{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T05:39:35Z","timestamp":1770356375787,"version":"3.49.0"},"reference-count":50,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2022,4,6]],"date-time":"2022-04-06T00:00:00Z","timestamp":1649203200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,4,6]],"date-time":"2022-04-06T00:00:00Z","timestamp":1649203200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61806109"],"award-info":[{"award-number":["61806109"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2022,6]]},"DOI":"10.1007\/s11263-022-01604-w","type":"journal-article","created":{"date-parts":[[2022,4,6]],"date-time":"2022-04-06T03:33:51Z","timestamp":1649216031000},"page":"1459-1473","update-policy":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":32,"title":["Sparse Black-Box Video Attack with Reinforcement Learning"],"prefix":"10.1007","volume":"130","author":[{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0000-0002-0778-8377","authenticated-orcid":false,"given":"Xingxing","family":"Wei","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huanqian","family":"Yan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,4,6]]},"reference":[{"key":"1604_CR1","doi-asserted-by":"publisher","first-page":"14410","DOI":"10.1109\/ACCESS.2018.2807385","volume":"6","author":"N Akhtar","year":"2018","unstructured":"Akhtar, N., & Mian, A. (2018). Threat of adversarial attacks on deep learning in computer vision: A survey. IEEE Access, 6, 14410\u201314430.","journal-title":"IEEE Access"},{"key":"1604_CR2","doi-asserted-by":"crossref","unstructured":"Bose, J. A., & Aarabi, P. (2018). Adversarial attacks on face detectors using neural net based constrained optimization. pp. 1\u20136.","DOI":"10.1109\/MMSP.2018.8547128"},{"key":"1604_CR3","unstructured":"Cheng, M., Le, T., Chen, P.-Y., Zhang, H., Yi, J., & Hsieh, C.-J. (2019). Query-efficient hard-label black-box attack: An optimization-based approach. In International conference on learning representations."},{"key":"1604_CR4","unstructured":"Cheng, M., Singh, S., Chen, P.-Y., Liu, S., & Hsieh, C.-J. (2020). Sign-opt: A query-efficient hard-label adversarial attack. In International conference on learning representations."},{"issue":"4","key":"1604_CR5","doi-asserted-by":"publisher","first-page":"1028","DOI":"10.1007\/s11263-019-01213-0","volume":"128","author":"F Croce","year":"2020","unstructured":"Croce, F., Rauber, J., & Hein, M. (2020). Scaling up the randomized gradient-free adversarial attack reveals overestimation of robustness using established attacks. In International Journal of Computer Vision, 128(4), 1028\u20131046.","journal-title":"In International Journal of Computer Vision"},{"key":"1604_CR6","doi-asserted-by":"crossref","unstructured":"Das, N., Shanbhogue, M., Chen, S., Hohman, F., Li, S., Chen, L., Kounavis, M. E., & Chau, D. H. (2018) Shield: Fast, practical defense and vaccination for deep learning using jpeg compression. Knowledge discovery and data mining, pp. 196\u2013204.","DOI":"10.1145\/3219819.3219910"},{"key":"1604_CR7","doi-asserted-by":"crossref","unstructured":"Deng,L., Chen, J., Sun, Q., He, X., Tang, S., Ming, Z., Zhang, Y. & Chua,T.-S. (2019). Mixed-dish recognition with contextual relation networks. Proceedings of the 27th ACM International conference on multimedia.","DOI":"10.1145\/3343031.3351147"},{"issue":"4","key":"1604_CR8","doi-asserted-by":"publisher","first-page":"677","DOI":"10.1109\/TPAMI.2016.2599174","volume":"39","author":"J Donahue","year":"2017","unstructured":"Donahue, J., Hendricks, L. A., Rohrbach, M., Venugopalan, S., Guadarrama, S., Saenko, K., & Darrell, T. (2017). Long-term recurrent convolutional networks for visual recognition and description. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(4), 677\u2013691.