{"id":"https://openalex.org/W4402979618","doi":"https://doi.org/10.1109/icme57554.2024.10687580","title":"Coarse-to-fine Alignment Makes Better Speech-image Retrieval","display_name":"Coarse-to-fine Alignment Makes Better Speech-image Retrieval","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402979618","doi":"https://doi.org/10.1109/icme57554.2024.10687580"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10687580","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icme57554.2024.10687580","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/A5049844296","display_name":"Lifeng Zhou","orcid":"https://orcid.org/0000-0001-5479-3681"},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lifeng Zhou","raw_affiliation_strings":["Netease Yidun AI Lab,Hangzhou,China"],"affiliations":[{"raw_affiliation_string":"Netease Yidun AI Lab,Hangzhou,China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100697204","display_name":"Yuke Li","orcid":"https://orcid.org/0009-0000-7282-8964"},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuke Li","raw_affiliation_strings":["Netease Yidun AI Lab,Hangzhou,China"],"affiliations":[{"raw_affiliation_string":"Netease Yidun AI Lab,Hangzhou,China","institution_ids":["https://openalex.org/I4210091137"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5049844296"],"corresponding_institution_ids":["https://openalex.org/I4210091137"],"apc_list":null,"apc_paid":null,"fwci":0.3616,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.67498994,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9965999722480774,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9965999722480774,"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/T11309","display_name":"Music and Audio Processing","score":0.975600004196167,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9639000296592712,"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":0.791675329208374},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.5810714364051819},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5805715322494507},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4476293623447418},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4044281840324402},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.39084428548812866},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3871980607509613},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3600883483886719}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.791675329208374},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.5810714364051819},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5805715322494507},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4476293623447418},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4044281840324402},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.39084428548812866},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3871980607509613},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3600883483886719}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme57554.2024.10687580","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icme57554.2024.10687580","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":[{"id":"https://metadata.un.org/sdg/10","score":0.4099999964237213,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2755342338","https://openalex.org/W2775347418","https://openalex.org/W2087793626","https://openalex.org/W2779427294","https://openalex.org/W2052697133","https://openalex.org/W2625805835","https://openalex.org/W2079911747","https://openalex.org/W3116076068","https://openalex.org/W2069885731","https://openalex.org/W2563206327"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,58,104],"propose":[4],"a":[5,25,50],"novel":[6],"framework":[7,117,144],"for":[8,132],"speech-image":[9,13,29,134],"retrieval.":[10],"We":[11],"utilize":[12,59],"contrastive":[14,91],"(SIC)":[15],"learning":[16,32,44,56,80,100],"tasks":[17,33,45,83],"to":[18,34],"align":[19],"speech":[20],"and":[21,28,42,69],"image":[22],"representations":[23,72],"at":[24],"coarse":[26],"level":[27],"matching":[30],"(SIM)":[31],"further":[35,98],"refine":[36],"the":[37,55,79,109,119,133],"fine-grained":[38],"cross-modal":[39],"alignment.":[40],"SIC":[41,74,95],"SIM":[43,82],"are":[46],"jointly":[47],"trained":[48],"in":[49,94,126,140],"unified":[51],"manner.":[52],"To":[53,97],"optimize":[54,99],"process,":[57],"an":[60],"embedding":[61],"queue":[62],"that":[63,115],"facilitates":[64],"efficient":[65],"sampling":[66],"of":[67,81],"high-quality":[68],"diverse":[70],"negative":[71],"during":[73],"learning.":[75],"Additionally,":[76],"it":[77],"enhances":[78],"by":[84,122],"effectively":[85],"mining":[86],"hard":[87],"negatives":[88],"based":[89],"on":[90,128],"similarities":[92],"calculated":[93],"tasks.":[96,136],"under":[101],"noisy":[102],"supervision,":[103],"incorporate":[105],"momentum":[106],"distillation":[107],"into":[108],"training":[110],"process.":[111],"Experimental":[112],"results":[113],"show":[114],"our":[116,143],"outperforms":[118],"state-of-the-art":[120],"method":[121],"more":[123],"than":[124],"4%":[125],"R@1":[127],"two":[129],"benchmark":[130],"datasets":[131],"retrieval":[135],"Moreover,":[137],"as":[138],"observed":[139],"zero-shot":[141],"experiments,":[142],"demonstrates":[145],"excellent":[146],"generalization":[147],"capabilities.":[148]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-12T08:34:05.389933","created_date":"2025-10-10T00:00:00"}