{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:39:37Z","timestamp":1763192377767,"version":"3.45.0"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100007706","name":"Ministero dello Sviluppo Economico","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100007706","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/ijcnn64981.2025.11228785","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:15Z","timestamp":1763145975000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Parallel Optimization of Quantized CNNs for Efficient GPU Inference"],"prefix":"10.1109","author":[{"given":"Marco","family":"Lettiero","sequence":"first","affiliation":[{"name":"University of Naples Parthenope,Dept. of Science and Technology,Naples,Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pasquale","family":"De Luca","sequence":"additional","affiliation":[{"name":"University of Naples Parthenope,Dept. of Science and Technology,Naples,Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"crossref","DOI":"10.21203\/rs.3.rs-510910\/v1","article-title":"Attention mechanisms and deep learning for machine vision: A survey of the state of the art","author":"Hafiz","year":"2021"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01179"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-024-10721-6"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3623402"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3390\/info14110598"},{"key":"ref6","first-page":"50358","article-title":"Scaling data-constrained language models","volume":"36","author":"Muennighoff","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3390\/app14052074"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3442188.3445922"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-024-09799-4"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.5957\/SMC-2022-074"},{"article-title":"Pitfalls of local explainability in complex black-box models","year":"2021","author":"Maratea","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.ascom.2025.100964"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-025-00985-0"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3390\/computers12030060"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-48577-4_9"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3055564"},{"key":"ref17","article-title":"Learning efficient object detection models with knowledge distillation","volume":"30","author":"Chen","year":"2017","journal-title":"Advances in neural information processing systems"},{"article-title":"To prune, or not to prune: exploring the efficacy of pruning for model compression","year":"2017","author":"Zhu","key":"ref18"},{"article-title":"Pruning filters for efficient convnets","year":"2016","author":"Li","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1201\/9781003162810-13"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00286"},{"article-title":"Very deep convolutional networks for large-scale image recognition","year":"2014","author":"Simonyan","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-77977-1_34"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-10450-3_33"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.physa.2023.128472"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-08760-8_4"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.3390\/app14177445"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00748"},{"article-title":"Model compression and efficient inference for large language models: A survey","year":"2024","author":"Wang","key":"ref29"},{"article-title":"Estimating or propagating gradients through stochastic neurons for conditional computation","year":"2013","author":"Bengio","key":"ref30"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.4.541"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.521"},{"key":"ref33","article-title":"Learning multiple layers of features from tiny images","volume-title":"tech. rep.","author":"Krizhevsky","year":"2009"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2025,6,30]]},"location":"Rome, Italy","end":{"date-parts":[[2025,7,5]]}},"container-title":["2025 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11227166\/11227148\/11228785.pdf?arnumber=11228785","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:37:23Z","timestamp":1763192243000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11228785\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11228785","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}