{"id":"https://openalex.org/W4411556713","doi":"https://doi.org/10.1007/s11263-025-02436-0","title":"Image Captions are Natural Prompts for Training Data Synthesis","display_name":"Image Captions are Natural Prompts for Training Data Synthesis","publication_year":2025,"publication_date":"2025-06-23","ids":{"openalex":"https://openalex.org/W4411556713","doi":"https://doi.org/10.1007/s11263-025-02436-0"},"language":"en","primary_location":{"id":"doi:10.1007/s11263-025-02436-0","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s11263-025-02436-0","pdf_url":null,"source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-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/A5036865546","display_name":"Shiye Lei","orcid":"https://orcid.org/0000-0001-7810-9346"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Shiye Lei","raw_affiliation_strings":["School of Computer Science, The University of Sydney, Darlington, Sydney, NSW, 2008, Australia"],"raw_orcid":"https://orcid.org/0000-0001-7810-9346","affiliations":[{"raw_affiliation_string":"School of Computer Science, The University of Sydney, Darlington, Sydney, NSW, 2008, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100353581","display_name":"Hao Chen","orcid":"https://orcid.org/0000-0002-6853-3298"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hao Chen","raw_affiliation_strings":["Electrical and Computer Engineering, Carnegie Mellon University, 5000 Forbes Ave., Pittsburgh, PA, 15213, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, Carnegie Mellon University, 5000 Forbes Ave., Pittsburgh, PA, 15213, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101925020","display_name":"Sen Zhang","orcid":"https://orcid.org/0000-0002-6630-570X"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Sen Zhang","raw_affiliation_strings":["School of Computer Science, The University of Sydney, Darlington, Sydney, NSW, 2008, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, The University of Sydney, Darlington, Sydney, NSW, 2008, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069245621","display_name":"Bo Zhao","orcid":"https://orcid.org/0000-0002-7834-6672"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Bo Zhao","raw_affiliation_strings":["School of Artificial Intelligence, Shanghai Jiao Tong University, No. 800 Dongchuan, Shanghai, 200240, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Shanghai Jiao Tong University, No. 800 Dongchuan, Shanghai, 200240, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074103823","display_name":"Dacheng Tao","orcid":"https://orcid.org/0000-0001-7225-5449"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]},{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["AU","SG"],"is_corresponding":true,"raw_author_name":"Dacheng Tao","raw_affiliation_strings":["College of Computing and Data Science, Nanyang Technological University, Nanyang Avenue, Singapore, 639798, Singapore","School of Computer Science, The University of Sydney, Darlington, Sydney, NSW, 2008, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computing and Data Science, Nanyang Technological University, Nanyang Avenue, Singapore, 639798, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"School of Computer Science, The University of Sydney, Darlington, Sydney, NSW, 2008, Australia","institution_ids":["https://openalex.org/I129604602"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5069245621","https://openalex.org/A5074103823"],"corresponding_institution_ids":["https://openalex.org/I129604602","https://openalex.org/I172675005","https://openalex.org/I183067930"],"apc_list":{"value":2890,"currency":"EUR","value_usd":3690},"apc_paid":null,"fwci":0.5615,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.64380353,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"133","issue":"8","first_page":"5435","last_page":"5454"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998000264167786,"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":0.9998000264167786,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9896000027656555,"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":0.9872000217437744,"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":0.6546200513839722},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6484555006027222},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5788383483886719},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5349570512771606},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5018215179443359},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4604871869087219},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.4398632049560547},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.4314485192298889},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4305749535560608},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.42260587215423584},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3320485055446625}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6546200513839722},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6484555006027222},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5788383483886719},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5349570512771606},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5018215179443359},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4604871869087219},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.4398632049560547},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.4314485192298889},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4305749535560608},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.42260587215423584},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3320485055446625},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s11263-025-02436-0","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s11263-025-02436-0","pdf_url":null,"source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"},{"id":"pmh:oai:dr.ntu.edu.sg:10356/207825","is_oa":false,"landing_page_url":"https://hdl.handle.net/10356/207825","pdf_url":null,"source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8877833081","display_name":null,"funder_award_id":"62306046","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1994616650","https://openalex.org/W2053637704","https://openalex.org/W2117539524","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2524985544","https://openalex.org/W2535690855","https://openalex.org/W2560647685","https://openalex.org/W2739748921","https://openalex.org/W2766527293","https://openalex.org/W2787774738","https://openalex.org/W2795435272","https://openalex.org/W2893749619","https://openalex.org/W2945027741","https://openalex.org/W2945785363","https://openalex.org/W2947707615","https://openalex.org/W2962793481","https://openalex.org/W2963073614","https://openalex.org/W2963470893","https://openalex.org/W2964024144","https://openalex.org/W2964137095","https://openalex.org/W2990138404","https://openalex.org/W2992308087","https://openalex.org/W3035682985","https://openalex.org/W3037492894","https://openalex.org/W3094502228","https://openalex.org/W3098397473","https://openalex.org/W3108655343","https://openalex.org/W3122887982","https://openalex.org/W3159481202","https://openalex.org/W3177096435","https://openalex.org/W3201822691","https://openalex.org/W4206337041","https://openalex.org/W4226125322","https://openalex.org/W4281485151","https://openalex.org/W4306820534","https://openalex.org/W4312108610","https://openalex.org/W4312453657","https://openalex.org/W4312933868","https://openalex.org/W4318718936","https://openalex.org/W4319453110","https://openalex.org/W4321337794","https://openalex.org/W4362641980","https://openalex.org/W4365475020","https://openalex.org/W4366330698","https://openalex.org/W4378505274","https://openalex.org/W4379261328","https://openalex.org/W4386076425","https://openalex.org/W4402716244","https://openalex.org/W6713645886","https://openalex.org/W6745136726","https://openalex.org/W6762931180","https://openalex.org/W6779823529","https://openalex.org/W6791436925","https://openalex.org/W6795288823","https://openalex.org/W6838728949","https://openalex.org/W6846948161","https://openalex.org/W7071865489"],"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/W4394050964","https://openalex.org/W2551249631"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-06-24T00:00:00"}
