{"id":"https://openalex.org/W4417165484","doi":"https://doi.org/10.1145/3779654","title":"High Feature Distinguishability for Adaptive Image-text Matching with Dual-stream Transformers","display_name":"High Feature Distinguishability for Adaptive Image-text Matching with Dual-stream Transformers","publication_year":2025,"publication_date":"2025-12-09","ids":{"openalex":"https://openalex.org/W4417165484","doi":"https://doi.org/10.1145/3779654"},"language":"en","primary_location":{"id":"doi:10.1145/3779654","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3779654","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","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/A5012931252","display_name":"Yangtao Wang","orcid":"https://orcid.org/0000-0003-4605-9270"},"institutions":[{"id":"https://openalex.org/I37987034","display_name":"Guangzhou University","ror":"https://ror.org/05ar8rn06","country_code":"CN","type":"education","lineage":["https://openalex.org/I37987034"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yangtao Wang","raw_affiliation_strings":["School of Computer Science and Cyber Engineering, Guangzhou University, Guangzhou, China","School of Computer Science and Cyber Engineering, Guangzhou University, China"],"raw_orcid":"https://orcid.org/0000-0003-4605-9270","affiliations":[{"raw_affiliation_string":"School of Computer Science and Cyber Engineering, Guangzhou University, Guangzhou, China","institution_ids":["https://openalex.org/I37987034"]},{"raw_affiliation_string":"School of Computer Science and Cyber Engineering, Guangzhou University, China","institution_ids":["https://openalex.org/I37987034"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108507704","display_name":"Weibin Huang","orcid":"https://orcid.org/0009-0006-7098-0501"},"institutions":[{"id":"https://openalex.org/I37987034","display_name":"Guangzhou University","ror":"https://ror.org/05ar8rn06","country_code":"CN","type":"education","lineage":["https://openalex.org/I37987034"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weibin Huang","raw_affiliation_strings":["School of Computer Science and Cyber Engineering, Guangzhou University, Guangzhou, China","School of Computer Science and Cyber Engineering, Guangzhou University, China"],"raw_orcid":"https://orcid.org/0009-0006-7098-0501","affiliations":[{"raw_affiliation_string":"School of Computer Science and Cyber Engineering, Guangzhou University, Guangzhou, China","institution_ids":["https://openalex.org/I37987034"]},{"raw_affiliation_string":"School of Computer Science and Cyber Engineering, Guangzhou University, China","institution_ids":["https://openalex.org/I37987034"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050542870","display_name":"Yanzhao Xie","orcid":"https://orcid.org/0000-0002-9274-2807"},"institutions":[{"id":"https://openalex.org/I37987034","display_name":"Guangzhou University","ror":"https://ror.org/05ar8rn06","country_code":"CN","type":"education","lineage":["https://openalex.org/I37987034"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanzhao Xie","raw_affiliation_strings":["School of Computer Science and Cyber Engineering, Guangzhou University, Guangzhou, China","School of Computer Science and Cyber Engineering, Guangzhou University, China"],"raw_orcid":"https://orcid.org/0000-0002-9274-2807","affiliations":[{"raw_affiliation_string":"School of Computer Science and Cyber Engineering, Guangzhou University, Guangzhou, China","institution_ids":["https://openalex.org/I37987034"]},{"raw_affiliation_string":"School of Computer Science and Cyber Engineering, Guangzhou University, China","institution_ids":["https://openalex.org/I37987034"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100429228","display_name":"Siyuan Chen","orcid":"https://orcid.org/0000-0001-9272-4804"},"institutions":[{"id":"https://openalex.org/I37987034","display_name":"Guangzhou University","ror":"https://ror.org/05ar8rn06","country_code":"CN","type":"education","lineage":["https://openalex.org/I37987034"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siyuan Chen","raw_affiliation_strings":["School of Computer Science and Cyber Engineering, Guangzhou University, Guangzhou, China","School of Computer Science and Cyber Engineering, Guangzhou University, China"],"raw_orcid":"https://orcid.org/0000-0001-9272-4804","affiliations":[{"raw_affiliation_string":"School of Computer Science and Cyber Engineering, Guangzhou University, Guangzhou, China","institution_ids":["https://openalex.org/I37987034"]},{"raw_affiliation_string":"School of Computer Science and Cyber Engineering, Guangzhou University, China","institution_ids":["https://openalex.org/I37987034"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052138365","display_name":"Weilong Peng","orcid":"https://orcid.org/0000-0001-5820-889X"},"institutions":[{"id":"https://openalex.org/I37987034","display_name":"Guangzhou University","ror":"https://ror.org/05ar8rn06","country_code":"CN","type":"education","lineage":["https://openalex.org/I37987034"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weilong Peng","raw_affiliation_strings":["School of Computer Science and Cyber Engineering, Guangzhou University, Guangzhou, China","School of Computer Science and Cyber Engineering, Guangzhou University, China"],"raw_orcid":"https://orcid.org/0000-0001-5820-889X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Cyber