{"id":"https://openalex.org/W4403791308","doi":"https://doi.org/10.1145/3664647.3680897","title":"Triple Alignment Strategies for Zero-shot Phrase Grounding under Weak Supervision","display_name":"Triple Alignment Strategies for Zero-shot Phrase Grounding under Weak Supervision","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791308","doi":"https://doi.org/10.1145/3664647.3680897"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3680897","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680897","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":"article","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/A5102631475","display_name":"Pengyue Lin","orcid":null},"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":true,"raw_author_name":"Pengyue Lin","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-6193-6983","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068728736","display_name":"Ruifan Li","orcid":"https://orcid.org/0000-0002-3543-6272"},"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":"Ruifan Li","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3543-6272","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109692658","display_name":"Yuzhe Ji","orcid":null},"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":"Yuzhe Ji","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-3122-2679","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101490809","display_name":"Zhihan Yu","orcid":"https://orcid.org/0009-0000-6411-9420"},"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":"Zhihan Yu","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-6411-9420","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013283012","display_name":"Fangxiang Feng","orcid":"https://orcid.org/0000-0002-4798-4233"},"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":"Fangxiang Feng","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4798-4233","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039812471","display_name":"Zhanyu Ma","orcid":"https://orcid.org/0000-0003-2950-2488"},"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":"Zhanyu Ma","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2950-2488","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100351304","display_name":"Xiaojie Wang","orcid":"https://orcid.org/0000-0003-0314-8951"},"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":"Xiaojie Wang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-0314-8951","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5102631475"],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":0.2381,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.53592529,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4312","last_page":"4321"},"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/T10028","display_name":"Topic Modeling","score":0.9980999827384949,"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/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/phrase","display_name":"Phrase","score":0.7565430402755737},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.618736982345581},{"id":"https://openalex.org/keywords/ground","display_name":"Ground","score":0.5787602066993713},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.5725577473640442},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5230603814125061},{"id":"https://openalex.org/keywords/one-shot","display_name":"One shot","score":0.4751301109790802},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40705347061157227},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.333420991897583},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.27776390314102173},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15346339344978333},{"id":"https://openalex.org/keywords/mechanical-engineering","display_name":"Mechanical engineering","score":0.0932815670967102},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.08667999505996704},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08667483925819397},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.06513601541519165},{"id":"https://openalex.org/keywords/quantum-mechanics","display_name":"Quantum mechanics","score":0.06483209133148193}],"concepts":[{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.7565430402755737},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.618736982345581},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.5787602066993713},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.5725577473640442},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5230603814125061},{"id":"https://openalex.org/C2992734406","wikidata":"https://www.wikidata.org/wiki/Q413267","display_name":"One shot","level":2,"score":0.4751301109790802},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40705347061157227},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.333420991897583},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.27776390314102173},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15346339344978333},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0932815670967102},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.08667999505996704},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08667483925819397},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.06513601541519165},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.06483209133148193},{"id":"https://openalex.org/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3680897","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680897","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"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1773149199","https://openalex.org/W1861492603","https://openalex.org/W1931639407","https://openalex.org/W2065429801","https://openalex.org/W2277195237","https://openalex.org/W2520141964","https://openalex.org/W2776207810","https://openalex.org/W2914911817","https://openalex.org/W2963080533","https://openalex.org/W2963914122","https://openalex.org/W2964393431","https://openalex.org/W2981645762","https://openalex.org/W2981663434","https://openalex.org/W2986803748","https://openalex.org/W2987401211","https://openalex.org/W2989176720","https://openalex.org/W3034727271","https://openalex.org/W3035524453","https://openalex.org/W3092659741","https://openalex.org/W3100393531","https://openalex.org/W3117585461","https://openalex.org/W3176196997","https://openalex.org/W3179041377","https://openalex.org/W3195830874","https://openalex.org/W3207872317","https://openalex.org/W4214650614","https://openalex.org/W4225517085","https://openalex.org/W4283312843","https://openalex.org/W4283688199","https://openalex.org/W4285192809","https://openalex.org/W4287022992","https://openalex.org/W4304099262","https://openalex.org/W4312509967","https://openalex.org/W4312960937","https://openalex.org/W4382240593","https://openalex.org/W4385764258","https://openalex.org/W4385901360","https://openalex.org/W4386065720","https://openalex.org/W4386071798","https://openalex.org/W4390872352","https://openalex.org/W4390872665","https://openalex.org/W4390873208","https://openalex.org/W4390873703","https://openalex.org/W4392543666","https://openalex.org/W4402727388"],"related_works":["https://openalex.org/W2497720472","https://openalex.org/W4292659306","https://openalex.org/W3044321615","https://openalex.org/W2806221744","https://openalex.org/W2326937258","https://openalex.org/W394267150","https://openalex.org/W2773965352","https://openalex.org/W4294892107","https://openalex.org/W2357748469","https://openalex.org/W2392917037"],"abstract_inverted_index":{"Phrase":[0],"Grounding,":[1],"i.e.,":[2],"PG":[3,13,24,63,69,140],"aims":[4],"to":[5,30,46,85],"locate":[6],"objects":[7],"referred":[8],"by":[9,100,125],"noun":[10],"phrases.":[11],"Recently,":[12],"under":[14,64],"weak":[15,65],"supervision":[16],"(i.e.,":[17,25],"grounding":[18,26],"without":[19],"region-level":[20,87],"annotations)":[21],"and":[22,49,112,130,146],"zero-shot":[23,62,144],"from":[27],"seen":[28,107],"categories":[29,51],"unseen":[31],"ones)":[32],"are":[33,43],"proposed,":[34],"respectively.":[35],"However,":[36],"for":[37],"real-world":[38],"applications":[39],"these":[40],"two":[41],"approaches":[42],"limited":[44],"due":[45],"slight":[47],"annotations":[48],"numerable":[50],"during":[52],"training.":[53],"In":[54],"this":[55],"paper,":[56],"we":[57,78,93,118],"propose":[58,79,94,119],"a":[59,80,95,120],"framework":[60,70,141],"of":[61,106,114],"supervision.":[66],"Specifically,":[67],"our":[68,138],"is":[71,151],"built":[72],"on":[73],"triple":[74],"alignment":[75,82,97,122],"strategies.":[76],"Firstly,":[77],"region-text":[81],"(RTA)":[83],"strategy":[84,99,124],"build":[86],"attribute":[88],"associations":[89],"via":[90],"CLIP.":[91],"Secondly,":[92],"domain":[96],"(DomA)":[98],"minimizing":[101],"the":[102,110,115],"difference":[103],"between":[104],"distributions":[105],"classes":[108],"in":[109],"training":[111],"those":[113],"pre-training.":[116],"Thirdly,":[117],"category":[121,128],"(CatA)":[123],"considering":[126],"both":[127],"semantics":[129],"region-category":[131],"relations.":[132],"Extensive":[133],"experimental":[134],"results":[135],"show":[136],"that":[137],"proposed":[139],"outperforms":[142],"previous":[143],"methods":[145],"weakly-supervised":[147],"methods.":[148],"Our":[149],"code":[150],"available":[152],"at":[153],"https://github.com/LinPengyue/ZS-WSG.":[154]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}