{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T15:45:21Z","timestamp":1768405521897,"version":"3.49.0"},"publisher-location":"Cham","reference-count":46,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031263187","type":"print"},{"value":"9783031263194","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-26319-4_38","type":"book-chapter","created":{"date-parts":[[2023,3,3]],"date-time":"2023-03-03T06:02:59Z","timestamp":1677823379000},"page":"635-651","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Training Dynamics Aware Neural Network Optimization with\u00a0Stabilization"],"prefix":"10.1007","author":[{"given":"Zilin","family":"Fang","sequence":"first","affiliation":[]},{"given":"Mohamad","family":"Shahbazi","sequence":"additional","affiliation":[]},{"given":"Thomas","family":"Probst","sequence":"additional","affiliation":[]},{"given":"Danda Pani","family":"Paudel","sequence":"additional","affiliation":[]},{"given":"Luc Van","family":"Gool","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,3,4]]},"reference":[{"key":"38_CR1","unstructured":"Cauchy, A.: Methode generale pour la resolution des systemes d\u2019equations simultanees. C.R. Acad. Sci. Paris 25, 536\u2013538 (1847)"},{"key":"38_CR2","unstructured":"Nesterov, Y.: A method for unconstrained convex minimization problem with the rate of convergence $$o(1\/k^2)$$ (1983)"},{"key":"38_CR3","unstructured":"Sutton, R.S.: Two problems with backpropagation and other steepest-descent learning procedures for networks. In: Proceedings of the Eighth Annual Conference of the Cognitive Science Society. Erlbaum, Hillsdale (1986)"},{"key":"38_CR4","unstructured":"Duchi, J.C., Hazan, E., Singer, Y.: Adaptive subgradient methods for online learning and stochastic optimization. In: J. Mach. Learn. Res. (2011)"},{"key":"38_CR5","unstructured":"McMahan, H.B., Streeter, M.J.: Delay-tolerant algorithms for asynchronous distributed online learning. In: NIPS (2014)"},{"key":"38_CR6","unstructured":"Recht, B., R\u00e9, C., Wright, S.J., Niu, F.: Hogwild: a lock-free approach to parallelizing stochastic gradient descent. In: NIPS (2011)"},{"key":"38_CR7","unstructured":"Zhang, S., Choroma\u0144ska, A., LeCun, Y.: Deep learning with elastic averaging SGD. In: NIPS (2015)"},{"key":"38_CR8","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. CoRR abs\/1412.6980 (2015)"},{"key":"38_CR9","unstructured":"Dozat, T.: Incorporating nesterov momentum into Adam (2016)"},{"key":"38_CR10","doi-asserted-by":"publisher","first-page":"146","DOI":"10.1007\/BF01931367","volume":"16","author":"S Linnainmaa","year":"1976","unstructured":"Linnainmaa, S.: Taylor expansion of the accumulated rounding error. BIT Numer. Math. 16, 146\u2013160 (1976)","journal-title":"BIT Numer. Math."},{"key":"38_CR11","doi-asserted-by":"crossref","unstructured":"Griewank, A.: Who invented the reverse mode of differentiation (2012)","DOI":"10.4171\/dms\/6\/38"},{"key":"38_CR12","doi-asserted-by":"crossref","unstructured":"LeCun, Y., Bottou, L., Orr, G., M\u00fcller, K.: Efficient backprop. In: Neural Networks: Tricks of the Trade (2012)","DOI":"10.1007\/978-3-642-35289-8_3"},{"key":"38_CR13","doi-asserted-by":"publisher","first-page":"1859","DOI":"10.1109\/TAC.2006.884922","volume":"51","author":"SP Boyd","year":"2006","unstructured":"Boyd, S.P., Vandenberghe, L.: Convex optimization. IEEE Trans. Autom. Control 51, 1859\u20131859 (2006)","journal-title":"IEEE Trans. Autom. Control"},{"key":"38_CR14","doi-asserted-by":"crossref","unstructured":"Helmke, U., Moore, J.: Optimization and dynamical systems. Proc. IEEE 84, 907- (1996)","DOI":"10.1109\/JPROC.1996.503147"},{"key":"38_CR15","unstructured":"Kendall, A., Gal, Y., Cipolla, R.: Multi-task learning using uncertainty to weigh losses for scene geometry and semantics. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7482\u20137491 (2018)"},{"key":"38_CR16","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1109\/TPAMI.2017.2781233","volume":"41","author":"R Ranjan","year":"2019","unstructured":"Ranjan, R., Patel, V., Chellappa, R.: Hyperface: a deep multi-task learning framework for face detection, landmark localization, pose estimation, and gender recognition. IEEE Trans. Pattern Anal. Mach. Intell. 