{"id":"https://openalex.org/W4413472016","doi":"https://doi.org/10.1109/tmm.2025.3599074","title":"Cross-DINO: Cross the Deep MLP and Transformer for Small Object Detection","display_name":"Cross-DINO: Cross the Deep MLP and Transformer for Small Object Detection","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4413472016","doi":"https://doi.org/10.1109/tmm.2025.3599074"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2025.3599074","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3599074","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-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":null,"display_name":"Guiping Cao","orcid":"https://orcid.org/0000-0002-0682-2158"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guiping Cao","raw_affiliation_strings":["Research Institute of Trustworthy Autonomous Systems and Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-0682-2158","affiliations":[{"raw_affiliation_string":"Research Institute of Trustworthy Autonomous Systems and Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060307752","display_name":"Wenjian Huang","orcid":"https://orcid.org/0000-0003-2408-8302"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjian Huang","raw_affiliation_strings":["Research Institute of Trustworthy Autonomous Systems and Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China","Southern University of Science and Technology, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-2408-8302","affiliations":[{"raw_affiliation_string":"Research Institute of Trustworthy Autonomous Systems and Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China","institution_ids":["https://openalex.org/I3045169105"]},{"raw_affiliation_string":"Southern University of Science and Technology, Shenzhen, China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055543314","display_name":"Xiangyuan Lan","orcid":"https://orcid.org/0000-0001-8564-0346"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangyuan Lan","raw_affiliation_strings":["Pengcheng Laboratory, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-8564-0346","affiliations":[{"raw_affiliation_string":"Pengcheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100461783","display_name":"Jianguo Zhang","orcid":"https://orcid.org/0000-0001-9317-0268"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianguo Zhang","raw_affiliation_strings":["Research Institute of Trustworthy Autonomous Systems and Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-9317-0268","affiliations":[{"raw_affiliation_string":"Research Institute of Trustworthy Autonomous Systems and Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102021514","display_name":"Dongmei Jiang","orcid":"https://orcid.org/0000-0002-6238-8499"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongmei Jiang","raw_affiliation_strings":["Pengcheng Laboratory, Shenzhen, China","Pengcheng LaboratoryShenzhen 518066, China"],"raw_orcid":"https://orcid.org/0000-0002-6238-8499","affiliations":[{"raw_affiliation_string":"Pengcheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]},{"raw_affiliation_string":"Pengcheng LaboratoryShenzhen 518066, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"last","author":{"id":null,"display_name":"Yaowei Wang","orcid":"https://orcid.org/0000-0003-2197-9038"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaowei Wang","raw_affiliation_strings":["Harbin Institute of Technology at Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-2197-9038","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology at Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7655,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.74094777,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"27","issue":null,"first_page":"7369","last_page":"7379"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9395999908447266,"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":0.9395999908447266,"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/T12389","display_name":"Infrared Target Detection Methodologies","score":0.933899998664856,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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":0.8057332634925842},{"id":"https://openalex.org/keywords/cross-platform","display_name":"Cross-platform","score":0.6428428888320923},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.530437707901001},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4922720491886139},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.49159011244773865},{"id":"https://openalex.org/keywords/cross-validation","display_name":"Cross-validation","score":0.42404186725616455},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3634154200553894},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.31212547421455383},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.10976800322532654},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.0936879813671112},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.08189290761947632}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8057332634925842},{"id":"https://openalex.org/C92400490","wikidata":"https://www.wikidata.org/wiki/Q174666","display_name":"Cross-platform","level":2,"score":0.6428428888320923},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.530437707901001},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4922720491886139},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.49159011244773865},{"id":"https://openalex.org/C27181475","wikidata":"https://www.wikidata.org/wiki/Q541014","display_name":"Cross-validation","level":2,"score":0.42404186725616455},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3634154200553894},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31212547421455383},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.10976800322532654},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0936879813671112},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.08189290761947632},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2025.3599074","