{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T00:08:21Z","timestamp":1755907701245,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":70,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,4,15]],"date-time":"2024-04-15T00:00:00Z","timestamp":1713139200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"University of Padova","award":["CRUI CARE"],"award-info":[{"award-number":["CRUI CARE"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,4,15]]},"DOI":"10.1145\/3625468.3647623","type":"proceedings-article","created":{"date-parts":[[2024,4,17]],"date-time":"2024-04-17T06:10:01Z","timestamp":1713334201000},"page":"190-201","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["A Modular System for Enhanced Robustness of Multimedia Understanding Networks via Deep Parametric Estimation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9893-5813","authenticated-orcid":false,"given":"Francesco","family":"Barbato","sequence":"first","affiliation":[{"name":"University of Padova, Samsung Research UK, Italy \/ United Kingdom and Samsung Research UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2666-4342","authenticated-orcid":false,"given":"Umberto","family":"Michieli","sequence":"additional","affiliation":[{"name":"Samsung Research UK, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1645-0877","authenticated-orcid":false,"given":"Mehmet Kerim","family":"Yucel","sequence":"additional","affiliation":[{"name":"Samsung Research UK, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9502-2389","authenticated-orcid":false,"given":"Pietro","family":"Zanuttigh","sequence":"additional","affiliation":[{"name":"University of Padova, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7189-7260","authenticated-orcid":false,"given":"Mete","family":"Ozay","sequence":"additional","affiliation":[{"name":"Samsung Research UK, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,4,17]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Generalized octave convolutions for learned multi-frequency image compression. arXiv preprint arXiv:2002.10032","author":"Akbari M.","year":"2020","unstructured":"Akbari, M., Liang, J., Han, J., and Tu, C. Generalized octave convolutions for learned multi-frequency image compression. arXiv preprint arXiv:2002.10032 (2020)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3551626.3564956"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01560"},{"key":"e_1_3_2_1_4_1","volume-title":"Road scenes segmentation across different domains by disentangling latent representations. arXiv preprint arXiv:2108.03021","author":"Barbato F.","year":"2021","unstructured":"Barbato, F., Michieli, U., Toldo, M., and Zanuttigh, P. Road scenes segmentation across different domains by disentangling latent representations. arXiv preprint arXiv:2108.03021 (2021)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00318"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00051"},{"key":"e_1_3_2_1_7_1","volume-title":"Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs","author":"Chen L.-C.","year":"2017","unstructured":"Chen, L.-C., Papandreou, G., Kokkinos, I., Murphy, K., and Yuille, A. L. Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs, 2017."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00819"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"e_1_3_2_1_10_1","volume-title":"Autoaugment: Learning augmentation policies from data. arXiv preprint arXiv:1805.09501","author":"Cubuk E. D.","year":"2018","unstructured":"Cubuk, E. D., Zoph, B., Mane, D., Vasudevan, V., and Le, Q. V. Autoaugment: Learning augmentation policies from data. arXiv preprint arXiv:1805.09501 (2018)."},{"key":"e_1_3_2_1_11_1","volume-title":"Diffusion models beat gans on image synthesis. Advances in neural information processing systems 34","author":"Dhariwal P.","year":"2021","unstructured":"Dhariwal, P., and Nichol, A. Diffusion models beat gans on image synthesis. Advances in neural information processing systems 34 (2021), 8780--8794."