{"id":"https://openalex.org/W2989377923","doi":"https://doi.org/10.18653/v1/d19-6405","title":"On the Role of Scene Graphs in Image Captioning","display_name":"On the Role of Scene Graphs in Image Captioning","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2989377923","doi":"https://doi.org/10.18653/v1/d19-6405","mag":"2989377923"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d19-6405","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d19-6405","pdf_url":"https://www.aclweb.org/anthology/D19-6405.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":"Proceedings of the Beyond Vision and LANguage: inTEgrating Real-world kNowledge (LANTERN)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/D19-6405.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102017606","display_name":"Dalin Wang","orcid":"https://orcid.org/0009-0009-2793-4333"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dalin Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101579884","display_name":"Daniel Beck","orcid":"https://orcid.org/0000-0002-8529-7792"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daniel Beck","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5078530959","display_name":"Trevor Cohn","orcid":"https://orcid.org/0000-0003-4363-1673"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Trevor Cohn","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":1.3725,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.88406463,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"29","last_page":"34"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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":0.9970999956130981,"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":0.9794999957084656,"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/closed-captioning","display_name":"Closed captioning","score":0.959296703338623},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8560724258422852},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.7578125596046448},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.5625189542770386},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5597311854362488},{"id":"https://openalex.org/keywords/scene-graph","display_name":"Scene graph","score":0.5390663743019104},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5128045678138733},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.49447154998779297},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.47204363346099854},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4419183135032654},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.4284713864326477},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.25088319182395935},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.06825610995292664}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.959296703338623},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8560724258422852},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.7578125596046448},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5625189542770386},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5597311854362488},{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.5390663743019104},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5128045678138733},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49447154998779297},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.47204363346099854},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4419183135032654},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.4284713864326477},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.25088319182395935},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.06825610995292664},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/d19-6405","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d19-6405","pdf_url":"https://www.aclweb.org/anthology/D19-6405.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":"Proceedings of the Beyond Vision and LANguage: inTEgrating Real-world kNowledge (LANTERN)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/d19-6405","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d19-6405","pdf_url":"https://www.aclweb.org/anthology/D19-6405.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":"Proceedings of the Beyond Vision and LANguage: inTEgrating Real-world kNowledge (LANTERN)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2989377923.pdf"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1514535095","https://openalex.org/W1861492603","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2133512280","https://openalex.org/W2154652894","https://openalex.org/W2277195237","https://openalex.org/W2506483933","https://openalex.org/W2525778437","https://openalex.org/W2564898401","https://openalex.org/W2575842049","https://openalex.org/W2579549467","https://openalex.org/W2600702321","https://openalex.org/W2607855566","https://openalex.org/W2745461083","https://openalex.org/W2795151422","https://openalex.org/W2810482788","https://openalex.org/W2890531016","https://openalex.org/W2904993015","https://openalex.org/W2913618459","https://openalex.org/W2962737704","https://openalex.org/W2963649796","https://openalex.org/W2964121744","https://openalex.org/W2981165461"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4287661223","https://openalex.org/W2754155766","https://openalex.org/W4287854977","https://openalex.org/W2963192850","https://openalex.org/W2769151336"],"abstract_inverted_index":{"Scene":[0],"graphs":[1,34,39,63],"represent":[2],"semantic":[3],"information":[4],"in":[5],"images,":[6],"which":[7],"can":[8,64,77],"help":[9,65],"image":[10,22,66],"captioning":[11,26,52,97],"system":[12],"to":[13,32,59],"produce":[14],"more":[15,94],"descriptive":[16],"outputs":[17],"versus":[18],"using":[19],"only":[20],"the":[21,46,84,90,96,101,104],"as":[23,81,83],"context.":[24],"Recent":[25],"approaches":[27,31],"rely":[28],"on":[29,51,95,100],"ad-hoc":[30],"obtain":[33],"for":[35],"images.":[36],"However,":[37],"those":[38],"introduce":[40],"noise":[41],"and":[42],"it":[43],"is":[44],"unclear":[45],"effect":[47],"of":[48,103],"parser":[49,76],"errors":[50],"accuracy.":[53],"In":[54],"this":[55],"work,":[56],"we":[57],"investigate":[58],"what":[60],"extent":[61],"scene":[62,74,105],"captioning.":[67],"Our":[68],"results":[69],"show":[70],"that":[71,89],"a":[72],"state-of-the-art":[73],"graph":[75,106],"boost":[78],"performance":[79,102],"almost":[80],"much":[82],"ground":[85],"truth":[86],"graphs,":[87],"showing":[88],"bottleneck":[91],"currently":[92],"resides":[93],"models":[98],"than":[99],"parser.":[107]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":5}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}