{"id":"https://openalex.org/W4392152051","doi":"https://doi.org/10.1109/tmm.2024.3369968","title":"A Mutually Textual and Visual Refinement Network for Image-Text Matching","display_name":"A Mutually Textual and Visual Refinement Network for Image-Text Matching","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4392152051","doi":"https://doi.org/10.1109/tmm.2024.3369968"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2024.3369968","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2024.3369968","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","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/A5006557413","display_name":"Shanmin Pang","orcid":"https://orcid.org/0000-0001-7217-864X"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shanmin Pang","raw_affiliation_strings":["School of Software Engineering, Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0001-7217-864X","affiliations":[{"raw_affiliation_string":"School of Software Engineering, Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101471837","display_name":"Yueyang Zeng","orcid":"https://orcid.org/0009-0006-3045-7628"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yueyang Zeng","raw_affiliation_strings":["School of Software Engineering, Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":"https://orcid.org/0009-0006-3045-7628","affiliations":[{"raw_affiliation_string":"School of Software Engineering, Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114585466","display_name":"Jiawei Zhao","orcid":"https://orcid.org/0009-0001-0204-7932"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiawei Zhao","raw_affiliation_strings":["School of Software Engineering, Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":"https://orcid.org/0009-0001-0204-7932","affiliations":[{"raw_affiliation_string":"School of Software Engineering, Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024309592","display_name":"Jianru Xue","orcid":"https://orcid.org/0000-0002-4994-9343"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianru Xue","raw_affiliation_strings":["School of Artificial Intelligence, Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0002-4994-9343","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I87445476"],"apc_list":null,"apc_paid":null,"fwci":4.4781,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.96042304,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"26","issue":null,"first_page":"7555","last_page":"7566"},"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":0.9980999827384949,"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/T11439","display_name":"Video Analysis and Summarization","score":0.995199978351593,"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":0.8673243522644043},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5258265733718872},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.520294725894928},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.426460862159729},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3917626738548279},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.37577784061431885},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3413376212120056}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8673243522644043},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5258265733718872},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.520294725894928},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.426460862159729},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3917626738548279},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.37577784061431885},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3413376212120056},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/tmm.2024.3369968","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2024.3369968","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.49000000953674316}],"awards":[{"id":"https://openalex.org/G6046388461","display_name":"\u9762\u5411\u8bed\u4e49\u5173\u8054\u7684\u5c42\u6b21\u5316\u89c6\u89c9\u8868\u793a\u65b9\u6cd5\u7814\u7a76","funder_award_id":"61972312","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":57,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W1931639407","https://openalex.org/W1957706851","https://openalex.org/W2105482032","https://openalex.org/W2123442489","https://openalex.org/W2185175083","https://openalex.org/W2277195237","https://openalex.org/W2539338396","https://openalex.org/W2546696630","https://openalex.org/W2552579943","https://openalex.org/W2731821979","https://openalex.org/W2745461083","https://openalex.org/W2778100917","https://openalex.org/W2896457183","https://openalex.org/W2956018683","https://openalex.org/W2962964995","https://openalex