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1604_CR9","doi-asserted-by":"publisher","first-page":"8247","DOI":"10.1609\/aaai.v33i01.33018247","volume":"33","author":"W Dong","year":"2019","unstructured":"Dong, W., Zhang, Z., & Tan, T. (2019). Attention-aware sampling via deep reinforcement learning for action recognition. In National Conference on Artificial Intelligence, 33, 8247\u20138254.","journal-title":"In National Conference on Artificial Intelligence"},{"key":"1604_CR10","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 Computer vision and pattern recognition, pp. 7714\u20137722.","DOI":"10.1109\/CVPR.2019.00790"},{"issue":"7639","key":"1604_CR11","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1038\/nature21056","volume":"542","author":"A Esteva","year":"2017","unstructured":"Esteva, A., Kuprel, B., Novoa, R. A., Ko, J. M., Swetter, S. M., Blau, H. M., & Thrun, S. (2017). Dermatologist-level classification of skin cancer with deep neural networks. Nature, 542(7639), 115\u2013118.","journal-title":"Nature"},{"key":"1604_CR12","unstructured":"Goodfellow, I. J., Jonathon, S., & Christian, S. (2015). Explaining and harnessing adversarial examples. In International conference on learning representations."},{"issue":"6","key":"1604_CR13","doi-asserted-by":"publisher","first-page":"719","DOI":"10.1007\/s11263-019-01160-w","volume":"127","author":"G Goswami","year":"2019","unstructured":"Goswami, G., Agarwal, A., Ratha, N., Singh, R., & Vatsa, M. (2019). Detecting and mitigating adversarial perturbations for robust face recognition. In International Journal of Computer Vision, 127(6), 719\u2013742.","journal-title":"In International Journal of Computer Vision"},{"key":"1604_CR14","unstructured":"Guo, C., Rana, M., Cisse, M., & Van Der Maaten, L. (2017). Countering adversarial images using input transformations. International conference on learning representations."},{"key":"1604_CR15","doi-asserted-by":"crossref","unstructured":"Hara, K., Kataoka, H., & Satoh, Y. (2018). Can spatiotemporal 3d cnns retrace the history of 2d cnns and imagenet? In computer vision and pattern recognition, pp. 6546\u20136555.","DOI":"10.1109\/CVPR.2018.00685"},{"key":"1604_CR16","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Computer vision and pattern recognition, pp. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"issue":"8","key":"1604_CR17","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735-1780.","journal-title":"Neural Computation"},{"key":"1604_CR18","unstructured":"Ilyas, A.,Engstrom, L., Athalye, A., Lin, J., Athalye, A., Engstrom, L., Ilyas, A., & Kwok, K. (2018). Black-box adversarial attacks with limited queries and information. In International conference on machine learning."},{"key":"1604_CR19","unstructured":"Jia, X., Wei, X., & Cao, X. (2019). Identifying and resisting adversarial videos using temporal consistency. arXiv preprint arXiv:1909.04837."},{"key":"1604_CR20","doi-asserted-by":"crossref","unstructured":"Jia, X., Wei, X., Cao, X., & Foroosh, H. (2019). Comdefend: An efficient image compression model to defend adversarial examples. In 2019 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), pp. 6084\u20136092.","DOI":"10.1109\/CVPR.2019.00624"},{"key":"1604_CR21","doi-asserted-by":"crossref","unstructured":"Jiang, L., Ma, X., Chen, S., Bailey, J., & Jiangl, Y.-G. (2019). Black-box adversarial attacks on video recognition models. In Acm multimedia, pp. 864\u2013872.","DOI":"10.1145\/3343031.3351088"},{"key":"1604_CR22","unstructured":"Kingma ,D. P. & Ba, J. (2015). Adam: A method for stochastic optimization. International conference on learning representations."},{"key":"1604_CR23","doi-asserted-by":"crossref","unstructured":"Kuehne, H., Jhuang, H., Garrote, E., Poggio, T., & Serre,T. (2011). Hmdb: A large video database for human motion recognition. In 2011 International conference on computer vision, IEEE. pp. 2556\u20132563.","DOI":"10.1109\/ICCV.2011.6126543"},{"issue":"7553","key":"1604_CR24","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y Lecun","year":"2015","unstructured":"Lecun, Y., Bengio, Y., & Hinton, G. E. (2015). Deep learning. Nature, 521(7553), 436\u2013444.","journal-title":"Nature"},{"key":"1604_CR25","doi-asserted-by":"crossref","unstructured":"Li, S., Neupane, A., Paul, S., Song, C., Krishnamurthy, S. V., Roy-Chowdhury, A. K., & Swami, A. (2019). In network and distributed system security symposium: Stealthy adversarial perturbations against real-time video classification systems.","DOI":"10.14722\/ndss.2019.23202"},{"key":"1604_CR26","unstructured":"Li, Y. (2017). Deep reinforcement learning: An overview. arXiv: Learning."