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3016485"},{"key":"e_1_3_2_1_13_1","volume-title":"Detecting adversarial samples from artifacts. arXiv preprint arXiv:1703.00410","author":"Feinman R.","year":"2017","unstructured":"Feinman, R., Curtin, R. R., Shintre, S., and Gardner, A. B. Detecting adversarial samples from artifacts. arXiv preprint arXiv:1703.00410 (2017)."},{"key":"e_1_3_2_1_14_1","volume-title":"Imagenet-trained cnns are biased towards texture","author":"Geirhos R.","year":"1811","unstructured":"Geirhos, R., Rubisch, P., Michaelis, C., Bethge, M., Wichmann, F. A., and Brendel, W. Imagenet-trained cnns are biased towards texture; increasing shape bias improves accuracy and robustness. arXiv preprint arXiv:1811.12231 (2018)."},{"key":"e_1_3_2_1_15_1","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Gong T.","year":"2022","unstructured":"Gong, T., Jeong, J., Kim, T., Kim, Y., Shin, J., and Lee, S.-J. NOTE: Robust continual test-time adaptation against temporal correlation. In Advances in Neural Information Processing Systems (NeurIPS) (2022)."},{"key":"e_1_3_2_1_16_1","volume-title":"On the (statistical) detection of adversarial examples. arXiv preprint arXiv:1702.06280","author":"Grosse K.","year":"2017","unstructured":"Grosse, K., Manoharan, P., Papernot, N., Backes, M., and McDaniel, P. On the (statistical) detection of adversarial examples. arXiv preprint arXiv:1702.06280 (2017)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2022.3221853"},{"key":"e_1_3_2_1_18_1","volume-title":"Deep residual learning for image recognition","author":"He K.","year":"2015","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. Deep residual learning for image recognition, 2015."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"e_1_3_2_1_22_1","volume-title":"International Conference on Learning Representations (ICLR)","author":"Hendrycks D.","year":"2019","unstructured":"Hendrycks, D., and Dietterich, T. Benchmarking neural network robustness to common corruptions and perturbations. International Conference on Learning Representations (ICLR) (2019)."},{"key":"e_1_3_2_1_23_1","volume-title":"Benchmarking neural network robustness to common corruptions and perturbations. arXiv preprint arXiv:1903.12261","author":"Hendrycks D.","year":"2019","unstructured":"Hendrycks, D., and Dietterich, T. Benchmarking neural network robustness to common corruptions and perturbations. arXiv preprint arXiv:1903.12261 (2019)."},{"key":"e_1_3_2_1_24_1","volume-title":"International Conference on Learning Representations (ICLR)","author":"Hendrycks D.","year":"2020","unstructured":"Hendrycks, D., Mu, N., Cubuk, E. D., Zoph, B., Gilmer, J., and Lakshminarayanan, B. AugMix: A simple data processing method to improve robustness and uncertainty. International Conference on Learning Representations (ICLR) (2020)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01628"},{"key":"e_1_3_2_1_26_1","volume-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Hendrycks D.","year":"2021","unstructured":"Hendrycks, D., Zou, A., Mazeika, M., Tang, L., Li, B., Song, D. X., and Steinhardt, J. Pixmix: Dreamlike pictures comprehensively improve safety measures. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2021)."},{"key":"e_1_3_2_1_27_1","volume-title":"International Conference on Learning Representations (ICLR)","author":"Hu X.","year":"2022","unstructured":"Hu, X., Uzunbas, M. G., Chen, S., Wang, R., Shah, A., Nevatia, R., and Lim, S.-N. Mixnorm: Test-time adaptation through online normalization estimation. International Conference on Learning Representations (ICLR) (2022)."},{"key":"e_1_3_2_1_28_1","volume-title":"SITA: Single Image Test-time Adaptation. ArXiv:2112.02355","author":"Khurana A.","year":"2021","unstructured":"Khurana, A., Paul, S., Rai, P., Biswas, S., and Aggarwal, G. SITA: Single Image Test-time Adaptation. ArXiv:2112.02355 (2021)."},{"key":"e_1_3_2_1_29_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma D. P.","year":"2014","unstructured":"Kingma, D. P., and Ba, J. