{"id":"https://openalex.org/W4391490506","doi":"https://doi.org/10.1145/3603273.3635666","title":"ISES: Instance-level Semantic Enhanced Score Model for Image-Text Retrieval","display_name":"ISES: Instance-level Semantic Enhanced Score Model for Image-Text Retrieval","publication_year":2023,"publication_date":"2023-11-18","ids":{"openalex":"https://openalex.org/W4391490506","doi":"https://doi.org/10.1145/3603273.3635666"},"language":"en","primary_location":{"id":"doi:10.1145/3603273.3635666","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3603273.3635666","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 International Conference on Advances in Artificial Intelligence and Applications","raw_type":"proceedings-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/A5101512008","display_name":"Bo Lu","orcid":"https://orcid.org/0000-0002-4879-1388"},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]},{"id":"https://openalex.org/I61565387","display_name":"Dalian Minzu University","ror":"https://ror.org/02hxfx521","country_code":"CN","type":"education","lineage":["https://openalex.org/I61565387"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Bo Lu","raw_affiliation_strings":["School of Computer Science and Engineering, Dalian Minzu University, China"],"raw_orcid":"https://orcid.org/0000-0002-4879-1388","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Dalian Minzu University, China","institution_ids":["https://openalex.org/I145897649","https://openalex.org/I61565387"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006997550","display_name":"Hanxing Cai","orcid":"https://orcid.org/0009-0002-9302-2040"},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]},{"id":"https://openalex.org/I61565387","display_name":"Dalian Minzu University","ror":"https://ror.org/02hxfx521","country_code":"CN","type":"education","lineage":["https://openalex.org/I61565387"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanxing Cai","raw_affiliation_strings":["School of Computer Science and Engineering, Dalian Minzu University, China"],"raw_orcid":"https://orcid.org/0009-0002-9302-2040","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Dalian Minzu University, China","institution_ids":["https://openalex.org/I145897649","https://openalex.org/I61565387"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009125179","display_name":"Y Chen","orcid":"https://orcid.org/0009-0004-8970-7447"},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]},{"id":"https://openalex.org/I61565387","display_name":"Dalian Minzu University","ror":"https://ror.org/02hxfx521","country_code":"CN","type":"education","lineage":["https://openalex.org/I61565387"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yangyang Chen","raw_affiliation_strings":["School of Computer Science and Engineering, Dalian Minzu University, China"],"raw_orcid":"https://orcid.org/0009-0004-8970-7447","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Dalian Minzu University, China","institution_ids":["https://openalex.org/I145897649","https://openalex.org/I61565387"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101450427","display_name":"Zhenshun Shi","orcid":"https://orcid.org/0000-0001-6250-1351"},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]},{"id":"https://openalex.org/I61565387","display_name":"Dalian Minzu University","ror":"https://ror.org/02hxfx521","country_code":"CN","type":"education","lineage":["https://openalex.org/I61565387"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengchun Shi","raw_affiliation_strings":["School of Computer Science and Engineering, Dalian Minzu University, China"],"raw_orcid":"https://orcid.org/0000-0001-6250-1351","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Dalian Minzu University, China","institution_ids":["https://openalex.org/I145897649","https://openalex.org/I61565387"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101944883","display_name":"Xiaodong Duan","orcid":"https://orcid.org/0009-0001-1775-6280"},"institutions":[{"id":"https://openalex.org/I145897649","display_name":"Minzu University of China","ror":"https://ror.org/0044e2g62","country_code":"CN","type":"education","lineage":["https://openalex.org/I145897649"]},{"id":"https://openalex.org/I61565387","display_name":"Dalian Minzu University","ror":"https://ror.org/02hxfx521","country_code":"CN","type":"education","lineage":["https://openalex.org/I61565387"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaodong Duan","raw_affiliation_strings":["School of Computer Science and Engineering, Dalian Minzu University, China"],"raw_orcid":"https://orcid.org/0009-0001-1775-6280","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Dalian Minzu University, China","institution_ids":["https://openalex.org/I145897649","https://openalex.org/I61565387"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101512008"],"corresponding_institution_ids":["https://openalex.org/I145897649","https://openalex.org/I61565387"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19228159,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"229","last_page":"232"},"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":0.9959999918937683,"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":0.9940000176429749,"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":0.7822220325469971},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6268476247787476},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.5794452428817749},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5358269214630127},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5322917103767395},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.5179416537284851},{"id":"https://openalex.org/keywords/explicit-semantic-analysis","display_name":"Explicit semantic