{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T19:43:44Z","timestamp":1782243824073,"version":"3.54.5"},"reference-count":107,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2024,9,26]],"date-time":"2024-09-26T00:00:00Z","timestamp":1727308800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,9,26]],"date-time":"2024-09-26T00:00:00Z","timestamp":1727308800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100007065","name":"Nvidia","doi-asserted-by":"publisher","award":["gift"],"award-info":[{"award-number":["gift"]}],"id":[{"id":"10.13039\/100007065","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.1007\/s11263-024-02226-0","type":"journal-article","created":{"date-parts":[[2024,9,26]],"date-time":"2024-09-26T12:02:42Z","timestamp":1727352162000},"page":"1238-1257","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Robust Deep Object Tracking against Adversarial Attacks"],"prefix":"10.1007","volume":"133","author":[{"given":"Shuai","family":"Jia","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chao","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yibing","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaokang","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4848-2304","authenticated-orcid":false,"given":"Ming-Hsuan","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,9,26]]},"reference":[{"key":"2226_CR1","doi-asserted-by":"crossref","unstructured":"Bertinetto, L., Valmadre, J., Henriques, J. F., Vedaldi, A., & Torr, P. H. (2016). Fully-convolutional siamese networks for object tracking. In  European Conference on Computer Vision (ECCV) .","DOI":"10.1007\/978-3-319-48881-3_56"},{"key":"2226_CR2","doi-asserted-by":"crossref","unstructured":"Bhat, G., Danelljan, M., Van\u00a0Gool, L., & Timofte, R. (2019). Learning discriminative model prediction for tracking. In IEEE\/CVF International Conference on Computer Vision (ICCV).","DOI":"10.1109\/ICCV.2019.00628"},{"key":"2226_CR3","doi-asserted-by":"crossref","unstructured":"Borsuk, V., Vei, R., Kupyn, O., Martyniuk, T., Krashenyi, I., & Matas, J. (2022). Fear: Fast, efficient, accurate and robust visual tracker. In European conference on computer vision (ECCV).","DOI":"10.1007\/978-3-031-20047-2_37"},{"key":"2226_CR4","unstructured":"Brendel, W., Rauber, J., & Bethge, M. (2018). Decision-based adversarial attacks: Reliable attacks against black-box machine learning models. In International conference on learning representations (ICLR)."},{"key":"2226_CR5","doi-asserted-by":"crossref","unstructured":"Cao, Z., Fu, C., Ye, J., Li, B., & Li, Y. (2021). Hift: Hierarchical feature transformer for aerial tracking. In IEEE\/CVF international conference on computer vision (ICCV).","DOI":"10.1109\/ICCV48922.2021.01517"},{"key":"2226_CR6","doi-asserted-by":"crossref","unstructured":"Chen, B., Li, P., Bai, L., Qiao, L., Shen, Q., Li, B., Gan, W., Wu, W., & Ouyang, W. (2022). Backbone is all your need: A simplified architecture for visual object tracking. In European conference on computer vision (ECCV).","DOI":"10.1007\/978-3-031-20047-2_22"},{"key":"2226_CR7","doi-asserted-by":"crossref","unstructured":"Chen, X., Yan, B., Zhu, J., Wang, D., Yang, X., & Lu, H. (2021). Transformer tracking. In IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR46437.2021.00803"},{"key":"2226_CR8","doi-asserted-by":"crossref","unstructured":"Chen, X., Yan, X., Zheng, F., Jiang, Y., Xia, S.\u00a0T., Zhao, Y., & Ji, R. (2020). One-shot adversarial attacks on visual tracking with dual attention. In IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR42600.2020.01019"},{"key":"2226_CR9","doi-asserted-by":"crossref","unstructured":"Chen, Z., Zhong, B., Li, G., Zhang, S., & Ji, R. (2020). Siamese box adaptive network for visual tracking. In IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR42600.2020.00670"},{"key":"2226_CR10","unstructured":"Cheng, M., Le, T., Chen, P.\u00a0Y., Zhang, H., Yi, J., & Hsieh, C.