{"id":"https://openalex.org/W4409685381","doi":"https://doi.org/10.1109/tpami.2025.3562866","title":"Diagnostic Captioning by Cooperative Task Interactions and Sample-Graph Consistency","display_name":"Diagnostic Captioning by Cooperative Task Interactions and Sample-Graph Consistency","publication_year":2025,"publication_date":"2025-04-22","ids":{"openalex":"https://openalex.org/W4409685381","doi":"https://doi.org/10.1109/tpami.2025.3562866","pmid":"https://pubmed.ncbi.nlm.nih.gov/40261788"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2025.3562866","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3562866","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5100676104","display_name":"Zhanyu Wang","orcid":"https://orcid.org/0000-0002-2079-4931"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Zhanyu Wang","raw_affiliation_strings":["School of Electrical and Information Engineering, University of Sydney, Camperdown, NSW, Australia","School of Electrical and Information Engineering, University of Sydney, Australia"],"raw_orcid":"https://orcid.org/0000-0002-2079-4931","affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, University of Sydney, Camperdown, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]},{"raw_affiliation_string":"School of Electrical and Information Engineering, University of Sydney, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100435848","display_name":"Lei Wang","orcid":"https://orcid.org/0000-0002-0961-0441"},"institutions":[{"id":"https://openalex.org/I204824540","display_name":"University of Wollongong","ror":"https://ror.org/00jtmb277","country_code":"AU","type":"education","lineage":["https://openalex.org/I204824540"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Lei Wang","raw_affiliation_strings":["School of Computing and Information Technology, University of Wollongong, Wollongong, NSW, Australia","School of Computing and Information Technology, University of Wollongong, Australia"],"raw_orcid":"https://orcid.org/0000-0002-0961-0441","affiliations":[{"raw_affiliation_string":"School of Computing and Information Technology, University of Wollongong, Wollongong, NSW, Australia","institution_ids":["https://openalex.org/I204824540"]},{"raw_affiliation_string":"School of Computing and Information Technology, University of Wollongong, Australia","institution_ids":["https://openalex.org/I204824540"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100754504","display_name":"Xiu Li","orcid":"https://orcid.org/0000-0003-0403-1923"},"institutions":[{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiu Li","raw_affiliation_strings":["Tsinghua Shenzhen International Graduate School, Shenzhen, China","Tsinghua Shenzhen International Graduate School, China"],"raw_orcid":"https://orcid.org/0000-0003-0403-1923","affiliations":[{"raw_affiliation_string":"Tsinghua Shenzhen International Graduate School, Shenzhen, China","institution_ids":["https://openalex.org/I4210114105"]},{"raw_affiliation_string":"Tsinghua Shenzhen International Graduate School, China","institution_ids":["https://openalex.org/I4210114105"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100643784","display_name":"Luping Zhou","orcid":"https://orcid.org/0000-0001-8762-2424"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Luping Zhou","raw_affiliation_strings":["School of Electrical and Information Engineering, University of Sydney, Camperdown, NSW, Australia","School of Electrical and Information Engineering, University of Sydney, Australia"],"raw_orcid":"https://orcid.org/0000-0001-8762-2424","affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, University of Sydney, Camperdown, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]},{"raw_affiliation_string":"School of Electrical and Information Engineering, University of Sydney, Australia","institution_ids":["https://openalex.org/I129604602"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":12.4332,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.97706996,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"47","issue":"8","first_page":"6585","last_page":"6598"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13310","display_name":"Subtitles and Audiovisual Media","score":0.9940999746322632,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13310","display_name":"Subtitles and Audiovisual Media","score":0.9940999746322632,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9846000075340271,"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":0.9027000069618225,"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":0.7126466035842896},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.6317071914672852},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6077254414558411},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.580041229724884},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5375397205352783},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5198160409927368},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4991931915283203},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.43300625681877136},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3715997338294983},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33300504088401794},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.23925995826721191},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.07551494240760803}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7126466035842896},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.6317071914672852},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6077254414558411},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.580041229724884},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5375397205352783},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5198160409927368},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4991931915283203},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43300625681877136},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3715997338294983},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33300504088401794},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.23925995826721191},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.07551494240760803},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2025.3562866","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3562866","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:40261788","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40261788","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"display_name":"Zero