41, 121\u2013135 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"38_CR17","doi-asserted-by":"crossref","unstructured":"Popovi\u0107, N., Paudel, D., Probst, T., Sun, G., Gool, L.: Compositetasking: understanding images by spatial composition of tasks. arXiv abs\/2012.09030 (2020)","DOI":"10.1109\/CVPR46437.2021.00680"},{"key":"38_CR18","unstructured":"Zhong, Z., Zheng, L., Kang, G., Li, S., Yang, Y.: Random erasing data augmentation. arXiv abs\/1708.04896 (2020)"},{"key":"38_CR19","unstructured":"Zhang, H., Ciss\u00e9, M., Dauphin, Y., Lopez-Paz, D.: Mixup: beyond empirical risk minimization. arXiv abs\/1710.09412 (2018)"},{"key":"38_CR20","doi-asserted-by":"crossref","unstructured":"Cubuk, E.D., Zoph, B., Shlens, J., Le, Q.V.: Randaugment: practical data augmentation with no separate search. arXiv abs\/1909.13719 (2019)","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"38_CR21","unstructured":"Vahdat, A., Kautz, J.: Nvae: a deep hierarchical variational autoencoder. arXiv abs\/2007.03898 (2020)"},{"key":"38_CR22","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational Bayes. CoRR abs\/1312.6114 (2014)"},{"key":"38_CR23","unstructured":"Rezende, D.J., Mohamed, S., Wierstra, D.: Stochastic backpropagation and approximate inference in deep generative models. In: ICML (2014)"},{"key":"38_CR24","unstructured":"Pascanu, R., Mikolov, T., Bengio, Y.: Understanding the exploding gradient problem. arXiv abs\/1211.5063 (2012)"},{"key":"38_CR25","unstructured":"Yu, T., Kumar, S., Gupta, A., Levine, S., Hausman, K., Finn, C.: Gradient surgery for multi-task learning. arXiv abs\/2001.06782 (2020)"},{"key":"38_CR26","unstructured":"Vuckovic, J.: Kalman gradient descent: adaptive variance reduction in stochastic optimization. arXiv abs\/1810.12273 (2018)"},{"key":"38_CR27","unstructured":"Zeiler, M.D.: Adadelta: an adaptive learning rate method. arXiv abs\/1212.5701 (2012)"},{"key":"38_CR28","doi-asserted-by":"publisher","first-page":"1580","DOI":"10.1109\/TNN.2006.880360","volume":"17","author":"Z Man","year":"2006","unstructured":"Man, Z., Wu, H.R., Liu, S.X.F., Yu, X.: A new adaptive backpropagation algorithm based on Lyapunov stability theory for neural networks. IEEE Trans. Neural Netw. 17, 1580\u20131591 (2006)","journal-title":"IEEE Trans. Neural Netw."},{"key":"38_CR29","unstructured":"Kang, Q., Song, Y., Ding, Q., Tay, W.P.: Stable neural ode with Lyapunov-stable equilibrium points for defending against adversarial attacks. arXiv abs\/2110.12976 (2021)"},{"key":"38_CR30","doi-asserted-by":"crossref","unstructured":"Ahmadi, A.A., Parrilo, P.A.: Joint spectral radius of rank one matrices and the maximum cycle mean problem. In: 2012 IEEE 51st IEEE Conference on Decision and Control (CDC), pp. 731\u2013733. IEEE (2012)","DOI":"10.1109\/CDC.2012.6425992"},{"key":"38_CR31","doi-asserted-by":"publisher","first-page":"687","DOI":"10.1137\/110855272","volume":"52","author":"AA Ahmadi","year":"2014","unstructured":"Ahmadi, A.A., Jungers, R.M., Parrilo, P.A., Roozbehani, M.: Joint spectral radius and path-complete graph Lyapunov functions. SIAM J. Control. Optim. 52, 687\u2013717 (2014)","journal-title":"SIAM J. Control. Optim."},{"key":"38_CR32","doi-asserted-by":"publisher","first-page":"510","DOI":"10.1137\/19M1264072","volume":"58","author":"JM Altschuler","year":"2020","unstructured":"Altschuler, J.M., Parrilo, P.A.: Lyapunov exponent of rank-one matrices: ergodic formula and inapproximability of the optimal distribution. SIAM J. Control. Optim. 58, 510\u2013528 (2020)","journal-title":"SIAM J. Control. Optim."