\u00a0J. (2018). Query-efficient hard-label black-box attack: An optimization-based approach. In International conference on learning representations (ICLR)."},{"key":"2226_CR11","doi-asserted-by":"crossref","unstructured":"Cui, Y., Jiang, C., Wang, L., & Wu, G. (2022) Mixformer: End-to-end tracking with iterative mixed attention. In IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR52688.2022.01324"},{"key":"2226_CR12","doi-asserted-by":"crossref","unstructured":"Dai, K., Zhang, Y., Wang, D., Li, J., Lu, H., & Yang, X. (2020). High-performance long-term tracking with meta-updater. In IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR42600.2020.00633"},{"key":"2226_CR13","doi-asserted-by":"crossref","unstructured":"Danelljan, M., Bhat, G., Khan, F.\u00a0S., & Felsberg, M. (2019). Atom: Accurate tracking by overlap maximization. In IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2019.00479"},{"key":"2226_CR14","doi-asserted-by":"crossref","unstructured":"Danelljan, M., Bhat, G., Khan, F.\u00a0S., & Felsberg, M. (2017). ECO: Efficient convolution operators for tracking. In IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2017.733"},{"key":"2226_CR15","doi-asserted-by":"crossref","unstructured":"Danelljan, M., Robinson, A., Khan, F.\u00a0S., & Felsberg, M. (2016). Beyond correlation filters: Learning continuous convolution operators for visual tracking. In European conference on computer vision (ECCV).","DOI":"10.1007\/978-3-319-46454-1_29"},{"key":"2226_CR16","doi-asserted-by":"crossref","unstructured":"Ding, L., Wang, Y., Yuan, K., Jiang, M., Wang, P., Huang, H., & Wang, Z. J. (2021). Towards universal physical attacks on single object tracking. In Proceedings of the AAAI conference on artificial intelligence (AAAI).","DOI":"10.1609\/aaai.v35i2.16211"},{"key":"2226_CR17","doi-asserted-by":"crossref","unstructured":"Dong, Y., Pang, T., Su, H., & Zhu, J. (2019). Evading defenses to transferable adversarial examples by translation-invariant attacks. In IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2019.00444"},{"key":"2226_CR18","doi-asserted-by":"crossref","unstructured":"Dong, Y., Su, H., Wu, B., Li, Z., Liu, W., Zhang, T., & Zhu, J. (2019). Efficient decision-based black-box adversarial attacks on face recognition. In IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2019.00790"},{"key":"2226_CR19","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., & Gelly, S., & Uszkoreit, J. (2020). An image is worth 16x16 words: Transformers for image recognition at scale. In International conference on learning representations (ICLR)."},{"key":"2226_CR20","doi-asserted-by":"crossref","unstructured":"Eykholt, K., Evtimov, I., Fernandes, E., Li, B., Rahmati, A., Xiao, C., Prakash, A., Kohno, T., & Song, D. (2018). Robust physical-world attacks on deep learning models. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR).","DOI":"10.1109\/CVPR.2018.00175"},{"key":"2226_CR21","doi-asserted-by":"crossref","unstructured":"Fan, H., Lin, L., Yang, F., Chu, P., Deng, G., Yu, S., Bai, H., Xu, Y., Liao, C., & Ling, H. (2019). Lasot: A high-quality benchmark for large-scale single object tracking. In IEEE\/CVF international conference on computer vision (ICCV).","DOI":"10.1109\/CVPR.2019.00552"},{"key":"2226_CR22","doi-asserted-by":"crossref","unstructured":"Fu, C., Li, S., Yuan, X., Ye, J., Cao, Z., & Ding, F. (2022). Ad2Attack: Adaptive adversarial attack on real-time UAV tracking. In 2022 international conference on robotics and automation (ICRA).","DOI":"10.1109\/ICRA46639.2022.9812056"},{"key":"2226_CR23","doi-asserted-by":"crossref","unstructured":"Gao, S., Zhou, C., Ma, C., Wang, X., & Yuan, J. (2022). Aiatrack: Attention in attention for transformer visual tracking. In European conference on computer vision (ECCV).","DOI":"10.1007\/978-3-031-20047-2_9"},{"key":"2226_CR24","doi-asserted-by":"crossref","unstructured":"Gao, S., Zhou, C., & Zhang, J. (2023) Generalized relation modeling for transformer tracking. In IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR52729.2023.01792"},{"key":"2226_CR25","unstructured":"Goodfellow, I.