{"id":"https://openalex.org/W3116367518","doi":"https://doi.org/10.1145/3430984.3431059","title":"Image Captioning with Pretrained Language Generators","display_name":"Image Captioning with Pretrained Language Generators","publication_year":2020,"publication_date":"2020-12-28","ids":{"openalex":"https://openalex.org/W3116367518","doi":"https://doi.org/10.1145/3430984.3431059","mag":"3116367518"},"language":"en","primary_location":{"id":"doi:10.1145/3430984.3431059","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3430984.3431059","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd ACM India Joint International Conference on Data Science & Management of Data (8th ACM IKDD CODS & 26th COMAD)","raw_type":"proceedings-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/A5056324204","display_name":"Saketh Vishnubhatla","orcid":"https://orcid.org/0009-0005-9288-1777"},"institutions":[{"id":"https://openalex.org/I4210101034","display_name":"Birla Institute of Technology and Science - Hyderabad Campus","ror":"https://ror.org/014ctt859","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210101034","https://openalex.org/I74796645"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Saketh Vishnubhatla","raw_affiliation_strings":["Bits Pilani Hyderabad Campus"],"affiliations":[{"raw_affiliation_string":"Bits Pilani Hyderabad Campus","institution_ids":["https://openalex.org/I4210101034"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091618586","display_name":"Nishant Sinha","orcid":"https://orcid.org/0000-0003-2366-4064"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nishant Sinha","raw_affiliation_strings":["OffNote Labs"],"affiliations":[{"raw_affiliation_string":"OffNote Labs","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5056324204"],"corresponding_institution_ids":["https://openalex.org/I4210101034"],"apc_list":null,"apc_paid":null,"fwci":0.0977,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.43002621,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"427","last_page":"427"},"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/T10028","display_name":"Topic Modeling","score":0.9948999881744385,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.989300012588501,"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":0.9858032464981079},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8496682643890381},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6306766867637634},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6077870726585388},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6003537774085999},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5906503200531006},{"id":"https://openalex.org/keywords/scene-graph","display_name":"Scene graph","score":0.5798556208610535},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.5612016320228577},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5471906661987305},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5409070253372192},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5348238945007324},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.410049706697464},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3946722745895386},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3269162178039551},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.13627848029136658},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1126047670841217},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.10534700751304626}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9858032464981079},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8496682643890381},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6306766867637634},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6077870726585388},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6003537774085999},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5906503200531006},{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.5798556208610535},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.5612016320228577},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5471906661987305},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5409070253372192},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5348238945007324},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.410049706697464},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3946722745895386},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3269162178039551},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.13627848029136658},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1126047670841217},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.10534700751304626},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating 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},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3430984.3431059","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3430984.3431059","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd ACM India Joint International Conference on Data Science & Management of Data (8th ACM IKDD CODS & 26th COMAD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W2745461083","https://openalex.org/W2890531016","https://openalex.org/W2963101956","https://openalex.org/W2963532001","https://openalex.org/W2963758027","https://openalex.org/W2981852735","https://openalex.org/W2989377923","https://openalex.org/W3035017890"],"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/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393","https://openalex.org/W4287661223"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,36],"novel":[3],"framework":[4],"for":[5,93],"image":[6,45,94],"captioning":[7],"combining":[8],"scene":[9,41,56],"graph":[10],"models":[11,92],"with":[12],"pre-trained":[13,49],"language":[14,50,79],"models.":[15],"This":[16],"is":[17],"in":[18,65,73,90],"contrast":[19],"to":[20,52,59,84],"previous":[21],"works,":[22],"which":[23],"largely":[24],"rely":[25],"on":[26],"an":[27,44,74],"encoder-decoder":[28],"like":[29],"architecture.":[30],"In":[31],"our":[32],"experiments":[33],"we":[34,81],"use":[35],"two-stage":[37],"pipeline:":[38],"a)":[39],"generating":[40],"graphs":[42,57],"from":[43],"and":[46,63],"b)":[47],"using":[48],"generators":[51],"obtain":[53],"captions.":[54],"Using":[55],"leads":[58],"more":[60],"grounded":[61],"captions":[62],"helps":[64],"exploiting":[66],"the":[67,86],"visual":[68],"context":[69],"between":[70],"different":[71],"objects":[72],"image.":[75],"By":[76],"fine-tuning":[77],"pretrained":[78],"models,":[80],"are":[82],"able":[83],"reuse":[85],"vast,":[87],"compressed":[88],"knowledge":[89],"these":[91],"captioning.":[95]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}