{"id":"https://openalex.org/W4401978738","doi":"https://doi.org/10.1145/3664647.3680860","title":"PC <sup>2</sup> : Pseudo-Classification Based Pseudo-Captioning for Noisy Correspondence Learning in Cross-Modal Retrieval","display_name":"PC <sup>2</sup> : Pseudo-Classification Based Pseudo-Captioning for Noisy Correspondence Learning in Cross-Modal Retrieval","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4401978738","doi":"https://doi.org/10.1145/3664647.3680860"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3680860","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680860","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2408.01349","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102993514","display_name":"Yue Duan","orcid":"https://orcid.org/0000-0003-4131-7146"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Duan","raw_affiliation_strings":["Nanjing University &amp; Ant Group, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-4131-7146","affiliations":[{"raw_affiliation_string":"Nanjing University &amp; Ant Group, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101878836","display_name":"Zhangxuan Gu","orcid":"https://orcid.org/0000-0002-2102-2693"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhangxuan Gu","raw_affiliation_strings":["Ant Group, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-2102-2693","affiliations":[{"raw_affiliation_string":"Ant Group, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071130920","display_name":"Zhenzhe Ying","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhenzhe Ying","raw_affiliation_strings":["Ant Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0000-9624-3776","affiliations":[{"raw_affiliation_string":"Ant Group, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100667506","display_name":"Lei Qi","orcid":"https://orcid.org/0000-0001-7091-0702"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Qi","raw_affiliation_strings":["Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-7091-0702","affiliations":[{"raw_affiliation_string":"Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005372125","display_name":"Changhua Meng","orcid":"https://orcid.org/0000-0001-8992-9833"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Changhua Meng","raw_affiliation_strings":["Ant Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-8992-9833","affiliations":[{"raw_affiliation_string":"Ant Group, Hangzhou, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103058012","display_name":"Yinghuan Shi","orcid":"https://orcid.org/0009-0008-0722-9744"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinghuan Shi","raw_affiliation_strings":["Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0008-0722-9744","affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9397","last_page":"9406"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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":0.9991000294685364,"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":0.9969000220298767,"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/closed-captioning","display_name":"Closed captioning","score":0.8305235505104065},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8222922682762146},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5985010266304016},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.5777221918106079},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5566638708114624},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5305054187774658},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.505439043045044},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.4871687591075897},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.44054001569747925},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4360373020172119},{"id":"https://openalex.org/keywords/intersection","display_name":"Intersection (aeronautics)","score":0.4228837490081787},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4107983112335205},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3587934970855713},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3500022888183594},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2491026520729065},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.20286774635314941}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8305235505104065},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8222922682762146},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5985010266304016},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.5777221918106079},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5566638708114624},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5305054187774658},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.505439043045044},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.4871687591075897},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.44054001569747925},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4360373020172119},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.4228837490081787},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4107983112335205},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3587934970855713},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3500022888183594},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2491026520729065},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.20286774635314941},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