{"id":"https://openalex.org/W4388332081","doi":"https://doi.org/10.1145/3631356","title":"Cross-modal Semantically Augmented Network for Image-text Matching","display_name":"Cross-modal Semantically Augmented Network for Image-text Matching","publication_year":2023,"publication_date":"2023-11-04","ids":{"openalex":"https://openalex.org/W4388332081","doi":"https://doi.org/10.1145/3631356"},"language":"en","primary_location":{"id":"doi:10.1145/3631356","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3631356","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3631356","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":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3631356","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016755979","display_name":"Tao Yao","orcid":"https://orcid.org/0000-0003-2660-1050"},"institutions":[{"id":"https://openalex.org/I182707071","display_name":"Ludong University","ror":"https://ror.org/028h95t32","country_code":"CN","type":"education","lineage":["https://openalex.org/I182707071"]},{"id":"https://openalex.org/I4800084","display_name":"Southwest Jiaotong University","ror":"https://ror.org/00hn7w693","country_code":"CN","type":"education","lineage":["https://openalex.org/I4800084"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Yao","raw_affiliation_strings":["Department of Information and Electrical Engineering, Ludong University; Yantai Research Institute of New Generation Information Technology at Southwest Jiaotong University, China","Department of Information and Electrical Engineering, Ludong University"],"raw_orcid":"https://orcid.org/0000-0003-2660-1050","affiliations":[{"raw_affiliation_string":"Department of Information and Electrical Engineering, Ludong University; Yantai Research Institute of New Generation Information Technology at Southwest Jiaotong University, China","institution_ids":["https://openalex.org/I182707071","https://openalex.org/I4800084"]},{"raw_affiliation_string":"Department of Information and Electrical Engineering, Ludong University","institution_ids":["https://openalex.org/I182707071"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068075990","display_name":"Yiru Li","orcid":"https://orcid.org/0000-0002-0424-0357"},"institutions":[{"id":"https://openalex.org/I152031979","display_name":"Nanjing Normal University","ror":"https://ror.org/036trcv74","country_code":"CN","type":"education","lineage":["https://openalex.org/I152031979"]},{"id":"https://openalex.org/I182707071","display_name":"Ludong University","ror":"https://ror.org/028h95t32","country_code":"CN","type":"education","lineage":["https://openalex.org/I182707071"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiru Li","raw_affiliation_strings":["Department of Information and Electrical Engineering, Ludong University, China","School of Computer and Electronic Information and the School of Artificial Intelligence, Nanjing Normal University, China"],"raw_orcid":"https://orcid.org/0000-0002-0424-0357","affiliations":[{"raw_affiliation_string":"Department of Information and Electrical Engineering, Ludong University, China","institution_ids":["https://openalex.org/I182707071"]},{"raw_affiliation_string":"School of Computer and Electronic Information and the School of Artificial Intelligence, Nanjing Normal University, China","institution_ids":["https://openalex.org/I152031979"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100785621","display_name":"Ying Li","orcid":"https://orcid.org/0000-0002-5695-4706"},"institutions":[{"id":"https://openalex.org/I152031979","display_name":"Nanjing Normal University","ror":"https://ror.org/036trcv74","country_code":"CN","type":"education","lineage":["https://openalex.org/I152031979"]},{"id":"https://openalex.org/I182707071","display_name":"Ludong University","ror":"https://ror.org/028h95t32","country_code":"CN","type":"education","lineage":["https://openalex.org/I182707071"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Li","raw_affiliation_strings":["Department of Information and Electrical Engineering, Ludong University, China","School of Computer and Electronic Information and the School of Artificial Intelligence, Nanjing Normal University, China"],"raw_orcid":"https://orcid.org/0000-0002-5695-4706","affiliations":[{"raw_affiliation_string":"Department of Information and Electrical Engineering, Ludong University, China","institution_ids":["https://openalex.org/I182707071"]},{"raw_affiliation_string":"School of Computer and Electronic Information and the School of Artificial Intelligence, Nanjing Normal University, China","institution_ids":["https://openalex.org/I152031979"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068185303","display_name":"Yingying Zhu","orcid":"https://orcid.org/0000-0002-3475-6186"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingying Zhu","raw_affiliation_strings":["School of Computer and Software, Shenzhen University, China"],"raw_orcid":"https://orcid.org/0000-0002-3475-6186","affiliations":[{"raw_affiliation_string":"School of Computer and Software, Shenzhen University, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100367306","display_name":"Gang Wang","orcid":"https://orcid.org/0000-0001-6759-1616"},"institutions":[{"id":"https://openalex.org/I182707071","display_name":"Ludong University","ror":"https://ror.org/028h95t32","country_code":"CN","type":"education","lineage":["https://openalex.org/I182707071"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gang Wang","raw_affiliation_strings":["Department of Information and Electrical Engineering, Ludong University, China"],"raw_orcid":"https://orcid.org/0000-0001-6759-1616","affiliations":[{"raw_affiliation_string":"Department of Information and Electrical Engineering, Ludong University, China","institution_ids":["https://openalex.org/I182707071"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101842071","display_name":"Jun Yue","orcid":"https://orcid.org/0009-0004-6458-2510"},"institutions":[{"id":"https://openalex.org/I182707071","display_name":"Ludong University","ror":"https://ror.org/028h95t32","country_code":"CN","type":"education","lineage":["https://openalex.org/I182707071"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Yue","raw_affiliation_strings":["Department of Information and Electrical Engineering, Ludong University, China"],"raw_orcid":"https://orcid.org/0009-0004-6458-2510","affiliations":[{"raw_affiliation_string":"Department of Information and Electrical Engineering, Ludong University, China","institution_ids":["https://openalex.org/I182707071"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9688,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.7424444,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"20","issue":"4","first_page":"1","last_page":"18"},"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":0.9994999766349792,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.996999979019165,"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":0.8318773508071899},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6633836627006531},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6412128210067749},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.6321613192558289},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6096723675727844},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5834683179855347},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5587674379348755},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5546207427978516},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5501589775085449},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5200300216674805},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5167590975761414},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4776800274848938},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4396430253982544},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.4245506227016449},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.22315213084220886},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08363282680511475}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8318773508071899},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6633836627006531},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6412128210067749},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.6321613192558289},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6096723675727844},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5834683179855347},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5587674379348755},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5546207427978516},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5501589775085449},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5200300216674805},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5167590975761414},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4776800274848938},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4396430253982544},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.4245506227016449},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.22315213084220886},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08363282680511475},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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},{"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3631356","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3631356","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3631356","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":{"id":"doi:10.1145/3631356","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3631356","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3631356","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"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.75}],"awards":[{"id":"https://openalex.org/G4406913046","display_name":null,"funder_award_id":"62102186","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5895949093","display_name":null,"funder_award_id":"ZR2023MF031","funder_id":"https://openalex.org/F4320324174","funder_display_name":"Natural Science Foundation of