\u00a0J., Shlens, J., & Szegedy, C. (2015). Explaining and harnessing adversarial examples. In International conference on learning representations (ICLR)."},{"key":"2226_CR26","unstructured":"Guo, C., Rana, M., Cisse, M., & Van Der\u00a0Maaten, L. (2018). Countering adversarial images using input transformations. In International conference on learning representations (ICLR)."},{"key":"2226_CR27","doi-asserted-by":"crossref","unstructured":"Guo, D., Wang, J., Cui, Y., Wang, Z., & Chen, S. (2020). Siamcar: Siamese fully convolutional classification and regression for visual tracking. In IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR42600.2020.00630"},{"key":"2226_CR28","doi-asserted-by":"crossref","unstructured":"Guo, Q., Cheng, Z., Juefei-Xu, F., Ma, L., Xie, X., Liu, Y., & Zhao, J. (2021). Learning to adversarially blur visual object tracking. In IEEE\/CVF international conference on computer vision (ICCV).","DOI":"10.1109\/ICCV48922.2021.01066"},{"key":"2226_CR29","doi-asserted-by":"crossref","unstructured":"Guo, Q., Xie, X., Juefei-Xu, F., Ma, L., Li, Z., Xue, W., Feng, W., & Liu, Y. (2020). Spark: Spatial-aware online incremental attack against visual tracking. In European conference on computer vision (ECCV).","DOI":"10.1007\/978-3-030-58595-2_13"},{"key":"2226_CR30","unstructured":"Gupta, K., Pesquet-Popescu, B., Kaakai, F., Pesquet, J.\u00a0C., & Malliaros, F.D. (2021). An adversarial attacker for neural networks in regression problems. In IJCAI workshop on artificial intelligence safety (AI Safety)."},{"key":"2226_CR31","doi-asserted-by":"crossref","unstructured":"Han, B., Sim, J., & Adam, H. (2017). Branchout: Regularization for online ensemble tracking with convolutional neural networks. In IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2017.63"},{"key":"2226_CR32","doi-asserted-by":"crossref","unstructured":"Held, D., Thrun, S., & Savarese, S. (2016). Learning to track at 100 fps with deep regression networks. In European conference on computer vision (ECCV).","DOI":"10.1007\/978-3-319-46448-0_45"},{"key":"2226_CR33","doi-asserted-by":"publisher","first-page":"1562","DOI":"10.1109\/TPAMI.2019.2957464","volume":"43","author":"L Huang","year":"2019","unstructured":"Huang, L., Zhao, X., & Huang, K. (2019). Got-10k: A large high-diversity benchmark for generic object tracking in the wild. IEEE Transactions on Pattern Analysis and Machine Intelligence, 43, 1562.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2226_CR34","unstructured":"Ilyas, A., Engstrom, L., Athalye, A., & Lin, J. (2018). Black-box adversarial attacks with limited queries and information. In International conference on machine learning (ICML)."},{"key":"2226_CR35","doi-asserted-by":"crossref","unstructured":"Jia, S., Ma, C., Song, Y., & Yang, X. (2020). Robust tracking against adversarial attacks. In European conference on computer vision (ECCV).","DOI":"10.1007\/978-3-030-58529-7_5"},{"key":"2226_CR36","doi-asserted-by":"crossref","unstructured":"Jia, S., Song, Y., Ma, C., & Yang, X. (2021). Iou attack: Towards temporally coherent black-box adversarial attack for visual object tracking. In IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR46437.2021.00664"},{"key":"2226_CR37","unstructured":"Jia, Y., Lu, Y., Shen, J., Chen, Q.\u00a0A., Zhong, Z., & Wei, T. (2019). Fooling detection alone is not enough: First adversarial attack against multiple object tracking. In International conference on learning representations (ICLR)."},{"key":"2226_CR38","doi-asserted-by":"crossref","unstructured":"Jung, I., Son, J., Baek, M., & Han, B. (2018). Real-time MDnet. In European conference on computer vision (ECCV).","DOI":"10.1007\/978-3-030-01225-0_6"},{"key":"2226_CR39","unstructured":"Kristan, M., Leonardis, A., Matas, J., Felsberg, M., Pflugfelder, R., Cehovin\u00a0Zajc, L., Vojir, T., Bhat, G., Lukezic, A., Eldesokey, A., Fernandez, G.