{"id":"https://openalex.org/W4285428325","doi":"https://doi.org/10.1145/3503161.3548108","title":"IDEA: Increasing Text Diversity via Online Multi-Label Recognition for Vision-Language Pre-training","display_name":"IDEA: Increasing Text Diversity via Online Multi-Label Recognition for Vision-Language Pre-training","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4285428325","doi":"https://doi.org/10.1145/3503161.3548108"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3548108","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548108","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2207.05333","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044478041","display_name":"Xinyu Huang","orcid":"https://orcid.org/0000-0003-3210-3891"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xinyu Huang","raw_affiliation_strings":["Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042517423","display_name":"Youcai Zhang","orcid":"https://orcid.org/0000-0003-1967-4091"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Youcai Zhang","raw_affiliation_strings":["Fudan University, Shanghai, China","OPPO Research Institute, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"OPPO Research Institute, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060790908","display_name":"Ying Cheng","orcid":"https://orcid.org/0000-0002-9103-6126"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Cheng","raw_affiliation_strings":["Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110964104","display_name":"Weiwei Tian","orcid":"https://orcid.org/0000-0002-3725-8457"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiwei Tian","raw_affiliation_strings":["Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100626035","display_name":"Rui-Wei Zhao","orcid":"https://orcid.org/0000-0002-8498-5761"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruiwei Zhao","raw_affiliation_strings":["Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109435836","display_name":"Rui Feng","orcid":"https://orcid.org/0000-0002-0611-9518"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Feng","raw_affiliation_strings":["Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070073283","display_name":"Yuejie Zhang","orcid":"https://orcid.org/0000-0001-7993-7223"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuejie Zhang","raw_affiliation_strings":["Fudan University, Shanghai, China","OPPO Research Institute, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"OPPO Research Institute, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100697596","display_name":"Yaqian Li","orcid":"https://orcid.org/0000-0002-3541-2836"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yaqian Li","raw_affiliation_strings":["OPPO Research Institute, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"OPPO Research Institute, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038064028","display_name":"Yandong Guo","orcid":"https://orcid.org/0000-0002-4594-8415"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yandong Guo","raw_affiliation_strings":["OPPO Research Institute, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"OPPO Research Institute, Shanghai, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5115592812","display_name":"Xiaobo Zhang","orcid":"https://orcid.org/0009-0005-0532-6100"},"institutions":[{"id":"https://openalex.org/I4210159329","display_name":"Children's Hospital of Fudan University","ror":"https://ror.org/05n13be63","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210159329"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaobo Zhang","raw_affiliation_strings":["Children's Hospital of Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Children's Hospital of Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I4210159329"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5044478041"],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":0.4188,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.70021292,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4573","last_page":"4583"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9984999895095825,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9916999936103821,"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":0.8085446357727051},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.6723190546035767},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6329785585403442},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6003769040107727},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5905910730361938},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.5651431083679199},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5389009714126587},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.4896419644355774},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.45908135175704956},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.44154250621795654},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4186365604400635},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3855217397212982},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.370606392621994},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3654188811779022},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.35948556661605835},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.13278895616531372}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8085446357727051},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.6723190546035767},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6329785585403442},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6003769040107727},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5905910730361938},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.5651431