Shandong Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320324174","display_name":"Natural Science Foundation of Shandong Province","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4388332081.pdf","grobid_xml":"https://content.openalex.org/works/W4388332081.grobid-xml"},"referenced_works_count":69,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1591801644","https://openalex.org/W1949478088","https://openalex.org/W2064675550","https://openalex.org/W2157331557","https://openalex.org/W2169813655","https://openalex.org/W2266728343","https://openalex.org/W2531563875","https://openalex.org/W2613718673","https://openalex.org/W2744745684","https://openalex.org/W2774267535","https://openalex.org/W2795832645","https://openalex.org/W2800732852","https://openalex.org/W2906146234","https://openalex.org/W2909384861","https://openalex.org/W2911695497","https://openalex.org/W2922521335","https://openalex.org/W2944466654","https://openalex.org/W2945524220","https://openalex.org/W2956018683","https://openalex.org/W2962813473","https://openalex.org/W2962964995","https://openalex.org/W2963389687","https://openalex.org/W2963467339","https://openalex.org/W2964216321","https://openalex.org/W2981448908","https://openalex.org/W2982065678","https://openalex.org/W2982078236","https://openalex.org/W2982905682","https://openalex.org/W2987671777","https://openalex.org/W2988823324","https://openalex.org/W2997143100","https://openalex.org/W2999606372","https://openalex.org/W3005971801","https://openalex.org/W3007952981","https://openalex.org/W3008072721","https://openalex.org/W3010277541","https://openalex.org/W3030772386","https://openalex.org/W3035454331","https://openalex.org/W3035605030","https://openalex.org/W3085694362","https://openalex.org/W3094172275","https://openalex.org/W3110042533","https://openalex.org/W3113055207","https://openalex.org/W3120181862","https://openalex.org/W3131251978","https://openalex.org/W3159088493","https://openalex.org/W3172636346","https://openalex.org/W3175888430","https://openalex.org/W3178075329","https://openalex.org/W3189718596","https://openalex.org/W3190055600","https://openalex.org/W3196486313","https://openalex.org/W3201835075","https://openalex.org/W3206477365","https://openalex.org/W3207267030","https://openalex.org/W3211258519","https://openalex.org/W3213100861","https://openalex.org/W4206314411","https://openalex.org/W4206430846","https://openalex.org/W4206546481","https://openalex.org/W4210593721","https://openalex.org/W4236965008","https://openalex.org/W4312761738","https://openalex.org/W4313429809","https://openalex.org/W4321793523","https://openalex.org/W4379382581","https://openalex.org/W4386388510","https://openalex.org/W6635446068"],"related_works":["https://openalex.org/W2965546495","https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W2761785940","https://openalex.org/W2487162673","https://openalex.org/W2942366970","https://openalex.org/W2110523656"],"abstract_inverted_index":{"Image-text":[0],"matching":[1,190],"plays":[2],"an":[3,125,165],"important":[4],"role":[5],"in":[6,53,110,119],"solving":[7],"the":[8,39,50,54,61,66,70,73,106,111,114,120,132,171,174,179,189],"problem":[9],"of":[10,69,116,173],"cross-modal":[11],"information":[12,68,75],"processing.":[13],"Since":[14],"there":[15],"are":[16,56,76],"nonnegligible":[17],"semantic":[18,175],"differences":[19],"between":[20,41,108],"heterogenous":[21],"pairwise":[22],"data,":[23],"a":[24,31,95,159],"crucial":[25],"challenge":[26],"is":[27],"how":[28],"to":[29,79,181],"learn":[30],"unified":[32],"representation.":[33],"Existing":[34],"methods":[35],"mainly":[36],"rely":[37],"on":[38],"alignment":[40,83,86,162,167],"regional":[42,51],"image":[43,55,112,151],"features":[44,52,152],"and":[45,65,72,84,144,164,186],"corresponding":[46],"entity":[47,63,138],"words.":[48],"However,":[49],"often":[57],"more":[58,183],"concerned":[59],"with":[60,113],"foreground":[62],"information,":[64,176],"attribute":[67,140],"entities":[71,109],"relational":[74,117],"ignored.":[77],"How":[78],"effectively":[80],"integrate":[81],"entity-attribute":[82,166],"relationship":[85,161],"has":[87],"not":[88],"been":[89],"fully":[90],"studied.":[91],"Therefore,":[92],"we":[93],"propose":[94],"Cross-Modal":[96],"Semantically":[97],"Augmented":[98],"Network":[99],"for":[100],"Image-Text":[101],"Matching":[102],"(CMSAN),":[103],"which":[104,177],"combines":[105],"relationships":[107],"semantics":[115],"words":[118,133],"text.":[121],"CMSAN":[122,156],"(1)":[123],"proposes":[124],"adaptive":[126],"word-type":[127],"prediction":[128],"model":[129,180],"that":[130,169],"classifies":[131],"into":[134],"four":[135],"types,":[136],"i.e.,":[137],"word,":[139,141,143],"relation":[142],"unnecessary":[145],"word.":[146],"It":[147],"can":[148],"align":[149],"different":[150],"at":[153],"multiple":[154],"levels.":[155],"(2)":[157],"designs":[158],"sophisticated":[160],"module":[163,168],"maximizes":[170],"exploitation":[172],"enables":[178],"have":[182],"discriminative":[184],"power":[185],"further":[187],"improves":[188],"accuracy.":[191]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}