{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,24]],"date-time":"2026-01-24T18:37:41Z","timestamp":1769279861626,"version":"3.49.0"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2024,12,27]],"date-time":"2024-12-27T00:00:00Z","timestamp":1735257600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,27]],"date-time":"2024-12-27T00:00:00Z","timestamp":1735257600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100008982","name":"Qatar National Research Fund","doi-asserted-by":"publisher","award":["PDRA7-0606-21012"],"award-info":[{"award-number":["PDRA7-0606-21012"]}],"id":[{"id":"10.13039\/100008982","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput &amp; Applic"],"published-print":{"date-parts":[[2025,2]]},"DOI":"10.1007\/s00521-024-10637-w","type":"journal-article","created":{"date-parts":[[2024,12,27]],"date-time":"2024-12-27T10:50:11Z","timestamp":1735296611000},"page":"4869-4879","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Accelerating deep learning with fixed time budget"],"prefix":"10.1007","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2925-8841","authenticated-orcid":false,"given":"Muhammad Asif","family":"Khan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ridha","family":"Hamila","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hamid","family":"Menouar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,27]]},"reference":[{"issue":"1","key":"10637_CR1","doi-asserted-by":"publisher","first-page":"1512","DOI":"10.1109\/JSYST.2022.3198711","volume":"17","author":"MA Khan","year":"2023","unstructured":"Khan MA, Hamila R, Erbad A, Gabbouj M (2023) Distributed inference in resource-constrained IoT for real-time video surveillance. IEEE Syst J 17(1):1512\u20131523. https:\/\/doi.org\/10.1109\/JSYST.2022.3198711","journal-title":"IEEE Syst J"},{"key":"10637_CR2","doi-asserted-by":"crossref","unstructured":"Sandler M, Howard AG, Zhu M, Zhmoginov A, Chen LC (2018) Mobilenetv2: Inverted residuals and linear bottlenecks. In: 2018 IEEE\/CVF Conf Computer Vision Pattern Recognition pp. 4510\u20134520","DOI":"10.1109\/CVPR.2018.00474"},{"key":"10637_CR3","unstructured":"Iandola FN, Moskewicz MW, Ashraf K, Han S, Dally WJ, Keutzer K (2016) Squeezenet: Alexnet-level accuracy with 50x fewer parameters and<1mb model size. ArXiv arXiv:abs\/1602.07360"},{"key":"10637_CR4","doi-asserted-by":"publisher","unstructured":"Khan MA, Menouar H, Hamila R (2023) Dronenet: Crowd density estimation using self-onns for drones. In: 2023 IEEE 20th Consumer Commun Network Conf(CCNC), pp. 455\u2013460. https:\/\/doi.org\/10.1109\/CCNC51644.2023.10059904","DOI":"10.1109\/CCNC51644.2023.10059904"},{"key":"10637_CR5","doi-asserted-by":"publisher","DOI":"10.1007\/s11554-023-01286-8","author":"MA Khan","year":"2023","unstructured":"Khan MA, Menouar H, Hamila R (2023) Lcdnet: a lightweight crowd density estimation model for real-time video surveillance. J Real-Time Image Process. https:\/\/doi.org\/10.1007\/s11554-023-01286-8","journal-title":"J Real-Time Image Process"},{"key":"10637_CR6","doi-asserted-by":"crossref","unstructured":"Gao C, Wang P, Gao Y (2019) Mobilecount: An efficient encoder-decoder framework for real-time crowd counting. In: Pattern Recognition Computer Vision - Second Chinese Conf, PRCV 2019, Xi\u2019an, China, November 8-11, 2019, Proceedings, Part II, Lecture Notes in Computer Science, 11858: 582\u2013595. Springer","DOI":"10.1007\/978-3-030-31723-2_50"},{"key":"10637_CR7","doi-asserted-by":"crossref","unstructured":"Khan MA, Hamila