identification. Knowl.-Based Syst. 252, 109354 (2022)","journal-title":"Knowl.-Based Syst."},{"key":"3074_CR15","doi-asserted-by":"crossref","unstructured":"Pervaiz, N., Fraz, M.M., Shahzad, M.: Per-former: rethinking person re-identification using transformer augmented with self-attention and contextual mapping. Vis. Comput. 1\u201316 (2022)","DOI":"10.1007\/s00371-022-02577-0"},{"key":"3074_CR16","doi-asserted-by":"crossref","unstructured":"Wang, G., Lai, J., Huang, P., Xie, X.: Spatial-temporal person re-identification. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 8933\u20138940 (2019)","DOI":"10.1609\/aaai.v33i01.33018933"},{"key":"3074_CR17","doi-asserted-by":"crossref","unstructured":"Zhuo, J., Chen, Z., Lai, J., Wang, G.: Occluded person re-identification. In: 2018 IEEE International Conference on Multimedia and Expo (ICME), pp. 1\u20136. IEEE (2018)","DOI":"10.1109\/ICME.2018.8486568"},{"issue":"5","key":"3074_CR18","doi-asserted-by":"publisher","first-page":"2142","DOI":"10.1109\/TNNLS.2020.2999517","volume":"32","author":"G Wang","year":"2020","unstructured":"Wang, G., Wang, G., Zhang, X., Lai, J., Yu, Z., Lin, L.: Weakly supervised person re-id: differentiable graphical learning and a new benchmark. IEEE Trans. Neural Netw. Learn. Syst. 32(5), 2142\u20132156 (2020)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"3074_CR19","doi-asserted-by":"crossref","unstructured":"Layne, R., Hospedales, T.M., Gong, S.: Investigating open-world person re-identification using a drone. In: European Conference on Computer Vision, pp. 225\u2013240 (2014)","DOI":"10.1007\/978-3-319-16199-0_16"},{"key":"3074_CR20","doi-asserted-by":"crossref","unstructured":"Schumann, A., Schuchert, T.: Deep person re-identification in aerial images. In: Optics and Photonics for Counterterrorism, Crime Fighting, and Defence XII, vol. 9995, pp. 174\u2013182. SPIE (2016)","DOI":"10.1117\/12.2241652"},{"key":"3074_CR21","doi-asserted-by":"crossref","unstructured":"Schumann, A., Metzler, J.: Person re-identification across aerial and ground-based cameras by deep feature fusion. In: Automatic Target Recognition XXVII, vol. 10202, pp. 56\u201367. SPIE (2017)","DOI":"10.1117\/12.2262295"},{"key":"3074_CR22","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"},{"issue":"1","key":"3074_CR23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13634-019-0647-z","volume":"2019","author":"A Grigorev","year":"2019","unstructured":"Grigorev, A., Tian, Z., Rho, S., Xiong, J., Liu, S., Jiang, F.: Deep person re-identification in UAV images. EURASIP J. Adv. Signal Process. 2019(1), 1\u201310 (2019)","journal-title":"EURASIP J. Adv. Signal Process."},{"key":"3074_CR24","doi-asserted-by":"crossref","unstructured":"Wan, W., Zhong, Y., Li, T., Chen, J.: Rethinking feature distribution for loss functions in image classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9117\u20139126 (2018)","DOI":"10.1109\/CVPR.2018.00950"},{"key":"3074_CR25","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., Polosukhin, I.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"key":"3074_CR26","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7132\u20137141 (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"3074_CR27","doi-asserted-by":"crossref","unstructured":"Pervaiz, N., Fraz, M., Shahzad, M.: Per-former: rethinking person re-identification using transformer augmented with self-attention and contextual mapping. Vis. Comput. 1\u201316 (2022)","DOI":"10.1007\/s00371-022-02577-0"},{"key":"3074_CR28","doi-asserted-by":"crossref","unstructured":"Zhou, Z., Huang, Y., Wang, W., Wang, L., Tan, T.: See the forest for the trees: joint spatial and temporal recurrent neural networks for video-based person re-identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.717"},{"key":"3074_CR29","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7794\u20137803 (2018)","DOI":"10.1109\/CVPR.2018.00813"},{"key":"3074_CR30","doi-asserted-by":"crossref","unstructured":"Chen, D., Li, H., Xiao, T., Yi, S., Wang, X.: Video person re-identification with competitive snippet-similarity aggregation and co-attentive snippet embedding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1169\u20131178 (2018)","DOI":"10.1109\/CVPR.2018.00128"},{"key":"3074_CR31","unstructured":"Liu, C.-T., Wu, C.