{"id":"https://openalex.org/W4411635573","doi":"https://doi.org/10.1145/3731715.3734427","title":"MGSGM: Multi-Granularity Selective Graph Mamba for Image-Text Retrieval","display_name":"MGSGM: Multi-Granularity Selective Graph Mamba for Image-Text Retrieval","publication_year":2025,"publication_date":"2025-06-25","ids":{"openalex":"https://openalex.org/W4411635573","doi":"https://doi.org/10.1145/3731715.3734427"},"language":"en","primary_location":{"id":"doi:10.1145/3731715.3734427","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3731715.3734427","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 International Conference on Multimedia Retrieval","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/A5102665049","display_name":"Yongle Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I25355098","display_name":"Chang'an University","ror":"https://ror.org/05mxya461","country_code":"CN","type":"education","lineage":["https://openalex.org/I25355098"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongle Huang","raw_affiliation_strings":["Chang'an University, Xi'an, Shaanxi, China"],"raw_orcid":"https://orcid.org/0009-0007-6462-6087","affiliations":[{"raw_affiliation_string":"Chang'an University, Xi'an, Shaanxi, China","institution_ids":["https://openalex.org/I25355098"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112754056","display_name":"Yongfeng Bu","orcid":"https://orcid.org/0009-0006-8898-4308"},"institutions":[{"id":"https://openalex.org/I25355098","display_name":"Chang'an University","ror":"https://ror.org/05mxya461","country_code":"CN","type":"education","lineage":["https://openalex.org/I25355098"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongfeng Bu","raw_affiliation_strings":["Chang'an University, Xi'an, Shaanxi, China"],"raw_orcid":"https://orcid.org/0009-0006-8898-4308","affiliations":[{"raw_affiliation_string":"Chang'an University, Xi'an, Shaanxi, China","institution_ids":["https://openalex.org/I25355098"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111012169","display_name":"Keyu Guo","orcid":"https://orcid.org/0009-0005-0699-3992"},"institutions":[{"id":"https://openalex.org/I25355098","display_name":"Chang'an University","ror":"https://ror.org/05mxya461","country_code":"CN","type":"education","lineage":["https://openalex.org/I25355098"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Keyu Guo","raw_affiliation_strings":["Chang'an University, Xi'an, Shaanxi, China"],"raw_orcid":"https://orcid.org/0009-0005-0699-3992","affiliations":[{"raw_affiliation_string":"Chang'an University, Xi'an, Shaanxi, China","institution_ids":["https://openalex.org/I25355098"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110814983","display_name":"Zedong Liu","orcid":"https://orcid.org/0009-0000-0345-804X"},"institutions":[{"id":"https://openalex.org/I25355098","display_name":"Chang'an University","ror":"https://ror.org/05mxya461","country_code":"CN","type":"education","lineage":["https://openalex.org/I25355098"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zedong Liu","raw_affiliation_strings":["Chang'an University, Xi'an, Shaanxi, China"],"raw_orcid":"https://orcid.org/0009-0000-0345-804X","affiliations":[{"raw_affiliation_string":"Chang'an University, Xi'an, Shaanxi, China","institution_ids":["https://openalex.org/I25355098"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053270215","display_name":"Xiangyu Song","orcid":"https://orcid.org/0000-0002-5550-6354"},"institutions":[{"id":"https://openalex.org/I25355098","display_name":"Chang'an University","ror":"https://ror.org/05mxya461","country_code":"CN","type":"education","lineage":["https://openalex.org/I25355098"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangyu Song","raw_affiliation_strings":["Chang'an University, Xi'an, Shaanxi, China"],"raw_orcid":"https://orcid.org/0000-0002-5550-6354","affiliations":[{"raw_affiliation_string":"Chang'an University, Xi'an, Shaanxi, China","institution_ids":["https://openalex.org/I25355098"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103070400","display_name":"Shijie Sun","orcid":"https://orcid.org/0000-0003-4043-8448"},"institutions":[{"id":"https://openalex.org/I25355098","display_name":"Chang'an University","ror":"https://ror.org/05mxya461","country_code":"CN","type":"education","lineage":["https://openalex.org/I25355098"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shijie Sun","raw_affiliation_strings":["Chang'an University, Xi'an, Shaanxi, China"],"raw_orcid":"https://orcid.org/0000-0003-4043-8448","affiliations":[{"raw_affiliation_string":"Chang'an University, Xi'an, Shaanxi, China","institution_ids":["https://openalex.org/I25355098"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10991322,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1983","last_page":"1987"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9980000257492065,"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/T10028","display_name":"Topic