{"id":"https://openalex.org/W4406761700","doi":"https://doi.org/10.1145/3714431","title":"<i>Hire</i> : Hybrid-Modal Interaction with Multiple Relational Enhancements for Image-Text Matching","display_name":"<i>Hire</i> : Hybrid-Modal Interaction with Multiple Relational Enhancements for Image-Text Matching","publication_year":2025,"publication_date":"2025-01-23","ids":{"openalex":"https://openalex.org/W4406761700","doi":"https://doi.org/10.1145/3714431"},"language":"en","primary_location":{"id":"doi:10.1145/3714431","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3714431","pdf_url":null,"source":{"id":"https://openalex.org/S2492086750","display_name":"ACM Transactions on Intelligent Systems and Technology","issn_l":"2157-6904","issn":["2157-6904","2157-6912"],"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 Intelligent Systems and Technology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://eprints.gla.ac.uk/view/author/60445.html>","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026473068","display_name":"Xuri Ge","orcid":"https://orcid.org/0000-0002-3925-4951"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]},{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["CN","GB"],"is_corresponding":true,"raw_author_name":"Xuri Ge","raw_affiliation_strings":["School of Artificial Intelligence, Shandong University, Jinan, China and University of Glasgow, Glasgow, United Kingdom of Great Britain and Northern Ireland","Shandong University, China and University of Glasgow, UK"],"raw_orcid":"https://orcid.org/0000-0002-3925-4951","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Shandong University, Jinan, China and University of Glasgow, Glasgow, United Kingdom of Great Britain and Northern Ireland","institution_ids":["https://openalex.org/I7882870"]},{"raw_affiliation_string":"Shandong University, China and University of Glasgow, UK","institution_ids":["https://openalex.org/I7882870","https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008400844","display_name":"Fuhai Chen","orcid":"https://orcid.org/0000-0001-5441-5998"},"institutions":[{"id":"https://openalex.org/I80947539","display_name":"Fuzhou University","ror":"https://ror.org/011xvna82","country_code":"CN","type":"education","lineage":["https://openalex.org/I80947539"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fuhai Chen","raw_affiliation_strings":["College of Computer and Data Science, Fuzhou University, Fuzhou, China","Fuzhou University, China"],"raw_orcid":"https://orcid.org/0000-0001-5441-5998","affiliations":[{"raw_affiliation_string":"College of Computer and Data Science, Fuzhou University, Fuzhou, China","institution_ids":["https://openalex.org/I80947539"]},{"raw_affiliation_string":"Fuzhou University, China","institution_ids":["https://openalex.org/I80947539"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029582812","display_name":"Songpei Xu","orcid":"https://orcid.org/0009-0001-5735-8674"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Songpei Xu","raw_affiliation_strings":["School of Computing Science, University of Glasgow, Glasgow, United Kingdom of Great Britain and Northern Ireland","University of Glasgow, UK"],"raw_orcid":"https://orcid.org/0009-0001-5735-8674","affiliations":[{"raw_affiliation_string":"School of Computing Science, University of Glasgow, Glasgow, United Kingdom of Great Britain and Northern Ireland","institution_ids":["https://openalex.org/I7882870"]},{"raw_affiliation_string":"University of Glasgow, UK","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087089516","display_name":"Fuxiang Tao","orcid":"https://orcid.org/0009-0007-5729-9014"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Fuxiang Tao","raw_affiliation_strings":["Department of Computer Science, The University of Sheffield, Sheffield, United Kingdom of Great Britain and Northern Ireland","The University of Sheffield, UK"],"raw_orcid":"https://orcid.org/0009-0007-5729-9014","affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Sheffield, Sheffield, United Kingdom of Great Britain and Northern Ireland","institution_ids":["https://openalex.org/I91136226"]},{"raw_affiliation_string":"The University of Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100440215","display_name":"Jie Wang","orcid":"https://orcid.org/0009-0005-7117-8580"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jie Wang","raw_affiliation_strings":["School