{"id":"https://openalex.org/W4384659783","doi":"https://doi.org/10.1145/3539618.3592038","title":"PiTL: Cross-modal Retrieval with Weakly-supervised Vision-language Pre-training via Prompting","display_name":"PiTL: Cross-modal Retrieval with Weakly-supervised Vision-language Pre-training via Prompting","publication_year":2023,"publication_date":"2023-07-18","ids":{"openalex":"https://openalex.org/W4384659783","doi":"https://doi.org/10.1145/3539618.3592038"},"language":"en","primary_location":{"id":"doi:10.1145/3539618.3592038","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3539618.3592038","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3539618.3592038","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3539618.3592038","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079044890","display_name":"Zixin Guo","orcid":"https://orcid.org/0000-0002-7088-2331"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Zixin Guo","raw_affiliation_strings":["Aalto University, Espoo, Finland"],"raw_orcid":"https://orcid.org/0000-0002-7088-2331","affiliations":[{"raw_affiliation_string":"Aalto University, Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077052515","display_name":"Tzu-Jui Julius Wang","orcid":"https://orcid.org/0000-0002-8840-3079"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Tzu-Jui Julius Wang","raw_affiliation_strings":["Aalto University, Espoo, Finland"],"raw_orcid":"https://orcid.org/0000-0002-8840-3079","affiliations":[{"raw_affiliation_string":"Aalto University, Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071798070","display_name":"Selen Pehlivan","orcid":"https://orcid.org/0000-0002-8658-8890"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Selen Pehlivan","raw_affiliation_strings":["Aalto University, Espoo, Finland"],"raw_orcid":"https://orcid.org/0000-0002-8658-8890","affiliations":[{"raw_affiliation_string":"Aalto University, Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049343215","display_name":"Abduljalil Radman","orcid":"https://orcid.org/0000-0002-6317-9752"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Abduljalil Radman","raw_affiliation_strings":["Aalto University, Espoo, Finland"],"raw_orcid":"https://orcid.org/0000-0002-6317-9752","affiliations":[{"raw_affiliation_string":"Aalto University, Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036133390","display_name":"Jorma Laaksonen","orcid":"https://orcid.org/0000-0001-7218-3131"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Jorma Laaksonen","raw_affiliation_strings":["Aalto University, Espoo, Finland"],"raw_orcid":"https://orcid.org/0000-0001-7218-3131","affiliations":[{"raw_affiliation_string":"Aalto University, Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I9927081"],"apc_list":null,"apc_paid":null,"fwci":0.8572,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.75177009,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2261","last_page":"2265"},"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":0.9944000244140625,"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":0.9907000064849854,"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":0.7443983554840088},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.7430830001831055},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5730282068252563},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5164077877998352},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4107632040977478},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.392996609210968},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.38224393129348755}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7443983554840088},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7430830001831055},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5730282068252563},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5164077877998352},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4107632040977478},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.392996609210968},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.38224393129348755},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"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/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3539618.3592038","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3539618.3592038","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3539618.3592038","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/123499","is_oa":true,"landing_page_url":"https://research.aalto.fi/en/publications/b56ead6f-7119-4bb0-9bb6-4b5b603ace02","pdf_url":null,"source":{"id":"https://openalex.org/S4306401663","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"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":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1145/3539618.3592038","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3539618.3592038","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3539618.3592038","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5799999833106995,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G4706251453","display_name":"Understanding speech and scene with ears and eyes","funder_award_id":"345791","funder_id":"https://openalex.org/F4320321108","funder_display_name":"Academy of Finland"},{"id":"https://openalex.org/G8994705204","display_name":null,"funder_award_id":"345791","funder_id":"https://openalex.org/F4320321108","funder_display_name":"Academy of Finland"}],"funders":[{"id":"https://openalex.org/F4320321108","display_name":"Academy of Finland","ror":"https://ror.org/05k73zm37"},{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4384659783.pdf","grobid_xml":"https://content.openalex.org/works/W4384659783.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W1566289585","https://openalex.org/W2108598243","https://openalex.org/W2886641317","https://openalex.org/W3035688398","https://openalex.org/W3090449556","https://openalex.org/W3168154341","https://openalex.org/W3173220247","https://openalex.org/W3176641147","https://openalex.org/W3177224328","https://openalex.org/W4285606530","https://openalex.org/W4287125738","https://openalex.org/W4312877428","https://openalex.org/W4312910992","https://openalex.org/W4385573407","https://openalex.org/W4385574358","https://openalex.org/W4404784092","https://openalex.org/W6600103761","https://openalex.org/W6600339457","https://openalex.org/W6601065604"],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W3216976533","https://openalex.org/W100620283","https://openalex.org/W2495260952","https://openalex.org/W4366179611","https://openalex.org/W2996078371"],"abstract_inverted_index":{"Vision-language":[0],"(VL)":[1],"Pre-training":[2],"(VLP)":[3],"has":[4],"shown":[5],"to":[6,71],"well":[7],"generalize":[8],"VL":[9,16],"models":[10],"over":[11],"a":[12,27,51],"wide":[13],"range":[14],"of":[15,30],"downstream":[17],"tasks,":[18],"especially":[19],"for":[20],"cross-modal":[21],"retrieval.":[22],"However,":[23],"it":[24],"hinges":[25],"on":[26],"huge":[28],"amount":[29],"image-text":[31],"pairs,":[32],"which":[33],"requires":[34],"tedious":[35],"and":[36,66],"costly":[37],"curation.":[38],"On":[39],"the":[40],"contrary,weakly-supervised":[41],"VLP":[42],"(W-VLP)":[43],"explores":[44],"means":[45],"with":[46],"object":[47,53],"tags":[48],"generated":[49],"by":[50],"pre-trained":[52],"detector":[54],"(OD)":[55],"from":[56],"images.":[57],"Yet,":[58],"they":[59],"still":[60],"require":[61],"paired":[62],"information,":[63],"i.e.":[64],"images":[65],"object-level":[67],"annotations,":[68],"as":[69],"supervision":[70],"train":[72],"an":[73],"OD.":[74]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2023-07-20T00:00:00"}
