{"id":"https://openalex.org/W4402715874","doi":"https://doi.org/10.1109/cvpr52733.2024.01331","title":"Visual Fact Checker: Enabling High-Fidelity Detailed Caption Generation","display_name":"Visual Fact Checker: Enabling High-Fidelity Detailed Caption Generation","publication_year":2024,"publication_date":"2024-06-16","ids":{"openalex":"https://openalex.org/W4402715874","doi":"https://doi.org/10.1109/cvpr52733.2024.01331"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52733.2024.01331","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52733.2024.01331","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5038696465","display_name":"Yunhao Ge","orcid":"https://orcid.org/0000-0002-8110-9280"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yunhao Ge","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102154982","display_name":"Xiaohui Zeng","orcid":"https://orcid.org/0000-0001-6686-0589"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaohui Zeng","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5096228239","display_name":"Jacob Samuel Huffman","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jacob Samuel Huffman","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113667106","display_name":"Tsung\u2010Yi Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tsung-Yi Lin","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100335524","display_name":"Ming-Yu Liu","orcid":"https://orcid.org/0000-0002-2239-8975"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ming-Yu Liu","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100303262","display_name":"Yin Cui","orcid":"https://orcid.org/0000-0003-2882-2033"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yin Cui","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]}],"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":false,"cited_by_count":15,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"14033","last_page":"14042"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.9990000128746033,"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":0.9957000017166138,"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":0.8135524988174438},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.42267125844955444},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.3383503556251526}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8135524988174438},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.42267125844955444},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3383503556251526}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52733.2024.01331","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52733.2024.01331","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1947481528","https://openalex.org/W2745461083","https://openalex.org/W2986670728","https://openalex.org/W3153469116","https://openalex.org/W4221166856","https://openalex.org/W4224308101","https://openalex.org/W4225323055","https://openalex.org/W4226182655","https://openalex.org/W4226352076","https://openalex.org/W4226399820","https://openalex.org/W4281735693","https://openalex.org/W4292779060","https://openalex.org/W4307106676","https://openalex.org/W4318718936","https://openalex.org/W4320561490","https://openalex.org/W4322718191","https://openalex.org/W4324321291","https://openalex.org/W4366330503","https://openalex.org/W4366850747","https://openalex.org/W4376312115","https://openalex.org/W4380559227","https://openalex.org/W4382490555","https://openalex.org/W4383472654","https://openalex.org/W4385574156","https://openalex.org/W4386075660","https://openalex.org/W4386302587","https://openalex.org/W4386395766","https://openalex.org/W4387436689","https://openalex.org/W4388328455","https://openalex.org/W4389520769","https://openalex.org/W4389523832","https://openalex.org/W4393149022","https://openalex.org/W4393160204","https://openalex.org/W6778883912","https://openalex.org/W6810334672","https://openalex.org/W6810447287","https://openalex.org/W6811013733","https://openalex.org/W6838792323","https://openalex.org/W6852952414"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"Existing":[0],"automatic":[1],"captioning":[2,53,116,168,198],"methods":[3,169],"for":[4,37,123,128,157,170],"visual":[5],"con-tent":[6],"face":[7],"challenges":[8],"such":[9,69,204],"as":[10,70,205],"lack":[11],"of":[12,46],"detail,":[13],"content":[14],"hallu-cination,":[15],"and":[16,34,41,73,93,136,177],"poor":[17],"instruction":[18],"following.":[19],"In":[20,99],"this":[21,100],"work,":[22],"we":[23,195],"propose":[24,55],"VisualFactChecker":[25],"(VFC),":[26],"a":[27,62,142,193],"flexible":[28],"training-free":[29],"pipeline":[30],"that":[31,163,187],"generates":[32,85],"high-fidelity":[33],"detailed":[35],"captions":[36,106],"both":[38],"2D":[39,171],"images":[40,172],"3D":[42,178],"objects.":[43],"VFC":[44,102,164],"consists":[45],"three":[47],"steps:":[48],"l)":[49,121],"proposal,":[50],"where":[51,61,82],"image-to-text":[52],"models":[54,75,191,203],"multiple":[56],"initial":[57],"captions;":[58,79],"2)":[59,126],"verification,":[60],"large":[63],"language":[64],"model":[65,144,213],"(LLM)":[66],"utilizes":[67],"tools":[68],"object":[71],"detection":[72],"VQA":[74],"to":[76,201],"fact-check":[77],"proposed":[78],"3)":[80,148],"captioning,":[81],"an":[83],"LLM":[84],"the":[86,94,130,134,137,146,174,181],"final":[87],"caption":[88,91],"by":[89,141,188],"summarizing":[90],"proposals":[92],"fact":[95],"check":[96],"verification":[97],"results.":[98],"step,":[101],"can":[103,196],"flexibly":[104],"generate":[105],"in":[107,212],"various":[108],"styles":[109],"following":[110],"complex":[111],"instructions.":[112],"We":[113],"conduct":[114],"comprehensive":[115],"evaluations":[117],"using":[118,145],"four":[119],"metrics:":[120],"CLIP-Score":[122],"image-text":[124],"similarity;":[125],"CLIP-Image-Score":[127],"measuring":[129],"image-image":[131],"similarity":[132],"be-tween":[133],"original":[135],"reconstructed":[138],"image":[139],"generated":[140],"text-to-image":[143],"caption.":[147],"human":[149],"study":[150,185],"on":[151,173,180],"Amazon":[152],"Mechanical":[153],"Turk;":[154],"4)":[155],"GPT-4V":[156],"fine-grained":[158],"evaluation.":[159],"Evaluation":[160],"results":[161],"show":[162],"outperforms":[165],"state-of-the-art":[166],"open-sourced":[167],"COCO":[175],"dataset":[176],"assets":[179],"Obja-verse":[182],"dataset.":[183],"Our":[184],"demonstrates":[186],"combining":[189],"open-source":[190],"into":[192],"pipeline,":[194],"attain":[197],"capability":[199],"comparable":[200],"proprietary":[202],"GPT-4V,":[206],"despite":[207],"being":[208],"over":[209],"l0x":[210],"smaller":[211],"size.":[214]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}