{"id":"https://openalex.org/W4285389151","doi":"https://doi.org/10.1145/3532627","title":"Adaptive Text Denoising Network for Image Caption Editing","display_name":"Adaptive Text Denoising Network for Image Caption Editing","publication_year":2022,"publication_date":"2022-07-14","ids":{"openalex":"https://openalex.org/W4285389151","doi":"https://doi.org/10.1145/3532627"},"language":"en","primary_location":{"id":"doi:10.1145/3532627","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3532627","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","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":"https://openalex.org/A5005487402","display_name":"Mengqi Yuan","orcid":"https://orcid.org/0000-0001-9183-3267"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Mengqi Yuan","raw_affiliation_strings":["Nanjing University of Postsand Telecommunications, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University of Postsand Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007962086","display_name":"Bing\u2010Kun Bao","orcid":"https://orcid.org/0000-0001-5956-831X"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing-Kun Bao","raw_affiliation_strings":["Nanjing University of Postsand Telecommunications, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University of Postsand Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026721130","display_name":"Zhiyi Tan","orcid":"https://orcid.org/0000-0002-1209-2817"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyi Tan","raw_affiliation_strings":["Nanjing University of Postsand Telecommunications, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University of Postsand Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022636178","display_name":"Changsheng Xu","orcid":"https://orcid.org/0000-0001-8343-9665"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changsheng Xu","raw_affiliation_strings":["Peng Cheng Laboratory; University of Chinese Academy of Sciences; NLPR, Institute of Automation, CAS, Beijing, China","Peng Cheng Laboratory","University of Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"Peng Cheng Laboratory; University of Chinese Academy of Sciences; NLPR, Institute of Automation, CAS, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038","https://openalex.org/I4210136793"]},{"raw_affiliation_string":"Peng Cheng Laboratory","institution_ids":["https://openalex.org/I4210136793"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5005487402"],"corresponding_institution_ids":["https://openalex.org/I41198531"],"apc_list":null,"apc_paid":null,"fwci":0.6113,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.67026581,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"19","issue":"1s","first_page":"1","last_page":"18"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9969000220298767,"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":0.994700014591217,"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":0.8804534077644348},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.8141786456108093},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.656530499458313},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6441171169281006},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6294875144958496},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4970550835132599},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.47725579142570496},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.460463285446167},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4527878165245056},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.4509838819503784},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4506422281265259},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4447672963142395},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.33069026470184326},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.32385963201522827},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10645186901092529}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8804534077644348},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8141786456108093},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.656530499458313},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6441171169281006},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6294875144958496},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4970550835132599},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47725579142570496},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.460463285446167},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4527878165245056},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.4509838819503784},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4506422281265259},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4447672963142395},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.33069026470184326},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32385963201522827},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10645186901092529},{"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3532627","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3532627","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7799999713897705}],"awards":[{"id":"https://openalex.org/G1097327202","display_name":null,"funder_award_id":"61936005, 61872424","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2449038238","display_name":null,"funder_award_id":"BK20200037, and BK20210595","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1593271688","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1956340063","https://openalex.org/W2117539524","https://openalex.org/W2186222003","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2481240925","https://openalex.org/W2550553598","https://openalex.org/W2575842049","https://openalex.org/W2596164567","https://openalex.org/W2599674900","https://openalex.org/W2745461083","https://openalex.org/W2885013662","https://openalex.org/W2889411261","https://openalex.org/W2955956881","https://openalex.org/W2963084599","https://openalex.org/W2963101956","https://openalex.org/W2965697393","https://openalex.org/W2965922392","https://openalex.org/W2970972587","https://openalex.org/W2974212192","https://openalex.org/W2986670728","https://openalex.org/W2987327987","https://openalex.org/W2998988444","https://openalex.org/W2999905431","https://openalex.org/W3003478339","https://openalex.org/W3034655362","https://openalex.org/W3034984754","https://openalex.org/W3035160838","https://openalex.org/W3035284526","https://openalex.org/W3039115681","https://openalex.org/W3088132234","https://openalex.org/W3092956019","https://openalex.org/W3102371147","https://openalex.org/W3102643993","https://openalex.org/W3110014757","https://openalex.org/W3167267673","https://openalex.org/W3174377922","https://openalex.org/W3202852550","https://openalex.org/W4212991200","https://openalex.org/W4234552385","https://openalex.org/W4249809564","https://openalex.org/W4297792979","https://openalex.org/W4312977351"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W3088136942","https://openalex.org/W2949362007","https://openalex.org/W2775506363","https://openalex.org/W4290852288","https://openalex.org/W4388893791","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2221419418"],"abstract_inverted_index":{"Image":[0],"caption":[1,35,53,138],"editing,":[2],"which":[3,200],"aims":[4],"at":[5,98,107,111],"editing":[6],"the":[7,11,25,29,45,61,69,71,99,104,112,127,136,144,152,159,165,178,183,193,197,202,205,213,220,228],"inaccurate":[8,34,137],"descriptions":[9],"of":[10,17,146,161,167,196,204,222],"images,":[12],"is":[13,48,132,189],"an":[14,41,168],"interdisciplinary":[15],"task":[16,26],"computer":[18],"vision":[19],"and":[20,31,37,76,102,149,218],"natural":[21],"language":[22],"processing.":[23],"As":[24],"requires":[27],"encoding":[28],"image":[30,43,52,75,148,215],"its":[32],"corresponding":[33],"simultaneously":[36],"decoding":[38],"to":[39,94,125,134,157,176,191],"generate":[40],"accurate":[42],"caption,":[44,170,199],"encoder-decoder":[46],"framework":[47],"widely":[49],"adopted":[50],"for":[51],"editing.":[54],"However,":[55],"existing":[56],"methods":[57],"mostly":[58],"focus":[59],"on":[60,68,143,164,212],"decoder,":[62],"yet":[63],"ignore":[64],"a":[65,83,117,173],"big":[66],"challenge":[67],"encoder:":[70],"semantic":[72,166,180],"inconsistency":[73],"between":[74],"caption.":[77,150,185],"To":[78],"this":[79],"end,":[80],"we":[81,115,171],"propose":[82],"novel":[84],"A":[85],"daptive":[86],"T":[87],"ext":[88],"D":[89],"enoising":[90],"Net":[91],"work":[92],"(ATD-Net)":[93],"filter":[95],"out":[96],"noises":[97],"word":[100,113,139,141],"level":[101],"improve":[103],"model\u2019s":[105],"robustness":[106,203],"sentence":[108,153],"level.":[109],"Specifically,":[110],"level,":[114,154],"design":[116],"cross-attention":[118],"mechanism":[119],"called":[120],"Textual":[121],"Attention":[122],"Mechanism":[123],"(TAM),":[124],"differentiate":[126],"misdescriptive":[128,162],"words.":[129],"The":[130,186],"TAM":[131],"designed":[133],"encode":[135],"by":[140],"based":[142],"content":[145],"both":[147],"At":[151],"in":[155],"order":[156],"minimize":[158],"influence":[160],"words":[163],"entire":[169],"introduce":[172],"Bidirectional":[174,187],"Encoder":[175,188],"extract":[177],"correct":[179],"representation":[181],"from":[182],"raw":[184,198],"able":[190],"model":[192],"global":[194],"semantics":[195],"enhances":[201],"framework.":[206],"We":[207],"extensively":[208],"evaluate":[209],"our":[210,223],"proposals":[211],"MS-COCO":[214],"captioning":[216],"dataset":[217],"prove":[219],"effectiveness":[221],"method":[224],"when":[225],"compared":[226],"with":[227],"state-of-the-arts.":[229]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}