(2018). The sixth visual object tracking vot2018 challenge results. In European conference on computer vision (ECCV) workshop."},{"key":"2226_CR40","doi-asserted-by":"crossref","unstructured":"Kristan, M., Leonardis, A., Matas, J., Felsberg, M., Pflugfelder, R., Cehovin\u00a0Zajc, L., Vojir, T., Hager, G., Lukezic, A., Eldesokey, A. (2016). The visual object tracking vot2016 challenge results. In European conference on computer vision (ECCV) workshop.","DOI":"10.1007\/978-3-319-48881-3_54"},{"key":"2226_CR41","doi-asserted-by":"crossref","unstructured":"Kristan, M., Matas, J., Leonardis, A., Felsberg, M., Pflugfelder, R., Kamarainen, J.\u00a0K., Cehovin\u00a0Zajc, L., Drbohlav, O., Lukezic, A., Berg, A., & Eldesokey, A. (2019). The seventh visual object tracking vot2019 challenge results. In European conference on computer vision (ECCV) workshop.","DOI":"10.1109\/ICCVW.2019.00276"},{"key":"2226_CR42","doi-asserted-by":"crossref","unstructured":"Kurakin, A., Goodfellow, I., & Bengio, S. (2017). Adversarial examples in the physical world. In International conference on learning representations (ICLR).","DOI":"10.1201\/9781351251389-8"},{"key":"2226_CR43","doi-asserted-by":"publisher","first-page":"6168","DOI":"10.1109\/TIP.2023.3329669","volume":"32","author":"P Lai","year":"2023","unstructured":"Lai, P., Cheng, G., Zhang, M., Ning, J., Zheng, X., & Han, J. (2023). Ncsiam: Reliable matching via neighborhood consensus for siamese-based object tracking. IEEE Transactions on Image Processing, 32, 6168.","journal-title":"IEEE Transactions on Image Processing"},{"key":"2226_CR44","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TGRS.2023.3339658","volume":"62","author":"P Lai","year":"2023","unstructured":"Lai, P., Zhang, M., Cheng, G., Li, S., Huang, X., & Han, J. (2023). Target-aware transformer for satellite video object tracking. IEEE Transactions on Geoscience and Remote Sensing, 62, 1\u201310.","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"2226_CR45","doi-asserted-by":"crossref","unstructured":"Li, B., Wu, W., Wang, Q., Zhang, F., Xing, J., & Yan, J. (2019). Siamrpn++: Evolution of siamese visual tracking with very deep networks. In IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2019.00441"},{"key":"2226_CR46","doi-asserted-by":"crossref","unstructured":"Li, B., Yan, J., Wu, W., Zhu, Z., & Hu, X. (2018). High performance visual tracking with siamese region proposal network. In IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2018.00935"},{"key":"2226_CR47","doi-asserted-by":"crossref","unstructured":"Li, F., Tian, C., Zuo, W., Zhang, L., & Yang, M.\u00a0H. (2018). Learning spatial-temporal regularized correlation filters for visual tracking. In IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2018.00515"},{"key":"2226_CR48","doi-asserted-by":"crossref","unstructured":"Liang, S., Wei, X., Yao, S., & Cao, X. (2020). Efficient adversarial attacks for visual object tracking. In European conference on computer vision (ECCV).","DOI":"10.1007\/978-3-030-58574-7_3"},{"key":"2226_CR49","doi-asserted-by":"crossref","unstructured":"Liao, F., Liang, M., Dong, Y., Pang, T., Hu, X., & Zhu, J. (2018). Defense against adversarial attacks using high-level representation guided denoiser. In IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2018.00191"},{"key":"2226_CR50","first-page":"16743","volume":"35","author":"L Lin","year":"2022","unstructured":"Lin, L., Fan, H., Zhang, Z., Xu, Y., & Ling, H. (2022). Swintrack: A simple and strong baseline for transformer tracking. Advances in Neural Information Processing Systems, 35, 16743.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2226_CR51","unstructured":"Liu, Y., Chen, X., Liu, C., & Song, D. (2017). Delving into transferable adversarial examples and black-box attacks. In International conference on learning representations (ICLR)."