{"id":"https://openalex.org/W4392902991","doi":"https://doi.org/10.1109/icassp48485.2024.10446913","title":"Enhancing Image-Text Matching with Adaptive Feature Aggregation","display_name":"Enhancing Image-Text Matching with Adaptive Feature Aggregation","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392902991","doi":"https://doi.org/10.1109/icassp48485.2024.10446913"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446913","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446913","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5080557429","display_name":"Zuhui Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I1327163397","display_name":"State University of New York","ror":"https://ror.org/01q1z8k08","country_code":"US","type":"education","lineage":["https://openalex.org/I1327163397"]},{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zuhui Wang","raw_affiliation_strings":["State University of New York at Stony Brook,USA","State University of New York at Stony Brook, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State University of New York at Stony Brook,USA","institution_ids":["https://openalex.org/I59553526","https://openalex.org/I1327163397"]},{"raw_affiliation_string":"State University of New York at Stony Brook, USA","institution_ids":["https://openalex.org/I59553526","https://openalex.org/I1327163397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101267356","display_name":"Yunting Yin","orcid":null},"institutions":[{"id":"https://openalex.org/I1327163397","display_name":"State University of New York","ror":"https://ror.org/01q1z8k08","country_code":"US","type":"education","lineage":["https://openalex.org/I1327163397"]},{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yunting Yin","raw_affiliation_strings":["State University of New York at Stony Brook,USA","State University of New York at Stony Brook, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State University of New York at Stony Brook,USA","institution_ids":["https://openalex.org/I59553526","https://openalex.org/I1327163397"]},{"raw_affiliation_string":"State University of New York at Stony Brook, USA","institution_ids":["https://openalex.org/I59553526","https://openalex.org/I1327163397"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005648942","display_name":"I. V. Ramakrishnan","orcid":"https://orcid.org/0000-0002-1768-7043"},"institutions":[{"id":"https://openalex.org/I1327163397","display_name":"State University of New York","ror":"https://ror.org/01q1z8k08","country_code":"US","type":"education","lineage":["https://openalex.org/I1327163397"]},{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"I.V. Ramakrishnan","raw_affiliation_strings":["State University of New York at Stony Brook,USA","State University of New York at Stony Brook, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State University of New York at Stony Brook,USA","institution_ids":["https://openalex.org/I59553526","https://openalex.org/I1327163397"]},{"raw_affiliation_string":"State University of New York at Stony Brook, USA","institution_ids":["https://openalex.org/I59553526","https://openalex.org/I1327163397"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3124,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.80346877,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"8245","last_page":"8249"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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":0.9998000264167786,"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":0.9986000061035156,"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/computer-science","display_name":"Computer science","score":0.8009078502655029},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6686711311340332},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.6676865816116333},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6504143476486206},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6186143755912781},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.586246907711029},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5786953568458557},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5519093871116638},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5418293476104736},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.5193432569503784},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4409283399581909},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.43626856803894043},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.35783398151397705},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3476703464984894},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10439297556877136}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8009078502655029},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6686711311340332},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.6676865816116333},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6504143476486206},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6186143755912781},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.586246907711029},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5786953568458557},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5519093871116638},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5418293476104736},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.5193432569503784},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4409283399581909},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.43626856803894043},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35783398151397705},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3476703464984894},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10439297556877136},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446913","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446913","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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":27,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W1933349210","https://openalex.org/W2185175083","https://openalex.org/W2194775991","https://openalex.org/W2301541953","https://openalex.org/W2302086703","https://openalex.org/W2596164567","https://openalex.org/W2842511635","https://openalex.org/W2885195348","https://openalex.org/W2962964995","https://openalex.org/W2988823324","https://openalex.org/W3110042533","https://openalex.org/W3118694826","https://openalex.org/W3175888430","https://openalex.org/W3190055600","https://openalex.org/W4213348104","https://openalex.org/W4224952037","https://openalex.org/W4297808394","https://openalex.org/W4298052789","https://openalex.org/W4307823382","https://openalex.org/W4308238260","https://openalex.org/W4366241040","https://openalex.org/W4385245566","https://openalex.org/W4386075677","https://openalex.org/W6747225742","https://openalex.org/W6843825070"],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W2037549926","https://openalex.org/W2188500270","https://openalex.org/W2303858293","https://openalex.org/W2345479200","https://openalex.org/W2183306018","https://openalex.org/W2915512527","https://openalex.org/W51364034","https://openalex.org/W2849310602","https://openalex.org/W2123991572"],"abstract_inverted_index":{"Image-text":[0],"matching":[1],"aims":[2],"to":[3,34],"find":[4],"matched":[5],"cross-modal":[6,16],"pairs":[7],"accurately.":[8],"While":[9],"current":[10],"methods":[11],"often":[12],"rely":[13],"on":[14,88],"projecting":[15],"features":[17,53],"into":[18],"a":[19,44,64],"common":[20],"embedding":[21],"space,":[22],"they":[23],"frequently":[24],"suffer":[25],"from":[26],"imbalanced":[27],"feature":[28],"representations":[29],"across":[30],"different":[31],"modalities,":[32],"leading":[33],"unreliable":[35],"retrieval":[36,80,95],"results.":[37],"To":[38],"address":[39],"these":[40],"limitations,":[41],"we":[42,62],"introduce":[43],"novel":[45],"Feature":[46],"Enhancement":[47],"Module":[48],"that":[49,68],"adaptively":[50],"aggregates":[51],"single-modal":[52],"for":[54],"more":[55],"balanced":[56],"and":[57,92],"robust":[58],"image-text":[59],"retrieval.":[60],"Additionally,":[61],"propose":[63],"new":[65],"loss":[66],"function":[67],"overcomes":[69],"the":[70],"shortcomings":[71],"of":[72],"original":[73],"triplet":[74],"ranking":[75],"loss,":[76],"thereby":[77],"significantly":[78],"improving":[79],"performance.":[81],"The":[82],"proposed":[83],"model":[84],"has":[85],"been":[86],"evaluated":[87],"two":[89],"public":[90],"datasets":[91],"achieves":[93],"competitive":[94],"performance":[96],"when":[97],"compared":[98],"with":[99],"several":[100],"state-of-the-art":[101],"models.":[102],"Implementation":[103],"codes":[104],"can":[105],"be":[106],"found":[107],"here.":[108]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}