{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T16:26:52Z","timestamp":1785428812053,"version":"3.56.0"},"reference-count":38,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3447888","type":"journal-article","created":{"date-parts":[[2024,8,22]],"date-time":"2024-08-22T18:47:25Z","timestamp":1724352445000},"page":"130603-130616","source":"Crossref","is-referenced-by-count":3,"title":["Fast&Focused-Net: Enhancing Small Object Encoding With VDP Layer in Deep Neural Networks"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8810-3025","authenticated-orcid":false,"given":"Tofik","family":"Ali","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, Indian Institute of Technology Roorkee, Roorkee, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5735-5254","authenticated-orcid":false,"given":"Partha","family":"Pratim Roy","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Indian Institute of Technology Roorkee, Roorkee, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8532-0895","authenticated-orcid":false,"given":"Rajkumar","family":"Saini","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Electrical, and Space Engineering, LuleåUniversity of Technology, Luleå, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"4898","article-title":"Understanding the effective receptive field in deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Luo"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-018-5704-3"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2019.8902732"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP46576.2022.9897165"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref6","first-page":"1","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Int. Conf. Learn. Represent. (ICLR)","author":"Dosovitskiy"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref8","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017","journal-title":"arXiv:1704.04861"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref11","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Vaswani"},{"key":"ref12","first-page":"9310","article-title":"SNIPER: Efficient multi-scale training","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Singh"},{"key":"ref13","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding","author":"Han","year":"2015","journal-title":"arXiv:1510.00149"},{"key":"ref14","first-page":"1","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Dosovitskiy"},{"key":"ref15","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref18","first-page":"4839","article-title":"Training neural networks with local error signals","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"N\u00f8kland"},{"key":"ref19","article-title":"Synthetic data and artificial neural networks for natural scene text recognition","author":"Jaderberg","year":"2014","journal-title":"CoRR"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.254"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/tai.2022.3185179"},{"key":"ref22","article-title":"WaveMix: A resource-efficient neural network for image analysis","author":"Jeevan","year":"2022","journal-title":"arXiv:2205. 14375"},{"key":"ref23","article-title":"Reduction of class activation uncertainty with background information","author":"M Dipu Kabir","year":"2023","journal-title":"arXiv:2305.03238"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00012"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00472"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01385"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00088"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref29","article-title":"Hiera: A hierarchical vision transformer without the bells-and-whistles","author":"Ryali","year":"2023","journal-title":"arXiv:2306.00989"},{"key":"ref30","article-title":"Symbolic discovery of optimization algorithms","author":"Chen","year":"2023","journal-title":"arXiv:2302.06675"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2848939"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6891"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01393"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00702"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86549-8_21"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_11"},{"key":"ref37","article-title":"CLIP4STR: A simple baseline for scene text recognition with pre-trained vision-language model","author":"Zhao","year":"2023","journal-title":"arXiv:2305.14014"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i11.26538"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10380310\/10643511.pdf?arnumber=10643511","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,25]],"date-time":"2024-09-25T05:41:44Z","timestamp":1727242904000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10643511\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3447888","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}