{"id":"https://openalex.org/W4411551194","doi":"https://doi.org/10.1109/cscwd64889.2025.11033544","title":"Enhancing Coarse-Grained and Fine-Grained Image-Text Retrieval Models via Multi-Scale Modal Distance Learning","display_name":"Enhancing Coarse-Grained and Fine-Grained Image-Text Retrieval Models via Multi-Scale Modal Distance Learning","publication_year":2025,"publication_date":"2025-05-05","ids":{"openalex":"https://openalex.org/W4411551194","doi":"https://doi.org/10.1109/cscwd64889.2025.11033544"},"language":"en","primary_location":{"id":"doi:10.1109/cscwd64889.2025.11033544","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cscwd64889.2025.11033544","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 28th International Conference on Computer Supported Cooperative Work in Design (CSCWD)","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":null,"display_name":"Kaili Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]},{"id":"https://openalex.org/I4210142748","display_name":"Shandong Academy of Sciences","ror":"https://ror.org/04y8d6y55","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kaili Zhou","raw_affiliation_strings":["Qilu University of Technology (Shandong Academy of Sciences),Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center,Jinan,China"],"affiliations":[{"raw_affiliation_string":"Qilu University of Technology (Shandong Academy of Sciences),Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center,Jinan,China","institution_ids":["https://openalex.org/I152269853","https://openalex.org/I4210142748"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107808842","display_name":"Yushui Geng","orcid":"https://orcid.org/0009-0001-7587-4242"},"institutions":[{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]},{"id":"https://openalex.org/I4210142748","display_name":"Shandong Academy of Sciences","ror":"https://ror.org/04y8d6y55","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yushui Geng","raw_affiliation_strings":["Qilu University of Technology (Shandong Academy of Sciences),Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center,Jinan,China"],"affiliations":[{"raw_affiliation_string":"Qilu University of Technology (Shandong Academy of Sciences),Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center,Jinan,China","institution_ids":["https://openalex.org/I152269853","https://openalex.org/I4210142748"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107342072","display_name":"Jing Zhao","orcid":"https://orcid.org/0009-0006-6839-9355"},"institutions":[{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]},{"id":"https://openalex.org/I4210142748","display_name":"Shandong Academy of Sciences","ror":"https://ror.org/04y8d6y55","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Zhao","raw_affiliation_strings":["Qilu University of Technology (Shandong Academy of Sciences),Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center,Jinan,China"],"affiliations":[{"raw_affiliation_string":"Qilu University of Technology (Shandong Academy of Sciences),Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center,Jinan,China","institution_ids":["https://openalex.org/I152269853","https://openalex.org/I4210142748"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5117409083","display_name":"Yiyun Xing","orcid":"https://orcid.org/0009-0008-8520-0760"},"institutions":[{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]},{"id":"https://openalex.org/I4210142748","display_name":"Shandong Academy of Sciences","ror":"https://ror.org/04y8d6y55","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiyun Xing","raw_affiliation_strings":["Qilu University of Technology (Shandong Academy of Sciences),Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center,Jinan,China"],"affiliations":[{"raw_affiliation_string":"Qilu University of Technology (Shandong Academy of Sciences),Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center,Jinan,China","institution_ids":["https://openalex.org/I152269853","https://openalex.org/I4210142748"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I152269853","https://openalex.org/I4210142748"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11975362,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1628","last_page":"1633"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9926999807357788,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9926999807357788,"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":0.9781000018119812,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9656999707221985,"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":0.7702866196632385},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6979041695594788},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.636756420135498},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4971156418323517},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.49195191264152527},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4377312660217285},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3700624108314514},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35303211212158203},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3512728214263916},