{"id":"https://openalex.org/W7123718623","doi":"https://doi.org/10.1142/s0218001426590056","title":"Similarity-Guided Denoising Reconstruction for Unsupervised Image Captioning","display_name":"Similarity-Guided Denoising Reconstruction for Unsupervised Image Captioning","publication_year":2026,"publication_date":"2026-01-14","ids":{"openalex":"https://openalex.org/W7123718623","doi":"https://doi.org/10.1142/s0218001426590056"},"language":"en","primary_location":{"id":"doi:10.1142/s0218001426590056","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218001426590056","pdf_url":null,"source":{"id":"https://openalex.org/S41486457","display_name":"International Journal of Pattern Recognition and Artificial Intelligence","issn_l":"0218-0014","issn":["0218-0014","1793-6381"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Pattern Recognition and Artificial Intelligence","raw_type":"journal-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":null,"display_name":"Dongnan Yang","orcid":"https://orcid.org/0009-0002-7751-6200"},"institutions":[{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongnan Yang","raw_affiliation_strings":["School of Computer, Electronics and Information, Guangxi University Nanning 530004, Guangxi, P. R. China"],"raw_orcid":"https://orcid.org/0009-0002-7751-6200","affiliations":[{"raw_affiliation_string":"School of Computer, Electronics and Information, Guangxi University Nanning 530004, Guangxi, P. R. China","institution_ids":["https://openalex.org/I150807315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122933090","display_name":"Lina Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lina Yang","raw_affiliation_strings":["School of Computer, Electronics and Information, Guangxi University Nanning 530004, Guangxi, P. R. China"],"raw_orcid":"https://orcid.org/0000-0003-3489-1887","affiliations":[{"raw_affiliation_string":"School of Computer, Electronics and Information, Guangxi University Nanning 530004, Guangxi, P. R. China","institution_ids":["https://openalex.org/I150807315"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Thomas Wu","orcid":"https://orcid.org/0000-0002-0674-9915"},"institutions":[{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Thomas Wu","raw_affiliation_strings":["School of Electrical Engineering, Guangxi University, Nanning 530004, Guangxi, P. R. China"],"raw_orcid":"https://orcid.org/0000-0002-0674-9915","affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Guangxi University, Nanning 530004, Guangxi, P. R. China","institution_ids":["https://openalex.org/I150807315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122947895","display_name":"Xichun Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210118063","display_name":"Guangxi Normal University for Nationalities","ror":"https://ror.org/02cejc171","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210118063"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xichun Li","raw_affiliation_strings":["School of Mathematics and Computer Science, Guangxi Normal University for Nationalities, Chongzuo 532200, Guangxi, P. R. China"],"raw_orcid":"https://orcid.org/0009-0006-1921-1651","affiliations":[{"raw_affiliation_string":"School of Mathematics and Computer Science, Guangxi Normal University for Nationalities, Chongzuo 532200, Guangxi, P. R. China","institution_ids":["https://openalex.org/I4210118063"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122916719","display_name":"Yuan Yan Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]},{"id":"https://openalex.org/I2800531931","display_name":"Hong Kong College of Technology","ror":"https://ror.org/014w0p014","country_code":"CN","type":"education","lineage":["https://openalex.org/I2800531931"]}],"countries":["CN","HK","MO"],"is_corresponding":false,"raw_author_name":"Yuan Yan Tang","raw_affiliation_strings":["Faculty of Science and Technology, UOW College Hong Kong, Hong Kong, P. R. China","Faculty of Science and Technology, University of Macau, Macau 999078, P. R. China"],"raw_orcid":"https://orcid.org/0000-0002-6887-130X","affiliations":[{"raw_affiliation_string":"Faculty of Science and Technology, UOW College Hong Kong, Hong Kong, P. R. China","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I2800531931"]},{"raw_affiliation_string":"Faculty of Science and Technology, University of Macau, Macau 999078, P. R. China","institution_ids":["https://openalex.org/I204512498"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077075722","display_name":"Patrick S. P. Wang","orcid":"https://orcid.org/0000-0002-9336-3155"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Patrick Shen-Pei Wang","raw_affiliation_strings":["Department of Computer and Information Science, Khoury College of Computer Sciences Northeastern University, Boston MA 02115, Guangxi, USA"],"raw_orcid":"https://orcid.org/0000-0002-9336-3155","affiliations":[{"raw_affiliation_string":"Department of Computer and Information Science, Khoury College of Computer Sciences Northeastern University, Boston MA 02115, Guangxi, USA","institution_ids":["https://openalex.org/I12912129"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05626684,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"06","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9796000123023987,"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":0.9796000123023987,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.009399999864399433,"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":0.0013000000035390258,"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":0.984000027179718},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5787000060081482},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.57669997215271},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5406000018119812},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5388000011444092},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5034999847412109},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4918000102043152},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.43630000948905945}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.984000027179718},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8507999777793884},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7001000046730042},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5787000060081482},