{"id":"https://openalex.org/W4408287655","doi":"https://doi.org/10.1145/3722223","title":"Fine-Grained Alignment Network for Zero-Shot Cross-Modal Retrieval","display_name":"Fine-Grained Alignment Network for Zero-Shot Cross-Modal Retrieval","publication_year":2025,"publication_date":"2025-03-10","ids":{"openalex":"https://openalex.org/W4408287655","doi":"https://doi.org/10.1145/3722223"},"language":"en","primary_location":{"id":"doi:10.1145/3722223","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3722223","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3722223","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/10.1145/3722223","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044227484","display_name":"Shiping Ge","orcid":"https://orcid.org/0000-0001-9198-5324"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shiping Ge","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","State Key Laboratory for Novel Software Technology, Nanjing University, China"],"raw_orcid":"https://orcid.org/0000-0001-9198-5324","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082553860","display_name":"Zhiwei Jiang","orcid":"https://orcid.org/0000-0001-5243-4992"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiwei Jiang","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","State Key Laboratory for Novel Software Technology, Nanjing University, China"],"raw_orcid":"https://orcid.org/0000-0001-5243-4992","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087888694","display_name":"Yafeng Yin","orcid":"https://orcid.org/0000-0002-9497-6244"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yafeng Yin","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","State Key Laboratory for Novel Software Technology, Nanjing University, China"],"raw_orcid":"https://orcid.org/0000-0002-9497-6244","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015574942","display_name":"Cong Wang","orcid":"https://orcid.org/0000-0003-0916-7803"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cong Wang","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","State Key Laboratory for Novel Software Technology, Nanjing University, China"],"raw_orcid":"https://orcid.org/0000-0003-0916-7803","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033620369","display_name":"Zifeng Cheng","orcid":"https://orcid.org/0000-0002-8486-2614"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zifeng Cheng","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","State Key Laboratory for Novel Software Technology, Nanjing University, China"],"raw_orcid":"https://orcid.org/0000-0002-8486-2614","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061025205","display_name":"Qing Gu","orcid":"https://orcid.org/0000-0002-1112-790X"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qing Gu","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","State Key Laboratory for Novel Software Technology, Nanjing University, China"],"raw_orcid":"https://orcid.org/0000-0002-1112-790X","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5044227484"],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":1.1332,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.75498357,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"21","issue":"10","first_page":"1","last_page":"24"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9995999932289124,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9975000023841858,"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":0.8595621585845947},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6590921878814697},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.647810161113739},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.4589880406856537},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4146469831466675},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.33622997999191284}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8595621585845947},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6590921878814697},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.647810161113739},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.4589880406856537},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4146469831466675},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33622997999191284},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3722223","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3722223","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3722223","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:10.1145/3722223","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3722223","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3722223","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":[],"awards":[{"id":"https://openalex.org/G25327397","display_name":null,"funder_award_id":"61972192, 