Engineering, Guangzhou University, Guangzhou, China","institution_ids":["https://openalex.org/I37987034"]},{"raw_affiliation_string":"School of Computer Science and Cyber Engineering, Guangzhou University, China","institution_ids":["https://openalex.org/I37987034"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067384850","display_name":"Maobin Tang","orcid":"https://orcid.org/0009-0005-5448-4172"},"institutions":[{"id":"https://openalex.org/I37987034","display_name":"Guangzhou University","ror":"https://ror.org/05ar8rn06","country_code":"CN","type":"education","lineage":["https://openalex.org/I37987034"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Maobin Tang","raw_affiliation_strings":["School of Computer Science and Cyber Engineering, Guangzhou University, Guangzhou, China","School of Computer Science and Cyber Engineering, Guangzhou University, China"],"raw_orcid":"https://orcid.org/0009-0005-5448-4172","affiliations":[{"raw_affiliation_string":"School of Computer Science and Cyber Engineering, Guangzhou University, Guangzhou, China","institution_ids":["https://openalex.org/I37987034"]},{"raw_affiliation_string":"School of Computer Science and Cyber Engineering, Guangzhou University, China","institution_ids":["https://openalex.org/I37987034"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073389511","display_name":"Meie Fang","orcid":"https://orcid.org/0000-0003-4292-8889"},"institutions":[{"id":"https://openalex.org/I37987034","display_name":"Guangzhou University","ror":"https://ror.org/05ar8rn06","country_code":"CN","type":"education","lineage":["https://openalex.org/I37987034"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meie Fang","raw_affiliation_strings":["School of Computer Science and Cyber Engineering, Guangzhou University, Guangzhou, China","School of Computer Science and Cyber Engineering, Guangzhou University, China"],"raw_orcid":"https://orcid.org/0000-0003-4292-8889","affiliations":[{"raw_affiliation_string":"School of Computer Science and Cyber Engineering, Guangzhou University, Guangzhou, China","institution_ids":["https://openalex.org/I37987034"]},{"raw_affiliation_string":"School of Computer Science and Cyber Engineering, Guangzhou University, China","institution_ids":["https://openalex.org/I37987034"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100414787","display_name":"Wensheng Zhang","orcid":"https://orcid.org/0000-0003-0752-941X"},"institutions":[{"id":"https://openalex.org/I37987034","display_name":"Guangzhou University","ror":"https://ror.org/05ar8rn06","country_code":"CN","type":"education","lineage":["https://openalex.org/I37987034"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wensheng Zhang","raw_affiliation_strings":["School of Computer Science and Cyber Engineering, Guangzhou University, Guangzhou, China","School of Computer Science and Cyber Engineering, Guangzhou University, China"],"raw_orcid":"https://orcid.org/0000-0003-0752-941X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Cyber Engineering, Guangzhou University, Guangzhou, China","institution_ids":["https://openalex.org/I37987034"]},{"raw_affiliation_string":"School of Computer Science and Cyber Engineering, Guangzhou University, China","institution_ids":["https://openalex.org/I37987034"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I37987034"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.36106624,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"22","issue":"2","first_page":"1","last_page":"23"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8555999994277954,"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":0.8555999994277954,"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":0.04479999840259552,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.03500000014901161,"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/transformer","display_name":"Transformer","score":0.737500011920929},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.6790000200271606},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.5595999956130981},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5360999703407288},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4927000105381012},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4887000024318695},{"id":"https://openalex.org/keywords/feature-matching","display_name":"Feature matching","score":0.4814999997615814}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8371000289916992},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.737500011920929},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.6790000200271606},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5728999972343445},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.5595999956130981},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5360999703407288},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4927000105381012},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4887000024318695},{"id":"https://openalex.org/C2983787585","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature