{"id":"https://openalex.org/W4384661029","doi":"https://doi.org/10.1145/3539618.3592025","title":"Multi-grained Representation Learning for Cross-modal Retrieval","display_name":"Multi-grained Representation Learning for Cross-modal Retrieval","publication_year":2023,"publication_date":"2023-07-18","ids":{"openalex":"https://openalex.org/W4384661029","doi":"https://doi.org/10.1145/3539618.3592025"},"language":"en","primary_location":{"id":"doi:10.1145/3539618.3592025","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3539618.3592025","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","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/A5103240423","display_name":"Shengwei Zhao","orcid":"https://orcid.org/0009-0004-3882-7959"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengwei Zhao","raw_affiliation_strings":["Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, Xian, China"],"raw_orcid":"https://orcid.org/0009-0004-3882-7959","affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, Xian, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013585366","display_name":"Linhai Xu","orcid":"https://orcid.org/0000-0001-7785-6913"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linhai Xu","raw_affiliation_strings":["Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, Xian, China"],"raw_orcid":"https://orcid.org/0000-0001-7785-6913","affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, Xian, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100685987","display_name":"Yuying Liu","orcid":"https://orcid.org/0000-0002-7295-3308"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuying Liu","raw_affiliation_strings":["Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, Xian, China"],"raw_orcid":"https://orcid.org/0000-0002-7295-3308","affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, Xian, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044668212","display_name":"Shaoyi Du","orcid":"https://orcid.org/0000-0002-7092-0596"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaoyi Du","raw_affiliation_strings":["Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, Xian, China"],"raw_orcid":"https://orcid.org/0000-0002-7092-0596","affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, Xian, China","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I87445476"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2194","last_page":"2198"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.9965000152587891,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.98580002784729,"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/computer-science","display_name":"Computer science","score":0.8479710817337036},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.6383041143417358},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.6381017565727234},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6069287657737732},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5345380306243896},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5250943899154663},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4886227250099182},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4841080904006958},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46360456943511963},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.42606157064437866},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3749764561653137},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.35016897320747375}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8479710817337036},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.6383041143417358},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.6381017565727234},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6069287657737732},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5345380306243896},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5250943899154663},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4886227250099182},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4841080904006958},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46360456943511963},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.42606157064437866},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3749764561653137},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.35016897320747375},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3539618.3592025","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3539618.3592025","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7400000095367432}],"awards":[{"id":"https://openalex.org/G1193541440","display_name":null,"funder_award_id":"2020AAA0108100","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G3833898155","display_name":null,"funder_award_id":"62088102","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6961380250","display_name":null,"funder_award_id":"61971343, 62088102","funder_id":"https://openalex.org/F4320334062","funder_display_name":"National Natural Science Foundation of China-Liaoning Joint Fund"},{"id":"https://openalex.org/G8396617935","display_name":"\u57fa\u4e8e\u56fe\u50cf\u70b9\u96c6\u914d\u51c6\u7684\u9ad8\u7cbe\u5ea6\u5927\u8303\u56f4\u4ea4\u901a\u573a\u666f\u4e09\u7ef4\u91cd\u5efa\u65b9\u6cd5\u7814\u7a76","funder_award_id":"61971343","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"},{"id":"https://openalex.org/F4320334062","display_name":"National Natural Science Foundation of China-Liaoning Joint Fund","ror":null},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2595551253","https://openalex.org/W3015591594","https://openalex.org/W3035454331","https://openalex.org/W3035605030","https://openalex.org/W3094550259","https://openalex.org/W3118694826","https://openalex.org/W4210913346","https://openalex.org/W4285606530","https://openalex.org/W4304014690","https://openalex.org/W4312096566","https://openalex.org/W4312372711","https://openalex.org/W6794595090"],"related_works":["https://openalex.org/W2931688134","https://openalex.org/W2377919138","https://openalex.org/W2378857091","https://openalex.org/W103652678","https://openalex.org/W4226090359","https://openalex.org/W2059697060","https://openalex.org/W936373746","https://openalex.org/W2975817033","https://openalex.org/W4382701072","https://openalex.org/W4256502920"],"abstract_inverted_index":{"The":[0],"purpose":[1],"of":[2,56,131,146,164],"audio-text":[3,29,142],"retrieval":[4,30,143],"is":[5,42,51,68,103,125],"to":[6,20,44,77,84,94,108,127],"learn":[7,95],"a":[8,17,25,36,89],"cross-modal":[9],"similarity":[10],"function":[11,83],"between":[12,64,114],"audio":[13,50,65,115,133],"and":[14,66,116,148,156],"text,":[15],"enabling":[16],"given":[18],"audio/text":[19],"find":[21,79],"similar":[22],"text/audio":[23],"from":[24],"candidate":[26],"set.":[27],"Recent":[28],"models":[31],"aggregate":[32,85],"multi-modal":[33,166],"features":[34,87],"into":[35,88],"single-grained":[37,40],"representation.":[38,98,168],"However,":[39],"representation":[41],"difficult":[43],"solve":[45],"the":[46,61,80,86,111,129,151,162],"situation":[47],"that":[48],"an":[49,73],"described":[52],"by":[53],"multiple":[54],"texts":[55],"different":[57,119],"granularity":[58],"levels,":[59],"because":[60],"association":[62],"pattern":[63],"text":[67,117],"complex.":[69],"Therefore,":[70],"we":[71],"propose":[72],"adaptive":[74],"aggregation":[75],"strategy":[76],"automatically":[78],"optimal":[81],"pool":[82],"comprehensive":[90],"representation,":[91],"so":[92],"as":[93],"valuable":[96],"multi-grained":[97,100,167],"And":[99],"comparative":[101],"learning":[102,165],"carried":[104],"out":[105],"in":[106,118,154],"order":[107],"focus":[109],"on":[110,140],"complex":[112],"correlation":[113],"granularity.":[120],"Meanwhile,":[121],"text-guided":[122],"token":[123],"interaction":[124],"used":[126],"reduce":[128],"impact":[130],"redundant":[132],"clips.":[134],"We":[135],"evaluated":[136],"our":[137],"proposed":[138],"method":[139],"two":[141],"benchmark":[144],"datasets":[145],"Audiocaps":[147],"Clotho,":[149],"achieving":[150],"state-of-the-art":[152],"results":[153],"text-to-audio":[155],"audio-to-text":[157],"retrieval.":[158],"Our":[159],"findings":[160],"emphasize":[161],"importance":[163]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}