{"id":"https://openalex.org/W4415537759","doi":"https://doi.org/10.1145/3746027.3755762","title":"Noise-Aware Decoding with Salient Region Enhancing for Zero-Shot Image Captioning","display_name":"Noise-Aware Decoding with Salient Region Enhancing for Zero-Shot Image Captioning","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415537759","doi":"https://doi.org/10.1145/3746027.3755762"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755762","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755762","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","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":null,"display_name":"YuXin Xie","orcid":"https://orcid.org/0009-0001-1184-0596"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"YuXin Xie","raw_affiliation_strings":["College of Information Science and Engineering, Northeastern University, Shenyang, Liaoning, China"],"raw_orcid":"https://orcid.org/0009-0001-1184-0596","affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Northeastern University, Shenyang, Liaoning, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013451601","display_name":"Dongyue Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongyue Chen","raw_affiliation_strings":["College of Information Science and Engineering, Northeastern University, Shenyang, Liaoning, China and National Frontiers Science Center for Industrial Intelligence and Systems Optimization, Northeastern University, Shenyang, Liaoning, China"],"raw_orcid":"https://orcid.org/0000-0003-0673-6767","affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Northeastern University, Shenyang, Liaoning, China and National Frontiers Science Center for Industrial Intelligence and Systems Optimization, Northeastern University, Shenyang, Liaoning, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112459031","display_name":"Yue Zhu","orcid":"https://orcid.org/0009-0002-1729-2583"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Zhu","raw_affiliation_strings":["College of Information Science and Engineering, Northeastern University, Shenyang, Liaoning, China"],"raw_orcid":"https://orcid.org/0009-0002-1729-2583","affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Northeastern University, Shenyang, Liaoning, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065669986","display_name":"Tong Jia","orcid":"https://orcid.org/0000-0003-1424-798X"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tong Jia","raw_affiliation_strings":["College of Information Science and Engineering, Northeastern University, Shenyang, Liaoning, China"],"raw_orcid":"https://orcid.org/0000-0003-1424-798X","affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Northeastern University, Shenyang, Liaoning, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091147127","display_name":"Shizhuo Deng","orcid":"https://orcid.org/0000-0002-6863-8516"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shizhuo Deng","raw_affiliation_strings":["College of Information Science and Engineering, Northeastern University, Shenyang, Liaoning, China and Foshan Graduate School of Innovation, Northeastern University, Foshan, Guangdong, China"],"raw_orcid":"https://orcid.org/0000-0002-6863-8516","affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Northeastern University, Shenyang, Liaoning, China and Foshan Graduate School of Innovation, Northeastern University, Foshan, Guangdong, China","institution_ids":["https://openalex.org/I9224756"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I9224756"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5120","last_page":"5129"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9990000128746033,"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/T10036","display_name":"Advanced Neural Network Applications","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/closed-captioning","display_name":"Closed captioning","score":0.9921000003814697},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.7703999876976013},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6902999877929688},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.6279000043869019},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5928000211715698},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5248000025749207},{"id":"https://openalex.org/keywords/fusion-mechanism","display_name":"Fusion mechanism","score":0.4205999970436096}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9921000003814697},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7875000238418579},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.7703999876976013},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6902999877929688},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.6279000043869019},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6276999711990356},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5928000211715698},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5248000025749207},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4397999942302704},{"id":"https://openalex.org/C173414695","wikidata":"https://www.wikidata.org/wiki/Q5510276","display_name":"Fusion mechanism","level":4,"score":0.4205999970436096},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4163999855518341},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3874000012874603},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.37790000438690186},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3197999894618988},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.2924000024795532},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.28940001130104065},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2833999991416931},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.2802000045776367},{"id":"https://openalex.org/C198352243","wikidata":"https://www.wikidata.org/wiki/Q37105","display_name":"Line (geometry)","level":2,"score":0.2734000086784363},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2685000002384186},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2612000107765198}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755762","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755762","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","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":16,"referenced_works":["https://openalex.org/W1536680647","https://openalex.org/W1773149199","https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W2101105183","https://openalex.org/W2133459682","https://openalex.org/W2173180041","https://openalex.org/W2745461083","https://openalex.org/W2795151422","https://openalex.org/W2890531016","https://openalex.org/W2962933664","https://openalex.org/W2963150697","https://openalex.org/W3173220247","https://openalex.org/W4386076004","https://openalex.org/W4393154592","https://openalex.org/W4405868000"],"related_works":[],"abstract_inverted_index":{"Image":[0,79],"captioning":[1,14,153,178,182],"aims":[2],"to":[3,32,115,120,180],"create":[4],"natural":[5],"language":[6],"descriptions":[7,34],"of":[8,87],"images.":[9],"Recent":[10],"advancements":[11],"in":[12,43,57,176],"image":[13,25,177],"have":[15],"explored":[16],"text-only":[17,185],"training":[18],"methods":[19,29,171],"that":[20,35,38,98,131,144],"eliminate":[21],"the":[22,44,51,85,169],"need":[23],"for":[24,77],"annotations.":[26],"However,":[27],"these":[28],"are":[30,47],"prone":[31],"generate":[33],"include":[36],"objects":[37],"do":[39],"not":[40],"actually":[41],"appear":[42],"image,":[45],"but":[46],"instead":[48],"drawn":[49],"from":[50],"retrieval":[52],"texts":[53],"or":[54],"hard":[55,107],"prompts-resulting":[56],"object":[58],"hallucinations.":[59],"To":[60],"address":[61],"this":[62],"issue,":[63],"we":[64,124],"propose":[65],"synergistic":[66],"prompting":[67],"mechanism":[68],"called":[69],"NASCap":[70,145],"(Noise-Aware":[71],"Decoding":[72],"with":[73,95,103,110],"Salient":[74],"Region":[75],"Enhancing":[76],"Zero-Shot":[78],"Captioning).":[80],"Our":[81],"method":[82],"further":[83,116],"improves":[84],"accuracy":[86],"generated":[88],"captions":[89,102],"by":[90,172],"designing":[91],"a":[92,126,147,173],"fusion":[93,129],"model":[94],"mask":[96],"attention":[97],"isolate":[99],"integrates":[100],"retrieved":[101],"input":[104],"features.":[105],"The":[106],"prompt":[108],"mixed":[109],"negative":[111],"entities":[112],"is":[113],"designed":[114],"improve":[117],"model's":[118],"robust":[119],"wrong":[121],"information.":[122],"Additionally,":[123],"introduce":[125],"training-free":[127],"multi-granularity":[128],"strategy":[130],"dynamically":[132],"perceive":[133],"and":[134,154],"enhance":[135],"salient":[136],"regions":[137],"into":[138],"global":[139],"representation.":[140],"Extensive":[141],"experiments":[142],"demonstrate":[143],"sets":[146],"new":[148],"state-of-the":[149],"art":[150],"cross-domain":[151],"(transferable)":[152],"performs":[155],"Through":[156],"extensive":[157],"experiments,":[158],"our":[159],"straightforward":[160],"yet":[161],"powerful":[162],"approach":[163],"has":[164],"demonstrated":[165],"its":[166],"efficacy,":[167],"outperforming":[168],"state-of-the-art":[170],"significant":[174],"margin":[175],"compared":[179],"zero-shot":[181],"based":[183],"on":[184],"training.":[186]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}