{"id":"https://openalex.org/W7164818280","doi":"https://doi.org/10.1145/3805622.3810607","title":"B-HFA: Parameter-Efficient Vision-Language Retrieval via Block-shared Adapters and Hierarchical Aggregation","display_name":"B-HFA: Parameter-Efficient Vision-Language Retrieval via Block-shared Adapters and Hierarchical Aggregation","publication_year":2026,"publication_date":"2026-06-15","ids":{"openalex":"https://openalex.org/W7164818280","doi":"https://doi.org/10.1145/3805622.3810607"},"language":null,"primary_location":{"id":"doi:10.1145/3805622.3810607","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810607","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805622.3810607","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138655594","display_name":"Rui Xu","orcid":"https://orcid.org/0009-0002-1662-2085"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Xu","raw_affiliation_strings":["Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0009-0002-1662-2085","affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067849522","display_name":"Lin Yao","orcid":"https://orcid.org/0000-0001-8138-6045"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Yao","raw_affiliation_strings":["Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0001-8138-6045","affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138629782","display_name":"Zhiyang Wu","orcid":"https://orcid.org/0009-0007-7982-6217"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyang Wu","raw_affiliation_strings":["Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0009-0007-7982-6217","affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076120553","display_name":"Xuyun Zhang","orcid":"https://orcid.org/0000-0001-7353-4159"},"institutions":[{"id":"https://openalex.org/I99043593","display_name":"Macquarie University","ror":"https://ror.org/01sf06y89","country_code":"AU","type":"education","lineage":["https://openalex.org/I99043593"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xuyun Zhang","raw_affiliation_strings":["Macquarie University, Sydney, Australia"],"raw_orcid":"https://orcid.org/0000-0001-7353-4159","affiliations":[{"raw_affiliation_string":"Macquarie University, Sydney, Australia","institution_ids":["https://openalex.org/I99043593"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029356396","display_name":"Guowei Wu","orcid":"https://orcid.org/0000-0002-3929-3598"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guowei Wu","raw_affiliation_strings":["Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0002-3929-3598","affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.93513912,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"242","last_page":"251"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9908000230789185,"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":0.9908000230789185,"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":0.004600000102072954,"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":0.0017999999690800905,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.7013000249862671},{"id":"https://openalex.org/keywords/generality","display_name":"Generality","score":0.5310999751091003},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.4415000081062317},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4154999852180481},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.3955000042915344},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3671000003814697},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.35409998893737793},{"id":"https://openalex.org/keywords/visual-word","display_name":"Visual Word","score":0.33009999990463257}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8237000107765198},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.7013000249862671},{"id":"https://openalex.org/C2780767217","wikidata":"https://www.wikidata.org/wiki/Q5532421","display_name":"Generality","level":2,"score":0.5310999751091003},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49799999594688416},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.4415000081062317},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4154999852180481},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.3955000042915344},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3671000003814697},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.35409998893737793},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.33009999990463257},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.31690001487731934},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.2922999858856201},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2904999852180481},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.28929999470710754},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.2881999909877777},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2831999957561493},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.2800000011920929},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2718999981880188},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26589998602867126},{"id":"https://openalex.org/C2777742833","wikidata":"https://www.wikidata.org/wiki/Q1964083","display_name":"Reciprocal","level":2,"score":0.262800008058548},{"id":"https://openalex.org/C177284502","wikidata":"https://www.wikidata.org/wiki/Q1005390","display_name":"Adapter (computing)","level":2,"score":0.26190000772476196}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805622.3810607","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810607","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805622.3810607","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810607","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5673189759254456,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G3049236034","display_name":null,"funder_award_id":"62272804","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1963826206","https://openalex.org/W2084472453","https://openalex.org/W2277195237","https://openalex.org/W2565639579","https://openalex.org/W2963017553","https://openalex.org/W2969876226","https://openalex.org/W3090449556","https://openalex.org/W3091588028","https://openalex.org/W3152798676","https://openalex.org/W3168640669","https://openalex.org/W3184784418","https://openalex.org/W3193402170","https://openalex.org/W3204588463","https://openalex.org/W3212456749","https://openalex.org/W3215626407","https://openalex.org/W3217059257","https://openalex.org/W4313186260","https://openalex.org/W4320855021","https://openalex.org/W4366208220","https://openalex.org/W4384918448","https://openalex.org/W4386071547","https://openalex.org/W4386076600","https://openalex.org/W4386076661","https://openalex.org/W4387687151","https://openalex.org/W4390723197","https://openalex.org/W4390874513","https://openalex.org/W4390874575","https://openalex.org/W4402727931","https://openalex.org/W4404011646","https://openalex.org/W4409364263","https://openalex.org/W4411631898","https://openalex.org/W4411635525","https://openalex.org/W6948369276","https://openalex.org/W7133196460"],"related_works":[],"abstract_inverted_index":{"Full":[0],"fine-tuning":[1],"of":[2,36,130,144],"large":[3],"vision-language":[4,70],"models":[5],"(VLMs)":[6],"for":[7,41,49,69,113],"cross-modal":[8],"retrieval":[9,119,149],"is":[10],"computationally":[11],"expensive":[12],"and":[13,33,86],"prone":[14],"to":[15,79],"overfitting.":[16],"Adapter-based":[17],"parameter-efficient":[18,67],"transfer":[19],"learning":[20],"offers":[21],"a":[22,66,74,87],"practical":[23],"alternative,":[24],"but":[25],"existing":[26],"designs":[27],"often":[28],"suffer":[29],"from":[30],"structural":[31],"redundancy":[32,81],"the":[34,142,145],"loss":[35],"fine-grained":[37,53],"visual":[38,97,110,138],"details":[39],"critical":[40],"accurate":[42],"matching.":[43],"These":[44],"limitations":[45],"are":[46],"particularly":[47],"detrimental":[48],"retrieval,":[50],"which":[51],"demands":[52],"perceptual":[54],"discrimination":[55],"beyond":[56,148],"semantic":[57],"alignment.":[58],"To":[59],"address":[60],"these":[61],"challenges,":[62],"we":[63],"propose":[64],"B-HFA,":[65],"framework":[68,147],"retrieval.":[71,114],"B-HFA":[72,123],"introduces":[73],"Block-wise":[75],"Shared":[76],"Adapter":[77],"(B-Adapter)":[78],"reduce":[80],"through":[82],"structured":[83],"parameter":[84],"sharing,":[85],"Hierarchical":[88],"Feature":[89],"Aggregation":[90],"(HFA)":[91],"module":[92],"that":[93,122],"dynamically":[94],"integrates":[95],"intermediate":[96],"features":[98],"guided":[99],"by":[100],"textual":[101],"semantics.":[102],"This":[103],"design":[104],"enables":[105],"efficient":[106],"adaptation":[107],"while":[108],"preserving":[109],"fidelity":[111],"essential":[112],"Extensive":[115],"experiments":[116],"on":[117,137],"multiple":[118],"benchmarks":[120],"demonstrate":[121],"achieves":[124],"competitive":[125,135],"performance":[126],"with":[127],"only":[128],"0.13%":[129],"trainable":[131],"parameters.":[132],"Moreover,":[133],"its":[134],"results":[136],"question":[139],"answering":[140],"suggest":[141],"generality":[143],"proposed":[146],"tasks.":[150]},"counts_by_year":[],"updated_date":"2026-06-16T07:37:23.134862","created_date":"2026-06-16T00:00:00"}