},{"key":"1604_CR27","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1016\/j.media.2017.07.005","volume":"42","author":"GJS Litjens","year":"2017","unstructured":"Litjens, G. J. S., Kooi, T., Bejnordi, B. E., Setio, A. A. A., Ciompi, F., Ghafoorian, M., Van Der Laak, J. A., Van Ginneken, B., & Sanchez, C. I. (2017). A survey on deep learning in medical image analysis. Medical Image Analysis, 42, 60\u201388.","journal-title":"Medical Image Analysis"},{"key":"1604_CR28","unstructured":"Liu, S., Chen, P.\u00a0Y., Chen, X., & Hong, M. (2019). Signsgd via zeroth-order oracle. In 7th International conference on learning representations, ICLR 2019."},{"key":"1604_CR29","unstructured":"Lu, J., Sibai, H., Fabry, E., & Forsyth, D. (2017). No need to worry about adversarial examples in object detection in autonomous vehicles. arXiv: Computer Vision and Pattern Recognition, 2017."},{"key":"1604_CR30","unstructured":"Madry, A., Makelov, A., Schmidt, L., Tsipras, D. & Vladu, A. (2017).Towards deep learning models resistant to adversarial attacks. International conference on learning representations."},{"key":"1604_CR31","unstructured":"Mnih, V., Kavukcuoglu, K., Silver, D., Graves, A., Antonoglou, I., Wierstra, D., & Martin, A. (2013). Riedmiller. Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602."},{"key":"1604_CR32","doi-asserted-by":"crossref","unstructured":"Moosavidezfooli, S., Fawzi, A., & Frossard, P. (2016). Deepfool: A simple and accurate method to fool deep neural networks. Computer vision and pattern recognition, pp. 2574\u20132582.","DOI":"10.1109\/CVPR.2016.282"},{"key":"1604_CR33","unstructured":"Nezami, O. M., Chaturvedi, A., Dras, M., & Garain, U. (2020). Pick-object-attack: Type-specific adversarial attack for object detection."},{"key":"1604_CR34","doi-asserted-by":"crossref","unstructured":"Prakash, A., Moran, N., Garber, S., DiLillo, A., & Storer, J. (2018). Deflecting adversarial attacks with pixel deflection. In 2018 IEEE\/CVF conference on computer vision and pattern recognition, pp. 8571\u20138580.","DOI":"10.1109\/CVPR.2018.00894"},{"issue":"7587","key":"1604_CR35","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver, D., Huang, A., Maddison, C. J., Guez, A., Sifre, L., van den Driessche, G., et al. (2016). Mastering the game of go with deep neural networks and tree search. Nature, 529(7587), 484-489.","journal-title":"Nature"},{"issue":"7676","key":"1604_CR36","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1038\/nature24270","volume":"550","author":"D Silver","year":"2017","unstructured":"Silver, D., Schrittwieser, J., Simonyan, K., Antonoglou, I., Huang, A., Guez, A., Hubert, T., Baker, L., Lai, M., Bolton, A., Chen, Y., Lillicrap, T. P., Hui, F., Sifre, L., van den Driessche, G., Graepel, T., & Hassabis, D. (2017). Mastering the game of go without human knowledge. Nature, 550(7676), 354\u2013359.","journal-title":"Nature"},{"key":"1604_CR37","unstructured":"Soomro K., Zamir, A. R., & Shah, M. (2012). Ucf101: A dataset of 101 human actions classes from videos in the wild. arXiv: Computer Vision and Pattern Recognition, 2012."},{"key":"1604_CR38","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., & Wojna, Z. (2016). Rethinking the inception architecture for computer vision. Computer vision and pattern recognition, pp. 2818\u20132826.","DOI":"10.1109\/CVPR.2016.308"},{"key":"1604_CR39","doi-asserted-by":"crossref","unstructured":"Teng, S., Zhang, S., Huang, Q., & Sebe N. (2021). Viewpoint and scale consistency reinforcement for UAV vehicle re-identification. International Journal of Computer Vision 129.3 719-735.","DOI":"10.1007\/s11263-020-01402-2"},{"key":"1604_CR40","unstructured":"Tram\u00e8r, F., Kurakin, A., Papernot, N., Goodfellow, I. J., Boneh, D., McDaniel, P. D. (2018). Ensemble adversarial training: Attacks and defenses. In International conference on learning representations."