matching","level":3,"score":0.4814999997615814},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.45750001072883606},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4253000020980835},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.39649999141693115},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.3808000087738037},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33660000562667847},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.3271999955177307},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.3197000026702881},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.3158000111579895},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3109000027179718}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3779654","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3779654","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G606836358","display_name":null,"funder_award_id":"62406082, 62506085, 62406083, and 62394334","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7640065491","display_name":null,"funder_award_id":"2023A1515110650 and 2023A1515110659","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2185175083","https://openalex.org/W2481240925","https://openalex.org/W2778940641","https://openalex.org/W2962964995","https://openalex.org/W3007551217","https://openalex.org/W3010277541","https://openalex.org/W3035552787","https://openalex.org/W3035588244","https://openalex.org/W3092820619","https://openalex.org/W3155230099","https://openalex.org/W3175888430","https://openalex.org/W4312761738","https://openalex.org/W4319663732","https://openalex.org/W4385895960","https://openalex.org/W4385934203","https://openalex.org/W4386071498","https://openalex.org/W4386071687","https://openalex.org/W4386212021","https://openalex.org/W4392678259","https://openalex.org/W4393154592","https://openalex.org/W4400228558","https://openalex.org/W4400909772","https://openalex.org/W4402683843","https://openalex.org/W4402703046","https://openalex.org/W4402704615","https://openalex.org/W4402715976","https://openalex.org/W4402754177","https://openalex.org/W4403577365","https://openalex.org/W4403916192","https://openalex.org/W4405778998","https://openalex.org/W4406857611"],"related_works":[],"abstract_inverted_index":{"Recently,":[0],"most":[1],"image-text":[2],"matching":[3],"(ITM)":[4],"approaches":[5],"have":[6],"embraced":[7],"a":[8,73,122,134,160,248],"dual-stream":[9,110],"transformer":[10,209],"architecture":[11],"to":[12,55,82,126,164,184,190],"facilitate":[13],"the":[14,23,30,48,61,66,85,117,155,166,181,186,191,200,219,258],"learning":[15],"and":[16,35,90,139,171,207,224,239],"alignment":[17],"of":[18,25,137,213,222,265],"cross-modal":[19,187,214],"semantic":[20,31,188,211,220],"information.":[21],"Despite":[22],"efficacy":[24],"this":[26,94,266],"methodology":[27],"in":[28,46,146,174],"bridging":[29],"disparity":[32],"between":[33,88,169],"images":[34],"texts,":[36],"it":[37,43],"exhibits":[38],"two":[39,232],"primary":[40],"limitations.":[41],"Firstly,":[42],"falls":[44],"short":[45],"discriminating":[47],"nuanced":[49],"similarities":[50],"among":[51],"features,":[52],"which":[53],"leads":[54],"misleading":[56],"outcomes":[57],"or":[58],"even":[59],"compromises":[60],"overall":[62],"ITM":[63,260],"process.":[64],"Secondly,":[65],"conventional":[67],"triplet":[68],"training":[69],"paradigm":[70],"relies":[71],"on":[72,196,231,255],"pre-determined,":[74],"fixed":[75],"margin":[76,161,182],"coefficient,":[77],"thereby":[78,178],"impeding":[79],"its":[80],"capacity":[81],"accurately":[83],"gauge":[84],"similarity":[86,167],"relationships":[87],"positive":[89,170,223],"negative":[91,172,225],"samples.":[92,226],"In":[93],"article,":[95],"we":[96,120,158,198],"propose":[97],"high":[98,147],"feature":[99,123,148],"D":[100],"istinguishability":[101],"for":[102,150],"A":[103],"daptive":[104],"I":[105],"mage-text":[106],"M":[107],"atching":[108],"with":[109,133],"transformers":[111],"(termed":[112],"as":[113],"DAIM).":[114],"To":[115,153],"address":[116,154],"first":[118],"limitation,":[119,157],"design":[121],"discriminability":[124],"module":[125,163],"bring":[127],"similar":[128],"features":[129,142],"closer":[130],"together":[131],"but":[132],"certain":[135],"degree":[136],"distinction":[138],"push":[140],"dissimilar":[141],"farther":[143],"apart,":[144],"resulting":[145],"distinguishability":[149],"accurate":[151],"ITM.":[152],"second":[156],"devise":[159],"optimization":[162],"perceive":[165],"distribution":[168],"samples":[173],"real-time":[175],"during":[176],"training,":[177],"adaptively":[179,217],"adjusting":[180],"coefficient":[183],"minimize":[185],"gap":[189],"greatest":[192],"extent":[193],"possible.":[194],"Based":[195],"this,":[197],"align":[199],"multi-level":[201],"(i.e.,":[202],"representations":[203],"from":[204],"low-,":[205],"middle-,":[206],"high-layer":[208],"encoders)":[210],"information":[212],"data":[215],"by":[216],"optimizing":[218],"distributions":[221],"We":[227],"conduct":[228],"extensive":[229],"experiments":[230],"commonly":[233],"used":[234],"benchmark":[235],"datasets,":[236],"including":[237],"MSCOCO":[238],"Flickr30K.":[240],"Experimental":[241],"results":[242],"verify":[243],"that":[244],"DAIM":[245],"can":[246],"achieve":[247],"higher":[249],"performance":[250],"(e.g.,":[251],"4.7%":[252],"RSUM":[253],"gain":[254],"MSCOCO)":[256],"than":[257],"state-of-the-art":[259],"methods.":[261],"The":[262],"open-sourced":[263],"code":[264],"project":[267],"is":[268],"available":[269],"at:":[270],"https://github.com/Hudjkfhdsjfhdjkg/DAIM.git":[271],".":[272]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-12-09T00:00:00"}