R, Menouar H (2023) Clip: Train faster with less data. In: 2023 IEEE Int Conf Big Data Smart Computing (BigComp), pp. 34\u201339. IEEE","DOI":"10.1109\/BigComp57234.2023.00014"},{"key":"10637_CR8","doi-asserted-by":"publisher","first-page":"111291","DOI":"10.1016\/j.asoc.2024.111291","volume":"153","author":"Z Zhou","year":"2024","unstructured":"Zhou Z, Hu Y, Yang X, Yang J (2024) Yolo-based marine organism detection using two-terminal attention mechanism and difficult-sample resampling. Appl Soft Comput 153:111291. https:\/\/doi.org\/10.1016\/j.asoc.2024.111291","journal-title":"Appl Soft Comput"},{"issue":"5","key":"10637_CR9","doi-asserted-by":"publisher","first-page":"1256","DOI":"10.1093\/icesjms\/fsad041","volume":"80","author":"Z Zhou","year":"2023","unstructured":"Zhou Z, Yang X, Ji H, Zhu Z (2023) Improving the classification accuracy of fishes and invertebrates using residual convolutional neural networks. ICES J Mar Sci 80(5):1256\u20131266. https:\/\/doi.org\/10.1093\/icesjms\/fsad041","journal-title":"ICES J Mar Sci"},{"key":"10637_CR10","doi-asserted-by":"publisher","unstructured":"Bengio Y, Louradour J, Collobert R, Weston J (2009) Curriculum learning. In: Proceedings of the 26th Annual Int Conf Mach Learn, ICML \u201909, p. 41-48. Association for Computing Machinery, New York, NY, USA. https:\/\/doi.org\/10.1145\/1553374.1553380","DOI":"10.1145\/1553374.1553380"},{"key":"10637_CR11","doi-asserted-by":"crossref","unstructured":"Khan MA, Menouar H, Hamila R (2024) Curriculum for crowd counting\u2013is it worthy? arXiv preprint arXiv:2401.07586","DOI":"10.5220\/0012414700003660"},{"key":"10637_CR12","unstructured":"Li M, Yumer E, Ramanan D (2019) Budgeted training: rethinking deep neural network training under resource constraints. In: Int Conf Learn Represent"},{"key":"10637_CR13","doi-asserted-by":"publisher","first-page":"109672","DOI":"10.1016\/j.patcog.2023.109672","volume":"142","author":"S Freitas","year":"2023","unstructured":"Freitas S, Laber E, Lazera P, Molinaro M (2023) Time-constrained learning. Pattern Recogn 142:109672","journal-title":"Pattern Recogn"},{"key":"10637_CR14","unstructured":"Yang S, Xie Z, Peng H, Xu M, Sun M, Li P (2022) Dataset pruning: reducing training data by examining generalization influence. ArXiv arXiv:abs\/2205.09329"},{"key":"10637_CR15","unstructured":"Paul M, Ganguli S, Dziugaite GK (2021) Deep learning on a data diet: finding important examples early in training. In: NeurIPS"},{"key":"10637_CR16","unstructured":"Katharopoulos A, Fleuret F (2018) Not all samples are created equal: deep learning with importance sampling. In: Int Conf Mach Learn. URL https:\/\/api.semanticscholar.org\/CorpusID:3663876"},{"key":"10637_CR17","unstructured":"Hacohen G, Weinshall D (2019) On the power of curriculum learning in training deep networks. ArXiv arXiv:abs\/1904.03626"},{"key":"10637_CR18","doi-asserted-by":"crossref","unstructured":"Guo S, Huang W, Zhang H, Zhuang C, Dong D, Scott MR, Huang D (2018) Curriculumnet: Weakly supervised learning from large-scale web images. ArXiv arXiv:abs\/1808.01097","DOI":"10.1007\/978-3-030-01249-6_9"},{"key":"10637_CR19","doi-asserted-by":"crossref","unstructured":"Li W, Cao Z, Wang Q, Chen S, Feng R (2021) Learning error-driven curriculum for crowd counting. In: 2020 25th Int Conf Pattern Recognition (ICPR) pp. 843\u2013849","DOI":"10.1109\/ICPR48806.2021.9413068"},{"key":"10637_CR20","unstructured":"Zayed A, Parthasarathi P, Mordido G, Palangi H, Shabanian S, Chandar S (2022) Deep learning on a healthy