{"id":"https://openalex.org/W4399423438","doi":"https://doi.org/10.1145/3652583.3658080","title":"Pseudo Content Hallucination for Unpaired Image Captioning","display_name":"Pseudo Content Hallucination for Unpaired Image Captioning","publication_year":2024,"publication_date":"2024-05-30","ids":{"openalex":"https://openalex.org/W4399423438","doi":"https://doi.org/10.1145/3652583.3658080"},"language":"en","primary_location":{"id":"doi:10.1145/3652583.3658080","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3658080","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3658080","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3658080","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033097783","display_name":"Huixia Ben","orcid":"https://orcid.org/0000-0001-7946-8199"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Huixia Ben","raw_affiliation_strings":["School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-7946-8199","affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100400159","display_name":"Shuo Wang","orcid":"https://orcid.org/0000-0002-4881-9344"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuo Wang","raw_affiliation_strings":["School of Computer Science and Information Engineering, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-4881-9344","affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Engineering, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100377147","display_name":"Meng Wang","orcid":"https://orcid.org/0000-0002-3094-7735"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Wang","raw_affiliation_strings":["School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-3094-7735","affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051332325","display_name":"Richang Hong","orcid":"https://orcid.org/0000-0001-5461-3986"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Richang Hong","raw_affiliation_strings":["School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-5461-3986","affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5033097783"],"corresponding_institution_ids":["https://openalex.org/I16365422"],"apc_list":null,"apc_paid":null,"fwci":0.9523,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.7524292,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"320","last_page":"329"},"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":0.9807000160217285,"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":0.9722999930381775,"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/hallucinating","display_name":"Hallucinating","score":0.9837305545806885},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.9743810892105103},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7322338819503784},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6591324806213379},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.593560516834259},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5329607129096985},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.511260986328125},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4485083520412445},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4278990626335144},{"id":"https://openalex.org/keywords/content","display_name":"Content (measure theory)","score":0.42666497826576233},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3506430685520172},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.12036699056625366},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0885053277015686}],"concepts":[{"id":"https://openalex.org/C2911011789","wikidata":"https://www.wikidata.org/wiki/Q130741","display_name":"Hallucinating","level":2,"score":0.9837305545806885},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9743810892105103},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7322338819503784},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6591324806213379},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.593560516834259},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5329607129096985},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.511260986328125},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4485083520412445},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4278990626335144},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.42666497826576233},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3506430685520172},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.12036699056625366},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0885053277015686},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3652583.3658080","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3658080","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3658080","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3652583.3658080","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3658080","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3658080","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1189641229","display_name":null,"funder_award_id":"No. 