analysis","score":0.5150394439697266},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.5087655186653137},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4916110634803772},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.48356935381889343},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.45376908779144287},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45010703802108765},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.42953264713287354},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4203830063343048},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33380281925201416},{"id":"https://openalex.org/keywords/semantic-computing","display_name":"Semantic computing","score":0.26989108324050903},{"id":"https://openalex.org/keywords/semantic-web","display_name":"Semantic Web","score":0.1573949158191681},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1133820116519928},{"id":"https://openalex.org/keywords/semantic-technology","display_name":"Semantic technology","score":0.0998765230178833}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7822220325469971},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6268476247787476},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.5794452428817749},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5358269214630127},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5322917103767395},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.5179416537284851},{"id":"https://openalex.org/C173862523","wikidata":"https://www.wikidata.org/wiki/Q5421270","display_name":"Explicit semantic analysis","level":5,"score":0.5150394439697266},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.5087655186653137},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4916110634803772},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.48356935381889343},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.45376908779144287},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45010703802108765},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.42953264713287354},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4203830063343048},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33380281925201416},{"id":"https://openalex.org/C511149849","wikidata":"https://www.wikidata.org/wiki/Q7449051","display_name":"Semantic computing","level":3,"score":0.26989108324050903},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.1573949158191681},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1133820116519928},{"id":"https://openalex.org/C6881194","wikidata":"https://www.wikidata.org/wiki/Q7449091","display_name":"Semantic technology","level":4,"score":0.0998765230178833},{"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},{"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3603273.3635666","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3603273.3635666","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 International Conference on Advances in Artificial Intelligence and Applications","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4699999988079071}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2138118304","https://openalex.org/W2185175083","https://openalex.org/W2883311563","https://openalex.org/W2988823324","https://openalex.org/W3118694826","https://openalex.org/W3190055600","https://openalex.org/W4206314411","https://openalex.org/W4210894218","https://openalex.org/W4226391640","https://openalex.org/W4292955459","https://openalex.org/W4312934263"],"related_works":["https://openalex.org/W2103835134","https://openalex.org/W1965623300","https://openalex.org/W2907506409","https://openalex.org/W2146812779","https://openalex.org/W4245135661","https://openalex.org/W1979325497","https://openalex.org/W2361271045","https://openalex.org/W4230743089","https://openalex.org/W3016822073","https://openalex.org/W2774861092"],"abstract_inverted_index":{"Image-Text":[0],"Retrieval":[1],"(ITR)":[2],"is":[3,133,145,206],"an":[4,110],"important":[5],"measure":[6],"of":[7,10,39,45,65,75,98,198],"the":[8,23,29,32,37,43,46,50,78,143,150,167,190,195,202],"performance":[9],"text":[11,68,173],"and":[12,26,67,80,142,172,210,215],"image":[13,168],"mutual":[14],"retrieval,":[15],"by":[16,208],"searching":[17],"for":[18,116],"semantically":[19],"relevant":[20,24],"information":[21,48,100,171],"in":[22,36,63],"modality":[25],"then":[27],"matching":[28],"corresponding":[30],"modality,":[31],"key":[33],"difficulty":[34],"lies":[35],"problem":[38],"how":[40],"to":[41,60,69,84,95,135,148,164,180],"find":[42],"relevance":[44],"semantic":[47,138,151,169,174],"between":[49,140,153],"interacting":[51],"modalities.":[52,102],"Previous":[53],"work":[54],"has":[55],"only":[56],"used":[57],"pre-trained":[58],"models":[59],"obtain":[61],"features":[62],"terms":[64],"images":[66],"achieve":[70],"matching.":[71],"However,":[72],"this":[73],"type":[74],"approach":[76],"lacks":[77],"pairing":[79],"embedding":[81],"methods":[82],"required":[83],"effectively":[85],"match":[86],"multimodal":[87],"data.":[88],"In":[89,155],"addition,":[90,156],"these":[91,105],"efforts":[92],"also":[93,158],"lead":[94],"significant":[96],"loss":[97,161],"fine-grained":[99],"within":[101],"To":[103],"alleviate":[104],"problems,":[106],"we":[107,120,157],"propose":[108],"ISES:":[109],"Instantiated":[111],"Semantic":[112,125],"Enhanced":[113],"Scoring":[114],"model":[115],"cross-modal":[117,183],"retrieval.":[118,217],"Specifically,":[119],"have":[121],"crafted":[122],"two":[123],"efficient":[124],"Enhancement":[126],"Score":[127],"(SES)":[128],"modules.":[129],"One":[130],"module":[131],"(SES-1)":[132],"specialized":[134,146],"learn":[136,149],"t5he":[137],"similarity":[139,152],"image-to-image":[141],"other":[144],"(SES-2)":[147],"text-to-text.":[154],"introduce":[159],"Instance":[160],"into":[162],"ITR":[163],"further":[165],"optimize":[166],"enhancement":[170,175],"information,":[176],"with":[177,189],"a":[178],"view":[179],"obtaining":[181],"better":[182],"retrieval":[184,214],"performance.":[185],"For":[186],"instance,":[187],"compared":[188],"existing":[191],"best":[192],"method":[193],"NAAF,":[194],"metric":[196],"R@1":[197],"our":[199],"ISES":[200],"on":[201,212],"MSCOCO":[203],"testing":[204],"set":[205],"improved":[207],"2.60%":[209],"1.21%":[211],"I2T":[213],"T2I":[216]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}