{"id":"https://openalex.org/W4415708135","doi":"https://doi.org/10.1109/icme59968.2025.11208998","title":"OSA: Object-level Scale Alignment for Small Object Detection in Large-Scale Images","display_name":"OSA: Object-level Scale Alignment for Small Object Detection in Large-Scale Images","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708135","doi":"https://doi.org/10.1109/icme59968.2025.11208998"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11208998","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11208998","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100394394","display_name":"Yuxiang Wang","orcid":"https://orcid.org/0000-0002-6945-6431"},"institutions":[{"id":"https://openalex.org/I108468826","display_name":"Stevens Institute of Technology","ror":"https://ror.org/02z43xh36","country_code":"US","type":"education","lineage":["https://openalex.org/I108468826"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuxiang Wang","raw_affiliation_strings":["Stevens Institute of Technology,School of Business"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stevens Institute of Technology,School of Business","institution_ids":["https://openalex.org/I108468826"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057258581","display_name":"Y. Y. Ji","orcid":null},"institutions":[{"id":"https://openalex.org/I21945476","display_name":"Shanghai Normal University","ror":"https://ror.org/01cxqmw89","country_code":"CN","type":"education","lineage":["https://openalex.org/I21945476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yixuan Ji","raw_affiliation_strings":["Shanghai Normal University,College of IMEE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Normal University,College of IMEE","institution_ids":["https://openalex.org/I21945476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061912579","display_name":"X. R. Chen","orcid":"https://orcid.org/0009-0003-9544-7672"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiangqin Chen","raw_affiliation_strings":["The Pennsylvania State University,College of ECSM"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University,College of ECSM","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chuanyuan Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I88694374","display_name":"Marshall University","ror":"https://ror.org/02erqft81","country_code":"US","type":"education","lineage":["https://openalex.org/I88694374"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chuanyuan Tan","raw_affiliation_strings":["Marshall University,College of ITED"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Marshall University,College of ITED","institution_ids":["https://openalex.org/I88694374"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039644978","display_name":"Li Yajin","orcid":"https://orcid.org/0000-0003-3815-3021"},"institutions":[{"id":"https://openalex.org/I172824197","display_name":"San Francisco Art Institute","ror":"https://ror.org/036qcm975","country_code":"US","type":"education","lineage":["https://openalex.org/I172824197"]},{"id":"https://openalex.org/I239307583","display_name":"Academy of Art University","ror":"https://ror.org/04jr0a134","country_code":"US","type":"education","lineage":["https://openalex.org/I239307583"]},{"id":"https://openalex.org/I76766440","display_name":"University of San Francisco","ror":"https://ror.org/029m7xn54","country_code":"US","type":"education","lineage":["https://openalex.org/I76766440"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yajin Li","raw_affiliation_strings":["City University of San Francisco,School of Art"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"City University of San Francisco,School of Art","institution_ids":["https://openalex.org/I172824197","https://openalex.org/I76766440","https://openalex.org/I239307583"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112761493","display_name":"Haozhong Xue","orcid":"https://orcid.org/0009-0006-0361-3904"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haozhong Xue","raw_affiliation_strings":["New York University,Tandon School of Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University,Tandon School of Engineering","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112126645","display_name":"Zheng Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I28813325","display_name":"Civil Aviation University of China","ror":"https://ror.org/03je71k37","country_code":"CN","type":"education","lineage":["https://openalex.org/I28813325"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng Zhao","raw_affiliation_strings":["University of China,College of EIEA Civil Aviation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of China,College of EIEA Civil Aviation","institution_ids":["https://openalex.org/I28813325"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.916700005531311,"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":0.916700005531311,"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/T11448","display_name":"Face recognition and