{"id":"https://openalex.org/W4416251595","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227998","title":"Enhancing Image-Text Retrieval with Phrase-aware and Modality Difference-aware Embeddings","display_name":"Enhancing Image-Text Retrieval with Phrase-aware and Modality Difference-aware Embeddings","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416251595","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227998"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11227998","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227998","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100425908","display_name":"Meng Meng","orcid":"https://orcid.org/0000-0001-5453-5754"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Meng","raw_affiliation_strings":["Shenzhen Institutes of Advanced Technology, CAS,Shenzhen Key Laboratory of Computer Vision and Pattern Recognition"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Institutes of Advanced Technology, CAS,Shenzhen Key Laboratory of Computer Vision and Pattern Recognition","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100757130","display_name":"Shifeng Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210122640","display_name":"Nigerian Institute For Oil Palm Reasearch","ror":"https://ror.org/02y05bg81","country_code":"NG","type":"government","lineage":["https://openalex.org/I4210122640"]}],"countries":["NG"],"is_corresponding":false,"raw_author_name":"Shifeng Zhang","raw_affiliation_strings":["Sangfor Technologies Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sangfor Technologies Inc","institution_ids":["https://openalex.org/I4210122640"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100686575","display_name":"Xiaofan Chen","orcid":"https://orcid.org/0000-0003-1628-9649"},"institutions":[{"id":"https://openalex.org/I4210122640","display_name":"Nigerian Institute For Oil Palm Reasearch","ror":"https://ror.org/02y05bg81","country_code":"NG","type":"government","lineage":["https://openalex.org/I4210122640"]}],"countries":["NG"],"is_corresponding":false,"raw_author_name":"Xiaofan Chen","raw_affiliation_strings":["Sangfor Technologies Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sangfor Technologies Inc","institution_ids":["https://openalex.org/I4210122640"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019433605","display_name":"Shifeng Chen","orcid":"https://orcid.org/0000-0003-0677-7358"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shifeng Chen","raw_affiliation_strings":["Shenzhen Institutes of Advanced Technology, CAS,Shenzhen Key Laboratory of Computer Vision and Pattern Recognition"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Institutes of Advanced Technology, CAS,Shenzhen Key Laboratory of Computer Vision and Pattern Recognition","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110577072","display_name":"Xu Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I4210122640","display_name":"Nigerian Institute For Oil Palm Reasearch","ror":"https://ror.org/02y05bg81","country_code":"NG","type":"government","lineage":["https://openalex.org/I4210122640"]}],"countries":["NG"],"is_corresponding":false,"raw_author_name":"Xu Zhou","raw_affiliation_strings":["Sangfor Technologies Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sangfor Technologies Inc","institution_ids":["https://openalex.org/I4210122640"]}]}],"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":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9199000000953674,"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":0.9199000000953674,"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":0.040699999779462814,"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":0.011599999852478504,"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/modality","display_name":"Modality (human\u2013computer interaction)","score":0.8213000297546387},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.7074999809265137},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5989000201225281},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.5148000121116638},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5056999921798706},{"id":"https://openalex.org/keywords/core","display_name":"Core (optical fiber)","score":0.4097000062465668},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.329800009727478},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3107999861240387}],"concepts":[{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.8213000297546387},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7716000080108643},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7074999809265137},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6743000149726868},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5989000201225281},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.5148000121116638},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5056999921798706},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4277999997138977},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.4097000062465668},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.329800009727478},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3107999861240387},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3061000108718872},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2987000048160553},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.2847000062465668},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2754000127315521},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2624000012874603},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.25679999589920044},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2547000050544739},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.2531000077724457},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.2517000138759613},{"id":"https://openalex.org/C59656382","wikidata":"https://www.wikidata.org/wiki/Q191536","display_name":"Conjunction (astronomy)","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11227998","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227998","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W2131774270","https://openalex.org/W2194775991","https://openalex.org/W2531958295","https://openalex.org/W2745461083","https://openalex.org/W2962964995","https://openalex.org/W2980216782","https://openalex.org/W2981586349","https://openalex.org/W2988823324","https://openalex.org/W2990571534","https://openalex.org/W2997403743","https://openalex.org/W2997525715","https://openalex.org/W3035212740","https://openalex.org/W3035454331","https://openalex.org/W3035588244","https://openalex.org/W3035605030","https://openalex.org/W3092820619","https://openalex.org/W3108373531","https://openalex.org/W3155230099","https://openalex.org/W3175888430","https://openalex.org/W3190055600","https://openalex.org/W4200141986","https://openalex.org/W4210894218","https://openalex.org/W4224952037","https://openalex.org/W4231582880","https://openalex.org/W4312761738","https://openalex.org/W4319299832","https://openalex.org/W4385245566","https://openalex.org/W4386071757","https://openalex.org/W4390874468","https://openalex.org/W4392678259","https://openalex.org/W4393154020","https://openalex.org/W4393160357","https://openalex.org/W4394625619","https://openalex.org/W4395447490","https://openalex.org/W4402727895","https://openalex.org/W4404879609"],"related_works":[],"abstract_inverted_index":{"Image-to-text":[0],"retrieval":[1],"aims":[2],"to":[3,27,33,113,120,141],"search":[4],"for":[5],"relevant":[6],"images":[7,53],"given":[8],"a":[9,17,69,88,93],"textual":[10,31,137],"description":[11],"or":[12],"vice":[13],"versa,":[14],"which":[15],"is":[16,26,103],"crucial":[18],"task":[19],"in":[20,92],"multi-modal":[21],"intelligence.":[22],"The":[23],"core":[24],"idea":[25],"learn":[28,114],"visual":[29,139],"and":[30,54,56,72,87,138],"embeddings":[32],"ensure":[34],"the":[35,46,57,97,104,128,134,143],"similarity":[36],"of":[37,52,59,99],"matched":[38],"image-text":[39],"pairs.":[40],"Its":[41],"challenges":[42],"originate":[43],"from":[44],"grasping":[45],"intricate":[47],"relationships":[48,123],"between":[49,124,136],"various":[50],"parts":[51],"texts,":[55],"difficulty":[58],"understanding":[60],"modality":[61,73,89,130],"differences.":[62],"To":[63,96],"alleviate":[64],"these":[65],"problems,":[66],"we":[67],"propose":[68],"novel":[70],"phrase-aware":[71,85,115],"difference-aware":[74,90,131],"embedding":[75],"learning":[76],"network":[77],"(PMD-Net)":[78],"by":[79],"jointly":[80],"using":[81],"an":[82,109],"optimal":[83,110],"transport-based":[84],"module":[86,91,132],"unified":[94],"model.":[95],"best":[98],"our":[100,155],"knowledge,":[101],"this":[102],"first":[105],"work":[106],"that":[107,154],"uses":[108],"transport":[111],"algorithm":[112],"features":[116,140],"with":[117,150],"varied":[118],"structures":[119],"effectively":[121],"represent":[122],"multi-modality":[125],"data.":[126],"Additionally,":[127],"proposed":[129],"leverages":[133],"variations":[135],"bridge":[142],"semantic":[144],"gap":[145],"effectively.":[146],"Extensive":[147],"experimental":[148],"results":[149],"two":[151,163],"backbones":[152],"demonstrate":[153],"PMD-Net":[156],"performs":[157],"favorably":[158],"against":[159],"state-of-the-art":[160],"methods":[161],"on":[162],"standard":[164],"datasets.":[165]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-14T00:00:00"}