hunger","id":"https://metadata.un.org/sdg/2"}],"awards":[{"id":"https://openalex.org/G457316252","display_name":null,"funder_award_id":"41876098","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":69,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1840435438","https://openalex.org/W1895577753","https://openalex.org/W1956340063","https://openalex.org/W2027423900","https://openalex.org/W2064675550","https://openalex.org/W2096733369","https://openalex.org/W2101105183","https://openalex.org/W2152772232","https://openalex.org/W2302086703","https://openalex.org/W2317125622","https://openalex.org/W2522300708","https://openalex.org/W2549599535","https://openalex.org/W2575842049","https://openalex.org/W2745461083","https://openalex.org/W2770165365","https://openalex.org/W2890531016","https://openalex.org/W2890888035","https://openalex.org/W2903721568","https://openalex.org/W2946580620","https://openalex.org/W2949167374","https://openalex.org/W2949376505","https://openalex.org/W2962937869","https://openalex.org/W2962964995","https://openalex.org/W2963084599","https://openalex.org/W2963101956","https://openalex.org/W2963389687","https://openalex.org/W2963466845","https://openalex.org/W2963846996","https://openalex.org/W2970641574","https://openalex.org/W2979861699","https://openalex.org/W2980483218","https://openalex.org/W2981165461","https://openalex.org/W2982078236","https://openalex.org/W2990818246","https://openalex.org/W2995225687","https://openalex.org/W2997704374","https://openalex.org/W3003817677","https://openalex.org/W3034655362","https://openalex.org/W3035284526","https://openalex.org/W3035323998","https://openalex.org/W3104609094","https://openalex.org/W3107503524","https://openalex.org/W3110042533","https://openalex.org/W3173688449","https://openalex.org/W3175737519","https://openalex.org/W3181252431","https://openalex.org/W4281729070","https://openalex.org/W4285531589","https://openalex.org/W4360604432","https://openalex.org/W4385245566","https://openalex.org/W4385546024","https://openalex.org/W4386003857","https://openalex.org/W4388713229","https://openalex.org/W4398157498","https://openalex.org/W6631190155","https://openalex.org/W6631516269","https://openalex.org/W6637356508","https://openalex.org/W6678262379","https://openalex.org/W6682631176","https://openalex.org/W6729046916","https://openalex.org/W6747225742","https://openalex.org/W6751711410","https://openalex.org/W6754047061","https://openalex.org/W6755207826","https://openalex.org/W6761205521","https://openalex.org/W6763643401","https://openalex.org/W6798001135","https://openalex.org/W6803086743"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W2963177403","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4283207562","https://openalex.org/W2330246314","https://openalex.org/W2949522393","https://openalex.org/W4289422896"],"abstract_inverted_index":{"Radiographic":[0],"images":[1,190],"are":[2,110],"similar":[3],"to":[4,13,33,97,117,122,156,182],"each":[5,133],"other,":[6],"making":[7],"it":[8],"challenging":[9],"for":[10,41,93],"diagnostic":[11,42],"captioning":[12],"narrate":[14],"fine-grained":[15],"visual":[16,89,206],"differences":[17],"of":[18,58,67,74,170,187],"clinical":[19],"importance.":[20],"In":[21],"this":[22],"paper,":[23],"we":[24],"propose":[25],"a":[26,75],"self-boosting":[27],"framework":[28,211],"integrating":[29],"two":[30,72,129,216],"novel":[31],"strategies":[32],"learn":[34],"tightly":[35],"correlated":[36,88],"image":[37,49,159],"and":[38,50,85,90,153,160,177],"text":[39,51,161],"features":[40,52,92],"captioning.":[43],"The":[44,78,101,147],"first":[45],"strategy":[46,149],"explicitly":[47,81],"aligns":[48,150],"through":[53],"training":[54],"an":[55],"auxiliary":[56],"task":[57,66],"image-text":[59,83,126],"matching":[60],"(ITM)":[61],"jointly":[62],"with":[63],"the":[64,94,119,138,167,171,180,184,188,193,197,204,222],"main":[65],"report":[68,218],"generation":[69,219],"(RG)":[70],"as":[71,112,179],"branches":[73,130],"network":[76],"model.":[77],"ITM":[79,120],"branch":[80,96,121],"learns":[82],"alignment":[84],"provides":[86],"highly":[87],"textual":[91],"RG":[95,106],"generate":[98],"high-quality":[99,102],"reports.":[100],"reports":[103,174,199],"generated":[104],"by":[105,203],"branch,":[107],"in":[108,196],"turn,":[109],"utilized":[111],"additional":[113],"harder":[114],"negative":[115],"samples":[116],"push":[118],"evolve":[123],"towards":[124],"better":[125],"alignment.":[127],"These":[128],"help":[131],"improve":[132],"other":[134],"progressively,":[135],"so":[136,191],"that":[137,192],"whole":[139],"model":[140],"is":[141,175],"self-boosted":[142],"without":[143],"requiring":[144],"external":[145],"resources.":[146],"second":[148],"image-sample":[151],"space":[152,155],"report-sample":[154],"achieve":[157,165],"consistent":[158],"feature":[162,207],"embeddings.":[163,208],"To":[164],"this,":[166],"sample":[168,185],"graph":[169,186],"embedded":[172,189],"ground-truth":[173,198],"built":[176],"used":[178],"target":[181],"train":[183],"fine":[194],"discrepancy":[195],"could":[200],"be":[201],"captured":[202],"learned":[205],"Our":[209],"proposed":[210],"demonstrates":[212],"its":[213],"superiority":[214],"on":[215],"medical":[217],"benchmarks,":[220],"including":[221],"largest":[223],"dataset":[224],"MIMIC-CXR.":[225]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}