{"id":"https://openalex.org/W4385895960","doi":"https://doi.org/10.1145/3581783.3612427","title":"Unifying Two-Stream Encoders with Transformers for Cross-Modal Retrieval","display_name":"Unifying Two-Stream Encoders with Transformers for Cross-Modal Retrieval","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4385895960","doi":"https://doi.org/10.1145/3581783.3612427"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612427","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612427","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2308.04343","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024408423","display_name":"Yi Bin","orcid":"https://orcid.org/0000-0001-9714-8738"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yi Bin","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-9714-8738","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100629473","display_name":"Haoxuan Li","orcid":"https://orcid.org/0009-0005-1355-6256"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoxuan Li","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0009-0005-1355-6256","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014129038","display_name":"Yahui Xu","orcid":"https://orcid.org/0000-0002-1123-6129"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yahui Xu","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-1123-6129","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009074046","display_name":"Xing Xu","orcid":"https://orcid.org/0000-0001-5685-3123"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xing Xu","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0001-5685-3123","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100397616","display_name":"Yang Yang","orcid":"https://orcid.org/0000-0002-5070-4511"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Yang","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-5070-4511","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052993469","display_name":"Heng Tao Shen","orcid":"https://orcid.org/0000-0002-2999-2088"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heng Tao Shen","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-2999-2088","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":33,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3041","last_page":"3050"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9991999864578247,"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":0.9983999729156494,"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":0.7987934350967407},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7608356475830078},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6691019535064697},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5075644254684448},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49064794182777405},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4895373284816742},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.379438579082489},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3456486463546753},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3400493264198303},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3273223638534546},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.09363201260566711}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7987934350967407},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7608356475830078},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6691019535064697},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5075644254684448},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49064794182777405},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4895373284816742},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.379438579082489},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3456486463546753},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3400493264198303},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3273223638534546},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.09363201260566711},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3581783.3612427","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612427","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2308.04343","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2308.04343","pdf_url":"https://arxiv.org/pdf/2308.04343","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2308.04343","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2308.04343","pdf_url":"https://arxiv.org/pdf/2308.04343","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5199999809265137}],"awards":[{"id":"https://openalex.org/G1294623083","display_name":null,"funder_award_id":"62220106008","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2464018058","display_name":null,"funder_award_id":"U20B2063","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8300731329","display_name":null,"funder_award_id":"62102070, 62220106008, U20B2063","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8836073055","display_name":null,"funder_award_id":"62102070","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320320709","display_name":"National Research Foundation