{"id":"https://openalex.org/W4408352125","doi":"https://doi.org/10.1109/icassp49660.2025.10888564","title":"Dual-Domain Feature-Guided Task Alignment for Enhanced Small Object Detection","display_name":"Dual-Domain Feature-Guided Task Alignment for Enhanced Small Object Detection","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352125","doi":"https://doi.org/10.1109/icassp49660.2025.10888564"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888564","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888564","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","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/A5052409500","display_name":"Fangrui Guo","orcid":"https://orcid.org/0009-0008-0165-2701"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fangrui Guo","raw_affiliation_strings":["University of California Los Angeles,Dept. Master of Engineering,Los Angles,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California Los Angeles,Dept. Master of Engineering,Los Angles,USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005014456","display_name":"Junwei Wu","orcid":"https://orcid.org/0000-0002-7346-5082"},"institutions":[{"id":"https://openalex.org/I146655781","display_name":"University of Liverpool","ror":"https://ror.org/04xs57h96","country_code":"GB","type":"education","lineage":["https://openalex.org/I146655781"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Junwei Wu","raw_affiliation_strings":["University of Liverpool,Dept. Computer Science,Liverpool,the UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Liverpool,Dept. Computer Science,Liverpool,the UK","institution_ids":["https://openalex.org/I146655781"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083044658","display_name":"Quan Zhang","orcid":"https://orcid.org/0000-0003-2237-3281"},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Quan Zhang","raw_affiliation_strings":["Xi&#x2019;an Jiaotong-Liverpool University,Dept. School of Advanced Technology,Suzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi&#x2019;an Jiaotong-Liverpool University,Dept. School of Advanced Technology,Suzhou,China","institution_ids":["https://openalex.org/I69356397"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8699,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.84141417,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9836000204086304,"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":0.9836000204086304,"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/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.9417999982833862,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7745035886764526},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.6558312773704529},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.602223813533783},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5801504254341125},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.540759265422821},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.48876214027404785},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4427160322666168},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43757447600364685},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3988058269023895},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32041895389556885},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07323822379112244}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7745035886764526},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.6558312773704529},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.602223813533783},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5801504254341125},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.540759265422821},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.48876214027404785},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4427160322666168},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43757447600364685},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3988058269023895},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32041895389556885},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07323822379112244},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888564","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888564","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":26,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W2963037989","https://openalex.org/W2964241181","https://openalex.org/W2964479623","https://openalex.org/W2982770724","https://openalex.org/W3080081801","https://openalex.org/W3159481202","https://openalex.org/W3205100603","https://openalex.org/W4214507171","https://openalex.org/W4289861074","https://openalex.org/W4318953537","https://openalex.org/W4327652243","https://openalex.org/W4378222290","https://openalex.org/W4378575119","https://openalex.org/W4382568144","https://openalex.org/W4389352554","https://openalex.org/W4392904527","https://openalex.org/W4392904678","https://openalex.org/W4392904697","https://openalex.org/W4394984976","https://openalex.org/W4399682598","https://openalex.org/W4400966748","https://openalex.org/W4401415788","https://openalex.org/W4401630652","https://openalex.org/W4403268181","https://openalex.org/W6873697166"],"related_works":["https://openalex.org/W2317351040","https://openalex.org/W2952466936","https://openalex.org/W3147584709","https://openalex.org/W2737719445","https://openalex.org/W1988622314","https://openalex.org/W2393949104","https://openalex.org/W4236344264","https://openalex.org/W3046201198","https://openalex.org/W4292830139","https://openalex.org/W4319309705"],"abstract_inverted_index":{"Small":[0,47],"object":[1,94],"detection":[2],"is":[3],"a":[4,88,106],"critical":[5],"challenge":[6],"in":[7,31,59,83,130],"Unmanned":[8],"Aerial":[9],"Vehicles":[10],"(UAVs)":[11],"due":[12],"to":[13,67],"the":[14,22,32,46,60,64,84,119,131,139,151],"limited":[15],"pixel":[16],"representation":[17],"of":[18,24,34,133],"small":[19,35,70,93,134],"objects":[20,36,71],"and":[21,114,161],"impact":[23],"successive":[25],"pooling":[26],"operations,":[27],"which":[28,53],"frequently":[29],"results":[30,137],"disappearance":[33],"within":[37],"intricate":[38],"backgrounds.":[39],"To":[40],"tackle":[41],"this":[42],"issue,":[43],"we":[44,104],"propose":[45],"Object":[48],"Enhancement":[49],"Pyramid":[50],"(SOEP)":[51],"module,":[52],"first":[54],"transforms":[55],"feature":[56,78],"representations":[57,79,95],"(i.e.,":[58],"spatial":[61,85],"domain)":[62],"into":[63],"frequency":[65],"domain":[66,86],"better":[68],"capture":[69],"typically":[72],"characterized":[73],"by":[74,96,154],"high-frequency":[75],"components.":[76],"These":[77],"are":[80,126],"then":[81],"fused":[82],"using":[87],"frequency-based":[89],"attention":[90],"map,":[91],"enhancing":[92],"integrating":[97],"information":[98],"from":[99],"both":[100],"complementary":[101],"domains.":[102],"Furthermore,":[103],"introduce":[105],"Task":[107],"Aligned":[108],"Head":[109],"(TAH)":[110],"that":[111,121,143],"integrates":[112],"classification":[113],"localization":[115],"tasks":[116,125],"interactively,":[117],"reducing":[118],"misalignment":[120],"occurs":[122],"when":[123],"these":[124],"learned":[127],"independently,":[128],"particularly":[129],"context":[132],"objects.":[135],"Experimental":[136],"on":[138,157],"Visdrone":[140],"dataset":[141],"verify":[142],"our":[144],"proposed":[145],"method":[146,153],"(D<sup":[147],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[148,159,163],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</sup>FTA)":[149],"outperforms":[150],"baseline":[152],"12.7%,":[155],"14.19%":[156],"mAP<inf":[158,162],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">0.5</inf>":[160],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">0.5:0.95</inf>.":[164]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}