},{"key":"38_CR33","doi-asserted-by":"crossref","unstructured":"Daubechies, I., Lagarias, J.C.: Two-scale difference equations ii. Local regularity, infinite products of matrices and fractals. SIAM J. Math. Anal. 23, pp. 1031\u20131079 (1992)","DOI":"10.1137\/0523059"},{"key":"38_CR34","doi-asserted-by":"crossref","unstructured":"Deaecto, G.S., Egidio, L.N.: Practical stability of discrete-time switched affine systems. In: 2016 European Control Conference (ECC), pp. 2048\u20132053 (2016)","DOI":"10.1109\/ECC.2016.7810593"},{"key":"38_CR35","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, pp. 2672\u20132680 (2014)"},{"key":"38_CR36","doi-asserted-by":"crossref","unstructured":"Shahbazi, M., Huang, Z., Paudel, D.P., Chhatkuli, A., Van Gool, L.: Efficient conditional GAN transfer with knowledge propagation across classes. In: 2021 IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2021 (2021)","DOI":"10.1109\/CVPR46437.2021.01199"},{"key":"38_CR37","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Zhou, D., Chen, S., Gao, S., Ma, Y.: Single-image crowd counting via multi-column convolutional neural network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 589\u2013597 (2016)","DOI":"10.1109\/CVPR.2016.70"},{"key":"38_CR38","doi-asserted-by":"crossref","unstructured":"Li, Y., Zhang, X., Chen, D.: CSRnet: dilated convolutional neural networks for understanding the highly congested scenes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1091\u20131100 (2018)","DOI":"10.1109\/CVPR.2018.00120"},{"key":"38_CR39","doi-asserted-by":"crossref","unstructured":"Farina, L., Rinaldi, S.: Positive Linear Systems: Theory and Applications (2000)","DOI":"10.1002\/9781118033029"},{"key":"38_CR40","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86, 2278\u20132324 (1998)","journal-title":"Proc. IEEE"},{"key":"38_CR41","doi-asserted-by":"publisher","first-page":"2141","DOI":"10.1109\/TPAMI.2020.3013269","volume":"43","author":"Q Wang","year":"2020","unstructured":"Wang, Q., Gao, J., Lin, W., Li, X.: NWPU-crowd: a large-scale benchmark for crowd counting and localization. IEEE Trans. Pattern Anal. Mach. Intell. 43, 2141\u20132149 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"38_CR42","unstructured":"Sun, G., Liu, Y., Probst, T., Paudel, D., Popovi\u0107, N., Gool, L.: Boosting crowd counting with transformers. arXiv abs\/2105.10926 (2021)"},{"key":"38_CR43","unstructured":"Krizhevsky, A., Hinton, G., et al.: Learning multiple layers of features from tiny images (2009)"},{"key":"38_CR44","unstructured":"Miyato, T., Kataoka, T., Koyama, M., Yoshida, Y.: Spectral normalization for generative adversarial networks. arXiv preprint arXiv:1802.05957 (2018)"},{"key":"38_CR45","unstructured":"Brock, A., Donahue, J., Simonyan, K.: Large scale GAN training for high fidelity natural image synthesis. arXiv preprint arXiv:1809.11096 (2018)"},{"key":"38_CR46","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: GANs trained by a two time-scale update rule converge to a local Nash equilibrium. In: NIPS (2017)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-26319-4_38","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,8]],"date-time":"2023-12-08T05:48:32Z","timestamp":1702014512000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-26319-4_38"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031263187","9783031263194"],"references-count":46,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-26319-4_38","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"4 March 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Macao","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 December 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 December 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.accv2022.org","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT Microsoft","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"836","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"277","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"33% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2.6","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"For the ACCV 2022 workshops 25 papers have been accepted from 40 submissions","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}