{"id":"https://openalex.org/W4411552615","doi":"https://doi.org/10.1109/cscwd64889.2025.11033666","title":"Context-Aware Enhancement and Transformer Network for Image-Text Retrieval","display_name":"Context-Aware Enhancement and Transformer Network for Image-Text Retrieval","publication_year":2025,"publication_date":"2025-05-05","ids":{"openalex":"https://openalex.org/W4411552615","doi":"https://doi.org/10.1109/cscwd64889.2025.11033666"},"language":"en","primary_location":{"id":"doi:10.1109/cscwd64889.2025.11033666","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cscwd64889.2025.11033666","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":"https://openalex.org/A5049496913","display_name":"Zheng\u2010Gao Dong","orcid":"https://orcid.org/0000-0003-1655-0253"},"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":"Zheng Dong","raw_affiliation_strings":["Ministry of Education, Shandong Computer Science Center, Qilu University of Technology (Shandong Academy of Sciences),Key Laboratory of Computing Power Network and Information Security,Jinan,China"],"affiliations":[{"raw_affiliation_string":"Ministry of Education, Shandong Computer Science Center, Qilu University of Technology (Shandong Academy of Sciences),Key Laboratory of Computing Power Network and Information Security,Jinan,China","institution_ids":["https://openalex.org/I152269853","https://openalex.org/I4210142748"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064065475","display_name":"Ruijia Zhang","orcid":"https://orcid.org/0009-0005-0471-0186"},"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":"Ruijia Zhang","raw_affiliation_strings":["Ministry of Education, Shandong Computer Science Center, Qilu University of Technology (Shandong Academy of Sciences),Key Laboratory of Computing Power Network and Information Security,Jinan,China"],"affiliations":[{"raw_affiliation_string":"Ministry of Education, Shandong Computer Science Center, Qilu University of Technology (Shandong Academy of Sciences),Key Laboratory of Computing Power Network and Information Security,Jinan,China","institution_ids":["https://openalex.org/I152269853","https://openalex.org/I4210142748"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100718730","display_name":"Jianqiang Zhang","orcid":"https://orcid.org/0000-0003-2019-1185"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianqiang Zhang","raw_affiliation_strings":["Shandong Branch of China Mobile Communication Group Design Institute Co.,Jinan,China"],"affiliations":[{"raw_affiliation_string":"Shandong Branch of China Mobile Communication Group Design Institute Co.,Jinan,China","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102703970","display_name":"Gongpeng Song","orcid":null},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gongpeng Song","raw_affiliation_strings":["Shandong Branch of China Mobile Communication Group Design Institute Co.,Jinan,China"],"affiliations":[{"raw_affiliation_string":"Shandong Branch of China Mobile Communication Group Design Institute Co.,Jinan,China","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019494928","display_name":"Lu Qin","orcid":"https://orcid.org/0000-0001-7305-0568"},"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":"Qin Lu","raw_affiliation_strings":["Ministry of Education, Shandong Computer Science Center, Qilu University of Technology (Shandong Academy of Sciences),Key Laboratory of Computing Power Network and Information Security,Jinan,China"],"affiliations":[{"raw_affiliation_string":"Ministry of Education, Shandong Computer Science Center, Qilu University of Technology (Shandong Academy of Sciences),Key Laboratory of Computing Power Network and Information Security,Jinan,China","institution_ids":["https://openalex.org/I152269853","https://openalex.org/I4210142748"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5049496913"],"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":0.15922635,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1698","last_page":"1703"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9973000288009644,"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":0.9973000288009644,"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":0.9932000041007996,"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":0.9621999859809875,"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":0.7405779957771301},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.581874430179596},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5816971659660339},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5027921199798584},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4143259823322296},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4034213423728943},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37049272656440735},