},{"key":"2226_CR52","unstructured":"Lu, J., Sibai, H., & Fabry, E. (2017). Adversarial examples that fool detectors. arXiv preprint arXiv:1712.02494"},{"key":"2226_CR53","doi-asserted-by":"publisher","unstructured":"Lin, D., Chen, Q., Zhou, C., & He, K. (2021). TraSw: Tracklet-switch adversarial attacks against multi-object tracking. https:\/\/doi.org\/10.31219\/osf.io\/tdc9b","DOI":"10.31219\/osf.io\/tdc9b"},{"key":"2226_CR54","doi-asserted-by":"crossref","unstructured":"Lu, X., Ma, C., Ni, B., Yang, X., Reid, I., & Yang, M.\u00a0H. (2018). Deep regression tracking with shrinkage loss. In European conference on computer vision (ECCV).","DOI":"10.1007\/978-3-030-01264-9_22"},{"key":"2226_CR55","doi-asserted-by":"crossref","unstructured":"Ma, C., Huang, J.\u00a0B., Yang, X., & Yang, M.\u00a0H. (2015). Hierarchical convolutional features for visual tracking. In IEEE\/CVF international conference on computer vision (ICCV).","DOI":"10.1109\/ICCV.2015.352"},{"key":"2226_CR56","doi-asserted-by":"crossref","unstructured":"Ma, F., Shou, M.Z., Zhu, L., Fan, H., Xu, Y., Yang, Y., & Yan, Z. (2022). Unified transformer tracker for object tracking. In IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR52688.2022.00858"},{"key":"2226_CR57","unstructured":"Madry, A., Makelov, A., Schmidt, L., Tsipras, D., & Vladu, A. (2018). Towards deep learning models resistant to adversarial attacks. In International conference on learning representations (ICLR)."},{"key":"2226_CR58","doi-asserted-by":"crossref","unstructured":"Mayer, C., Danelljan, M., Bhat, G., Paul, M., Paudel, D.\u00a0P., Yu, F., & Van\u00a0Gool, L. (2022). Transforming model prediction for tracking. In IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR52688.2022.00853"},{"key":"2226_CR59","doi-asserted-by":"crossref","unstructured":"Moosavi-Dezfooli, S.\u00a0M., Fawzi, A., Fawzi, O., & Frossard, P. (2017). Universal adversarial perturbations. In IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2017.17"},{"key":"2226_CR60","doi-asserted-by":"crossref","unstructured":"Moosavi-Dezfooli, S.\u00a0M., Fawzi, A., & Frossard, P. (2016). Deepfool: A simple and accurate method to fool deep neural networks. In IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2016.282"},{"key":"2226_CR61","doi-asserted-by":"crossref","unstructured":"Mueller, M., Smith, N., & Ghanem, B. (2016). A benchmark and simulator for UAV tracking. In European conference on computer vision (ECCV).","DOI":"10.1007\/978-3-319-46448-0_27"},{"key":"2226_CR62","doi-asserted-by":"crossref","unstructured":"Nam, H., & Han, B. (2016). Learning multi-domain convolutional neural networks for visual tracking. In IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2016.465"},{"key":"2226_CR63","unstructured":"Pu, S., Song, Y., Ma, C., Zhang, H., & Yang, M.\u00a0H. (2018). Deep attentive tracking via reciprocative learning. In Advances in neural information processing systems (NeurIPS)."},{"key":"2226_CR64","doi-asserted-by":"crossref","unstructured":"Qi, Y., Zhang, S., Qin, L., Yao, H., Huang, Q., Lim, J., & Yang, M.\u00a0H. (2016). Hedged deep tracking. In IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2016.466"},{"key":"2226_CR65","unstructured":"Ren, S., He, K., Girshick, R., & Sun, J. (2015). Faster r-cnn: Towards real-time object detection with region proposal networks. In Advances in neural information processing systems (NeurIPS)."},{"key":"2226_CR66","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2016","unstructured":"Ren, S., He, K., Girshick, R., & Sun, J. (2016). Faster r-cnn: Towards real-time object detection with region proposal networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39, 1137.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2226_CR67","doi-asserted-by":"crossref","unstructured":"Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., & Savarese, S. (2019). Generalized intersection over union: A metric and a loss for bounding box regression. