{"id":"https://openalex.org/W4403760415","doi":"https://doi.org/10.1007/978-3-031-72664-4_23","title":"Removing Distributional Discrepancies in\u00a0Captions Improves Image-Text Alignment","display_name":"Removing Distributional Discrepancies in\u00a0Captions Improves Image-Text Alignment","publication_year":2024,"publication_date":"2024-10-25","ids":{"openalex":"https://openalex.org/W4403760415","doi":"https://doi.org/10.1007/978-3-031-72664-4_23"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-031-72664-4_23","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-72664-4_23","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","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":null,"display_name":"Yuheng Li","orcid":"https://orcid.org/0000-0001-6082-6398"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]},{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yuheng Li","raw_affiliation_strings":["Adobe Research, San Francisco, USA","University of Wisconsin-Madison, Madison, USA"],"raw_orcid":"https://orcid.org/0000-0001-6082-6398","affiliations":[{"raw_affiliation_string":"Adobe Research, San Francisco, USA","institution_ids":["https://openalex.org/I1306409833"]},{"raw_affiliation_string":"University of Wisconsin-Madison, Madison, USA","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103047904","display_name":"Haotian Liu","orcid":"https://orcid.org/0000-0002-9554-7839"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haotian Liu","raw_affiliation_strings":["University of Wisconsin-Madison, Madison, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison, Madison, USA","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081591501","display_name":"Mu Cai","orcid":"https://orcid.org/0009-0008-7967-9752"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mu Cai","raw_affiliation_strings":["University of Wisconsin-Madison, Madison, USA"],"raw_orcid":"https://orcid.org/0009-0008-7967-9752","affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison, Madison, USA","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100447637","display_name":"Yijun Li","orcid":"https://orcid.org/0000-0001-7295-8750"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]},{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yijun Li","raw_affiliation_strings":["Adobe Research, San Francisco, USA","University of Wisconsin-Madison, Madison, USA"],"raw_orcid":"https://orcid.org/0000-0001-7295-8750","affiliations":[{"raw_affiliation_string":"Adobe Research, San Francisco, USA","institution_ids":["https://openalex.org/I1306409833"]},{"raw_affiliation_string":"University of Wisconsin-Madison, Madison, USA","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024777042","display_name":"Eli Shechtman","orcid":"https://orcid.org/0000-0002-6783-1795"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eli Shechtman","raw_affiliation_strings":["Adobe Research, San Francisco, USA"],"raw_orcid":"https://orcid.org/0000-0002-6783-1795","affiliations":[{"raw_affiliation_string":"Adobe Research, San Francisco, USA","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101564904","display_name":"Zhe Lin","orcid":"https://orcid.org/0000-0003-1154-9907"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhe Lin","raw_affiliation_strings":["Adobe Research, San Francisco, USA"],"raw_orcid":"https://orcid.org/0000-0003-1154-9907","affiliations":[{"raw_affiliation_string":"Adobe Research, San Francisco, USA","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072079475","display_name":"Yong Jae Lee","orcid":"https://orcid.org/0000-0001-9863-1270"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yong Jae Lee","raw_affiliation_strings":["University of Wisconsin-Madison, Madison, USA"],"raw_orcid":"https://orcid.org/0000-0001-9863-1270","affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison, Madison, USA","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101960524","display_name":"Krishna Kumar Singh","orcid":null},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Krishna Kumar Singh","raw_affiliation_strings":["Adobe Research, San Francisco, USA"],"raw_orcid":"https://orcid.org/0000-0002-8066-6835","affiliations":[{"raw_affiliation_string":"Adobe Research, San Francisco, USA","institution_ids":["https://openalex.org/I1306409833"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1306409833","https://openalex.org/I135310074"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.3886,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.70667389,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"405","last_page":"422"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9995999932289124,"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":0.9995999932289124,"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/T13310","display_name":"Subtitles and Audiovisual Media","score":0.9965999722480774,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9930999875068665,"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":0.8243789672851562},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5943149328231812},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.49921298027038574},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4914911985397339},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4646446406841278},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.38199466466903687},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.3248862326145172},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.322115421295166}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8243789672851562},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5943149328231812},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.49921298027038574},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4914911985397339},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4646446406841278},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.38199466466903687},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3248862326145172},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.322115421295166}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-031-72664-4_23","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-72664-4_23","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1981276685","https://openalex.org/W2886641317","https://openalex.org/W3135367836","https://openalex.org/W3153469116","https://openalex.org/W3176641147","https://openalex.org/W4225323055","https://openalex.org/W4306820534","https://openalex.org/W4311252447","https://openalex.org/W4312261477","https://openalex.org/W4312605942","https://openalex.org/W4312910992","https://openalex.org/W4312933868","https://openalex.org/W4365600514","https://openalex.org/W4367365797","https://openalex.org/W4379251375","https://openalex.org/W4385570204","https://openalex.org/W4385572962","https://openalex.org/W4386072101","https://openalex.org/W4386076015","https://openalex.org/W4389519483","https://openalex.org/W4389523832","https://openalex.org/W4390874566","https://openalex.org/W4402727764","https://openalex.org/W6600669965","https://openalex.org/W6601365666","https://openalex.org/W6631455383","https://openalex.org/W6702248584"],"related_works":["https://openalex.org/W2755342338","https://openalex.org/W2779427294","https://openalex.org/W2775347418","https://openalex.org/W2625805835","https://openalex.org/W2079911747","https://openalex.org/W3116076068","https://openalex.org/W3003936178","https://openalex.org/W2145652935","https://openalex.org/W2563206327","https://openalex.org/W2069885731"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}