of Computing Science, University of Glasgow, Glasgow, United Kingdom of Great Britain and Northern Ireland","University of Glasgow, UK"],"raw_orcid":"https://orcid.org/0009-0005-7117-8580","affiliations":[{"raw_affiliation_string":"School of Computing Science, University of Glasgow, Glasgow, United Kingdom of Great Britain and Northern Ireland","institution_ids":["https://openalex.org/I7882870"]},{"raw_affiliation_string":"University of Glasgow, UK","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069702331","display_name":"Joemon M. Jose","orcid":"https://orcid.org/0000-0001-9228-1759"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Joemon M. Jose","raw_affiliation_strings":["University of Glasgow, Glasgow, United Kingdom of Great Britain and Northern Ireland","University of Glasgow, UK"],"raw_orcid":"https://orcid.org/0000-0001-9228-1759","affiliations":[{"raw_affiliation_string":"University of Glasgow, Glasgow, United Kingdom of Great Britain and Northern Ireland","institution_ids":["https://openalex.org/I7882870"]},{"raw_affiliation_string":"University of Glasgow, UK","institution_ids":["https://openalex.org/I7882870"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5026473068"],"corresponding_institution_ids":["https://openalex.org/I154099455","https://openalex.org/I7882870"],"apc_list":null,"apc_paid":null,"fwci":3.3997,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.91012895,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"16","issue":"3","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":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":0.994700014591217,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9929999709129333,"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":0.9014819860458374},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.7093438506126404},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.6253069639205933},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5962391495704651},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5603069067001343},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4420483708381653},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4078959822654724},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3521769642829895},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.32584959268569946}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9014819860458374},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7093438506126404},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6253069639205933},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5962391495704651},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5603069067001343},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4420483708381653},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4078959822654724},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3521769642829895},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32584959268569946},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3714431","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3714431","pdf_url":null,"source":{"id":"https://openalex.org/S2492086750","display_name":"ACM Transactions on Intelligent Systems and Technology","issn_l":"2157-6904","issn":["2157-6904","2157-6912"],"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 Intelligent Systems and Technology","raw_type":"journal-article"},{"id":"pmh:oai:eprints.gla.ac.uk:345520","is_oa":true,"landing_page_url":"https://eprints.gla.ac.uk/view/author/60445.html>","pdf_url":null,"source":{"id":"https://openalex.org/S4210235606","display_name":"ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam)","issn_l":"2622-8912","issn":["2622-8912","2622-8920"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"}],"best_oa_location":{"id":"pmh:oai:eprints.gla.ac.uk:345520","is_oa":true,"landing_page_url":"https://eprints.gla.ac.uk/view/author/60445.html>","pdf_url":null,"source":{"id":"https://openalex.org/S4210235606","display_name":"ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam)","issn_l":"2622-8912","issn":["2622-8912","2622-8920"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W1931639407","https://openalex.org/W2185175083","https://openalex.org/W2250861254","https://openalex.org/W2552161745","https://openalex.org/W2560920409","https://openalex.org/W2606473278","https://openalex.org