{"id":"https://openalex.org/W4416035939","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.75","title":"What Makes for Good Image Captions?","display_name":"What Makes for Good Image Captions?","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416035939","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.75"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.75","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.75","pdf_url":"https://aclanthology.org/2025.findings-emnlp.75.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.75.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020620488","display_name":"Delong Chen","orcid":"https://orcid.org/0000-0002-8172-2894"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Delong Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084836777","display_name":"Samuel Cahyawijaya","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Samuel Cahyawijaya","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010121592","display_name":"Etsuko Ishii","orcid":"https://orcid.org/0000-0002-6423-539X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Etsuko Ishii","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113197264","display_name":"Ho Shu Chan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ho Shu Chan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113851214","display_name":"Yejin Bang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yejin Bang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5065856469","display_name":"Pascale Fung","orcid":"https://orcid.org/0000-0002-0628-7132"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pascale Fung","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1420","last_page":"1437"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9909999966621399,"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":0.9909999966621399,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.0008999999845400453,"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":0.0006000000284984708,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.95660001039505},{"id":"https://openalex.org/keywords/pyramid","display_name":"Pyramid (geometry)","score":0.6521999835968018},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.6335999965667725},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.555400013923645},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5394999980926514},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.43230000138282776},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.42100000381469727}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.95660001039505},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7455999851226807},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.6521999835968018},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6335999965667725},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6191999912261963},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.555400013923645},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5394999980926514},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4429999887943268},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4345000088214874},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.43230000138282776},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.42100000381469727},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.39739999175071716},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.3935000002384186},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.3228999972343445},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2996000051498413},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.29030001163482666},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.28760001063346863},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.28610000014305115},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.27399998903274536},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.25440001487731934}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.75","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.75","pdf_url":"https://aclanthology.org/2025.findings-emnlp.75.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-168860","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-168860","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Conference paper"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.75","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.75","pdf_url":"https://aclanthology.org/2025.findings-emnlp.75.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416035939.pdf","grobid_xml":"https://content.openalex.org/works/W4416035939.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"establishes":[2],"a":[3,55],"formal":[4],"informationtheoretic":[5],"framework":[6,23,53],"for":[7,58],"image":[8,27,62,111],"captioning,":[9],"conceptualizing":[10],"captions":[11,28,83],"as":[12,46],"compressed":[13],"linguistic":[14],"representations":[15],"that":[16,25,95],"selectively":[17],"encode":[18],"semantic":[19],"units":[20],"in":[21],"images.Our":[22],"posits":[24],"good":[26],"should":[29],"balance":[30],"three":[31],"key":[32],"aspects:":[33],"informationally":[34],"sufficient,":[35],"minimally":[36],"redundant,":[37],"and":[38,60,87,103,114],"readily":[39],"comprehensible":[40],"by":[41,84],"humans.By":[42],"formulating":[43],"these":[44],"aspects":[45],"quantitative":[47],"measures":[48],"with":[49],"adjustable":[50],"weights,":[51],"our":[52],"provides":[54],"flexible":[56],"foundation":[57],"analyzing":[59],"optimizing":[61],"captioning":[63,112],"systems":[64],"across":[65,109],"diverse":[66],"task":[67],"requirements.To":[68],"demonstrate":[69],"its":[70,107],"applicability,":[71],"we":[72],"introduce":[73],"the":[74],"Pyramid":[75],"of":[76,106],"Captions":[77],"(PoCa)":[78],"method,":[79],"which":[80],"generates":[81],"enriched":[82],"integrating":[85],"local":[86],"global":[88],"visual":[89],"information.We":[90],"present":[91],"both":[92],"theoretical":[93],"proof":[94],"PoCa":[96],"improves":[97],"caption":[98],"quality":[99],"under":[100],"certain":[101],"assumptions,":[102],"empirical":[104],"validation":[105],"effectiveness":[108],"various":[110],"models":[113],"datasets.":[115]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-08T00:00:00"}