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.07191568613052368},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.07135751843452454}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7702866196632385},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6979041695594788},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.636756420135498},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4971156418323517},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.49195191264152527},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4377312660217285},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3700624108314514},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35303211212158203},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3512728214263916},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.07191568613052368},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.07135751843452454},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cscwd64889.2025.11033544","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cscwd64889.2025.11033544","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 28th International Conference on Computer Supported Cooperative Work in Design (CSCWD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4699999988079071}],"awards":[{"id":"https://openalex.org/G228520245","display_name":null,"funder_award_id":"2023YFB3308403","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W2064675550","https://openalex.org/W2100235303","https://openalex.org/W2194775991","https://openalex.org/W2342543219","https://openalex.org/W2606473278","https://openalex.org/W2765440071","https://openalex.org/W2894786240","https://openalex.org/W2956018683","https://openalex.org/W2962964995","https://openalex.org/W2964187781","https://openalex.org/W2967957126","https://openalex.org/W2988823324","https://openalex.org/W2994818707","https://openalex.org/W2998124234","https://openalex.org/W3035356601","https://openalex.org/W3035454331","https://openalex.org/W3035588244","https://openalex.org/W3118694826","https://openalex.org/W3130289102","https://openalex.org/W3176646400","https://openalex.org/W3182683290","https://openalex.org/W3197035208","https://openalex.org/W3216130706","https://openalex.org/W4293519407","https://openalex.org/W4386071498","https://openalex.org/W4386160421","https://openalex.org/W6747225742","https://openalex.org/W6755207826"],"related_works":["https://openalex.org/W2379392295","https://openalex.org/W3160965418","https://openalex.org/W613940353","https://openalex.org/W2320915480","https://openalex.org/W2362990116","https://openalex.org/W2381300099","https://openalex.org/W2714992399","https://openalex.org/W2383812217","https://openalex.org/W2326515389","https://openalex.org/W2491005386"],"abstract_inverted_index":{"The":[0],"current":[1],"image-text":[2,35],"cross-modal":[3,183],"retrieval":[4,161],"faces":[5],"challenges":[6],"due":[7],"to":[8,27,51,66,86,103,138],"the":[9,29,38,126,135,144,152],"heterogeneous":[10],"nature":[11],"of":[12,31,130],"different":[13,131],"modalities.":[14],"This":[15,173],"paper":[16,115],"proposes":[17],"an":[18,42,175],"improved":[19,43],"model":[20],"based":[21],"on":[22,143],"multi-scale":[23,119],"modal":[24,120],"distance":[25,127],"learning":[26],"enhance":[28],"performance":[30],"coarse-grained":[32],"and":[33,61,69,94,147,163,170,178],"fine-grained":[34,171],"matching.":[36,112],"In":[37],"image":[39,92,107],"encoding":[40],"part,":[41],"ResNet":[44],"architecture":[45],"is":[46],"adopted,":[47],"utilizing":[48],"upsampling":[49],"techniques":[50],"better":[52],"preserve":[53],"key":[54],"semantic":[55,139],"information.":[56],"For":[57],"text":[58,95],"encoding,":[59],"BERT":[60],"Bi-LSTM":[62],"models":[63],"are":[64],"combined":[65],"extract":[67],"shallow":[68],"deep":[70],"textual":[71],"features,":[72],"respectively.":[73],"We":[74],"design":[75],"a":[76,82,117],"coarse-fine":[77],"granularity":[78],"interaction":[79,90],"mechanism,":[80],"leveraging":[81],"bidirectional":[83],"stacked":[84],"Transformer":[85],"achieve":[87],"local":[88],"similarity":[89,111],"between":[91,128,168],"regions":[93],"words,":[96],"while":[97],"also":[98],"using":[99],"Bi-LSTM-extracted":[100],"contextual":[101],"features":[102,108],"interact":[104],"with":[105],"global":[106,110],"for":[109,182],"Additionally,":[113],"this":[114],"introduces":[116],"novel":[118],"contrastive":[121],"loss,":[122],"which":[123],"dynamically":[124],"adjusts":[125],"samples":[129],"modalities,":[132],"thereby":[133],"improving":[134],"model's":[136],"sensitivity":[137],"similarity.":[140],"Experimental":[141],"results":[142],"COCO":[145],"5K":[146],"Flickr30K":[148],"datasets":[149],"demonstrate":[150],"that":[151],"proposed":[153],"method":[154],"outperforms":[155],"existing":[156],"mainstream":[157],"methods":[158],"in":[159],"both":[160],"accuracy":[162],"efficiency,":[164],"achieving":[165],"complementary":[166],"advantages":[167],"coarse-":[169],"features.":[172],"provides":[174],"effective":[176],"solution":[177],"new":[179],"research":[180],"direction":[181],"retrieval.":[184]},"counts_by_year":[],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-10-10T00:00:00"}