analysis","score":0.013299999758601189,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.00800000037997961,"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":0.6912999749183655},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.6862000226974487},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.6341000199317932},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5884000062942505},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5598000288009644},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5099999904632568},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.49970000982284546}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7918999791145325},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6912999749183655},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.6862000226974487},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6840000152587891},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6723999977111816},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.6341000199317932},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5884000062942505},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5598000288009644},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5099999904632568},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.49970000982284546},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.48590001463890076},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.48420000076293945},{"id":"https://openalex.org/C11727466","wikidata":"https://www.wikidata.org/wiki/Q1628157","display_name":"Inpainting","level":3,"score":0.4650999903678894},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.4377000033855438},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4108000099658966},{"id":"https://openalex.org/C99102927","wikidata":"https://www.wikidata.org/wiki/Q3058184","display_name":"Scale space","level":4,"score":0.34150001406669617}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11208998","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11208998","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1965555277","https://openalex.org/W2031489346","https://openalex.org/W2077604257","https://openalex.org/W2107775979","https://openalex.org/W2108598243","https://openalex.org/W2114701396","https://openalex.org/W2146950091","https://openalex.org/W2165736859","https://openalex.org/W2565639579","https://openalex.org/W2886362581","https://openalex.org/W2962721361","https://openalex.org/W2963351448","https://openalex.org/W2964241181","https://openalex.org/W2982103617","https://openalex.org/W2982770724","https://openalex.org/W3009396058","https://openalex.org/W3159937784","https://openalex.org/W4288083516","https://openalex.org/W4311360133","https://openalex.org/W4367323473","https://openalex.org/W4367834670","https://openalex.org/W4379928223","https://openalex.org/W4386075956","https://openalex.org/W4387189847","https://openalex.org/W4388688962","https://openalex.org/W4392903273","https://openalex.org/W4396910024","https://openalex.org/W4401386895"],"related_works":[],"abstract_inverted_index":{"Detecting":[0],"small":[1,76],"objects":[2],"(e.g.,":[3],"those":[4],"smaller":[5],"than":[6],"20":[7,9],"\u00d7":[8],"pixels)":[10],"in":[11],"large-scale":[12],"images":[13],"remains":[14],"a":[15,81,125,155],"significant":[16],"and":[17,33,53,56,107,150],"challenging":[18],"problem.":[19],"Modern":[20],"CNN-based":[21],"detectors":[22,139,153],"often":[23],"struggle":[24],"due":[25],"to":[26,65,98],"the":[27,34,46,73,85,95,99,103,112,147],"scale":[28,49,61,92,121],"mismatch":[29],"between":[30,51,105],"pre-training":[31,52,106],"datasets":[32],"target":[35,54,108],"dataset":[36,149],"used":[37],"for":[38,132],"detector":[39],"fine-tuning.":[40],"In":[41],"this":[42],"paper,":[43],"we":[44,79,123],"investigate":[45],"impact":[47],"of":[48,75,84,115],"alignment":[50,93],"datasets,":[55,70],"introduce":[57,124],"an":[58],"effective":[59],"Object":[60],"alignmenting":[62],"(OSA)":[63],"approach":[64],"align":[66],"object":[67],"scales":[68],"across":[69,137],"thereby":[71],"enhancing":[72],"representation":[74],"objects.":[77],"Furthermore,":[78],"propose":[80],"refined":[82],"version":[83],"OSA":[86],"method,":[87],"termed":[88],"OSA-RF,":[89],"which":[90],"improves":[91,144],"from":[94],"image":[96,116],"level":[97],"instance":[100],"level,":[101],"strengthening":[102],"similarity":[104],"datasets.":[109],"To":[110],"address":[111],"potential":[113],"distortion":[114],"structure":[117],"caused":[118],"by":[119,154],"traditional":[120],"alignmenting,":[122],"novel":[126],"Probabilistic":[127],"Structure":[128],"Inpainting":[129],"(PSI)":[130],"method":[131],"background":[133],"processing.":[134],"Extensive":[135],"experiments":[136],"multiple":[138],"demonstrate":[140],"that":[141],"OSA-RF":[142],"significantly":[143],"performance":[145],"on":[146],"TinyPerson":[148],"outperforms":[151],"state-of-the-art":[152],"considerable":[156],"margin.":[157]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":10}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-30T00:00:00"}