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR).","DOI":"10.1109\/CVPR.2019.00075"},{"key":"2226_CR68","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., & Berg, A. C. (2015). Imagenet large scale visual recognition challenge. International Journal of Computer Vision, 115, 211.","journal-title":"International Journal of Computer Vision"},{"key":"2226_CR69","doi-asserted-by":"crossref","unstructured":"Shen, Q., Qiao, L., Guo, J., Li, P., Li, X., Li, B., Feng, W., Gan, W., Wu, W., & Ouyang, W. (2022). Unsupervised learning of accurate siamese tracking. In IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR52688.2022.00793"},{"key":"2226_CR70","doi-asserted-by":"crossref","unstructured":"Song, Y., Ma, C., Gong, L., Zhang, J., Lau, R.W., & Yang, M.\u00a0H. (2017). CREST: Convolutional residual learning for visual tracking. In IEEE\/CVF international conference on computer vision (ICCV).","DOI":"10.1109\/ICCV.2017.279"},{"key":"2226_CR71","doi-asserted-by":"crossref","unstructured":"Song, Y., Ma, C., Wu, X., Gong, L., Bao, L., Zuo, W., Shen, C., Lau, R.W., & Yang, M.H. (2018). VITAL: Visual tracking via adversarial learning. In IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2018.00937"},{"key":"2226_CR72","doi-asserted-by":"crossref","unstructured":"Song, Z., Yu, J., Chen, Y.\u00a0P.\u00a0P., & Yang, W. (2022). Transformer tracking with cyclic shifting window attention. In IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR52688.2022.00859"},{"key":"2226_CR73","doi-asserted-by":"crossref","unstructured":"Sun, B., Tsai, N.h., Liu, F., Yu, R., & Su, H. (2019). Adversarial defense by stratified convolutional sparse coding. In IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2019.01171"},{"key":"2226_CR74","doi-asserted-by":"crossref","unstructured":"Sun, X., Cheng, G., Li, H., Pei, L., Han, J. (2022). Exploring effective data for surrogate training towards black-box attack. In IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR52688.2022.01492"},{"key":"2226_CR75","doi-asserted-by":"publisher","first-page":"2972","DOI":"10.1109\/TIP.2023.3276331","volume":"32","author":"X Sun","year":"2023","unstructured":"Sun, X., Cheng, G., Li, H., Pei, L., & Han, J. (2023). On single-model transferable targeted attacks: A closer look at decision-level optimization. IEEE Transactions on Image Processing, 32, 2972.","journal-title":"IEEE Transactions on Image Processing"},{"key":"2226_CR76","doi-asserted-by":"crossref","unstructured":"Sun, Y., Sun, C., Wang, D., He, Y., & Lu, H. (2019). Roi pooled correlation filters for visual tracking. In IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2019.00593"},{"key":"2226_CR77","unstructured":"Szegedy, C., Zaremba, W., Sutskever, I., Bruna, J., Erhan, D., Goodfellow, I., & Fergus, R. (2014). Intriguing properties of neural networks. In International conference on learning representations (ICLR)."},{"key":"2226_CR78","unstructured":"Tram\u00e8r, F., Boneh, D., Kurakin, A., Goodfellow, I., Papernot, N., & McDaniel, P. (2018). Ensemble adversarial training: Attacks and defenses. In International conference on learning representations (ICLR)."},{"key":"2226_CR79","doi-asserted-by":"crossref","unstructured":"Valmadre, J., Bertinetto, L., Henriques, J., Vedaldi, A., & Torr, P.\u00a0H. (2017). End-to-end representation learning for correlation filter based tracking. In IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2017.531"},{"key":"2226_CR80","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., & Polosukhin, I. (2017). Attention is all you need. In Advances in neural information processing systems (NeurIPS)."