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3440856337547302},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.14251354336738586},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0998762845993042},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.06642907857894897},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.06639063358306885}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7405779957771301},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.581874430179596},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5816971659660339},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5027921199798584},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4143259823322296},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4034213423728943},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37049272656440735},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3440856337547302},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.14251354336738586},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0998762845993042},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.06642907857894897},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.06639063358306885},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cscwd64889.2025.11033666","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cscwd64889.2025.11033666","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W2185175083","https://openalex.org/W2277195237","https://openalex.org/W2552579943","https://openalex.org/W2765440071","https://openalex.org/W2894786240","https://openalex.org/W2962964995","https://openalex.org/W2963389687","https://openalex.org/W2981586349","https://openalex.org/W2988823324","https://openalex.org/W2994818707","https://openalex.org/W3035454331","https://openalex.org/W3088460296","https://openalex.org/W3092820619","https://openalex.org/W3121848148","https://openalex.org/W3175888430","https://openalex.org/W3213100861","https://openalex.org/W4292794834","https://openalex.org/W4312761738","https://openalex.org/W4386071757","https://openalex.org/W4390872733","https://openalex.org/W4402727805","https://openalex.org/W6678470764"],"related_works":["https://openalex.org/W2087793626","https://openalex.org/W2755342338","https://openalex.org/W2779427294","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],"matching":[1,68,187],"is":[2,146],"an":[3,89],"important":[4],"and":[5,23,72,100,135,172,192],"challenging":[6],"task":[7],"in":[8,42,185,197],"the":[9,17,105,158,190],"field":[10,28],"of":[11,97,160,194],"multimedia":[12],"analysis,":[13],"aimed":[14],"at":[15,132],"bridging":[16],"semantic":[18,56,107],"gap":[19],"between":[20],"visual":[21,74,98],"content":[22],"language":[24],"descriptions.":[25],"Although":[26],"this":[27,60],"has":[29],"significant":[30],"implications":[31],"for":[32,119],"enhancing":[33],"cross-modal":[34,199],"interaction,":[35],"most":[36],"previous":[37],"work":[38],"still":[39],"faces":[40],"challenges":[41],"accurately":[43],"aligning":[44],"images":[45,53],"with":[46,52,78,152],"text":[47,80,101,154],"descriptions,":[48],"especially":[49],"when":[50],"dealing":[51],"containing":[54],"rich":[55],"information.":[57],"To":[58,156],"address":[59],"issue,":[61],"we":[62,87,163],"propose":[63],"a":[64,83,125],"novel":[65],"context-aware":[66,91],"image-text":[67,186],"model":[69,113,180,196],"that":[70,178],"extracts":[71],"summarizes":[73],"region":[75],"information":[76,118],"aligned":[77],"multiple":[79,133],"descriptions":[81],"from":[82],"single":[84],"image.":[85],"Specifically,":[86],"designed":[88],"adaptive":[90],"self-attention":[92],"module":[93],"to":[94,129,148],"extract":[95,130],"representations":[96],"regions":[99],"words.":[102],"By":[103],"controlling":[104],"complementary":[106],"relationships":[108],"within":[109],"each":[110,120],"modality,":[111],"our":[112,161,179,195],"can":[114],"adaptively":[115],"capture":[116],"contextual":[117],"modality.":[121],"We":[122],"then":[123],"introduce":[124],"Transformer-based":[126],"encoder":[127],"layer":[128],"features":[131,138,151],"levels":[134],"aggregate":[136],"region-level":[137],"into":[139],"image-level":[140],"features.":[141,155],"Finally,":[142],"fine-grained":[143],"word-region":[144],"alignment":[145],"conducted":[147,164],"match":[149],"image":[150],"corresponding":[153],"evaluate":[157],"effectiveness":[159,191],"method,":[162],"extensive":[165],"experiments":[166],"on":[167],"two":[168],"benchmark":[169],"datasets,":[170],"Flickr30K":[171],"MS-COCO.":[173],"The":[174],"experimental":[175],"results":[176],"show":[177],"outper-forms":[181],"several":[182],"state-of-the-art":[183],"baselines":[184],"tasks,":[188],"demonstrating":[189],"practicality":[193],"handline":[198],"retrieval":[200],"tasks.":[201]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}