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"e_1_3_2_1_31_1","article-title":"Spn2d-gan: Semantic prior based night-to-day image-to-image translation","author":"Li X.","year":"2022","unstructured":"Li, X., and Guo, X. Spn2d-gan: Semantic prior based night-to-day image-to-image translation. IEEE Transactions on Multimedia (2022).","journal-title":"IEEE Transactions on Multimedia ("},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01088"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2016.06.008"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.56"},{"key":"e_1_3_2_1_36_1","volume-title":"Towards deep learning models resistant to adversarial attacks. arXiv preprint arXiv:1706.06083","author":"Madry A.","year":"2017","unstructured":"Madry, A., Makelov, A., Schmidt, L., Tsipras, D., and Vladu, A. Towards deep learning models resistant to adversarial attacks. arXiv preprint arXiv:1706.06083 (2017)."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2014.03.006"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341474"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.2970615"},{"key":"e_1_3_2_1_40_1","first-page":"3571","article-title":"On interaction between augmentations and corruptions in natural corruption robustness","volume":"34","author":"Mintun E.","year":"2021","unstructured":"Mintun, E., Kirillov, A., and Xie, S. On interaction between augmentations and corruptions in natural corruption robustness. Advances in Neural Information Processing Systems 34 (2021), 3571--3583.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19806-9_36"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3023615"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.07.085"},{"key":"e_1_3_2_1_44_1","volume-title":"International Conference on Learning Representations (ICLR)","author":"Niu S.","year":"2023","unstructured":"Niu, S., Wu, J., Zhang, Y., Wen, Z., Chen, Y., Zhao, P., and Tan, M. Towards stable test-time adaptation in dynamic wild world. In International Conference on Learning Representations (ICLR) (2023)."},{"key":"e_1_3_2_1_45_1","volume-title":"Learning transferable visual models from natural language supervision. ArXiv:2103.00020","author":"Radford A.","year":"2021","unstructured":"Radford, A., Kim, J. W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., Krueger, G., and Sutskever, I. Learning transferable visual models from natural language supervision. ArXiv:2103.00020 (2021)."},{"key":"e_1_3_2_1_46_1","first-page":"10811","article-title":"Do imagenet classifiers generalize to imagenet?","author":"Recht B.","year":"1902","unstructured":"Recht, B., Roelofs, R., Schmidt, L., and Shankar, V. Do imagenet classifiers generalize to imagenet? ArXiv:1902.10811 (2019).","journal-title":"ArXiv"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00235"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01005"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00747"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01059"},{"key":"e_1_3_2_1_52_1","volume-title":"Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556","author":"Simonyan K.","year":"2014","unstructured":"Simonyan, K., and Zisserman, A. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)."},{"key":"e_1_3_2_1_53_1","volume-title":"ptflops: a flops counting tool for neural networks in pytorch framework","author":"Sovrasov V.","year":"2018","unstructured":"Sovrasov, V. ptflops: a flops counting tool for neural networks in pytorch framework, 2018--2023."},{"key":"e_1_3_2_1_54_1","volume-title":"Intriguing properties of neural networks. arXiv preprint arXiv:1312.6199","author":"Szegedy C.","year":"2013","unstructured":"Szegedy, C., Zaremba, W., Sutskever, I., Bruna, J., Erhan, D., Goodfellow, I., and Fergus, R. Intriguing properties of neural networks. arXiv preprint arXiv:1312.6199 (2013)."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3257086"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2020.07.025"},{"key":"e_1_3_2_1_57_1","volume-title":"TorchVision: PyTorch's Computer Vision library. https:\/\/github.com\/pytorch\/vision","author":"TorchVision","year":"2016","unstructured":"TorchVision maintainers and contributors. TorchVision: PyTorch's Computer Vision library. https:\/\/github.com\/pytorch\/vision, 2016."