},{"key":"2226_CR81","doi-asserted-by":"publisher","first-page":"7427","DOI":"10.1109\/TCYB.2020.3041481","volume":"52","author":"D Wang","year":"2021","unstructured":"Wang, D., Li, C., Wen, S., Han, Q. L., Nepal, S., Zhang, X., & Xiang, Y. (2021). Daedalus: Breaking nonmaximum suppression in object detection via adversarial examples. IEEE Transactions on Cybernetics, 52, 7427.","journal-title":"IEEE Transactions on Cybernetics"},{"key":"2226_CR82","doi-asserted-by":"crossref","unstructured":"Wang, L., Ouyang, W., Wang, X., & Lu, H. (2015). Visual tracking with fully convolutional networks. In IEEE\/CVF international conference on computer vision (ICCV).","DOI":"10.1109\/ICCV.2015.357"},{"key":"2226_CR83","doi-asserted-by":"crossref","unstructured":"Wang, N., Song, Y., Ma, C., Zhou, W., Liu, W., & Li, H. (2019). Unsupervised deep tracking. In IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2019.00140"},{"key":"2226_CR84","doi-asserted-by":"publisher","first-page":"400","DOI":"10.1007\/s11263-020-01357-4","volume":"129","author":"N Wang","year":"2020","unstructured":"Wang, N., Zhou, W., Song, Y., Ma, C., Liu, W., & Li, H. (2020). Unsupervised deep representation learning for real-time tracking. International Journal of Computer Vision, 129, 400.","journal-title":"International Journal of Computer Vision"},{"key":"2226_CR85","doi-asserted-by":"crossref","unstructured":"Wang, N., Zhou, W., Wang, J., & Li, H. (2021). Transformer meets tracker: Exploiting temporal context for robust visual tracking. In IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR46437.2021.00162"},{"key":"2226_CR86","doi-asserted-by":"crossref","unstructured":"Wang, W., Yin, B., Yao, T., Zhang, L., Fu, Y., Ding, S., Li, J., Huang, F., Xue, X. (2021). Delving into data: Effectively substitute training for black-box attack. In IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR46437.2021.00473"},{"key":"2226_CR87","doi-asserted-by":"crossref","unstructured":"Wei, X., Bai, Y., Zheng, Y., Shi, D., & Gong, Y. (2023). Autoregressive visual tracking. In IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR52729.2023.00935"},{"key":"2226_CR88","doi-asserted-by":"crossref","unstructured":"Wiyatno, R.\u00a0R., & Xu, A. (2019). Physical adversarial textures that fool visual object tracking. In IEEE\/CVF international conference on computer vision (ICCV).","DOI":"10.1109\/ICCV.2019.00492"},{"key":"2226_CR89","doi-asserted-by":"crossref","unstructured":"Wu, Y., Lim, J., & Yang, M.\u00a0H. (2015). Object tracking benchmark. IEEE Transactions on Pattern Analysis and Machine Intelligence.","DOI":"10.1109\/TPAMI.2014.2388226"},{"key":"2226_CR90","doi-asserted-by":"crossref","unstructured":"Xiao, C., Deng, R., Li, B., Yu, F., Liu, M., & Song, D. (2018). Characterizing adversarial examples based on spatial consistency information for semantic segmentation. In European conference on computer vision (ECCV).","DOI":"10.1007\/978-3-030-01249-6_14"},{"key":"2226_CR91","unstructured":"Xie, C., Wang, J., Zhang, Z., Ren, Z., & Yuille, A. (2017). Mitigating adversarial effects through randomization. arXiv preprint arXiv:1711.01991"},{"key":"2226_CR92","doi-asserted-by":"crossref","unstructured":"Xie, C., Wang, J., Zhang, Z., Zhou, Y., Xie, L., & Yuille, A. (2017). Adversarial examples for semantic segmentation and object detection. In IEEE\/CVF international conference on computer vision (ICCV).","DOI":"10.1109\/ICCV.2017.153"},{"key":"2226_CR93","doi-asserted-by":"crossref","unstructured":"Xie, C., Wu, Y., van der Maaten, L., Yuille, A.\u00a0L., & He, K. (2019). Feature denoising for improving adversarial robustness. In IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2019.00059"},{"key":"2226_CR94","doi-asserted-by":"crossref","unstructured":"Xie, F., Wang, C., Wang, G., Cao, Y., Yang, W., & Zeng, W. (2022). Correlation-aware deep tracking. In IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR52688.2022.00855"},{"key":"2226_CR95","doi-asserted-by":"crossref","unstructured":"Xie, F., Wang, C., Wang, G., Yang, W., & Zeng, W. (2021). Learning tracking representations via dual-branch fully transformer networks. In IEEE\/CVF international conference on computer vision (ICCV).","DOI":"10.1109\/ICCVW54120.2021.00303"},{"key":"2226_CR96","doi-asserted-by":"crossref","unstructured":"Xing, D., Evangeliou, N., Tsoukalas, A., & Tzes, A. (2022). Siamese transformer pyramid networks for real-time UAV tracking. In IEEE\/CVF winter