{"id":"https://openalex.org/W3035164585","doi":"https://doi.org/10.1145/3397271.3401149","title":"Correlated Features Synthesis and Alignment for Zero-shot Cross-modal Retrieval","display_name":"Correlated Features Synthesis and Alignment for Zero-shot Cross-modal Retrieval","publication_year":2020,"publication_date":"2020-07-25","ids":{"openalex":"https://openalex.org/W3035164585","doi":"https://doi.org/10.1145/3397271.3401149","mag":"3035164585"},"language":"en","primary_location":{"id":"doi:10.1145/3397271.3401149","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3397271.3401149","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 43rd 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/A5009074046","display_name":"Xing Xu","orcid":"https://orcid.org/0000-0001-5685-3123"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xing Xu","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049942254","display_name":"Kaiyi Lin","orcid":"https://orcid.org/0000-0003-4237-5313"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]},{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaiyi Lin","raw_affiliation_strings":["University of Electronic Science and Technology of China & Peking University, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China & Peking University, Chengdu, China","institution_ids":["https://openalex.org/I150229711","https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019035804","display_name":"Huimin Lu","orcid":"https://orcid.org/0000-0001-9794-3221"},"institutions":[{"id":"https://openalex.org/I207014233","display_name":"Kyushu Institute of Technology","ror":"https://ror.org/02278tr80","country_code":"JP","type":"education","lineage":["https://openalex.org/I207014233"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Huimin Lu","raw_affiliation_strings":["Kyushu Institute of Technology, Kitakyushu, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyushu Institute of Technology, Kitakyushu, Japan","institution_ids":["https://openalex.org/I207014233"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066645546","display_name":"Lianli Gao","orcid":"https://orcid.org/0000-0002-2522-6394"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lianli Gao","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052993469","display_name":"Heng Tao Shen","orcid":"https://orcid.org/0000-0002-2999-2088"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heng Tao Shen","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1419","last_page":"1428"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9997000098228455,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9997000098228455,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9997000098228455,"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":0.9993000030517578,"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":0.7596940398216248},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5806959867477417},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.492799311876297},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.48934119939804077},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4886332154273987},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4210549592971802}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7596940398216248},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5806959867477417},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.492799311876297},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.48934119939804077},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4886332154273987},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4210549592971802},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3397271.3401149","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3397271.3401149","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6399999856948853,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1523385540","https://openalex.org/W1686810756","https://openalex.org/W1949478088","https://openalex.org/W1972420097","https://openalex.org/W2007972815","https://openalex.org/W2013535308","https://openalex.org/W2106277773","https://openalex.org/W2109317801","https://openalex.org/W2128532956","https://openalex.org/W2187089797","https://openalex.org/W2211092169","https://openalex.org/W2326180695","https://openalex.org/W2466618734","https://openalex.org/W2552383788","https://openalex.org/W2574447816","https://openalex.org/W2591669147","https://openalex.org/W2603445054","https://openalex.org/W2605649771","https://openalex.org/W2611632661","https://openalex.org/W2739748921","https://openalex.org/W2765440071","https://openalex.org/W2795389793","https://openalex.org/W2807887362","https://openalex.org/W2808336545","https://openalex.org/W2885402090","https://openalex.org/W2887567284","https://openalex.org/W2915533878","https://openalex.org/W2962945761","https://openalex.org/W2962990451","https://openalex.org/W2963960318","https://openalex.org/W2964216321","https://openalex.org/W2988772405","https://openalex.org/W3003735286","https://openalex.org/W3023628276","https://openalex.org/W6601867051"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W2745001401","https://openalex.org/W4321353415","https://openalex.org/W2130974462","https://openalex.org/W972276598","https://openalex.org/W4246352526","https://openalex.org/W2033914206","https://openalex.org/W2042327336","https://openalex.org/W4386159726","https://openalex.org/W4388321867"],"abstract_inverted_index":{"The":[0],"goal":[1],"of":[2,46,88,194,242],"cross-modal":[3,56,192],"retrieval":[4,57,221,228],"is":[5,80],"to":[6,84,129,149,158,179,206],"search":[7],"for":[8,34,40,140,166,219,226],"semantically":[9],"similar":[10],"instances":[11],"in":[12,74],"one":[13],"modality":[14],"by":[15,234],"using":[16],"a":[17,120,180,240],"query":[18],"from":[19],"another":[20],"modality.":[21],"Existing":[22],"approaches":[23],"mainly":[24],"consider":[25],"the":[26,31,37,43,61,71,75,86,89,104,109,170,191,201,207,211,230],"standard":[27],"scenario":[28],"that":[29,67],"requires":[30],"source":[32,76,110],"set":[33,39,63],"training":[35],"and":[36,99,102,111,125,137,172,200,222],"target":[38,62,112],"testing":[41],"share":[42],"same":[44],"scope":[45],"classes.":[47],"However,":[48],"they":[49],"may":[50],"not":[51],"generalize":[52],"well":[53],"on":[54,215],"zero-shot":[55],"(ZS-CMR)":[58],"task,":[59],"where":[60,190],"contains":[64],"unseen":[65,90,100,208],"classes":[66,73,91,209],"are":[68,176,198],"disjoint":[69],"with":[70,163,239],"seen":[72,98],"set.":[77,113],"This":[78],"task":[79],"more":[81],"challenging":[82],"due":[83],"1)":[85],"absence":[87],"during":[92],"training,":[93],"2)":[94],"inconsistent":[95],"semantics":[96],"across":[97],"classes,":[101],"3)":[103],"heterogeneous":[105],"multimodal":[106,131,161,174],"distributions":[107],"between":[108],"To":[114],"address":[115],"these":[116],"issues,":[117],"we":[118],"propose":[119],"novel":[121],"Correlated":[122],"Feature":[123],"Synthesis":[124],"Alignment":[126],"(CFSA)":[127],"approach":[128],"integrate":[130],"feature":[132],"synthesis,":[133],"common":[134,181],"space":[135,183],"learning":[136],"knowledge":[138,202],"transfer":[139],"ZS-CMR.":[141],"Our":[142],"CFSA":[143],"first":[144],"utilizes":[145],"class-level":[146],"word":[147],"embeddings":[148],"guide":[150],"two":[151,223],"coupled":[152],"Wassertein":[153],"generative":[154],"adversarial":[155],"networks":[156],"(WGANs)":[157],"synthesize":[159],"sufficient":[160],"features":[162,175,197],"semantic":[164,182,196],"correlation":[165],"stable":[167],"training.":[168],"Then":[169],"synthetic":[171],"true":[173],"jointly":[177],"mapped":[178],"via":[184],"an":[185],"effective":[186],"distribution":[187],"alignment":[188],"scheme,":[189],"correlations":[193],"different":[195],"captured":[199],"can":[203],"be":[204],"transferred":[205],"under":[210],"cycle-consistency":[212],"constraint.":[213],"Experiments":[214],"four":[216],"benchmark":[217],"datasets":[218,225],"image-text":[220],"large-scale":[224],"image-sketch":[227],"show":[229],"remarkable":[231],"improvements":[232],"achieved":[233],"our":[235],"CFAS":[236],"method":[237],"comparing":[238],"bundle":[241],"state-of-the-art":[243],"approaches.":[244]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}