Modeling","score":0.9922000169754028,"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/granularity","display_name":"Granularity","score":0.7675482034683228},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7347837090492249},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5938593149185181},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.5475694537162781},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4682173728942871},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37562060356140137},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.34937578439712524},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.15251323580741882},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.04906013607978821}],"concepts":[{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.7675482034683228},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7347837090492249},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5938593149185181},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.5475694537162781},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4682173728942871},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37562060356140137},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.34937578439712524},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.15251323580741882},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.04906013607978821}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3731715.3734427","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3731715.3734427","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 International Conference on Multimedia Retrieval","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":27,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1933349210","https://openalex.org/W2123442489","https://openalex.org/W2185175083","https://openalex.org/W2510661833","https://openalex.org/W2962810718","https://openalex.org/W2962845008","https://openalex.org/W2962964995","https://openalex.org/W2964303913","https://openalex.org/W2967957126","https://openalex.org/W2988823324","https://openalex.org/W3035212740","https://openalex.org/W3035552787","https://openalex.org/W3035588244","https://openalex.org/W3035605030","https://openalex.org/W3093088671","https://openalex.org/W3118694826","https://openalex.org/W3133780103","https://openalex.org/W4214540501","https://openalex.org/W4214819138","https://openalex.org/W4319299832","https://openalex.org/W4384661029","https://openalex.org/W4386071498","https://openalex.org/W4386071757","https://openalex.org/W4388334650","https://openalex.org/W4391344842","https://openalex.org/W6601897980"],"related_works":["https://openalex.org/W2931688134","https://openalex.org/W2377919138","https://openalex.org/W2378857091","https://openalex.org/W1986902711","https://openalex.org/W2396760013","https://openalex.org/W2148433556","https://openalex.org/W2171776552","https://openalex.org/W98391849","https://openalex.org/W1600907701","https://openalex.org/W2726741344"],"abstract_inverted_index":{"Image-Text":[0],"Retrieval":[1],"(ITR)":[2],"serves":[3],"as":[4],"a":[5,81],"fundamental":[6],"task":[7],"in":[8,27],"multimodal":[9],"information":[10],"retrieval,":[11],"aiming":[12],"to":[13,55,66,99],"bridge":[14],"the":[15,93,142],"semantic":[16,36,118],"gap":[17],"between":[18,44,120],"visual":[19,46,59],"and":[20,48,61,68,138],"textual":[21,63],"modalities.":[22],"The":[23,111],"core":[24],"challenge":[25],"resides":[26],"overcoming":[28],"intrinsic":[29],"modality":[30],"discrepancies":[31],"while":[32],"effectively":[33],"capturing":[34],"cross-modal":[35,73],"relationships.":[37],"Fine-grained":[38],"retrieval":[39],"approaches":[40],"can":[41],"model":[42],"associations":[43],"salient":[45],"regions":[47],"their":[49],"linguistic":[50],"counterparts,":[51],"but":[52],"are":[53],"prone":[54],"interference":[56],"from":[57],"irrelevant":[58],"embeddings":[60],"non-predicative":[62],"components,":[64],"leading":[65],"misalignments":[67],"degraded":[69],"embedding":[70],"quality":[71],"for":[72,88,107],"retrieval.":[74],"To":[75],"address":[76],"these":[77],"challenges,":[78],"we":[79],"propose":[80],"Multi-Granularity":[82],"Selective":[83,94],"Graph":[84],"Mamba":[85,113],"(MGSGM)":[86],"framework":[87],"discriminative":[89,132],"embeddings.":[90,133],"It":[91],"uses":[92],"Relationship":[95],"Reasoning":[96],"Module":[97],"(SRRM)":[98],"suppress":[100],"intra-modal":[101],"redundancy,":[102],"followed":[103],"by":[104],"graph":[105],"refinement":[106],"medium-grained":[108],"feature":[109],"extraction.":[110],"Cross-modal":[112],"Alignment":[114],"(CMA)":[115],"establishes":[116],"selective":[117],"bridges":[119],"inter-modal":[121],"entities.":[122],"A":[123],"hierarchical":[124],"fusion":[125],"mechanism":[126],"ultimately":[127],"integrates":[128],"multi-granularity":[129],"representations":[130],"into":[131],"Extensive":[134],"experiments":[135],"on":[136],"Flickr30K":[137],"MS-COCO":[139],"datasets":[140],"demonstrate":[141],"superiority":[143],"of":[144],"our":[145],"method.":[146]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}