},{"key":"e_1_3_2_1_58_1","volume-title":"Efficient diffusion models for vision: A survey","author":"Ulhaq A.","year":"2022","unstructured":"Ulhaq, A., Akhtar, N., and Pogrebna, G. Efficient diffusion models for vision: A survey, 2022."},{"key":"e_1_3_2_1_59_1","volume-title":"International Conference on Learning Representations (ICLR)","author":"Wang D.","year":"2021","unstructured":"Wang, D., Shelhamer, E., Liu, S., Olshausen, B., and Darrell, T. Tent: Fully test-time adaptation by entropy minimization. In International Conference on Learning Representations (ICLR) (2021)."},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_4"},{"key":"e_1_3_2_1_61_1","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Wang H.","year":"2021","unstructured":"Wang, H., Xiao, C., Kossaifi, J., Yu, Z., Anandkumar, A., and Wang, Z. Augmax: Adversarial composition of random augmentations for robust training. In Advances in Neural Information Processing Systems (NeurIPS) (2021)."},{"key":"e_1_3_2_1_62_1","volume-title":"Test-time training on video streams. arXiv:2307.05014","author":"Wang R.","year":"2023","unstructured":"Wang, R., Sun, Y., Gandelsman, Y., Chen, X., Efros, A. A., and Wang, X. Test-time training on video streams. arXiv:2307.05014 (2023)."},{"key":"e_1_3_2_1_63_1","volume-title":"Feature squeezing: Detecting adversarial examples in deep neural networks. arXiv preprint arXiv:1704.01155","author":"Xu W.","year":"2017","unstructured":"Xu, W., Evans, D., and Qi, Y. Feature squeezing: Detecting adversarial examples in deep neural networks. arXiv preprint arXiv:1704.01155 (2017)."},{"key":"e_1_3_2_1_64_1","volume-title":"Failure modes of variational autoencoders and their effects on downstream tasks. arXiv preprint arXiv:2007.07124","author":"Yacoby Y.","year":"2020","unstructured":"Yacoby, Y., Pan, W., and Doshi-Velez, F. Failure modes of variational autoencoders and their effects on downstream tasks. arXiv preprint arXiv:2007.07124 (2020)."},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01130"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2022.104392"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00526"},{"key":"e_1_3_2_1_68_1","first-page":"1","article-title":"Color-patterned fabric defect detection algorithm based on triplet attention multi-scale u-shape denoising convolutional auto-encoder","author":"Zhang H.","year":"2023","unstructured":"Zhang, H., Liu, S., Wang, C., Lu, S., and Xiong, W. Color-patterned fabric defect detection algorithm based on triplet attention multi-scale u-shape denoising convolutional auto-encoder. The Journal of Supercomputing (2023), 1--26.","journal-title":"The Journal of Supercomputing ("},{"key":"e_1_3_2_1_69_1","volume-title":"Memo: Test time robustness via adaptation and augmentation. Advances in Neural Information Processing Systems (NeurIPS)","author":"Zhang M.","year":"2022","unstructured":"Zhang, M., Levine, S., and Finn, C. Memo: Test time robustness via adaptation and augmentation. Advances in Neural Information Processing Systems (NeurIPS) (2022)."},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF01257768"}],"event":{"name":"MMSys '24: ACM Multimedia Systems Conference 2024","sponsor":["SIGMM ACM Special Interest Group on Multimedia","SIGCOMM ACM Special Interest Group on Data Communication","SIGMOBILE ACM Special Interest Group on Mobility of Systems, Users, Data and Computing"],"location":"Bari Italy","acronym":"MMSys '24"},"container-title":["Proceedings of the ACM Multimedia Systems Conference 2024 on ZZZ"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3625468.3647623","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3625468.3647623","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T17:27:16Z","timestamp":1755883636000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3625468.3647623"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,15]]},"references-count":70,"alternative-id":["10.1145\/3625468.3647623","10.1145\/3625468"],"URL":"https:\/\/doi.org\/10.1145\/3625468.3647623","relation":{},"subject":[],"published":{"date-parts":[[2024,4,15]]},"assertion":[{"value":"2024-04-17","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}