{"id":"https://openalex.org/W7225459354","doi":"https://doi.org/10.5281/zenodo.24040744","title":"Localising jersey numbers without pretraining: how much of the gap to YOLOv8n is pretraining?","display_name":"Localising jersey numbers without pretraining: how much of the gap to YOLOv8n is pretraining?","publication_year":2026,"publication_date":"2026-11-07","ids":{"openalex":"https://openalex.org/W7225459354","doi":"https://doi.org/10.5281/zenodo.24040744"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.24040744","doi":"https://doi.org/10.5281/zenodo.24040744","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24040744","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.24040744","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076561462","display_name":"Muzammal Hussain","orcid":"https://orcid.org/0000-0002-7320-4413","observed_orcids":["https://orcid.org/0000-0002-7320-4413"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Hussain, Muzammal","raw_affiliation_strings":["Independent researcher"],"raw_orcid":"https://orcid.org/0009-0001-2570-5686","affiliations":[{"raw_affiliation_string":"Independent researcher","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5076561462"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9955999851226807,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9955999851226807,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0010999999940395355,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.0007999999797903001,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/object-detection","display_name":"object detection","score":0.5299999713897705},{"id":"https://openalex.org/keywords/pretraining","display_name":"pre-training","score":0.5339999794960022},{"id":"https://openalex.org/keywords/yolov8n","display_name":"YOLOv8n","score":0.8610000014305115},{"id":"https://openalex.org/keywords/centernet","display_name":"CenterNet","score":0.9319999814033508},{"id":"https://openalex.org/keywords/training-from-scratch","display_name":"training from scratch","score":0.5699999928474426},{"id":"https://openalex.org/keywords/data-augmentation","display_name":"data augmentation","score":0.8090000152587891},{"id":"https://openalex.org/keywords/input-size","display_name":"input size","score":0.6050000190734863}],"concepts":[{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.7766000032424927},{"id":"https://openalex.org/C2781235140","wikidata":"https://www.wikidata.org/wiki/Q275131","display_name":"Scratch","level":2,"score":0.7325000166893005},{"id":"https://openalex.org/C2778671685","wikidata":"https://www.wikidata.org/wiki/Q219239","display_name":"Recipe","level":2,"score":0.5867999792098999},{"id":"https://openalex.org/C21780288","wikidata":"https://www.wikidata.org/wiki/Q5139731","display_name":"Coco","level":2,"score":0.5478000044822693},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.501800000667572},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4602999985218048},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.45820000767707825},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.4474000036716461},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.4375999867916107},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4307999908924103},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32749998569488525},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32739999890327454},{"id":"https://openalex.org/C2777027219","wikidata":"https://www.wikidata.org/wiki/Q1284190","display_name":"Constant (computer programming)","level":2,"score":0.3167000114917755},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.31189998984336853},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2754000127315521},{"id":"https://openalex.org/C85079727","wikidata":"https://www.wikidata.org/wiki/Q3560114","display_name":"Quarter (Canadian coin)","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.24040744","doi":"https://doi.org/10.5281/zenodo.24040744","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24040744","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.5281/zenodo.24040745","doi":"https://doi.org/10.5281/zenodo.24040745","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24040745","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.5281/zenodo.24040744","doi":"https://doi.org/10.5281/zenodo.24040744","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24040744","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4409427204","https://openalex.org/W7165767392","https://openalex.org/W7104008000","https://openalex.org/W7171959607","https://openalex.org/W3168971211","https://openalex.org/W7202367345","https://openalex.org/W2796347433","https://openalex.org/W7139111207","https://openalex.org/W4416213557","https://openalex.org/W4388681595"],"abstract_inverted_index":{"We":[0,49,61],"study":[1],"how":[2,20],"far":[3],"a":[4,26,39,54,170,174,189,237,247,252,263],"detector":[5,57,135,249],"trained":[6,58,66],"from":[7,59,67,70,104,108,153],"random":[8],"initialisation":[9],"can":[10],"go":[11],"in":[12,16],"localising":[13],"jersey":[14],"numbers":[15],"ice-hockey":[17],"images,":[18,221],"and":[19,69,91,106,117,133,137,173,216,255,270],"much":[21],"of":[22,97,166,218],"its":[23,232],"gap":[24,187,245],"to":[25,31,156,180,188,246],"COCO-pretrained":[27],"YOLOv8n":[28,65,101,152,191],"is":[29,80,123,250],"due":[30],"pretraining.":[32],"Our":[33],"earlier":[34],"single-box":[35],"regressor":[36],"barely":[37],"beat":[38],"constant":[40],"mean":[41,44],"box":[42],"(test":[43],"IoU":[45],"0.044":[46],"against":[47,236],"0.016).":[48],"replace":[50],"it":[51,63],"with":[52,64,82,88,148],"JerseyNet,":[53],"4.7M-parameter":[55],"CenterNet-style":[56],"scratch.":[60],"compare":[62],"scratch":[68,105,154],"COCO":[71,109,222],"weights":[72,110],"on":[73,210],"the":[74,112,128,134,167,186,193,207,211,219,244],"same":[75,113,194,208],"public":[76],"split.":[77],"Every":[78],"model":[79],"scored":[81],"COCO-style":[83],"AP":[84,209],"over":[85],"all":[86,257],"boxes,":[87],"bootstrap":[89],"intervals":[90],"three":[92],"seeds.":[93],"JerseyNet":[94,179,229],"reaches":[95,102],"AP50:95":[96],"0.241":[98],"\u00b1":[99,158,182,198],"0.006.":[100],"0.352":[103],"0.384":[107],"at":[111,119,192,234],"256":[114],"px":[115,176],"input,":[116],"0.419":[118],"640":[120],"px.":[121],"Pretraining":[122],"worth":[124],"about":[125,164],"0.03":[126],"AP,":[127],"input":[129,177,195,202],"size":[130,196],"another":[131],"0.035,":[132],"design":[136],"training":[138,220],"recipe":[139,253],"0.111.":[140],"Four":[141],"further":[142],"experiments":[143],"locate":[144],"that":[145,201],"gap:":[146],"Trained":[147],"JerseyNet's":[149],"light":[150],"augmentation,":[151],"falls":[155],"0.280":[157],"0.012,":[159],"so":[160],"augmentation":[161,259],"accounts":[162],"for":[163,239],"two-thirds":[165],"gap.":[168,265],"Mosaic,":[169],"GIoU":[171],"loss":[172],"384":[175],"raise":[178],"0.308":[181],"0.005.":[183],"This":[184],"halves":[185],"from-scratch":[190],"(0.366":[197],"0.005).":[199],"At":[200],"size,":[203],"both":[204],"detectors":[205],"have":[206],"smallest":[212],"numbers.":[213],"With":[214],"10%":[215],"25%":[217],"pretraining":[223,264],"still":[224],"adds":[225],"only":[226],"0.04":[227],"AP.":[228],"loses":[230],"half":[231],"accuracy":[233],"10%,":[235],"quarter":[238],"YOLOv8n.":[240],"On":[241],"this":[242],"task":[243],"modern":[248],"mainly":[251],"gap,":[254,260],"above":[256],"an":[258],"rather":[261],"than":[262],"Code,":[266],"configurations,":[267],"Kaggle":[268],"notebooks":[269],"archived":[271],"results:":[272],"https://github.com/MHKhan50/jersey-number-detection":[273],"(version":[274],"2.1.0).":[275]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-11-08T00:00:00"}