data diet: finding important examples for fairness. ArXiv arXiv:abs\/2211.11109"},{"key":"10637_CR21","unstructured":"Covert IC, Lundberg S, Lee SI (2020) Understanding global feature contributions with additive importance measures. NIPS\u201920. Curran Associates Inc., Red Hook, NY, USA"},{"key":"10637_CR22","doi-asserted-by":"crossref","unstructured":"Casalicchio G, Molnar C, Bischl B (2018) Visualizing the feature importance for black box models. In: ECML\/PKDD","DOI":"10.1007\/978-3-030-10925-7_40"},{"key":"10637_CR23","doi-asserted-by":"publisher","first-page":"1189","DOI":"10.1214\/aos\/1013203451","volume":"29","author":"JH Friedman","year":"2001","unstructured":"Friedman JH (2001) Greedy function approximation: a gradient boosting machine. Ann Stat 29:1189\u20131232","journal-title":"Ann Stat"},{"key":"10637_CR24","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1080\/10618600.2014.907095","volume":"24","author":"A Goldstein","year":"2013","unstructured":"Goldstein A, Kapelner A, Bleich J, Pitkin E (2013) Peeking inside the black box: visualizing statistical learning with plots of individual conditional expectation. J Comput Graph Stat 24:44\u201365","journal-title":"J Comput Graph Stat"},{"key":"10637_CR25","unstructured":"Lundberg SM, Erion GG, Lee SI (2018) Consistent individualized feature attribution for tree ensembles. ArXiv arXiv:abs\/1802.03888"},{"key":"10637_CR26","doi-asserted-by":"publisher","unstructured":"Poulinakis K, Drikakis D, Kokkinakis IW, Spottswood SM (2023) Machine-learning methods on noisy and sparse data. Mathematics https:\/\/doi.org\/10.3390\/math11010236. URL https:\/\/www.mdpi.com\/2227-7390\/11\/1\/236","DOI":"10.3390\/math11010236"},{"issue":"3","key":"10637_CR27","doi-asserted-by":"publisher","first-page":"035155","DOI":"10.1063\/5.0200167","volume":"36","author":"F Sofos","year":"2024","unstructured":"Sofos F, Drikakis D, Kokkinakis IW (2024) Deep learning architecture for sparse and noisy turbulent flow data. Phys Fluids 36(3):035155. https:\/\/doi.org\/10.1063\/5.0200167","journal-title":"Phys Fluids"},{"key":"10637_CR28","doi-asserted-by":"crossref","unstructured":"Khan MA, Menouar H, Hamila R (2022) Revisiting crowd counting: State-of-the-art, trends, and future perspectives. ArXiv arXiv:abs\/2209.07271","DOI":"10.1016\/j.imavis.2022.104597"},{"key":"10637_CR29","unstructured":"Gao G, Gao J, Liu Q, Wang Q, Wang Y (2020) Cnn-based density estimation and crowd counting: a survey. ArXiv arXiv:abs\/2003.12783"},{"key":"10637_CR30","doi-asserted-by":"publisher","first-page":"224","DOI":"10.1016\/j.neucom.2021.02.103","volume":"472","author":"Z Fan","year":"2021","unstructured":"Fan Z, Zhang H, Zhang Z, Lu G, Zhang Y, Wang Y (2021) A survey of crowd counting and density estimation based on convolutional neural network. Neurocomputing 472:224\u2013251","journal-title":"Neurocomputing"},{"key":"10637_CR31","doi-asserted-by":"publisher","first-page":"13637","DOI":"10.1007\/s11042-022-13957-y","volume":"82","author":"G Yang","year":"2022","unstructured":"Yang G, Zhu D (2022) Survey on algorithms of people counting in dense crowd and crowd density estimation. Multimed Tools Appl 82:13637\u201313648","journal-title":"Multimed Tools Appl"},{"key":"10637_CR32","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.neucom.2022.08.037","volume":"508","author":"H Bai","year":"2020","unstructured":"Bai H, Mao J, Chan SHG (2020) A survey on deep learning-based single image crowd counting: network design, loss function and supervisory