conference on applications of computer vision (WACV).","DOI":"10.1109\/WACV51458.2022.00196"},{"key":"2226_CR97","doi-asserted-by":"crossref","unstructured":"Yan, B., Jiang, Y., Sun, P., Wang, D., Yuan, Z., Luo, P., & Lu, H. (2022). Towards grand unification of object tracking. In European conference on computer vision (ECCV).","DOI":"10.1007\/978-3-031-19803-8_43"},{"key":"2226_CR98","doi-asserted-by":"crossref","unstructured":"Yan, B., Peng, H., Fu, J., Wang, D., & Lu, H. (2021). Learning spatio-temporal transformer for visual tracking. In IEEE\/CVF international conference on computer vision (ICCV).","DOI":"10.1109\/ICCV48922.2021.01028"},{"key":"2226_CR99","doi-asserted-by":"crossref","unstructured":"Yan, B., Wang, D., Lu, H., & Yang, X. (2020). Cooling-shrinking attack: Blinding the tracker with imperceptible noises. In IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR42600.2020.00107"},{"key":"2226_CR100","doi-asserted-by":"crossref","unstructured":"Yu, B., Tang, M., Zheng, L., Zhu, G., Wang, J., Feng, H., Feng, X., & Lu, H. (2021). High-performance discriminative tracking with transformers. In IEEE\/CVF international conference on computer vision (ICCV).","DOI":"10.1109\/ICCV48922.2021.00971"},{"key":"2226_CR101","doi-asserted-by":"crossref","unstructured":"Zhang, L., Gonzalez-Garcia, A., Weijer, J.\u00a0V.\u00a0D., Danelljan, M., & Khan, F.\u00a0S. (2019). Learning the model update for siamese trackers. In IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/ICCV.2019.00411"},{"key":"2226_CR102","doi-asserted-by":"crossref","unstructured":"Zhang, T., Xu, C., & Yang, M.\u00a0H. (2017) Multi-task correlation particle filter for robust object tracking. In IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2017.512"},{"key":"2226_CR103","doi-asserted-by":"crossref","unstructured":"Zhang, Z., & Peng, H. (2019). Deeper and wider siamese networks for real-time visual tracking. In IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2019.00472"},{"key":"2226_CR104","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Peng, H., Fu, J., Li, B., & Hu, W. (2020). Ocean: Object-aware anchor-free tracking. In European conference on computer vision (ECCV).","DOI":"10.1007\/978-3-030-58589-1_46"},{"key":"2226_CR105","doi-asserted-by":"crossref","unstructured":"Zhou, M., Wu, J., Liu, Y., Liu, S., & Zhu, C. (2020). Dast: Data-free substitute training for adversarial attacks. In IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR42600.2020.00031"},{"key":"2226_CR106","doi-asserted-by":"crossref","unstructured":"Zhou, T., Ye, Q., Luo, W., Zhang, K., Shi, Z., & Chen, J. (2023). F &f attack: Adversarial attack against multiple object trackers by inducing false negatives and false positives. In IEEE\/CVF international conference on computer vision (ICCV).","DOI":"10.1109\/ICCV51070.2023.00422"},{"key":"2226_CR107","doi-asserted-by":"crossref","unstructured":"Zhu, Z., Wang, Q., Li, B., Wu, W., Yan, J., & Hu, W. (2018). Distractor-aware siamese networks for visual object tracking. In European conference on computer vision (ECCV).","DOI":"10.1007\/978-3-030-01240-3_7"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02226-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-024-02226-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02226-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,24]],"date-time":"2025-02-24T10:06:47Z","timestamp":1740391607000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-024-02226-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,26]]},"references-count":107,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2025,3]]}},"alternative-id":["2226"],"URL":"https:\/\/doi.org\/10.1007\/s11263-024-02226-0","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9,26]]},"assertion":[{"value":"5 September 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 August 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 September 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}