{"id":"https://openalex.org/W4304080357","doi":"https://doi.org/10.1145/3503161.3547814","title":"Synthesizing Counterfactual Samples for Effective Image-Text Matching","display_name":"Synthesizing Counterfactual Samples for Effective Image-Text Matching","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304080357","doi":"https://doi.org/10.1145/3503161.3547814"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3547814","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3503161.3547814","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3503161.3547814","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":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3503161.3547814","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084193091","display_name":"Wei Hao","orcid":"https://orcid.org/0000-0002-1747-1218"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hao Wei","raw_affiliation_strings":["Key Lab of Intell. Info. Process., Inst. of Comput. Tech., CAS & University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Lab of Intell. Info. Process., Inst. of Comput. Tech., CAS & University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100669242","display_name":"Shuhui Wang","orcid":"https://orcid.org/0000-0002-5931-0527"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuhui Wang","raw_affiliation_strings":["Key Lab of Intell. Info. Process., Inst. of Comput. Tech., CAS & Peng Cheng Laboratory, Beijing;Shenzhen, China","Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Key Lab of Intell. Info. Process., Inst. of Comput. Tech., CAS & Peng Cheng Laboratory, Beijing;Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]},{"raw_affiliation_string":"Shenzhen, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049313711","display_name":"Xinzhe Han","orcid":"https://orcid.org/0000-0002-4599-7399"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinzhe Han","raw_affiliation_strings":["Key Lab of Intell. Info. Process., Inst. of Comput. Tech., CAS & University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Lab of Intell. Info. Process., Inst. of Comput. Tech., CAS & University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088046237","display_name":"Zhe Xue","orcid":"https://orcid.org/0000-0001-6123-0043"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhe Xue","raw_affiliation_strings":["Beijing Key Laboratory of Intelligent Telecommunication Software and Multimedia, BUPT, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Intelligent Telecommunication Software and Multimedia, BUPT, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100749734","display_name":"Bin Ma","orcid":"https://orcid.org/0000-0002-9030-7393"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bin Ma","raw_affiliation_strings":["Meituan Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Meituan Inc., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102862658","display_name":"Xiaoming Wei","orcid":"https://orcid.org/0000-0002-6788-4790"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaoming Wei","raw_affiliation_strings":["Meituan Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Meituan Inc., Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009222019","display_name":"Xiaolin Wei","orcid":"https://orcid.org/0000-0002-3983-047X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaolin Wei","raw_affiliation_strings":["Meituan Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Meituan Inc., Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5084193091"],"corresponding_institution_ids":["https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.5965,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.76760363,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4355","last_page":"4364"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9991000294685364,"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":0.9990000128746033,"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/counterfactual-thinking","display_name":"Counterfactual thinking","score":0.7924772500991821},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.737831711769104},{"id":"https://openalex.org/keywords/generality","display_name":"Generality","score":0.6548281311988831},{"id":"https://openalex.org/keywords/causal-inference","display_name":"Causal inference","score":0.5626174807548523},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.539519190788269},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5176061391830444},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4921414256095886},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.4477423131465912},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.43441492319107056},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.43271690607070923},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42560920119285583},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.39059796929359436},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36094164848327637},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34444817900657654},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15741780400276184},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.15282952785491943}],"concepts":[{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.7924772500991821},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.737831711769104},{"id":"https://openalex.org/C2780767217","wikidata":"https://www.wikidata.org/wiki/Q5532421","display_name":"Generality","level":2,"score":0.6548281311988831},{"id":"https://openalex.org/C158600405","wikidata":"https://www.wikidata.org/wiki/Q5054566","display_name":"Causal