{"id":"https://openalex.org/W4402979766","doi":"https://doi.org/10.1109/icme57554.2024.10688342","title":"CoVLR: Coordinating Cross-Modal Consistency and Intra-Modal Relations for Vision-Language Retrieval","display_name":"CoVLR: Coordinating Cross-Modal Consistency and Intra-Modal Relations for Vision-Language Retrieval","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402979766","doi":"https://doi.org/10.1109/icme57554.2024.10688342"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10688342","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10688342","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","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/A5114236921","display_name":"Fengqiang Wan","orcid":null},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Fengqiang Wan","raw_affiliation_strings":["Nanjing University of Science and Technology"],"affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021998562","display_name":"Xiangyu Wu","orcid":"https://orcid.org/0000-0003-2055-5890"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangyu Wu","raw_affiliation_strings":["Nanjing University of Science and Technology"],"affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004376958","display_name":"Zhihao Guan","orcid":"https://orcid.org/0000-0002-1292-0117"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihao Guan","raw_affiliation_strings":["Nanjing University of Science and Technology"],"affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107677649","display_name":"Yang Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Yang","raw_affiliation_strings":["Nanjing University of Science and Technology"],"affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology","institution_ids":["https://openalex.org/I36399199"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5114236921"],"corresponding_institution_ids":["https://openalex.org/I36399199"],"apc_list":null,"apc_paid":null,"fwci":0.7895,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.73549488,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9968000054359436,"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":0.9968000054359436,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9790999889373779,"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/T12031","display_name":"Speech and dialogue systems","score":0.960099995136261,"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/modal","display_name":"Modal","score":0.8392797708511353},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7115538120269775},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6740209460258484},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46640530228614807},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.444046288728714}],"concepts":[{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.8392797708511353},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7115538120269775},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6740209460258484},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46640530228614807},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.444046288728714},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/icme57554.2024.10688342","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10688342","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2808958151","https://openalex.org/W2962964995","https://openalex.org/W3035333188","https://openalex.org/W3118694826","https://openalex.org/W3161727935","https://openalex.org/W3175481246","https://openalex.org/W3187464273","https://openalex.org/W4288966168","https://openalex.org/W4312761738","https://openalex.org/W4388304009","https://openalex.org/W6736057607","https://openalex.org/W6747225742","https://openalex.org/W6755207826","https://openalex.org/W6766904570","https://openalex.org/W6767291801","https://openalex.org/W6839415613"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Vision-language":[0],"retrieval":[1,61,133],"aims":[2],"to":[3,98,128],"perform":[4],"cross-modal":[5,79,101],"instances":[6,50],"search":[7],"by":[8],"learning":[9],"consistent":[10],"vision-language":[11,17,42],"representations.":[12],"However,":[13],"in":[14,21,32,59],"real":[15],"applications,":[16],"divergence":[18],"always":[19],"results":[20,126],"strong":[22],"and":[23,26,81],"weak":[24],"modalities":[25,28],"different":[27],"have":[29],"various":[30,132],"performances":[31],"uni-modal":[33,49,60],"tasks.":[34],"In":[35],"this":[36,65],"paper,":[37],"we":[38,67],"reveal":[39],"that":[40,75],"traditional":[41],"hard":[43],"consistency":[44,80,102],"disrupts":[45],"the":[46,52,95,100,107],"relationships":[47],"among":[48],"considering":[51],"weak-strong":[53],"modal":[54],"scenario,":[55],"causing":[56],"a":[57,73,86],"decline":[58],"capability.":[62],"To":[63],"address":[64],"issue,":[66],"propose":[68],"Coordinated":[69],"Vision-Language":[70],"Retrieval":[71],"(CoVLR),":[72],"solution":[74],"cooperatively":[76],"optimizes":[77],"both":[78],"intra-modal":[82,92],"structure-preserving":[83,93],"objectives":[84],"via":[85],"meta-learning":[87],"strategy.":[88],"Specifically,":[89],"CoVLR":[90,113],"utilizes":[91],"as":[94],"meta-test":[96],"task":[97],"validate":[99],"loss,":[103],"which":[104,123],"is":[105,114],"considered":[106],"meta-train":[108],"task.":[109],"The":[110],"effectiveness":[111],"of":[112],"validated":[115],"through":[116],"extensive":[117],"experiments":[118],"on":[119,131],"commonly":[120],"used":[121],"datasets,":[122],"demonstrate":[124],"superior":[125],"compared":[127],"other":[129],"baselines":[130],"scenarios.":[134]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}