.org/W2963389687","https://openalex.org/W2963966654","https://openalex.org/W2965809241","https://openalex.org/W2981586349","https://openalex.org/W2982078236","https://openalex.org/W2994818707","https://openalex.org/W2996478685","https://openalex.org/W2997525715","https://openalex.org/W3005881764","https://openalex.org/W3010277541","https://openalex.org/W3035454331","https://openalex.org/W3035552787","https://openalex.org/W3035588244","https://openalex.org/W3088460296","https://openalex.org/W3090449556","https://openalex.org/W3118694826","https://openalex.org/W3175888430","https://openalex.org/W3189718596","https://openalex.org/W3190055600","https://openalex.org/W3206477365","https://openalex.org/W3213100861","https://openalex.org/W4200528395","https://openalex.org/W4206314411","https://openalex.org/W4210894218","https://openalex.org/W4213348104","https://openalex.org/W4214819138","https://openalex.org/W4282937133","https://openalex.org/W4283812943","https://openalex.org/W4312761738","https://openalex.org/W4319663732","https://openalex.org/W4321607993","https://openalex.org/W4385245566","https://openalex.org/W4386071498","https://openalex.org/W4386071757","https://openalex.org/W4386075677","https://openalex.org/W6747225742","https://openalex.org/W6798805250","https://openalex.org/W6804095316","https://openalex.org/W6811013733"],"related_works":["https://openalex.org/W1972035260","https://openalex.org/W4301594054","https://openalex.org/W2794488505","https://openalex.org/W3125889879","https://openalex.org/W3124422538","https://openalex.org/W2295467472","https://openalex.org/W2097909533","https://openalex.org/W3125188128","https://openalex.org/W2144398666","https://openalex.org/W3122481182"],"abstract_inverted_index":{"Image-text":[0],"matching":[1,137,216],"is":[2,13,38,250],"vital":[3],"important":[4],"in":[5,15,81,142,148],"the":[6,34,59,62,90,93,102,126,152,169,207,214,220],"field":[7],"of":[8,61,92,194,209,240],"multi-modal":[9],"intelligence.":[10],"Recently,":[11],"it":[12],"advocated":[14],"a":[16,32,69,116,132,160,185],"way":[17],"that":[18,98,163,190,248],"decomposes":[19],"images":[20,149],"and":[21,26,119,197,222,230,235,244],"texts":[22],"into":[23,168],"local":[24,195,221],"fragments":[25],"followed":[27],"by":[28,40,138],"region-word":[29,46],"aligning.":[30],"As":[31],"result,":[33],"image-text":[35,215],"relevance":[36],"score":[37],"given":[39],"aggregating":[41],"semantic":[42,82,96,104,146,186,203],"similarities":[43,218],"between":[44,233],"matched":[45],"pairs.":[47],"Despite":[48],"effectiveness,":[49],"this":[50,109,112],"strategy":[51],"fails":[52],"to":[53,124,150,172,200,227,252],"express":[54],"data":[55],"relations":[56],"exactly.":[57],"From":[58,89],"perspective":[60,91],"text":[63,65,170,175,198],"side,":[64,95],"words":[66],"decomposed":[67],"from":[68],"concise":[70],"language":[71],"sentence":[72],"usually":[73],"have":[74],"limited":[75],"contextual":[76,140,166],"information,":[77],"which":[78],"can":[79,106],"result":[80],"identical":[83],"but":[84],"actually":[85],"false":[86],"text-region":[87],"alignments.":[88],"image":[94,196,204,211],"ambiguity":[97,147],"multiple":[99],"objects":[100],"share":[101],"same":[103],"meaning":[105],"further":[107,183],"exacerbate":[108],"problem.":[110,130],"In":[111,131],"manuscript,":[113],"we":[114,158,182],"introduce":[115],"mutually":[117],"Textual":[118],"Visual":[120],"Refinement":[121],"Network":[122],"(TVRN),":[123],"tackle":[125],"inaccurate":[127],"cross-modal":[128],"alignment":[129,187],"nutshell,":[133],"TVRN":[134,249],"improves":[135],"inter-modal":[136],"improving":[139],"information":[141],"sentences":[143],"meanwhile":[144],"reduces":[145],"capture":[151,228],"maximized":[153],"relevant":[154],"relations.":[155],"More":[156],"specifically,":[157],"develop":[159],"new":[161],"module":[162,189],"integrates":[164],"visual":[165],"clues":[167],"modality":[171],"generate":[173],"informational":[174],"features":[176,199],"with":[177,206],"richer":[178],"geometric":[179],"contexts.":[180],"Mutually,":[181],"design":[184],"enhancement":[188],"leverages":[191],"consensus":[192],"affinity":[193],"guide":[201],"deeper":[202],"embedding":[205],"supervision":[208],"global":[210,223],"vectors.":[212],"At":[213],"stage,":[217],"at":[219],"levels":[224],"are":[225],"integrated":[226],"coarse-grained":[229],"fine-grained":[231],"interactions":[232],"vision":[234],"language.":[236],"A":[237],"large":[238],"number":[239],"experiments":[241],"on":[242],"Flickr30K":[243],"MS-COCO":[245],"benchmarks":[246],"demonstrate":[247],"superior":[251],"existing":[253],"methods.":[254]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-16T13:24:37.021932","created_date":"2025-10-10T00:00:00"}