-W., Wang, Y.-C.F., Chien, S.-Y.: Spatially and temporally efficient non-local attention network for video-based person re-identification. arXiv preprint arXiv:1908.01683 (2019)"},{"key":"3074_CR32","doi-asserted-by":"crossref","unstructured":"Li, W., Zhu, X., Gong, S.: Harmonious attention network for person re-identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2285\u20132294 (2018)","DOI":"10.1109\/CVPR.2018.00243"},{"key":"3074_CR33","doi-asserted-by":"crossref","unstructured":"Chen, T., Ding, S., Xie, J., Yuan, Y., Chen, W., Yang, Y., Ren, Z., Wang, Z.: Abd-net: attentive but diverse person re-identification. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8351\u20138361 (2019)","DOI":"10.1109\/ICCV.2019.00844"},{"issue":"9","key":"3074_CR34","doi-asserted-by":"publisher","first-page":"3914","DOI":"10.1109\/TCYB.2019.2962000","volume":"50","author":"L Luo","year":"2020","unstructured":"Luo, L., Chen, L., Hu, S., Lu, Y., Wang, X.: Discriminative and geometry-aware unsupervised domain adaptation. IEEE Trans. Cybern. 50(9), 3914\u20133927 (2020)","journal-title":"IEEE Trans. Cybern."},{"key":"3074_CR35","doi-asserted-by":"crossref","unstructured":"Luo, L., Chen, L., Hu, S.: Attention regularized Laplace graph for domain adaptation. IEEE Trans. Image Process. (2022)","DOI":"10.1109\/TIP.2022.3216781"},{"key":"3074_CR36","doi-asserted-by":"crossref","unstructured":"Li, Y.-J., Yang, F.-E., Liu, Y.-C., Yeh, Y.-Y., Du, X., Frank\u00a0Wang, Y.-C.: Adaptation and re-identification network: an unsupervised deep transfer learning approach to person re-identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 172\u2013178 (2018)","DOI":"10.1109\/CVPRW.2018.00054"},{"key":"3074_CR37","unstructured":"Huang, Y., Peng, P., Jin, Y., Xing, J., Lang, C., Feng, S.: Domain adaptive attention model for unsupervised cross-domain person re-identification. arXiv preprint arXiv:1905.10529 (2019)"},{"key":"3074_CR38","doi-asserted-by":"crossref","unstructured":"Zhu, J.-Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2223\u20132232 (2017)","DOI":"10.1109\/ICCV.2017.244"},{"key":"3074_CR39","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.107173","volume":"102","author":"L Song","year":"2020","unstructured":"Song, L., Wang, C., Zhang, L., Du, B., Zhang, Q., Huang, C., Wang, X.: Unsupervised domain adaptive re-identification: theory and practice. Pattern Recognit. 102, 107173 (2020)","journal-title":"Pattern Recognit."},{"key":"3074_CR40","doi-asserted-by":"crossref","unstructured":"Luo, L., Chen, L., Hu, S.: Discriminative noise robust sparse orthogonal label regression-based domain adaptation. Int. J. Comput. Vis. (2023)","DOI":"10.1007\/s11263-023-01865-z"},{"issue":"7","key":"3074_CR41","doi-asserted-by":"publisher","first-page":"2623","DOI":"10.1109\/TNNLS.2019.2933590","volume":"31","author":"M Zhang","year":"2019","unstructured":"Zhang, M., Wang, N., Li, Y., Gao, X.: Neural probabilistic graphical model for face sketch synthesis. IEEE Trans. Neural Netw. Learn. Syst. 31(7), 2623\u20132637 (2019)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"3","key":"3074_CR42","doi-asserted-by":"publisher","first-page":"904","DOI":"10.1109\/TCYB.2017.2664499","volume":"48","author":"M Zhang","year":"2017","unstructured":"Zhang, M., Li, J., Wang, N., Gao, X.: Compositional model-based sketch generator in facial entertainment. IEEE Trans. Cybern. 48(3), 904\u2013915 (2017)","journal-title":"IEEE Trans. Cybern."},{"issue":"10","key":"3074_CR43","doi-asserted-by":"publisher","first-page":"3109","DOI":"10.1109\/TNNLS.2018.2890017","volume":"30","author":"M Zhang","year":"2019","unstructured":"Zhang, M., Wang, N., Li, Y., Gao, X.: Deep latent low-rank representation for face sketch synthesis. IEEE Trans. Neural Netw. Learn. Syst. 30(10), 3109\u20133123 (2019)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"3074_CR44","doi-asserted-by":"crossref","unstructured":"Zhang, M., Xin, J., Zhang, J., Tao, D., Gao, X.: Curvature consistent network for microscope chip image super-resolution. IEEE Trans. Neural Netw. Learn. Syst. (2022)","DOI":"10.1109\/TNNLS.2022.3168540"},{"issue":"1","key":"3074_CR45","doi-asserted-by":"publisher","first-page":"578","DOI":"10.1109\/TCYB.2022.3163294","volume":"53","author":"M Zhang","year":"2022","unstructured":"Zhang, M., Wu, Q., Zhang, J., Gao, X., Guo, J., Tao, D.: Fluid micelle network for image super-resolution reconstruction. IEEE Trans. Cybern. 