083679199},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5389009714126587},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.4896419644355774},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.45908135175704956},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44154250621795654},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4186365604400635},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3855217397212982},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.370606392621994},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3654188811779022},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.35948556661605835},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.13278895616531372},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3503161.3548108","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548108","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2207.05333","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2207.05333","pdf_url":"https://arxiv.org/pdf/2207.05333","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2207.05333","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2207.05333","pdf_url":"https://arxiv.org/pdf/2207.05333","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.6899999976158142,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G612163380","display_name":null,"funder_award_id":"No.2021ZD0113501","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G8266941071","display_name":null,"funder_award_id":"No.62172101, No.61976057","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/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":56,"referenced_works":["https://openalex.org/W12634471","https://openalex.org/W639708223","https://openalex.org/W1889081078","https://openalex.org/W1977295328","https://openalex.org/W2017814585","https://openalex.org/W2047643928","https://openalex.org/W2108598243","https://openalex.org/W2143017621","https://openalex.org/W2155904486","https://openalex.org/W2277195237","https://openalex.org/W2533598788","https://openalex.org/W2886641317","https://openalex.org/W2896457183","https://openalex.org/W2916025244","https://openalex.org/W2953320089","https://openalex.org/W2963263347","https://openalex.org/W2966715458","https://openalex.org/W2968124245","https://openalex.org/W2969792713","https://openalex.org/W2970231061","https://openalex.org/W2990138404","https://openalex.org/W3030520226","https://openalex.org/W3035682985","https://openalex.org/W3090449556","https://openalex.org/W3091588028","https://openalex.org/W3094502228","https://openalex.org/W3096609285","https://openalex.org/W3118608800","https://openalex.org/W3126337491","https://openalex.org/W3135367836","https://openalex.org/W3152798676","https://openalex.org/W3158124198","https://openalex.org/W3159481202","https://openalex.org/W3165691894","https://openalex.org/W3166396011","https://openalex.org/W3173220247","https://openalex.org/W3176799298","https://openalex.org/W3181158454","https://openalex.org/W3184087575","https://openalex.org/W3184735396","https://openalex.org/W3184784418","https://openalex.org/W3216083537","https://openalex.org/W4221167444","https://openalex.org/W4226027139","https://openalex.org/W4226058394","https://openalex.org/W4226095984","https://openalex.org/W4226182655","https://openalex.org/W4286336838","https://openalex.org/W4286906902","https://openalex.org/W4288083516","https://openalex.org/W4297808394","https://openalex.org/W4302301828","https://openalex.org/W4312480274","https://openalex.org/W4312629998","https://openalex.org/W4312784228","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2366906938","https://openalex.org/W2349391998","https://openalex.org/W4205655149","https://openalex.org/W4243145179","https://openalex.org/W4255875982","https://openalex.org/W4244853958","https://openalex.org/W2000775715","https://openalex.org/W4292830139","https://openalex.org/W4319309705","https://openalex.org/W2794942387"],"abstract_inverted_index":{"Vision-Language":[0],"Pre-training":[1],"(VLP)":[2],"with":[3,97,138],"large-scale":[4],"image-text":[5,16],"pairs":[6,17],"has":[7],"demonstrated":[8],"superior":[9],"performance":[10,133],"in":[11],"various":[12],"fields.":[13],"However,":[14,47],"the":[15,20,48,57,62,67,70,102,132],"co-occurrent":[18],"on":[19,134],"Internet":[21],"typically":[22],"lack":[23],"explicit":[24,121],"alignment":[25],"information,":[26,76],"which":[27,80],"is":[28,51],"suboptimal":[29],"for":[30,82,90],"VLP.":[31,91,109],"Existing":[32],"methods":[33],"proposed":[34],"to":[35,41,118],"adopt":[36],"an":[37],"off-the-shelf":[38],"object":[39,49,59],"detector":[40,50],"utilize":[42],"additional":[43],"image":[44,75,98,115],"tag":[45],"information.":[46],"time-consuming":[52],"and":[53],"can":[54,104,112,129],"only":[55],"identify":[56,113],"pre-defined":[58],"categories,":[60],"limiting":[61],"model":[63],"capacity.":[64],"Inspired":[65],"by":[66],"observation":[68],"that":[69,94,127],"texts":[71,103],"incorporate":[72],"incomplete":[73],"fine-grained":[74],"we":[77],"introduce":[78],"IDEA,":[79],"stands":[81],"increasing":[83],"text":[84],"diversity":[85],"via":[86],"online":[87,117],"multi-label":[88,95],"recognition":[89],"IDEA":[92,111,128],"shows":[93],"learning":[96],"tags":[99,116],"extracted":[100],"from":[101],"be":[105],"jointly":[106],"optimized":[107],"during":[108],"Moreover,":[110],"valuable":[114],"provide":[119],"more":[120],"textual":[122],"supervision.":[123],"Comprehensive":[124],"experiments":[125],"demonstrate":[126],"significantly":[130],"boost":[131],"multiple":[135],"downstream":[136],"datasets":[137],"a":[139],"small":[140],"extra":[141],"computational":[142],"cost.":[143]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2022-07-15T00:00:00"}