Singapore","ror":"https://ror.org/03cpyc314"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385895960.pdf","grobid_xml":"https://content.openalex.org/works/W4385895960.grobid-xml"},"referenced_works_count":84,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1522301498","https://openalex.org/W1527575280","https://openalex.org/W1614298861","https://openalex.org/W1849277567","https://openalex.org/W1889081078","https://openalex.org/W1905882502","https://openalex.org/W1933349210","https://openalex.org/W1957706851","https://openalex.org/W2006031689","https://openalex.org/W2020842694","https://openalex.org/W2070753207","https://openalex.org/W2102605133","https://openalex.org/W2106277773","https://openalex.org/W2115752676","https://openalex.org/W2123024445","https://openalex.org/W2133564696","https://openalex.org/W2138118304","https://openalex.org/W2185175083","https://openalex.org/W2187089797","https://openalex.org/W2190008860","https://openalex.org/W2194775991","https://openalex.org/W2765440071","https://openalex.org/W2766237723","https://openalex.org/W2774267535","https://openalex.org/W2778940641","https://openalex.org/W2883311563","https://openalex.org/W2887712318","https://openalex.org/W2896457183","https://openalex.org/W2962964995","https://openalex.org/W2963026768","https://openalex.org/W2963351113","https://openalex.org/W2970597249","https://openalex.org/W2972312591","https://openalex.org/W2981586349","https://openalex.org/W2981852735","https://openalex.org/W2982078236","https://openalex.org/W2982260486","https://openalex.org/W2988823324","https://openalex.org/W2990428574","https://openalex.org/W2994818707","https://openalex.org/W2996428491","https://openalex.org/W2997525715","https://openalex.org/W2998215884","https://openalex.org/W3003735286","https://openalex.org/W3005971801","https://openalex.org/W3010277541","https://openalex.org/W3026458074","https://openalex.org/W3029678209","https://openalex.org/W3034445277","https://openalex.org/W3034999214","https://openalex.org/W3035454331","https://openalex.org/W3035552787","https://openalex.org/W3035588244","https://openalex.org/W3035605030","https://openalex.org/W3091588028","https://openalex.org/W3092820619","https://openalex.org/W3094502228","https://openalex.org/W3100308117","https://openalex.org/W3138516171","https://openalex.org/W3155230099","https://openalex.org/W3171516518","https://openalex.org/W3175888430","https://openalex.org/W3206675006","https://openalex.org/W3206723373","https://openalex.org/W3211490618","https://openalex.org/W4225681728","https://openalex.org/W4287547182","https://openalex.org/W4288086191","https://openalex.org/W4288089799","https://openalex.org/W4288102874","https://openalex.org/W4292779060","https://openalex.org/W4300954432","https://openalex.org/W4310671573","https://openalex.org/W4312761738","https://openalex.org/W4313156423","https://openalex.org/W4313855701","https://openalex.org/W4317796337","https://openalex.org/W4319663732","https://openalex.org/W4385245566","https://openalex.org/W4385934203","https://openalex.org/W4386071847","https://openalex.org/W6600688380","https://openalex.org/W6601676141"],"related_works":["https://openalex.org/W4390516098","https://openalex.org/W2181948922","https://openalex.org/W2384362569","https://openalex.org/W2142795561","https://openalex.org/W4205302943","https://openalex.org/W2561132942","https://openalex.org/W3155418658","https://openalex.org/W4243199227","https://openalex.org/W2379948177","https://openalex.org/W2334580170"],"abstract_inverted_index":{"Most":[0],"existing":[1],"cross-modal":[2,81],"retrieval":[3,82],"methods":[4],"employ":[5],"two-stream":[6,87],"encoders":[7,113],"with":[8,72,117],"different":[9,29,152],"architectures":[10,26,71],"for":[11,17,21,74,121],"images":[12,18,38,48,122,155],"and":[13,19,33,39,41,49,103,123,125,129,156,175,196,202,211,213],"texts,":[14,40,124],"e.g.,":[15],"CNN":[16],"RNN/Transformer":[20],"texts.":[22,50,157],"Such":[23],"discrepancy":[24],"in":[25,44,62],"may":[27],"induce":[28],"semantic":[30],"distribution":[31],"spaces":[32],"limit":[34],"the":[35,69,112,127,138,160,163],"interactions":[36,128],"between":[37,47,131,154],"further":[42],"result":[43],"inferior":[45],"alignment":[46,106,145],"To":[51,158],"fill":[52],"this":[53],"research":[54],"gap,":[55],"inspired":[56],"by":[57,185],"recent":[58],"advances":[59],"of":[60,96,151,162,207],"Transformers":[61,73,92],"vision":[63],"tasks,":[64,193],"we":[65,78,141,166],"propose":[66],"to":[67,136,147],"unify":[68],"encoder":[70],"both":[75],"modalities.":[76],"Specifically,":[77,189],"design":[79],"a":[80,100,104,143,186],"framework":[83],"purely":[84],"based":[85],"on":[86,170,190,209,215],"Transformers,":[88],"dubbed":[89],"Hierarchical":[90],"Alignment":[91],"(HAT),":[93],"which":[94],"consists":[95],"an":[97],"image":[98],"Transformer,":[99,102],"text":[101],"hierarchical":[105,144],"module.":[107],"With":[108],"such":[109],"identical":[110],"architectures,":[111],"could":[114],"produce":[115],"representations":[116],"more":[118],"similar":[119],"characteristics":[120],"make":[126],"alignments":[130],"them":[132],"much":[133],"easier.":[134],"Besides,":[135],"leverage":[137],"rich":[139],"semantics,":[140],"devise":[142],"scheme":[146],"explore":[148],"multi-level":[149],"correspondences":[150],"layers":[153],"evaluate":[159],"effectiveness":[161],"proposed":[164],"HAT,":[165],"conduct":[167],"extensive":[168],"experiments":[169],"two":[171,191],"benchmark":[172],"datasets,":[173],"MSCOCO":[174],"Flickr30K.":[176],"Experimental":[177],"results":[178],"demonstrate":[179],"that":[180],"HAT":[181,199],"outperforms":[182],"SOTA":[183],"baselines":[184],"large":[187],"margin.":[188],"key":[192],"i.e.,":[194],"image-to-text":[195],"text-to-image":[197],"retrieval,":[198],"achieves":[200],"7.6%":[201],"16.7%":[203],"relative":[204],"score":[205],"improvement":[206],"Recall@1":[208],"MSCOCO,":[210],"4.4%":[212],"11.6%":[214],"Flickr30k":[216],"respectively.":[217],"The":[218],"code":[219],"is":[220],"available":[221],"at":[222],"https://github.com/LuminosityX/HAT.":[223]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}