53(1), 578\u2013591 (2022)","journal-title":"IEEE Trans. Cybern."},{"key":"3074_CR46","unstructured":"Zhang, M., Wu, Q., Guo, J., Li, Y., Gao, X.: Heat transfer-inspired network for image super-resolution reconstruction. IEEE Trans. Neural Netw. Learn. Syst. (2022)"},{"key":"3074_CR47","doi-asserted-by":"crossref","unstructured":"Yan, H., Ding, Y., Li, P., Wang, Q., Xu, Y., Zuo, W.: Mind the class weight bias: Weighted maximum mean discrepancy for unsupervised domain adaptation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2272\u20132281 (2017)","DOI":"10.1109\/CVPR.2017.107"},{"key":"3074_CR48","unstructured":"Long, M., Cao, Y., Wang, J., Jordan, M.: Learning transferable features with deep adaptation networks. In: International Conference on Machine Learning, pp. 97\u2013105. PMLR (2015)"},{"key":"3074_CR49","first-page":"513","volume":"19","author":"A Gretton","year":"2006","unstructured":"Gretton, A., Borgwardt, K., Rasch, M., Sch\u00f6lkopf, B., Smola, A.: A kernel method for the two-sample-problem. Adv. Neural. Inf. Process. Syst. 19, 513\u2013520 (2006)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3074_CR50","doi-asserted-by":"crossref","unstructured":"Rubner, Y., Tomasi, C., Guibas, L.J.: The Earth Mover\u2019s Distance as a Metric for Image Retrieval (2000)","DOI":"10.1007\/978-1-4757-3343-3_2"},{"key":"3074_CR51","doi-asserted-by":"crossref","unstructured":"Deng, W., Zheng, L., Ye, Q., Kang, G., Yang, Y., Jiao, J.: Image-image domain adaptation with preserved self-similarity and domain-dissimilarity for person re-identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 994\u20131003 (2018)","DOI":"10.1109\/CVPR.2018.00110"},{"key":"3074_CR52","unstructured":"Fan, X., Jiang, W., Luo, H., Mao, W.: Modality-transfer generative adversarial network and dual-level unified latent representation for visible thermal person re-identification. Vis. Comput. 1\u201316 (2022)"},{"key":"3074_CR53","unstructured":"Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., Bengio, Y.: Generative adversarial nets. Adv. Neural Inf. Process. Syst. 27 (2014)"},{"key":"3074_CR54","unstructured":"Liang, W., Wang, G., Lai, J., Zhu, J.: M2m-gan: Many-to-many generative adversarial transfer learning for person re-identification. arXiv preprint arXiv:1811.03768 (2018)"},{"key":"3074_CR55","doi-asserted-by":"crossref","unstructured":"Fu, Y., Wei, Y., Wang, G., Zhou, Y., Shi, H., Huang, T.S.: Self-similarity grouping: a simple unsupervised cross domain adaptation approach for person re-identification. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6112\u20136121 (2019)","DOI":"10.1109\/ICCV.2019.00621"},{"key":"3074_CR56","doi-asserted-by":"crossref","unstructured":"Yang, F., Li, K., Zhong, Z., Luo, Z., Sun, X., Cheng, H., Guo, X., Huang, F., Ji, R., Li, S.: Asymmetric co-teaching for unsupervised cross-domain person re-identification. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 12597\u201312604 (2020)","DOI":"10.1609\/aaai.v34i07.6950"},{"key":"3074_CR57","doi-asserted-by":"crossref","unstructured":"Wang, G., Lai, J.-H., Liang, W., Wang, G.: Smoothing adversarial domain attack and p-memory reconsolidation for cross-domain person re-identification. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10568\u201310577 (2020)","DOI":"10.1109\/CVPR42600.2020.01058"},{"key":"3074_CR58","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"},{"key":"3074_CR59","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., Fei-Fei, L.: Imagenet: A large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"3074_CR60","unstructured":"Hermans, A., Beyer, L., Leibe, B.: In defense of the triplet loss for person re-identification. arXiv preprint arXiv:1703.07737 (2017)"},{"issue":"10","key":"3074_CR61","doi-asserted-by":"publisher","first-page":"2993","DOI":"10.1016\/j.patcog.2015.04.005","volume":"48","author":"S Ding","year":"2015","unstructured":"Ding, S., Lin, L., Wang, G., Chao, H.: Deep feature learning with relative distance comparison for person re-identification. Pattern Recognit. 48(10), 2993\u20133003 (2015)","journal-title":"Pattern Recognit."