62172208, 61906085","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":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4408287655.pdf"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W1949478088","https://openalex.org/W2007972815","https://openalex.org/W2098411764","https://openalex.org/W2106277773","https://openalex.org/W2108598243","https://openalex.org/W2169783907","https://openalex.org/W2187089797","https://openalex.org/W2243225650","https://openalex.org/W2326180695","https://openalex.org/W2388114291","https://openalex.org/W2603445054","https://openalex.org/W2606965845","https://openalex.org/W2765440071","https://openalex.org/W2807887362","https://openalex.org/W2808336545","https://openalex.org/W2915533878","https://openalex.org/W2962856082","https://openalex.org/W2967957126","https://openalex.org/W3026092005","https://openalex.org/W3046882683","https://openalex.org/W3095602948","https://openalex.org/W3096831136","https://openalex.org/W3171007011","https://openalex.org/W3175613352","https://openalex.org/W3177017840","https://openalex.org/W3201053014","https://openalex.org/W3211536067","https://openalex.org/W3214094165","https://openalex.org/W4284675277","https://openalex.org/W4301409532","https://openalex.org/W4376607849","https://openalex.org/W4392545520","https://openalex.org/W4400679250","https://openalex.org/W6777179611","https://openalex.org/W6784694379"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574","https://openalex.org/W2359774528","https://openalex.org/W4298312966","https://openalex.org/W2325697621"],"abstract_inverted_index":{"Zero-Shot":[0],"Cross-Modal":[1],"Retrieval":[2],"(ZS-CMR)":[3],"aims":[4],"to":[5,20,120,157,180,203],"perform":[6,204],"cross-modal":[7],"retrieval":[8],"on":[9,64,88,212],"data":[10],"of":[11,43,47,55,72,82,128,139,242],"unseen":[12,89,121],"classes,":[13],"where":[14],"a":[15,36,96,151,174,207,226],"key":[16],"challenge":[17,32],"is":[18],"how":[19],"address":[21],"the":[22,48,52,65,70,146,164,169,222,240],"modality-gap":[23],"and":[24,68,85,133,142,162,197],"domain-shift":[25],"problems":[26],"simultaneously.":[27],"Existing":[28],"methods":[29,61,224],"tackle":[30],"this":[31,92],"mainly":[33],"by":[34,225],"embracing":[35],"sample-label":[37],"alignment":[38,67,71,110,161],"paradigm,":[39],"which":[40,237],"aligns":[41],"samples":[42],"different":[44],"modalities":[45],"but":[46],"same":[49],"class":[50,57],"with":[51,107],"word":[53],"embedding":[54,132,196],"their":[56],"label.":[58,143],"However,":[59],"these":[60],"only":[62],"focus":[63],"class-level":[66,160],"overlook":[69],"rich":[73],"fine-grained":[74,109,129,183],"semantic":[75,184],"information":[76,185],"in":[77],"samples,":[78,187],"incurring":[79],"coarse":[80],"understanding":[81],"sample":[83],"matching":[84],"poor":[86],"generalization":[87],"classes.":[90,122],"In":[91],"article,":[93],"we":[94,124,149,172,245],"propose":[95,150,173],"novel":[97],"Fine-Grained":[98,152,175],"Alignment":[99,177],"Network,":[100],"an":[101],"end-to-end":[102],"framework":[103],"that":[104,115,218],"learns":[105],"representation":[106,113],"two":[108,126],"strategies,":[111],"yielding":[112],"space":[114],"can":[116],"be":[117,250],"better":[118],"generalized":[119],"Specifically,":[123],"extract":[125],"kinds":[127],"representations,":[130],"region":[131,147,195],"label":[134,170,191,198],"distribution,":[135,171],"respectively,":[136],"from":[137],"aspects":[138],"both":[140,194],"feature":[141],"To":[144,167],"optimize":[145,168],"embedding,":[148],"Contrastive":[153],"Learning":[154],"(FGCL)":[155],"strategy":[156,179],"simultaneously":[158],"conduct":[159],"model":[163],"intra-class":[165],"discrepancy.":[166],"Label":[176],"(FGLA)":[178],"align":[181],"diverse":[182],"among":[186],"rather":[188],"than":[189],"merely":[190],"information.":[192],"Finally,":[193],"distribution":[199],"are":[200],"utilized":[201],"together":[202],"ZS-CMR":[205],"at":[206,252],"finer":[208],"granularity.":[209],"Experimental":[210],"results":[211],"three":[213],"widely":[214],"used":[215],"datasets":[216],"demonstrate":[217],"our":[219],"method":[220],"outperforms":[221],"state-of-the-art":[223],"large":[227],"margin.":[228],"Detailed":[229],"ablation":[230],"studies":[231],"have":[232],"also":[233],"been":[234],"carried":[235],"out,":[236],"provably":[238],"affirm":[239],"advantage":[241],"each":[243],"component":[244],"propose.":[246],"Our":[247],"code":[248],"will":[249],"available":[251],"https://github.com/ShipingGe/FGAN":[253],".":[254]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}