3664647.3680860","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680860","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2408.01349","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.01349","pdf_url":"https://arxiv.org/pdf/2408.01349","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2408.01349","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.01349","pdf_url":"https://arxiv.org/pdf/2408.01349","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4300000071525574,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G2767813700","display_name":null,"funder_award_id":"62192783","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5700602903","display_name":null,"funder_award_id":"62222604","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G571287390","display_name":null,"funder_award_id":"BK20210224","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"},{"id":"https://openalex.org/G6421693584","display_name":null,"funder_award_id":"62206052","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6794352704","display_name":null,"funder_award_id":"2024M750424","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"},{"id":"https://openalex.org/G7336104399","display_name":null,"funder_award_id":"020214380120","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320318398","display_name":"Ant Group","ror":null},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"},{"id":"https://openalex.org/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4401978738.pdf","grobid_xml":"https://content.openalex.org/works/W4401978738.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1930223417","https://openalex.org/W2131774270","https://openalex.org/W2302086703","https://openalex.org/W2745461083","https://openalex.org/W2886641317","https://openalex.org/W2962681491","https://openalex.org/W2963389687","https://openalex.org/W2985951359","https://openalex.org/W2988281744","https://openalex.org/W2988823324","https://openalex.org/W3035454331","https://openalex.org/W3042609801","https://openalex.org/W3090449556","https://openalex.org/W3110446398","https://openalex.org/W3113960880","https://openalex.org/W3118694826","https://openalex.org/W3158278463","https://openalex.org/W3159481202","https://openalex.org/W3176451698","https://openalex.org/W3194543108","https://openalex.org/W4304014355","https://openalex.org/W4312108898","https://openalex.org/W4312891522","https://openalex.org/W4386076004","https://openalex.org/W4386076160","https://openalex.org/W4386076631","https://openalex.org/W4390872613","https://openalex.org/W4392172801","https://openalex.org/W4393147410","https://openalex.org/W4393156560","https://openalex.org/W4402753983"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393","https://openalex.org/W4289422896"],"abstract_inverted_index":{"In":[0,123],"the":[1,18,75,111,119],"realm":[2],"of":[3,113,121,136,153],"cross-modal":[4,162],"retrieval,":[5],"seamlessly":[6],"integrating":[7],"diverse":[8],"modalities":[9],"within":[10],"multimedia":[11],"remains":[12],"a":[13,36,58,83,130,142],"formidable":[14],"challenge,":[15],"especially":[16],"given":[17],"complexities":[19],"introduced":[20],"by":[21],"noisy":[22,42],"correspondence":[23],"learning":[24],"(NCL).":[25],"Such":[26],"noise":[27,148],"often":[28],"stems":[29],"from":[30,40],"mismatched":[31,108],"data":[32],"pairs,":[33],"which":[34,139],"is":[35,115],"significant":[37],"obstacle":[38],"distinct":[39],"traditional":[41],"labels.":[43],"This":[44],"paper":[45],"introduces":[46],"Pseudo-Classification":[47],"based":[48],"Pseudo-Captioning":[49],"(PC$^2$)":[50],"framework":[51],"to":[52,77,99,117,125],"address":[53],"this":[54],"challenge.":[55],"PC$^2$":[56,154],"offers":[57],"threefold":[59],"strategy:":[60],"firstly,":[61],"it":[62],"establishes":[63],"an":[64],"auxiliary":[65],"\"pseudo-classification\"":[66],"task":[67],"that":[68],"interprets":[69],"captions":[70],"as":[71],"categorical":[72],"labels,":[73],"steering":[74],"model":[76],"learn":[78],"image-text":[79],"semantic":[80],"similarity":[81],"through":[82],"non-contrastive":[84],"mechanism.":[85],"Secondly,":[86],"unlike":[87],"prevailing":[88],"margin-based":[89],"techniques,":[90],"capitalizing":[91],"on":[92,165],"PC$^2$'s":[93],"pseudo-classification":[94,114],"capability,":[95],"we":[96,128],"generate":[97],"pseudo-captions":[98],"provide":[100],"more":[101],"informative":[102],"and":[103,168,178],"tangible":[104],"supervision":[105],"for":[106],"each":[107],"pair.":[109],"Thirdly,":[110],"oscillation":[112],"borrowed":[116],"assistant":[118],"correction":[120],"correspondence.":[122],"addition":[124],"technical":[126],"contributions,":[127],"develop":[129],"realistic":[131,169],"NCL":[132,145,173],"dataset":[133,177],"called":[134],"Noise":[135],"Web":[137],"(NoW),":[138],"could":[140],"be":[141],"new":[143],"powerful":[144],"benchmark":[146],"where":[147],"exists":[149],"naturally.":[150],"Empirical":[151],"evaluations":[152],"showcase":[155],"marked":[156],"improvements":[157],"over":[158],"existing":[159],"state-of-the-art":[160],"robust":[161],"retrieval":[163],"techniques":[164],"both":[166],"simulated":[167],"datasets":[170],"with":[171],"various":[172],"settings.":[174],"The":[175],"contributed":[176],"source":[179],"code":[180],"are":[181],"released":[182],"at":[183],"https://github.com/alipay/PC2-NoiseofWeb.":[184]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2024-08-29T00:00:00"}