},{"issue":"10","key":"3074_CR62","doi-asserted-by":"publisher","first-page":"2777","DOI":"10.1109\/TCSVT.2017.2748698","volume":"28","author":"G Wang","year":"2018","unstructured":"Wang, G., Lai, J., Xie, X.: P2snet: Can an image match a video for person re-identification in an end-to-end way? IEEE Trans. Circuits Syst. Video Technol. 28(10), 2777\u20132787 (2018). https:\/\/doi.org\/10.1109\/TCSVT.2017.2748698","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"3074_CR63","doi-asserted-by":"crossref","unstructured":"Li, W., Zhao, R., Xiao, T., Wang, X.: Deepreid: Deep filter pairing neural network for person re-identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 152\u2013159 (2014)","DOI":"10.1109\/CVPR.2014.27"},{"key":"3074_CR64","doi-asserted-by":"crossref","unstructured":"Zheng, L., Shen, L., Tian, L., Wang, S., Wang, J., Tian, Q.: Scalable person re-identification: a benchmark. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1116\u20131124 (2015)","DOI":"10.1109\/ICCV.2015.133"},{"key":"3074_CR65","unstructured":"Xiao, T., Li, S., Wang, B., Lin, L., Wang, X.: End-to-end deep learning for person search. arXiv preprint arXiv:1604.01850 2(2), 4 (2016)"},{"key":"3074_CR66","doi-asserted-by":"crossref","unstructured":"Moritz, L., Specker, A., Schumann, A.: A study of person re-identification design characteristics for aerial data. In: Pattern Recognition and Tracking XXXII, vol. 11735, pp. 161\u2013175. SPIE (2021)","DOI":"10.1117\/12.2587946"},{"key":"3074_CR67","doi-asserted-by":"crossref","unstructured":"Sommer, L., Specker, A., Schumann, A.: Deep learning based person search in aerial imagery. In: Automatic Target Recognition XXXI, vol. 11729, pp. 207\u2013220. SPIE (2021)","DOI":"10.1117\/12.2588179"},{"issue":"9","key":"3074_CR68","doi-asserted-by":"publisher","first-page":"1627","DOI":"10.1109\/TPAMI.2009.167","volume":"32","author":"PF Felzenszwalb","year":"2010","unstructured":"Felzenszwalb, P.F., Girshick, R.B., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part-based models. IEEE Trans. Pattern Anal. Mach. Intell. 32(9), 1627\u20131645 (2010)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3074_CR69","doi-asserted-by":"crossref","unstructured":"Ustinova, E., Ganin, Y., Lempitsky, V.: Multi-region bilinear convolutional neural networks for person re-identification. In: 2017 14th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), pp. 1\u20136. IEEE (2017)","DOI":"10.1109\/AVSS.2017.8078460"},{"key":"3074_CR70","doi-asserted-by":"crossref","unstructured":"Zheng, Z., Zheng, L., Yang, Y.: Unlabeled samples generated by GAN improve the person re-identification baseline in vitro. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3754\u20133762 (2017)","DOI":"10.1109\/ICCV.2017.405"},{"key":"3074_CR71","doi-asserted-by":"crossref","unstructured":"Zhao, L., Li, X., Zhuang, Y., Wang, J.: Deeply-learned part-aligned representations for person re-identification. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3219\u20133228 (2017)","DOI":"10.1109\/ICCV.2017.349"},{"key":"3074_CR72","doi-asserted-by":"crossref","unstructured":"Sun, Y., Zheng, L., Deng, W., Wang, S.: Svdnet for pedestrian retrieval. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3800\u20133808 (2017)","DOI":"10.1109\/ICCV.2017.410"},{"key":"3074_CR73","unstructured":"Zhang, X., Luo, H., Fan, X., Xiang, W., Sun, Y., Xiao, Q., Jiang, W., Zhang, C., Sun, J.: Alignedreid: Surpassing human-level performance in person re-identification. arXiv preprint arXiv:1711.08184 (2017)"},{"key":"3074_CR74","doi-asserted-by":"crossref","unstructured":"Wang, G., Yuan, Y., Chen, X., Li, J., Zhou, X.: Learning discriminative features with multiple granularities for person re-identification. In: Proceedings of the 26th ACM International Conference on Multimedia, pp. 274\u2013282 (2018)","DOI":"10.1145\/3240508.3240552"},{"key":"3074_CR75","doi-asserted-by":"crossref","unstructured":"Zhou, K., Yang, Y., Cavallaro, A., Xiang, T.: Omni-scale feature learning for person re-identification. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3702\u20133712 (2019)","DOI":"10.1109\/ICCV.2019.00380"},{"key":"3074_CR76","doi-asserted-by":"crossref","unstructured":"He, L., Liang, J., Li, H., Sun, Z.: Deep spatial feature reconstruction for partial person re-identification: Alignment-free approach. