{"id":"https://openalex.org/W4406457911","doi":"https://doi.org/10.1109/bigdata62323.2024.10825003","title":"Disentangling Fine-Tuning from Pre-Training in Visual Captioning with Hybrid Markov Logic","display_name":"Disentangling Fine-Tuning from Pre-Training in Visual Captioning with Hybrid Markov Logic","publication_year":2024,"publication_date":"2024-12-15","ids":{"openalex":"https://openalex.org/W4406457911","doi":"https://doi.org/10.1109/bigdata62323.2024.10825003"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata62323.2024.10825003","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825003","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.13847","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101042181","display_name":"Monika Shah","orcid":null},"institutions":[{"id":"https://openalex.org/I94658018","display_name":"University of Memphis","ror":"https://ror.org/01cq23130","country_code":"US","type":"education","lineage":["https://openalex.org/I94658018"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Monika Shah","raw_affiliation_strings":["University of Memphis"],"affiliations":[{"raw_affiliation_string":"University of Memphis","institution_ids":["https://openalex.org/I94658018"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023589965","display_name":"Somdeb Sarkhel","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":"Somdeb Sarkhel","raw_affiliation_strings":["Adobe Research"],"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103421781","display_name":"Deepak Venugopal","orcid":"https://orcid.org/0000-0001-7466-5417"},"institutions":[{"id":"https://openalex.org/I94658018","display_name":"University of Memphis","ror":"https://ror.org/01cq23130","country_code":"US","type":"education","lineage":["https://openalex.org/I94658018"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Deepak Venugopal","raw_affiliation_strings":["University of Memphis"],"affiliations":[{"raw_affiliation_string":"University of Memphis","institution_ids":["https://openalex.org/I94658018"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101042181"],"corresponding_institution_ids":["https://openalex.org/I94658018"],"apc_list":null,"apc_paid":null,"fwci":0.2597,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.58594436,"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":"5422","last_page":"5431"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9984999895095825,"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":0.9976999759674072,"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/closed-captioning","display_name":"Closed captioning","score":0.903051495552063},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7126998901367188},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5315746068954468},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4510495066642761},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4354555606842041},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4207285940647125},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.32924216985702515},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.23393836617469788},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.14310017228126526},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10388734936714172}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.903051495552063},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7126998901367188},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5315746068954468},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4510495066642761},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4354555606842041},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4207285940647125},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.32924216985702515},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.23393836617469788},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.14310017228126526},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10388734936714172},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"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:10.1109/bigdata62323.2024.10825003","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825003","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2503.13847","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.13847","pdf_url":"https://arxiv.org/pdf/2503.13847","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2503.13847","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.13847","pdf_url":"https://arxiv.org/pdf/2503.13847","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1511986666","https://openalex.org/W1997945384","https://openalex.org/W2020999234","https://openalex.org/W2069739265","https://openalex.org/W2084933300","https://openalex.org/W2108598243","https://openalex.org/W2109586012","https://openalex.org/W2116064496","https://openalex.org/W2133459682","https://openalex.org/W2154914325","https://openalex.org/W2159080219","https://openalex.org/W2162531249","https://openalex.org/W2165646510","https://openalex.org/W2250378130","https://openalex.org/W2277195237","https://openalex.org/W2294621531","https://openalex.org/W2506483933","https://openalex.org/W2950735465","https://openalex.org/W2952215760","https://openalex.org/W2963095307","https://openalex.org/W2963101956","https://openalex.org/W2963572185","https://openalex.org/W2986670728","https://openalex.org/W3034655362","https://openalex.org/W3035284526","https://openalex.org/W3153469116","https://openalex.org/W3176641147","https://openalex.org/W4229005866","https://openalex.org/W4302605998","https://openalex.org/W4304080690","https://openalex.org/W4320024125","https://openalex.org/W4385573668","https://openalex.org/W4389524413","https://openalex.org/W4389760941","https://openalex.org/W4406072499","https://openalex.org/W4406072911","https://openalex.org/W6620707391","https://openalex.org/W6635963527","https://openalex.org/W6638588478","https://openalex.org/W6676497082","https://openalex.org/W6682998845","https://openalex.org/W6753938374","https://openalex.org/W6764233798","https://openalex.org/W6791353385","https://openalex.org/W6811340617","https://openalex.org/W6849177959","https://openalex.org/W6875851775","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W2963177403","https://openalex.org/W2379651310","https://openalex.org/W2113019827","https://openalex.org/W1541249122","https://openalex.org/W2413828414","https://openalex.org/W4236062181","https://openalex.org/W2367222340"],"abstract_inverted_index":{"Multimodal":[0],"systems":[1],"have":[2,130,143],"highly":[3],"complex":[4],"processing":[5],"pipelines":[6],"and":[7],"are":[8],"pretrained":[9],"over":[10,60],"large":[11],"datasets":[12],"before":[13],"being":[14],"fine-tuned":[15],"for":[16,109,119],"specific":[17],"tasks":[18],"such":[19],"as":[20,151],"visual":[21,73,149],"captioning.":[22],"However,":[23],"it":[24,39,141],"becomes":[25],"hard":[26],"to":[27,43,147,153],"disentangle":[28],"what":[29,38],"the":[30,34,61,70,77,85,92,106,127,134,136],"model":[31,53,122,137],"learns":[32],"during":[33],"fine-tuning":[35,128],"process":[36],"from":[37,69,76],"already":[40],"knows":[41],"due":[42],"its":[44],"pretraining.":[45],"In":[46],"this":[47],"work,":[48],"we":[49,83],"learn":[50],"a":[51,80,125,159],"probabilistic":[52,96],"using":[54,95],"Hybrid":[55],"Markov":[56],"Logic":[57],"Networks":[58],"(HMLNs)":[59],"training":[62,88],"examples":[63,89],"by":[64],"relating":[65],"symbolic":[66],"knowledge":[67,135,146],"(extracted":[68,75],"caption)":[71],"with":[72],"features":[74],"image).":[78],"For":[79],"generated":[81],"caption,":[82],"quantify":[84],"influence":[86,132],"of":[87,102,112],"based":[90],"on":[91,105,133],"HMLN":[93],"distribution":[94],"inference.":[97],"We":[98],"evaluate":[99],"two":[100],"types":[101,111],"inference":[103],"procedures":[104],"MSCOCO":[107],"dataset":[108],"different":[110],"captioning":[113,150],"models.":[114],"Our":[115],"results":[116],"show":[117],"that":[118,123,155],"BLIP2":[120],"(a":[121],"uses":[124],"LLM),":[126],"may":[129,142],"smaller":[131],"has":[138],"acquired":[139],"since":[140],"more":[144],"general":[145],"perform":[148],"compared":[152],"models":[154],"do":[156],"not":[157],"use":[158],"LLM.":[160]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}