},{"key":"1604_CR41","doi-asserted-by":"crossref","unstructured":"Wei, X., Liang, S., Chen, N. & Cao, X. (2019). Transferable adversarial attacks for image and video object detection. International joint conference on artificial intelligence, pp. 954\u2013960.","DOI":"10.24963\/ijcai.2019\/134"},{"key":"1604_CR42","doi-asserted-by":"crossref","unstructured":"Wei, X., Zhu, J., Feng, S., Su, H. (2018) Video-to-video translation with global temporal consistency. Proceedings of the 26th ACM International conference on multimedia.","DOI":"10.1145\/3240508.3240708"},{"key":"1604_CR43","doi-asserted-by":"publisher","first-page":"8973","DOI":"10.1609\/aaai.v33i01.33018973","volume":"33","author":"X Wei","year":"2019","unstructured":"Wei, X., Zhu, J., Yuan, S., & Hang, S. (2019). Sparse adversarial perturbations for videos. In National Conference on Artificial Intelligence, 33, 8973\u20138980.","journal-title":"In National Conference on Artificial Intelligence"},{"key":"1604_CR44","doi-asserted-by":"crossref","unstructured":"Wei, Z., Chen, J., Wei, X., & Yugang, J. (2020). Heuristic black-box adversarial attacks on video recognition models. In National conference on artificial intelligence.","DOI":"10.1609\/aaai.v34i07.6918"},{"issue":"1","key":"1604_CR45","first-page":"949","volume":"15","author":"D Wierstra","year":"2014","unstructured":"Wierstra, D., Schaul, T., Glasmachers, T., Sun, Y., Peters, J., & Schmidhuber, J. (2014). Natural evolution strategies. The Journal of Machine Learning Research, 15(1), 949\u2013980.","journal-title":"The Journal of Machine Learning Research"},{"issue":"3\u20134","key":"1604_CR46","first-page":"229","volume":"8","author":"RJ Williams","year":"1992","unstructured":"Williams, R. J. (1992). Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine Learning, 8(3\u20134), 229\u2013256.","journal-title":"Machine Learning"},{"key":"1604_CR47","unstructured":"Xie, C., Wang, J.,Zhang, Z., Ren, Z.,&Yuille, A. L. (2017) Mitigating adversarial effects through randomization. International conference on learning representations."},{"key":"1604_CR48","doi-asserted-by":"crossref","unstructured":"Xie, C., Wang, J., Zhang, Z., Zhou, Y., Xie, L., & Yuille, A. L. (2017). Adversarial examples for semantic segmentation and object detection. International conference on computer vision, pp. 1378\u20131387.","DOI":"10.1109\/ICCV.2017.153"},{"key":"1604_CR49","doi-asserted-by":"crossref","unstructured":"Zhang, H., & Wang, J. (2019). Towards adversarially robust object detection. International conference on computer vision, pp. 421\u2013430.","DOI":"10.1109\/ICCV.2019.00051"},{"key":"1604_CR50","doi-asserted-by":"crossref","unstructured":"Zhou, K., Qiao, Y., Xiang, T. (2018). Deep reinforcement learning for unsupervised video summarization with diversity-representativeness reward. In National conference on artificial intelligence.","DOI":"10.1609\/aaai.v32i1.12255"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/link.springer.com\/content\/pdf\/10.1007\/s11263-022-01604-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/link.springer.com\/article\/10.1007\/s11263-022-01604-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/link.springer.com\/content\/pdf\/10.1007\/s11263-022-01604-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,31]],"date-time":"2023-01-31T18:59:28Z","timestamp":1675191568000},"score":1,"resource":{"primary":{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/link.springer.com\/10.1007\/s11263-022-01604-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,6]]},"references-count":50,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2022,6]]}},"alternative-id":["1604"],"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1007\/s11263-022-01604-w","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,4,6]]},"assertion":[{"value":"31 July 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 March 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 April 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}