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3599074","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5578921854","display_name":null,"funder_award_id":"62402252","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1861492603","https://openalex.org/W2031454541","https://openalex.org/W2108598243","https://openalex.org/W2193145675","https://openalex.org/W2194775991","https://openalex.org/W2295107390","https://openalex.org/W2956268511","https://openalex.org/W2963037989","https://openalex.org/W2963150697","https://openalex.org/W2963351448","https://openalex.org/W2963786238","https://openalex.org/W2964241181","https://openalex.org/W2979332630","https://openalex.org/W2986357608","https://openalex.org/W2989604896","https://openalex.org/W2997408160","https://openalex.org/W3012573144","https://openalex.org/W3035239218","https://openalex.org/W3096609285","https://openalex.org/W3106753828","https://openalex.org/W3122799380","https://openalex.org/W3138516171","https://openalex.org/W3151130473","https://openalex.org/W3158261146","https://openalex.org/W3160733999","https://openalex.org/W3171660447","https://openalex.org/W3172752666","https://openalex.org/W3175630421","https://openalex.org/W3205100603","https://openalex.org/W3212972574","https://openalex.org/W4214627427","https://openalex.org/W4220678948","https://openalex.org/W4283819626","https://openalex.org/W4289890839","https://openalex.org/W4295123323","https://openalex.org/W4312312588","https://openalex.org/W4312443924","https://openalex.org/W4312823573","https://openalex.org/W4312853765","https://openalex.org/W4313172897","https://openalex.org/W4320002812","https://openalex.org/W4322730938","https://openalex.org/W4379928223","https://openalex.org/W4382568144","https://openalex.org/W4386065740","https://openalex.org/W4386076325","https://openalex.org/W4386076493","https://openalex.org/W4390871672","https://openalex.org/W4390872937","https://openalex.org/W4390873750","https://openalex.org/W4390873752","https://openalex.org/W4390873840","https://openalex.org/W4390889742","https://openalex.org/W4403888306","https://openalex.org/W4404582922","https://openalex.org/W4404612908","https://openalex.org/W4413222003"],"related_works":["https://openalex.org/W816105089","https://openalex.org/W912456583","https://openalex.org/W4318240167","https://openalex.org/W1527929073","https://openalex.org/W2509272512","https://openalex.org/W4404731582","https://openalex.org/W4405425614","https://openalex.org/W1987563485","https://openalex.org/W2745532314","https://openalex.org/W4231960479"],"abstract_inverted_index":{"Small":[0],"Object":[1],"Detection":[2],"(SOD)":[3],"poses":[4],"significant":[5],"challenges":[6],"due":[7],"to":[8,46,67,74,89,118,142,147,193],"limited":[9],"information":[10,51,129],"and":[11,70,126,173,210,261],"the":[12,36,48,59,79,94,114,148,153,171,195,200,218,245],"model's":[13,80],"low":[14],"class":[15,82,196],"prediction":[16,83,197],"score.":[17],"While":[18],"Transformer-based":[19],"detectors":[20],"have":[21],"shown":[22],"promising":[23],"performance,":[24],"their":[25],"potential":[26],"for":[27,52,130,238],"SOD":[28,239],"remains":[29],"largely":[30],"unexplored.":[31],"In":[32],"typical":[33],"DETR-like":[34,221],"frameworks,":[35],"CNN":[37],"backbone":[38],"network,":[39],"specialized":[40],"in":[41,58,64],"aggregating":[42],"local":[43],"information,":[44],"struggles":[45],"capture":[47],"necessary":[49],"contextual":[50],"SOD.":[53,97,131,224],"The":[54],"multiple":[55],"attention":[56],"layers":[57],"Transformer":[60,149],"Encoder":[61,150],"face":[62],"difficulties":[63],"effectively":[65],"attending":[66],"small":[68,86,156],"objects":[69,87,91],"can":[71],"also":[72],"lead":[73],"blurring":[75],"of":[76,85,96,155,164,175,199,220],"features.":[77],"Furthermore,":[78],"lower":[81],"score":[84,198],"compared":[88],"large":[90],"further":[92],"increases":[93],"difficulty":[95],"To":[98],"address":[99],"these":[100,144],"challenges,":[101],"we":[102,159,184],"introduce":[103,160],"a":[104,133,161,186],"novel":[105],"approach":[106,112],"called":[107,190],"<bold":[108,229,248],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[109,230,233,249,252],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Cross-DINO</b>.":[110],"This":[111],"incorporates":[113],"deep":[115],"MLP":[116],"network":[117],"aggregate":[119],"initial":[120,145],"feature":[121],"representations":[122,146],"with":[123,240,258],"both":[124],"short":[125],"long":[127],"range":[128],"Then,":[132],"new":[134,162,181,187],"Cross":[135],"Coding":[136],"Twice":[137],"Module":[138],"(CCTM)":[139],"is":[140],"applied":[141],"integrate":[143],"feature,":[151],"enhancing":[152],"details":[154],"objects.":[157,176],"Additionally,":[158],"kind":[163],"soft":[165],"label":[166],"named":[167],"Category-Size":[168],"(CS),":[169],"integrating":[170],"Category":[172],"Size":[174],"By":[177],"treating":[178],"CS":[179],"as":[180],"ground":[182],"truth,":[183],"propose":[185],"loss":[188],"function":[189],"Boost":[191],"Loss":[192],"improve":[194],"model.":[201],"Extensive":[202],"experimental":[203],"results":[204],"on":[205,223,236],"COCO,":[206],"WiderPerson,":[207],"VisDrone,":[208],"AI-TOD,":[209],"SODA-D":[211],"datasets":[212],"demonstrate":[213],"that":[214],"Cross-DINO":[215],"efficiently":[216],"improves":[217],"performance":[219],"models":[222],"Specifically,":[225],"our":[226],"model":[227],"achieves":[228],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">36.4%</b>":[231],"AP<inline-formula":[232,251],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><tex-math":[234,253],"notation=\"LaTeX\">$_{S}$</tex-math></inline-formula>":[235,254],"COCO":[237],"only":[241],"45M":[242],"parameters,":[243],"outperforming":[244],"DINO":[246],"by":[247],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">+4.4%</b>":[250],"(36.4%":[255],"vs.":[256],"32.0%)":[257],"fewer":[259],"parameters":[260],"FLOPs,":[262],"under":[263],"12":[264],"epochs":[265],"training":[266],"setting.":[267]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}