{"id":"https://openalex.org/W4416017419","doi":"https://doi.org/10.1145/3746252.3760959","title":"Sparse and Dense Retrievers Learn Better Together: Joint Sparse-Dense Optimization for Text-Image Retrieval","display_name":"Sparse and Dense Retrievers Learn Better Together: Joint Sparse-Dense Optimization for Text-Image Retrieval","publication_year":2025,"publication_date":"2025-11-08","ids":{"openalex":"https://openalex.org/W4416017419","doi":"https://doi.org/10.1145/3746252.3760959"},"language":null,"primary_location":{"id":"doi:10.1145/3746252.3760959","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746252.3760959","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746252.3760959","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Jonghyun Song","orcid":"https://orcid.org/0009-0002-5812-4746"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Jonghyun Song","raw_affiliation_strings":["Graduate School of Data Science, Seoul National University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0002-5812-4746","affiliations":[{"raw_affiliation_string":"Graduate School of Data Science, Seoul National University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007984753","display_name":"Youngjune Lee","orcid":"https://orcid.org/0009-0008-1997-4135"},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Youngjune Lee","raw_affiliation_strings":["NAVER Corporation, Seongnam, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0008-1997-4135","affiliations":[{"raw_affiliation_string":"NAVER Corporation, Seongnam, Republic of Korea","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Gyu-Hwung Cho","orcid":"https://orcid.org/0009-0000-0944-209X"},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Gyu-Hwung Cho","raw_affiliation_strings":["NAVER Corporation, Seongnam, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0000-0944-209X","affiliations":[{"raw_affiliation_string":"NAVER Corporation, Seongnam, Republic of Korea","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032791644","display_name":"Ilhyeon Song","orcid":"https://orcid.org/0009-0007-2120-313X"},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Ilhyeon Song","raw_affiliation_strings":["NAVER Corporation, Seongnam, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0007-2120-313X","affiliations":[{"raw_affiliation_string":"NAVER Corporation, Seongnam, Republic of Korea","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103197440","display_name":"Saehun Kim","orcid":"https://orcid.org/0000-0002-7250-2654"},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Saehun Kim","raw_affiliation_strings":["NAVER Corporation, Seongnam, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-7250-2654","affiliations":[{"raw_affiliation_string":"NAVER Corporation, Seongnam, Republic of Korea","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021733732","display_name":"Yohan Jo","orcid":"https://orcid.org/0009-0006-9296-3403"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yohan Jo","raw_affiliation_strings":["Graduate School of Data Science, Seoul National University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0006-9296-3403","affiliations":[{"raw_affiliation_string":"Graduate School of Data Science, Seoul National University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.31723894,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5268","last_page":"5272"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8021000027656555,"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":0.8021000027656555,"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":0.06549999862909317,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.02459999918937683,"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/interpretability","display_name":"Interpretability","score":0.7470999956130981},{"id":"https://openalex.org/keywords/sparse-approximation","display_name":"Sparse approximation","score":0.5719000101089478},{"id":"https://openalex.org/keywords/neural-coding","display_name":"Neural coding","score":0.5625},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.4343000054359436},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4332999885082245},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.40939998626708984},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.39239999651908875},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.38940000534057617}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7897999882698059},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.7470999956130981},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6371999979019165},{"id":"https://openalex.org/C124066611","wikidata":"https://www.wikidata.org/wiki/Q28684319","display_name":"Sparse