61932009","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1829462488","display_name":null,"funder_award_id":"61932009","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4066691768","display_name":null,"funder_award_id":"62202439","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4399423438.pdf","grobid_xml":"https://content.openalex.org/works/W4399423438.grobid-xml"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W1773149199","https://openalex.org/W1861492603","https://openalex.org/W2101105183","https://openalex.org/W2156830856","https://openalex.org/W2277195237","https://openalex.org/W2463955103","https://openalex.org/W2557728737","https://openalex.org/W2588822708","https://openalex.org/W2745461083","https://openalex.org/W2765407302","https://openalex.org/W2801271919","https://openalex.org/W2886641317","https://openalex.org/W2896487916","https://openalex.org/W2962529143","https://openalex.org/W2963048642","https://openalex.org/W2963536419","https://openalex.org/W2963622213","https://openalex.org/W2963743213","https://openalex.org/W2965778995","https://openalex.org/W2981994675","https://openalex.org/W2990307191","https://openalex.org/W3004328990","https://openalex.org/W3009270862","https://openalex.org/W3034302069","https://openalex.org/W3034493371","https://openalex.org/W3081796931","https://openalex.org/W3086385316","https://openalex.org/W3097062010","https://openalex.org/W3135254306","https://openalex.org/W3152980002","https://openalex.org/W3160190143","https://openalex.org/W3172675210","https://openalex.org/W3174159092","https://openalex.org/W4213207626","https://openalex.org/W4220978858","https://openalex.org/W4224329855","https://openalex.org/W4226117651","https://openalex.org/W4287866072","https://openalex.org/W4301156730","https://openalex.org/W4304014785","https://openalex.org/W4309157236","https://openalex.org/W4386148430","https://openalex.org/W4387967919","https://openalex.org/W4393147864"],"related_works":["https://openalex.org/W3164229987","https://openalex.org/W3215212336","https://openalex.org/W4290852288","https://openalex.org/W3217388757","https://openalex.org/W3122720459","https://openalex.org/W4298897568","https://openalex.org/W4289422896","https://openalex.org/W1938708284","https://openalex.org/W4380190185","https://openalex.org/W2506045685"],"abstract_inverted_index":{"Unpaired":[0],"Image":[1],"Captioning":[2],"(UIC)":[3],"is":[4,18,48],"designed":[5],"to":[6,40,54,63,80,146,161,215],"describe":[7],"an":[8],"image":[9,67],"without":[10],"relying":[11],"on":[12,194],"matched":[13],"vision-language":[14,28],"training":[15,33,136],"data.":[16],"It":[17],"a":[19,122,127,152,211],"challenging":[20],"task":[21,34],"since":[22],"(1)":[23],"the":[24,32,36,51,56,66,82,86,89,94,97,132,135,141,148,163,172,178,184,188,195,203,216,219,226],"implicit":[25],"and":[26,45,92,110,156,200],"unpaired":[27],"data":[29],"nature":[30],"of":[31,65,88,134,180,205],"limits":[35],"captioning":[37,52,83,164,173],"model's":[38],"ability":[39],"represent":[41],"diverse":[42],"scene":[43,124],"representations,":[44],"(2)":[46],"it":[47],"difficult":[49],"for":[50,116,171],"model":[53,84,174],"discern":[55],"intrinsic":[57],"relationships":[58,142],"among":[59,143],"objects,":[60],"potentially":[61],"leading":[62],"misinterpretation":[64],"con-":[68],"tent.":[69],"To":[70],"solve":[71],"these":[72,144],"issues,":[73],"we":[74,100,139],"propose":[75],"pseudo":[76,108,158],"content":[77,109,115,120,154],"hallucination":[78,155],"(PCH)":[79],"help":[81],"enlarge":[85],"perception":[87],"ob-":[90],"jects":[91],"capture":[93,179],"relations":[95],"between":[96],"objects.":[98],"Specifically,":[99],"select":[101],"similar":[102,123],"objects":[103,145],"from":[104,183],"different":[105,128],"images":[106],"as":[107,151,175],"then":[111],"hallucinate":[112],"new":[113],"visual":[114],"training.":[117],"This":[118],"hallucinated":[119,167],"contains":[121],"but":[125],"with":[126,222],"representation,":[129],"thus":[130],"enriching":[131],"diversity":[133],"samples.":[137],"Meanwhile,":[138],"utilize":[140],"improve":[147],"generated":[149],"captions":[150],"textual":[153],"construct":[157],"image-sentence":[159],"pairs":[160],"refine":[162],"model.":[165],"These":[166],"sentences":[168],"are":[169],"beneficial":[170],"they":[176],"enable":[177],"additional":[181],"semantics":[182],"image,":[185],"ultimately":[186],"enhancing":[187],"sentence":[189],"generation":[190],"ability.":[191],"Extensive":[192],"experiments":[193],"two":[196],"benchmarks,":[197],"i.e.,":[198],"MSCOCO,":[199],"Flickr30k,":[201],"show":[202,210],"effectiveness":[204],"our":[206],"method.":[207],"The":[208],"results":[209],"significant":[212],"improvement":[213],"compared":[214],"baseline":[217],"in":[218,225],"MSCOCO":[220],"dataset,":[221],"1.5":[223],"increase":[224],"CIDEr":[227],"score.":[228]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}