inference","level":2,"score":0.5626174807548523},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.539519190788269},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5176061391830444},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4921414256095886},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.4477423131465912},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.43441492319107056},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.43271690607070923},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42560920119285583},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39059796929359436},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36094164848327637},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34444817900657654},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15741780400276184},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.15282952785491943},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503161.3547814","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3503161.3547814","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3503161.3547814","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"}],"best_oa_location":{"id":"doi:10.1145/3503161.3547814","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3503161.3547814","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3503161.3547814","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"},"sustainable_development_goals":[{"score":0.6600000262260437,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G3168249121","display_name":null,"funder_award_id":"62022083, U21B2038 and 61931008","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5327851226","display_name":null,"funder_award_id":"62022083","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6212863906","display_name":null,"funder_award_id":"U21B2038","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7801426869","display_name":null,"funder_award_id":"61931008","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/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4304080357.pdf","grobid_xml":"https://content.openalex.org/works/W4304080357.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W1586079445","https://openalex.org/W2096733369","https://openalex.org/W2185175083","https://openalex.org/W2486285194","https://openalex.org/W2560674852","https://openalex.org/W2592249290","https://openalex.org/W2605649771","https://openalex.org/W2747329762","https://openalex.org/W2765440071","https://openalex.org/W2798991696","https://openalex.org/W2962858109","https://openalex.org/W2963026686","https://openalex.org/W2963775347","https://openalex.org/W2965809241","https://openalex.org/W2965848243","https://openalex.org/W2970231061","https://openalex.org/W2982078236","https://openalex.org/W3008672977","https://openalex.org/W3099884329","https://openalex.org/W3104788521","https://openalex.org/W3110042533","https://openalex.org/W3177934633","https://openalex.org/W4220848927","https://openalex.org/W6600109629","https://openalex.org/W6600577311","https://openalex.org/W6601630192","https://openalex.org/W6602430550","https://openalex.org/W6603054696"],"related_works":["https://openalex.org/W3201448254","https://openalex.org/W4286970243","https://openalex.org/W2045049461","https://openalex.org/W2066431708","https://openalex.org/W4381094582","https://openalex.org/W1978893398","https://openalex.org/W3025615835","https://openalex.org/W4384133558","https://openalex.org/W173210993","https://openalex.org/W4372260129"],"abstract_inverted_index":{"Image-text":[0],"matching":[1,146],"is":[2,165],"a":[3,47],"fundamental":[4],"research":[5],"topic":[6],"bridging":[7],"vision":[8],"and":[9,24,70,106,125,133,149,162],"language.":[10],"Recent":[11],"works":[12],"use":[13],"hard":[14,42,67,115],"negative":[15,31,68,116],"mining":[16,69],"to":[17,43,57],"capture":[18],"the":[19,28,37,64,122,128],"multiple":[20],"correspondences":[21],"between":[22,66,131],"visual":[23],"textual":[25],"domains.":[26],"Unfortunately,":[27],"truly":[29],"informative":[30],"samples":[32],"are":[33,41],"quite":[34],"sparse":[35],"in":[36,46,140],"training":[38],"data,":[39],"which":[40],"obtain":[44],"only":[45],"randomly":[48],"sampled":[49],"mini-batch.":[50],"Motivated":[51],"by":[52,61],"causal":[53,71,103],"inference,":[54],"we":[55,75],"aim":[56],"overcome":[58],"this":[59],"shortcoming":[60],"carefully":[62],"analyzing":[63],"analogy":[65],"effects":[72],"optimizing.":[73],"Further,":[74],"propose":[76],"Counterfactual":[77],"Matching":[78],"(CFM)":[79],"framework":[80],"for":[81,96,102,108],"more":[82],"effective":[83],"image-text":[84,145],"correspondence":[85],"mining.":[86],"CFM":[87,139],"contains":[88],"three":[89,143],"major":[90],"components,":[91],"\\ie,":[92],"Gradient-Guided":[93],"Feature":[94],"Selection":[95],"automatic":[97],"casual":[98],"factor":[99,104],"identification,":[100],"Self-Exploration":[101],"completeness,":[105],"Self-Adjustment":[107],"counterfactual":[109],"sample":[110],"synthesis.":[111],"Compared":[112],"with":[113,142],"traditional":[114],"mining,":[117],"our":[118,138],"method":[119],"largely":[120],"alleviates":[121],"over-fitting":[123],"phenomenon":[124],"effectively":[126],"captures":[127],"fine-grained":[129],"correlations":[130],"image":[132],"text":[134],"modality.":[135],"We":[136],"evaluate":[137],"combination":[141],"state-of-the-art":[144],"architectures.":[147],"Quantitative":[148],"qualitative":[150],"experiments":[151],"conducted":[152],"on":[153],"two":[154],"publicly":[155],"available":[156,166],"datasets":[157],"demonstrate":[158],"its":[159],"strong":[160],"generality":[161],"effectiveness.":[163],"Code":[164],"at:":[167],"https://github.com/weihao20/cfm.":[168]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}