{"id":"https://openalex.org/W4415192993","doi":"https://doi.org/10.1109/iccv51701.2025.02149","title":"SC-Captioner: Improving Image Captioning with Self-Correction by Reinforcement Learning","display_name":"SC-Captioner: Improving Image Captioning with Self-Correction by Reinforcement Learning","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4415192993","doi":"https://doi.org/10.1109/iccv51701.2025.02149"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.02149","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02149","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2508.06125","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5107700607","display_name":"Lin Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Zhang","raw_affiliation_strings":["College of Future Information Technology, Fudan University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Future Information Technology, Fudan University,China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022110331","display_name":"Xianfang Zeng","orcid":"https://orcid.org/0000-0003-1251-2129"},"institutions":[{"id":"https://openalex.org/I3019120426","display_name":"China Iron and Steel Research Institute Group","ror":"https://ror.org/02e42hc22","country_code":"CN","type":"facility","lineage":["https://openalex.org/I3019120426"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianfang Zeng","raw_affiliation_strings":["StepFun,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"StepFun,China","institution_ids":["https://openalex.org/I3019120426"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078355895","display_name":"Kunchang Li","orcid":"https://orcid.org/0000-0001-5612-0341"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kangcong Li","raw_affiliation_strings":["College of Future Information Technology, Fudan University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Future Information Technology, Fudan University,China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003400275","display_name":"Gang Yu","orcid":"https://orcid.org/0000-0001-5570-2710"},"institutions":[{"id":"https://openalex.org/I3019120426","display_name":"China Iron and Steel Research Institute Group","ror":"https://ror.org/02e42hc22","country_code":"CN","type":"facility","lineage":["https://openalex.org/I3019120426"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gang Yu","raw_affiliation_strings":["StepFun,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"StepFun,China","institution_ids":["https://openalex.org/I3019120426"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100765926","display_name":"Tao Chen","orcid":"https://orcid.org/0000-0003-3550-2310"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Chen","raw_affiliation_strings":["College of Future Information Technology, Fudan University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Future Information Technology, Fudan University,China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":"23145","last_page":"23155"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9822999835014343,"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":0.9768000245094299,"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":0.8349000215530396},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.6958000063896179},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6934000253677368},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.6438000202178955},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6431999802589417},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.6136000156402588},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.576200008392334},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.5667999982833862},{"id":"https://openalex.org/keywords/mistake","display_name":"Mistake","score":0.4819999933242798}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8349000215530396},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.774399995803833},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6958000063896179},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6934000253677368},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.6438000202178955},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6431999802589417},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6316999793052673},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.6136000156402588},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.576200008392334},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.5667999982833862},{"id":"https://openalex.org/C2777179996","wikidata":"https://www.wikidata.org/wiki/Q911222","display_name":"Mistake","level":2,"score":0.4819999933242798},{"id":"https://openalex.org/C2779795794","wikidata":"https://www.wikidata.org/wiki/Q7315343","display_name":"Reset (finance)","level":2,"score":0.4575999975204468},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.45239999890327454},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4043000042438507},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38019999861717224},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.373199999332428},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.34869998693466187},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3440000116825104},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.3377000093460083},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.3046000003814697},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29600000381469727},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.29330000281333923},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.2696000039577484},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26829999685287476},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.26460000872612},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.25920000672340393}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.02149","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02149","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2508.06125","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.06125","pdf_url":"https://arxiv.org/pdf/2508.06125","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2508.06125","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2508.06125","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2508.06125","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.06125","pdf_url":"https://arxiv.org/pdf/2508.06125","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5058943624","display_name":null,"funder_award_id":"2022ZD0160101","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G5491202952","display_name":"\u9762\u5411\u6709\u9650\u7b97\u529b\u548c\u6570\u636e\u8d44\u6e90\u7684\u591a\u6a21\u6001\u878d\u5408\u4e0e\u77e5\u8bc6\u63a8\u7406\u7814\u7a76","funder_award_id":"23ZR1402900","funder_id":"https://openalex.org/F4320309612","funder_display_name":"Natural Science Foundation of Shanghai"}],"funders":[{"id":"https://openalex.org/F4320309612","display_name":"Natural Science Foundation of Shanghai","ror":null},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,50],"propose":[1,102],"SC-Captioner,":[2],"a":[3,103,124],"reinforcement":[4],"learning":[5],"framework":[6],"that":[7,110,141],"enables":[8],"the":[9,21,24,33,52,73,93,158],"self-correcting":[10],"capability":[11],"of":[12,23,57,105,132],"image":[13,97,127,151],"caption":[14,30,98,128],"models.":[15],"Our":[16],"crucial":[17],"technique":[18],"lies":[19],"in":[20],"design":[22],"reward":[25],"function":[26],"to":[27,62,76],"incentivize":[28],"accurate":[29,81],"corrections.":[31],"Specifically,":[32],"predicted":[34],"and":[35,43,59,65,83,89,116],"reference":[36,74],"captions":[37,61,152],"are":[38,70],"decomposed":[39],"into":[40],"object,":[41],"attribute,":[42],"relation":[44,118],"sets":[45,56,75],"using":[46],"scene-graph":[47],"parsing":[48],"algorithms.":[49],"calculate":[51,77],"set":[53,104],"difference":[54],"between":[55],"initial":[58],"self-corrected":[60],"identify":[63],"added":[64],"removed":[66],"elements.":[67],"These":[68],"elements":[69],"matched":[71],"against":[72],"correctness":[78],"bonuses":[79],"for":[80,86],"refinements":[82],"mistake":[84],"punishments":[85],"wrong":[87],"additions":[88],"removals,":[90],"thereby":[91],"forming":[92],"final":[94],"reward.":[95],"For":[96],"quality":[99],"assessment,":[100],"we":[101,122],"metrics":[106],"refined":[107],"from":[108,136],"CAPTURE":[109],"alleviate":[111],"its":[112],"incomplete":[113],"precision":[114],"evaluation":[115],"inefficient":[117],"matching":[119],"problems.":[120],"Furthermore,":[121],"collect":[123],"fine-grained":[125],"annotated":[126],"dataset,":[129],"RefinedCaps,":[130],"consisting":[131],"6.5K":[133],"diverse":[134],"images":[135],"COCO":[137],"dataset.":[138],"Experiments":[139],"show":[140],"applying":[142],"SC-Captioner":[143],"on":[144],"large":[145],"visual-language":[146],"models":[147],"can":[148],"generate":[149],"better":[150],"across":[153],"various":[154],"scenarios,":[155],"significantly":[156],"outperforming":[157],"direct":[159],"preference":[160],"optimization":[161],"training":[162],"strategy.":[163]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-15T00:00:00"}