{"id":"https://openalex.org/W4402302067","doi":"https://doi.org/10.1109/tmm.2024.3453061","title":"VLDadaptor: Domain Adaptive Object Detection With Vision-Language Model Distillation","display_name":"VLDadaptor: Domain Adaptive Object Detection With Vision-Language Model Distillation","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4402302067","doi":"https://doi.org/10.1109/tmm.2024.3453061"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2024.3453061","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2024.3453061","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":"https://openalex.org/A5030485695","display_name":"Junjie Ke","orcid":"https://orcid.org/0000-0001-8512-3744"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Junjie Ke","raw_affiliation_strings":["Visual Information Processing Laboratory, School of Electronic Engineering, Xidian University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Visual Information Processing Laboratory, School of Electronic Engineering, Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039837634","display_name":"Lihuo He","orcid":"https://orcid.org/0000-0002-0555-3574"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lihuo He","raw_affiliation_strings":["Visual Information Processing Laboratory, School of Electronic Engineering, Xidian University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Visual Information Processing Laboratory, School of Electronic Engineering, Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101936635","display_name":"Bo Han","orcid":"https://orcid.org/0000-0001-6282-5428"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Han","raw_affiliation_strings":["Visual Information Processing Laboratory, School of Electronic Engineering, Xidian University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Visual Information Processing Laboratory, School of Electronic Engineering, Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jie Li","orcid":"https://orcid.org/0000-0001-7950-4233"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Li","raw_affiliation_strings":["Visual Information Processing Laboratory, School of Electronic Engineering, Xidian University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Visual Information Processing Laboratory, School of Electronic Engineering, Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Di Wang","orcid":"https://orcid.org/0000-0001-8027-4287"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Di Wang","raw_affiliation_strings":["School of Computer Science and Technology, Xidian University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101785348","display_name":"Xinbo Gao","orcid":"https://orcid.org/0000-0002-7985-0037"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinbo Gao","raw_affiliation_strings":["Visual Information Processing Laboratory, School of Electronic Engineering, Xidian University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Visual Information Processing Laboratory, School of Electronic Engineering, Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5030485695"],"corresponding_institution_ids":["https://openalex.org/I149594827"],"apc_list":null,"apc_paid":null,"fwci":2.2049,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.89106469,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"26","issue":null,"first_page":"11316","last_page":"11331"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9911999702453613,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9911999702453613,"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":0.9905999898910522,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9879999756813049,"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/computer-science","display_name":"Computer science","score":0.8805035352706909},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.6008232235908508},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5810056924819946},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5697968006134033},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5209247469902039},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5116384625434875},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.487468957901001},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35094931721687317},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3363221287727356},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.30293193459510803}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8805035352706909},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.6008232235908508},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5810056924819946},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5697968006134033},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5209247469902039},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5116384625434875},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.487468957901001},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35094931721687317},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3363221287727356},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.30293193459510803},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2024.3453061","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2024.3453061","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/G2022121445","display_name":null,"funder_award_id":"U21A20514","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3301621070","display_name":null,"funder_award_id":"62072354","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G463811269","display_name":null,"funder_award_id":"62276203","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G913836228","display_name":null,"funder_award