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.57669997215271},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5406000018119812},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5388000011444092},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5034999847412109},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4918000102043152},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.43630000948905945},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4250999987125397},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.39800000190734863},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3889999985694885},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.37619999051094055},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.37310001254081726},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.3671000003814697},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3522000014781952},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3411000072956085},{"id":"https://openalex.org/C197115733","wikidata":"https://www.wikidata.org/wiki/Q1003136","display_name":"Forcing (mathematics)","level":2,"score":0.3328999876976013},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.29170000553131104},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.2867000102996826},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.2599000036716461},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.25540000200271606}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s0218001426590056","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218001426590056","pdf_url":null,"source":{"id":"https://openalex.org/S41486457","display_name":"International Journal of Pattern Recognition and Artificial Intelligence","issn_l":"0218-0014","issn":["0218-0014","1793-6381"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Pattern Recognition and Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8513115644454956,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G3150721642","display_name":null,"funder_award_id":"62461004","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7226221071","display_name":null,"funder_award_id":"62371144","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7494446569","display_name":null,"funder_award_id":"62172458","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":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W2108325777","https://openalex.org/W2133459682","https://openalex.org/W2185175083","https://openalex.org/W2302086703","https://openalex.org/W2506483933","https://openalex.org/W2550553598","https://openalex.org/W2575842049","https://openalex.org/W2745461083","https://openalex.org/W2808138519","https://openalex.org/W2963084599","https://openalex.org/W2981165461","https://openalex.org/W2986670728","https://openalex.org/W3005983418","https://openalex.org/W3034655362","https://openalex.org/W3035284526","https://openalex.org/W3091588028","https://openalex.org/W3106925514","https://openalex.org/W3110019360","https://openalex.org/W3205071568","https://openalex.org/W3207942052","https://openalex.org/W4285491539","https://openalex.org/W4285606530","https://openalex.org/W4292828275","https://openalex.org/W4312933868","https://openalex.org/W4312938727","https://openalex.org/W4385567053","https://openalex.org/W4386075882","https://openalex.org/W4390111074","https://openalex.org/W4390873546","https://openalex.org/W4396713940","https://openalex.org/W4411201031"],"related_works":[],"abstract_inverted_index":{"Image":[0],"captioning":[1,21,48,103],"aims":[2],"to":[3,122,138,141,211],"generate":[4],"natural":[5],"and":[6,74,82,146,156,168,174,176,185],"accurate":[7],"textual":[8],"descriptions":[9],"of":[10,57,126],"given":[11],"images.":[12],"Although":[13],"significant":[14],"progress":[15],"has":[16],"been":[17],"made":[18],"in":[19,23],"image":[20,47,102],"models":[22,60],"recent":[24],"years,":[25],"most":[26,201],"existing":[27],"approaches":[28],"heavily":[29],"rely":[30],"on":[31,52,182,204],"high-quality":[32],"image-text":[33],"paired":[34],"datasets":[35],"that":[36,105,189],"require":[37],"expensive":[38],"human":[39],"annotation,":[40],"thus":[41],"limiting":[42],"model":[43,80,137],"scalability.":[44],"Current":[45],"unsupervised":[46,101],"methods":[49],"primarily":[50],"focus":[51],"leveraging":[53],"zero-shot":[54],"learning":[55],"capabilities":[56],"large":[58],"pre-trained":[59],"(e.g.":[61],"CLIP,":[62],"GPT-2),":[63],"yet":[64],"still":[65],"face":[66],"persistent":[67],"challenges":[68],"including":[69],"modality":[70,109],"gaps,":[71],"inefficient":[72],"inference,":[73],"excessive":[75],"noise":[76,150],"incorporation,":[77],"which":[78],"constrain":[79],"accuracy":[81,173],"generalization":[83],"capabilities.":[84],"To":[85],"address":[86],"these":[87],"limitations,":[88],"we":[89],"propose":[90],"SGDR-Cap":[91],"(":[92],"Similarity-":[93],"Guided":[94],"Denoising":[95],"Reconstruction":[96],"for":[97],"Captioning),":[98],"a":[99,112],"novel":[100],"method":[104,118,191],"bridges":[106],"the":[107,124,136,183,200,205],"vision-language":[108],"gap":[110],"through":[111],"similarity-guided":[113],"denoising":[114,165],"reconstruction":[115,125,166],"module.":[116],"Our":[117],"leverages":[119],"similarity":[120],"information":[121],"guide":[123],"authentic":[127],"text":[128],"features":[129,145],"during":[130],"caption":[131],"generation":[132],"while":[133],"simultaneously":[134],"forcing":[135],"learn":[139],"how":[140],"extract":[142],"crucial":[143],"image-relevant":[144],"filter":[147],"out":[148],"unnecessary":[149],"information.":[151],"This":[152],"enhances":[153],"both":[154],"coarse-":[155],"fine-grained":[157],"cross-modal":[158],"alignment.":[159],"Furthermore,":[160],"our":[161,190],"approach":[162],"jointly":[163],"optimizes":[164],"loss":[167],"language":[169],"modeling":[170],"loss,":[171],"ensuring":[172],"fluency,":[175],"promoting":[177],"greater":[178],"diversity.":[179],"Extensive":[180],"evaluations":[181],"MSCOCO":[184],"Flickr30K":[186],"benchmarks":[187],"demonstrate":[188],"achieves":[192],"state-of-the-art":[193],"results":[194],"across":[195],"all":[196],"major":[197],"metrics,":[198],"with":[199],"notable":[202],"gain":[203],"CIDEr":[206],"score,":[207],"improving":[208],"from":[209],"101.1":[210],"104.4.":[212]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-01-14T00:00:00"}