{"id":"https://openalex.org/W7133545303","doi":"https://doi.org/10.48550/arxiv.2603.02924","title":"HDINO: A Concise and Efficient Open-Vocabulary Detector","display_name":"HDINO: A Concise and Efficient Open-Vocabulary Detector","publication_year":2026,"publication_date":"2026-03-03","ids":{"openalex":"https://openalex.org/W7133545303","doi":"https://doi.org/10.48550/arxiv.2603.02924"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.02924","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.02924","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.02924","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128049850","display_name":"Hao F. Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Hao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123930986","display_name":"Yiqun Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yiqun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128040279","display_name":"Qinran Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Qinran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128093619","display_name":"Runze Fan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fan, Runze","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5128036756","display_name":"Yong Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Yong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"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":0.4097999930381775,"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":0.4097999930381775,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.39800000190734863,"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":0.09539999812841415,"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/construct","display_name":"Construct (python library)","score":0.6881999969482422},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6349999904632568},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.6265000104904175},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6090999841690063},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5685999989509583},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.5546000003814697},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5246000289916992},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4706000089645386},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.42289999127388}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7577999830245972},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.6881999969482422},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6349999904632568},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6265000104904175},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6162999868392944},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6090999841690063},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5685999989509583},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.5546000003814697},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5246000289916992},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4706000089645386},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.42289999127388},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.4171000123023987},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.41370001435279846},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3619000017642975},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33970001339912415},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3384000062942505},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.3375999927520752},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32170000672340393},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.3100999891757965},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.304500013589859},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.301800012588501},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.29190000891685486},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.2809999883174896},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.27970001101493835},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.2784999907016754},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.2745000123977661},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2728999853134155},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2646999955177307},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.26159998774528503},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.2614000141620636},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2581000030040741},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.2533999979496002},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.25110000371932983}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.02924","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.02924","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.02924","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.02924","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Despite":[0],"the":[1,45,59,64,84,117,128,138,164,204],"growing":[2],"interest":[3],"in":[4,8],"open-vocabulary":[5,40],"object":[6,41,74],"detection":[7,105,156],"recent":[9],"years,":[10],"most":[11],"existing":[12],"methods":[13],"rely":[14],"heavily":[15],"on":[16,47,103,146,184,191],"manually":[17],"curated":[18],"fine-grained":[19],"training":[20,55,150],"datasets":[21],"as":[22,24,71],"well":[23],"resource-intensive":[25],"layer-wise":[26],"cross-modal":[27],"feature":[28,122],"extraction.":[29],"In":[30,63,116],"this":[31],"paper,":[32],"we":[33,51],"propose":[34,52],"HDINO,":[35],"a":[36,53,78,120],"concise":[37],"yet":[38],"efficient":[39],"detector":[42],"that":[43],"eliminates":[44],"dependence":[46],"these":[48],"components.":[49],"Specifically,":[50],"two-stage":[54],"strategy":[56],"built":[57],"upon":[58],"transformer-based":[60],"DINO":[61],"model.":[62],"first":[65],"stage,":[66,119],"noisy":[67],"samples":[68],"are":[69,182,214],"treated":[70],"additional":[72],"positive":[73],"instances":[75],"to":[76,107,127,131,134],"construct":[77],"One-to-Many":[79],"Semantic":[80],"Alignment":[81],"Mechanism(O2M)":[82],"between":[83],"visual":[85],"and":[86,111,163,172,177,186,194,200,206,212],"textual":[87],"modalities,":[88],"thereby":[89],"facilitating":[90],"semantic":[91],"alignment.":[92],"A":[93],"Difficulty":[94],"Weighted":[95],"Classification":[96],"Loss":[97],"(DWCL)":[98],"is":[99,125],"also":[100],"designed":[101],"based":[102],"initial":[104],"difficulty":[106],"mine":[108],"hard":[109],"examples":[110],"further":[112,196],"improve":[113],"model":[114],"performance.":[115],"second":[118],"lightweight":[121],"fusion":[123],"module":[124],"applied":[126],"aligned":[129],"representations":[130],"enhance":[132],"sensitivity":[133],"linguistic":[135],"semantics.":[136],"Under":[137],"Swin":[139],"Transformer-T":[140],"setting,":[141],"HDINO-T":[142,193],"achieves":[143],"\\textbf{49.2}":[144],"mAP":[145,176,199],"COCO":[147],"using":[148],"2.2M":[149],"images":[151],"from":[152],"two":[153],"publicly":[154],"available":[155,215],"datasets,":[157],"without":[158],"any":[159],"manual":[160],"data":[161],"curation":[162],"use":[165],"of":[166,208],"grounding":[167],"data,":[168],"surpassing":[169],"Grounding":[170],"DINO-T":[171],"T-Rex2":[173],"by":[174],"\\textbf{0.8}":[175],"\\textbf{2.8}":[178],"mAP,":[179,202],"respectively,":[180],"which":[181],"trained":[183],"5.4M":[185],"6.5M":[187],"images.":[188],"After":[189],"fine-tuning":[190],"COCO,":[192],"HDINO-L":[195],"achieve":[197],"\\textbf{56.4}":[198],"\\textbf{59.2}":[201],"highlighting":[203],"effectiveness":[205],"scalability":[207],"our":[209],"approach.":[210],"Code":[211],"models":[213],"at":[216],"https://github.com/HaoZ416/HDINO.":[217]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-03-05T00:00:00"}