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7073\u20137082 (2018)","DOI":"10.1109\/CVPR.2018.00739"},{"key":"3074_CR77","doi-asserted-by":"crossref","unstructured":"Chung, D., Tahboub, K., Delp, E.J.: A two stream siamese convolutional neural network for person re-identification. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1983\u20131991 (2017)","DOI":"10.1109\/ICCV.2017.218"},{"key":"3074_CR78","doi-asserted-by":"crossref","unstructured":"Rao, S., Rahman, T., Rochan, M., Wang, Y.: Video-based person re-identification using spatial-temporal attention networks. arXiv preprint arXiv:1810.11261 (2018)","DOI":"10.1109\/AVSS.2019.8909869"},{"key":"3074_CR79","doi-asserted-by":"crossref","unstructured":"Li, S., Bak, S., Carr, P., Wang, X.: Diversity regularized spatiotemporal attention for video-based person re-identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 369\u2013378 (2018)","DOI":"10.1109\/CVPR.2018.00046"},{"key":"3074_CR80","doi-asserted-by":"crossref","unstructured":"Li, J., Wang, J., Tian, Q., Gao, W., Zhang, S.: Global-local temporal representations for video person re-identification. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3958\u20133967 (2019)","DOI":"10.1109\/ICCV.2019.00406"},{"key":"3074_CR81","doi-asserted-by":"crossref","unstructured":"Gu, X., Ma, B., Chang, H., Shan, S., Chen, X.: Temporal knowledge propagation for image-to-video person re-identification. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9647\u20139656 (2019)","DOI":"10.1109\/ICCV.2019.00974"},{"key":"3074_CR82","doi-asserted-by":"crossref","unstructured":"Liu, Y., Yuan, Z., Zhou, W., Li, H.: Spatial and temporal mutual promotion for video-based person re-identification. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 8786\u20138793 (2019)","DOI":"10.1609\/aaai.v33i01.33018786"},{"key":"3074_CR83","doi-asserted-by":"crossref","unstructured":"Subramaniam, A., Nambiar, A., Mittal, A.: Co-segmentation inspired attention networks for video-based person re-identification. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 562\u2013572 (2019)","DOI":"10.1109\/ICCV.2019.00065"},{"key":"3074_CR84","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2021.104356","volume":"118","author":"H Fu","year":"2022","unstructured":"Fu, H., Zhang, K., Li, H., Wang, J., Wang, Z.: Spatial temporal and channel aware network for video-based person re-identification. Image Vis. Comput. 118, 104356 (2022)","journal-title":"Image Vis. Comput."},{"issue":"10","key":"3074_CR85","doi-asserted-by":"publisher","first-page":"14755","DOI":"10.1007\/s11042-022-13833-9","volume":"82","author":"C Han","year":"2023","unstructured":"Han, C., Jiang, B., Tang, J.: Multi-granularity cross attention network for person re-identification. Multimedia Tools Appl. 82(10), 14755\u201314773 (2023)","journal-title":"Multimedia Tools Appl."},{"key":"3074_CR86","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.-Y., Kweon, I.S.: Cbam: Convolutional block attention module. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 3\u201319 (2018)","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"3074_CR87","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-cam: Visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 618\u2013626 (2017)","DOI":"10.1109\/ICCV.2017.74"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-023-03074-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-023-03074-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-023-03074-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,6]],"date-time":"2024-06-06T11:13:12Z","timestamp":1717672392000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-023-03074-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,19]]},"references-count":87,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2024,6]]}},"alternative-id":["3074"],"URL":"https:\/\/doi.org\/10.1007\/s00371-023-03074-8","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"type":"print","value":"0178-2789"},{"type":"electronic","value":"1432-2315"}],"subject":[],"published":{"date-parts":[[2023,9,19]]},"assertion":[{"value":"21 August 2023","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 September 2023","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 authors declared that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}