approximation","level":2,"score":0.5719000101089478},{"id":"https://openalex.org/C77637269","wikidata":"https://www.wikidata.org/wiki/Q7002051","display_name":"Neural coding","level":2,"score":0.5625},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.4343000054359436},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4332999885082245},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.40939998626708984},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.39239999651908875},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.38940000534057617},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.3889999985694885},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.3878999948501587},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3702000081539154},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.35040000081062317},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.31130000948905945},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.2904999852180481},{"id":"https://openalex.org/C2988886741","wikidata":"https://www.wikidata.org/wiki/Q25304494","display_name":"Dictionary learning","level":3,"score":0.2888999879360199},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.27799999713897705},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.26980000734329224},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2605000138282776},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.2578999996185303},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.25429999828338623}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746252.3760959","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746252.3760959","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3746252.3760959","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746252.3760959","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1773149199","https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W2149530645","https://openalex.org/W3154280800","https://openalex.org/W3154755316","https://openalex.org/W4292828275","https://openalex.org/W4312749754","https://openalex.org/W4321471832","https://openalex.org/W4386065462","https://openalex.org/W4387272106","https://openalex.org/W4389524238","https://openalex.org/W4390603585","https://openalex.org/W4390872633","https://openalex.org/W4392846392","https://openalex.org/W4396821195"],"related_works":[],"abstract_inverted_index":{"Vision-Language":[0],"Pretrained":[1],"(VLP)":[2],"models":[3],"have":[4],"achieved":[5,106],"impressive":[6],"performance":[7,172],"on":[8,15,60,154],"multimodal":[9,53],"tasks,":[10],"including":[11],"text-image":[12],"retrieval,":[13],"based":[14],"dense":[16,70,95,115,138,177],"representations.":[17,127],"Meanwhile,":[18],"Learned":[19],"Sparse":[20],"Retrieval":[21],"(LSR)":[22],"has":[23,48],"gained":[24],"traction":[25],"in":[26],"text-only":[27],"settings":[28],"due":[29],"to":[30,51],"its":[31],"interpretability":[32],"and":[33,96,116,140,156],"efficiency":[34],"with":[35],"fast":[36],"term-based":[37],"lookup":[38],"via":[39],"inverted":[40],"indexes.":[41],"Inspired":[42],"by":[43],"these":[44,56,81],"advantages,":[45],"recent":[46],"work":[47],"extended":[49],"LSR":[50],"the":[52,74,133,137,141,181],"domain.":[54],"However,":[55],"methods":[57],"often":[58],"rely":[59],"computationally":[61],"expensive":[62],"contrastive":[63],"pre-training,":[64],"or":[65],"distillation":[66],"from":[67],"a":[68,85,121],"frozen":[69],"model,":[71],"which":[72],"limits":[73],"potential":[75],"for":[76,125],"mutual":[77],"enhancement.":[78],"To":[79,128],"address":[80],"limitations,":[82],"we":[83,131],"propose":[84],"simple":[86],"yet":[87],"effective":[88],"framework":[89],"that":[90,159],"enables":[91],"bi-directional":[92,103],"learning":[93,104],"between":[94],"sparse":[97,117,142,161,167,184],"representations":[98],"through":[99],"Self-Knowledge":[100],"Distillation.":[101],"This":[102],"is":[105],"using":[107],"an":[108],"integrated":[109],"similarity":[110],"score-a":[111],"weighted":[112],"sum":[113],"of":[114,136,148,183],"similarities-which":[118],"serves":[119],"as":[120],"shared":[122],"teacher":[123],"signal":[124],"both":[126],"ensure":[129],"efficiency,":[130],"fine-tune":[132],"final":[134],"layer":[135],"encoder":[139],"projection":[143],"head,":[144],"enabling":[145],"easy":[146],"adaptation":[147],"any":[149],"existing":[150,166],"VLP":[151],"model.":[152],"Experiments":[153],"MSCOCO":[155],"Flickr30k":[157],"demonstrate":[158],"our":[160],"retriever":[162],"not":[163],"only":[164],"outperforms":[165],"baselines,":[168],"but":[169],"also":[170],"achieves":[171],"comparable":[173],"to-or":[174],"even":[175],"surpassing-its":[176],"counterparts,":[178],"while":[179],"retaining":[180],"benefits":[182],"models.":[185]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-11-08T00:00:00"}