signal. Neurocomputing 508:1\u201318","journal-title":"Neurocomputing"},{"key":"10637_CR33","doi-asserted-by":"publisher","unstructured":"Zhang Y, Zhou D, Chen S, Gao S, Ma Y (2016) Single-image crowd counting via multi-column convolutional neural network. In: 2016 IEEE Conf Computer Vision Pattern Recognition (CVPR), pp. 589\u2013597. https:\/\/doi.org\/10.1109\/CVPR.2016.70","DOI":"10.1109\/CVPR.2016.70"},{"key":"10637_CR34","doi-asserted-by":"crossref","unstructured":"Hsieh MR, Lin YL, Hsu WH (2017) Drone-based object counting by spatially regularized regional proposal network. In: 2017 IEEE Int Conf Computer Vision (ICCV) pp. 4165\u20134173","DOI":"10.1109\/ICCV.2017.446"},{"key":"10637_CR35","doi-asserted-by":"publisher","unstructured":"Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions. In: 2015 IEEE Conf Computer Vision Pattern Recognition (CVPR), pp. 1\u20139. https:\/\/doi.org\/10.1109\/CVPR.2015.7298594","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"10637_CR36","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: 2016 IEEE Conf Computer Vision Pattern Recognition (CVPR), pp. 770\u2013778. IEEE Computer Society, Los Alamitos, CA, USA","DOI":"10.1109\/CVPR.2016.90"},{"key":"10637_CR37","doi-asserted-by":"crossref","unstructured":"Sindagi VA, Patel VM (2017) Cnn-based cascaded multi-task learning of high-level prior and density estimation for crowd counting. In: 2017 14th IEEE Int Conf Adv Video Signal Based Surveillance (AVSS) pp. 1\u20136","DOI":"10.1109\/AVSS.2017.8078491"},{"key":"10637_CR38","doi-asserted-by":"crossref","unstructured":"Li Y, Zhang X, Chen D (2018) Csrnet: Dilated convolutional neural networks for understanding the highly congested scenes. In: 2018 IEEE\/CVF Conf Comput Vision Pattern Recognition pp. 1091\u20131100","DOI":"10.1109\/CVPR.2018.00120"},{"key":"10637_CR39","doi-asserted-by":"crossref","unstructured":"Jiang X, Xiao Z, Zhang B, Zhen X, Cao X, Doermann DS, Shao L (2019) Crowd counting and density estimation by trellis encoder-decoder networks. In: 2019 IEEE\/CVF Conf Computer Vision Pattern Recognition (CVPR) pp. 6126\u20136135","DOI":"10.1109\/CVPR.2019.00629"},{"key":"10637_CR40","doi-asserted-by":"crossref","unstructured":"Jiang X, Zhang L, Xu M, Zhang T, Lv P, Zhou B, Yang X, Pang Y (2020) Attention scaling for crowd counting. In: 2020 IEEE\/CVF Conf Computer Vision Pattern Recognition (CVPR) pp. 4705\u20134714","DOI":"10.1109\/CVPR42600.2020.00476"},{"key":"10637_CR41","doi-asserted-by":"crossref","unstructured":"Song Q, Wang C, Wang Y, Tai Y, Wang C, Li J, Wu J, Ma J (2021) To choose or to fuse? scale selection for crowd counting. In: AAAI","DOI":"10.1609\/aaai.v35i3.16360"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-024-10637-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-024-10637-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-024-10637-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,8]],"date-time":"2025-02-08T19:34:18Z","timestamp":1739043258000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-024-10637-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,27]]},"references-count":41,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,2]]}},"alternative-id":["10637"],"URL":"https:\/\/doi.org\/10.1007\/s00521-024-10637-w","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,27]]},"assertion":[{"value":"20 April 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 October 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 December 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}