/W2745461083","https://openalex.org/W2798354744","https://openalex.org/W2897195437","https://openalex.org/W2963389687","https://openalex.org/W2963536419","https://openalex.org/W2964120214","https://openalex.org/W2964276596","https://openalex.org/W2967957126","https://openalex.org/W2982078236","https://openalex.org/W2994818707","https://openalex.org/W2998356391","https://openalex.org/W3005971801","https://openalex.org/W3010277541","https://openalex.org/W3035309251","https://openalex.org/W3035454331","https://openalex.org/W3035552787","https://openalex.org/W3035588244","https://openalex.org/W3094172275","https://openalex.org/W3110042533","https://openalex.org/W3118694826","https://openalex.org/W3152619510","https://openalex.org/W3155230099","https://openalex.org/W3175888430","https://openalex.org/W3203447128","https://openalex.org/W4205811793","https://openalex.org/W4210894218","https://openalex.org/W4213348104","https://openalex.org/W4214819138","https://openalex.org/W4283805294","https://openalex.org/W4309337107","https://openalex.org/W4312761738","https://openalex.org/W4386071498","https://openalex.org/W4387968071","https://openalex.org/W4392977092","https://openalex.org/W4393942911","https://openalex.org/W4394593157","https://openalex.org/W4400528838","https://openalex.org/W4400530533"],"related_works":["https://openalex.org/W1972035260","https://openalex.org/W2379392295","https://openalex.org/W3160965418","https://openalex.org/W613940353","https://openalex.org/W2320915480","https://openalex.org/W4301594054","https://openalex.org/W2794488505","https://openalex.org/W2362990116","https://openalex.org/W2381300099","https://openalex.org/W2714992399"],"abstract_inverted_index":{"Image-Text":[0],"Matching":[1],"(ITM)":[2],"is":[3,108,214],"a":[4,70],"fundamental":[5],"problem":[6],"in":[7,14],"computer":[8],"vision.":[9],"The":[10],"key":[11],"issue":[12],"lies":[13],"jointly":[15,169],"learning":[16],"the":[17,44,48,53,58,84,101,112,127,131,153,161,179,184,190,205,220],"visual":[18,116,162,191],"and":[19,86,91,95,121,135,163,174,197,211,229],"textual":[20,164,185],"representation":[21,50,114,193],"to":[22,110,151],"estimate":[23],"their":[24,136],"similarity":[25],"accurately.":[26],"Most":[27],"existing":[28],"methods":[29],"focus":[30],"on":[31,52,227],"feature":[32,37],"enhancement":[33],"within":[34],"modality":[35],"or":[36],"interaction":[38,208],"across":[39],"modalities,":[40],"which,":[41],"however,":[42],"neglects":[43],"contextual":[45,63,113],"information":[46],"of":[47,115,130,156,181],"object":[49],"based":[51],"inter-object":[54],"relationships":[55,129],"that":[56,204],"match":[57],"corresponding":[59],"sentences":[60],"with":[61,73,93,118,183,209],"rich":[62],"semantics.":[64],"In":[65,99],"this":[66],"article,":[67],"we":[68,187],"propose":[69],"Hybrid-modal":[71],"Interaction":[72],"multiple":[74],"Relational":[75],"Enhancements":[76],"(termed":[77],"Hire":[78,222],")":[79],"for":[80,144,217],"ITM,":[81],"which":[82],"correlates":[83],"intra-":[85],"inter-modal":[87,171],"semantics":[88],"between":[89],"objects":[90,117,182],"words":[92],"implicit":[94,141,210],"explicit":[96,102,128,149,157,212],"relationship":[97,142,146,158],"modeling.":[98],"particular,":[100],"intra-modal":[103],"spatial-semantic":[104],"graph-based":[105],"reasoning":[106],"network":[107],"designed":[109],"improve":[111,152],"salient":[119],"spatial":[120,133],"semantic":[122,165,192],"relational":[123],"connectivities,":[124],"guided":[125],"by":[126],"objects\u2019":[132],"positions":[134],"scene":[137],"graph.":[138],"We":[139],"use":[140],"modeling":[143,150,213],"potential":[145],"interactions":[147],"before":[148],"fault":[154],"tolerance":[155],"detection.":[159],"Then":[160],"representations":[166],"are":[167],"refined":[168],"via":[170,194],"interactive":[172,199],"attention":[173],"cross-modal":[175],"alignment.":[176],"To":[177],"correlate":[178],"context":[180],"context,":[186],"further":[188],"refine":[189],"cross-level":[195],"object-sentence":[196],"word-image-based":[198],"attention.":[200],"Extensive":[201],"experiments":[202],"validate":[203],"proposed":[206,221],"hybrid-modal":[207],"more":[215],"beneficial":[216],"ITM.":[218],"And":[219],"obtains":[223],"new":[224],"state-of-the-art":[225],"results":[226],"MS-COCO":[228],"Flickr30K":[230],"benchmarks.":[231]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}