_id":"62036007","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":75,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W2037227137","https://openalex.org/W2117539524","https://openalex.org/W2150066425","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2340897893","https://openalex.org/W2504335775","https://openalex.org/W2549139847","https://openalex.org/W2565639579","https://openalex.org/W2601564443","https://openalex.org/W2748021867","https://openalex.org/W2916798096","https://openalex.org/W2928165649","https://openalex.org/W2962823940","https://openalex.org/W2963351448","https://openalex.org/W2963730616","https://openalex.org/W2964115968","https://openalex.org/W2968634921","https://openalex.org/W2977464309","https://openalex.org/W2982770724","https://openalex.org/W3034779842","https://openalex.org/W3034937575","https://openalex.org/W3035175896","https://openalex.org/W3035564946","https://openalex.org/W3035673985","https://openalex.org/W3080913582","https://openalex.org/W3107610277","https://openalex.org/W3109679703","https://openalex.org/W3110011650","https://openalex.org/W3129242782","https://openalex.org/W3163893908","https://openalex.org/W3166409449","https://openalex.org/W3174551531","https://openalex.org/W3176895448","https://openalex.org/W3180426564","https://openalex.org/W3194643899","https://openalex.org/W3202277637","https://openalex.org/W3203554015","https://openalex.org/W3204359931","https://openalex.org/W3204821053","https://openalex.org/W4205294740","https://openalex.org/W4226412070","https://openalex.org/W4281692368","https://openalex.org/W4283807782","https://openalex.org/W4293428377","https://openalex.org/W4301802352","https://openalex.org/W4312284139","https://openalex.org/W4312310776","https://openalex.org/W4312563428","https://openalex.org/W4312747482","https://openalex.org/W4312754496","https://openalex.org/W4312775058","https://openalex.org/W4312815761","https://openalex.org/W4312980231","https://openalex.org/W4313160378","https://openalex.org/W4313893207","https://openalex.org/W4385245566","https://openalex.org/W4386066015","https://openalex.org/W4386066484","https://openalex.org/W4386071764","https://openalex.org/W4386071781","https://openalex.org/W4386231664","https://openalex.org/W4387969003","https://openalex.org/W4388430511","https://openalex.org/W4390190228","https://openalex.org/W4390489059","https://openalex.org/W4390874577","https://openalex.org/W6637373629","https://openalex.org/W6639480849","https://openalex.org/W6776700526","https://openalex.org/W6790019176","https://openalex.org/W6791353385","https://openalex.org/W6801795037","https://openalex.org/W6803559075"],"related_works":["https://openalex.org/W3026162553","https://openalex.org/W2768175398","https://openalex.org/W2344382886","https://openalex.org/W19111321","https://openalex.org/W2412887479","https://openalex.org/W32245304","https://openalex.org/W2953684491","https://openalex.org/W4285338581","https://openalex.org/W4292830139","https://openalex.org/W4319309705"],"abstract_inverted_index":{"Domain":[0],"adaptive":[1,69],"object":[2,70],"detection":[3],"(DAOD)":[4],"aims":[5],"to":[6,15,50,138,170,181,212],"develop":[7],"a":[8,67,166],"detector":[9,71,95,104,126],"trained":[10],"on":[11,73,209,220],"labeled":[12],"source":[13,56],"domains":[14],"identify":[16],"objects":[17],"in":[18,25,45],"unlabeled":[19],"target":[20],"domains.":[21,57,112,197],"A":[22],"primary":[23],"challenge":[24],"DAOD":[26],"is":[27],"the":[28,51,60,79,88,94,103,120,140,145,150,156,161,186,203],"domain":[29,40,68],"shift":[30],"problem.":[31],"Most":[32],"existing":[33],"methods":[34],"learn":[35],"domain-invariant":[36,107],"features":[37,110,173,184],"within":[38],"single":[39],"embedding":[41,188],"space,":[42],"often":[43],"resulting":[44],"heavy":[46],"model":[47,61,193],"biases":[48],"due":[49],"intrinsic":[52],"data":[53],"properties":[54],"of":[55,91,123,153],"To":[58],"mitigate":[59],"biases,":[62],"this":[63],"paper":[64],"proposes":[65],"VLDadaptor,":[66],"based":[72],"vision-language":[74],"models":[75],"(VLMs)":[76],"distillation.":[77],"Firstly,":[78],"proposed":[80,157,204],"method":[81,158,205],"integrates":[82],"domain-mixed":[83,116],"contrastive":[84],"knowledge":[85],"distillation":[86,118],"between":[87,119],"visual":[89,108,133,151,183],"encoder":[90,122,148,152],"CLIP":[92,124],"and":[93,125,149,216],"by":[96,127,164],"transferring":[97],"category-level":[98,141],"instance":[99,109,134],"features,":[100,135],"which":[101,136],"guarantees":[102],"can":[105],"extract":[106,182],"across":[111],"Then,":[113],"VLDadaptor":[114,180],"employs":[115],"consistency":[117,143],"text":[121,129,147],"aligning":[128],"prompt":[130],"embeddings":[131],"with":[132,224],"helps":[137],"maintain":[139],"feature":[142],"among":[144],"detector,":[146],"VLMs.":[154],"Finally,":[155],"further":[159],"promotes":[160],"adaptation":[162,214],"ability":[163],"adopting":[165],"prompt-based":[167],"memory":[168],"bank":[169],"generate":[171],"semantic-complete":[172],"for":[174],"graph":[175],"matching.":[176],"These":[177],"contributions":[178],"enable":[179],"into":[185],"visual-language":[187],"space":[189],"without":[190],"any":[191],"evident":[192],"bias":[194],"towards":[195],"specific":[196],"Extensive":[198],"experimental":[199],"results":[200],"demonstrate":[201],"that":[202],"achieves":[206],"state-of-the-art":[207],"performance":[208],"Pascal":[210],"VOC":[211],"Clipart":[213],"tasks":[215,223],"exhibits":[217],"high":[218],"accuracy":[219],"driving":[221],"scenario":[222],"significantly":[225],"less":[226],"training":[227],"time.":[228]},"counts_by_year":[{"year":2025,"cited_by_count":9}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}