{"id":"https://openalex.org/W4200283487","doi":"https://doi.org/10.1109/tvcg.2021.3138933","title":"Towards Better Caption Supervision for Object Detection","display_name":"Towards Better Caption Supervision for Object Detection","publication_year":2021,"publication_date":"2021-12-28","ids":{"openalex":"https://openalex.org/W4200283487","doi":"https://doi.org/10.1109/tvcg.2021.3138933","pmid":"https://pubmed.ncbi.nlm.nih.gov/34962870"},"language":"en","primary_location":{"id":"doi:10.1109/tvcg.2021.3138933","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvcg.2021.3138933","pdf_url":null,"source":{"id":"https://openalex.org/S84775595","display_name":"IEEE Transactions on Visualization and Computer Graphics","issn_l":"1077-2626","issn":["1077-2626","1941-0506","2160-9306"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Visualization and Computer Graphics","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":null,"display_name":"Changjian Chen","orcid":"https://orcid.org/0000-0003-2715-8839"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changjian Chen","raw_affiliation_strings":["School of Software, BNRist, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2715-8839","affiliations":[{"raw_affiliation_string":"School of Software, BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jing Wu","orcid":"https://orcid.org/0000-0001-5123-9861"},"institutions":[{"id":"https://openalex.org/I79510175","display_name":"Cardiff University","ror":"https://ror.org/03kk7td41","country_code":"GB","type":"education","lineage":["https://openalex.org/I79510175"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jing Wu","raw_affiliation_strings":["Cardiff University, Cardiff, U.K"],"raw_orcid":"https://orcid.org/0000-0001-5123-9861","affiliations":[{"raw_affiliation_string":"Cardiff University, Cardiff, U.K","institution_ids":["https://openalex.org/I79510175"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiaohan Wang","orcid":"https://orcid.org/0000-0001-6206-7911"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaohan Wang","raw_affiliation_strings":["Zhejiang University, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0001-6206-7911","affiliations":[{"raw_affiliation_string":"Zhejiang University, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shouxing Xiang","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shouxing Xiang","raw_affiliation_strings":["School of Software, BNRist, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software, BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Song-Hai Zhang","orcid":"https://orcid.org/0000-0003-0460-1586"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Song-Hai Zhang","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-0460-1586","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Qifeng Tang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qifeng Tang","raw_affiliation_strings":["Shanghai Lianshu IoT Company Ltd., Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Lianshu IoT Company Ltd., Shanghai, China","institution_ids":[]}]},{"author_position":"last","author":{"id":null,"display_name":"Shixia Liu","orcid":"https://orcid.org/0000-0003-4499-6420"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shixia Liu","raw_affiliation_strings":["School of Software, BNRist, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-4499-6420","affiliations":[{"raw_affiliation_string":"School of Software, BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5414,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.83508108,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"28","issue":"4","first_page":"1941","last_page":"1954"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9365000128746033,"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":0.9365000128746033,"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":0.02969999983906746,"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":0.013799999840557575,"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/object-detection","display_name":"Object detection","score":0.7800999879837036},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.7132999897003174},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6861000061035156},{"id":"https://openalex.org/keywords/minimum-bounding-box","display_name":"Minimum bounding box","score":0.6798999905586243},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5828999876976013},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.5382000207901001},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.5307000279426575},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4172999858856201}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8650000095367432},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.7800999879837036},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.713699996471405},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.7132999897003174},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6894000172615051},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6861000061035156},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.6798999905586243},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5828999876976013},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.5382000207901001},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.5307000279426575},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4172999858856201},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3772999942302704},{"id":"https://openalex.org/C71681937","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object-class detection","level":5,"score":0.3456000089645386},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.33230000734329224},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3287000060081482},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.30239999294281006},{"id":"https://openalex.org/C172367668","wikidata":"https://www.wikidata.org/wiki/Q6504956","display_name":"Data visualization","level":3,"score":0.27639999985694885},{"id":"https://openalex.org/C3019635856","wikidata":"https://www.wikidata.org/wiki/Q1619726","display_name":"Background image","level":3,"score":0.25760000944137573},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2547999918460846},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.2538999915122986},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.25290000438690186}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/tvcg.2021.3138933","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvcg.2021.3138933","pdf_url":null,"source":{"id":"https://openalex.org/S84775595","display_name":"IEEE Transactions on Visualization and Computer Graphics","issn_l":"1077-2626","issn":["1077-2626","1941-0506","2160-9306"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Visualization and Computer Graphics","raw_type":"journal-article"},{"id":"pmid:34962870","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34962870","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 visualization and computer graphics","raw_type":null},{"id":"pmh:oai:http://orca.cardiff.ac.uk:146505","is_oa":false,"landing_page_url":"https://orca.cardiff.ac.uk/id/eprint/146505/1/MutualDetector-postprint-combined.pdf","pdf_url":"https://orca.cardiff.ac.uk/id/eprint/146505/1/MutualDetector-postprint-combined.pdf","source":{"id":"https://openalex.org/S4306401195","display_name":"ORCA Online Research @Cardiff (Cardiff University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79510175","host_organization_name":"Cardiff University","host_organization_lineage":["https://openalex.org/I79510175"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Article"},{"id":"pmh:oai:http://orca-dev.cardiff.ac.uk:146505","is_oa":false,"landing_page_url":"https://orca.cardiff.ac.uk/id/eprint/146505/","pdf_url":null,"source":{"id":"https://openalex.org/S4306401195","display_name":"ORCA Online Research @Cardiff (Cardiff University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79510175","host_organization_name":"Cardiff University","host_organization_lineage":["https://openalex.org/I79510175"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1544458871","display_name":null,"funder_award_id":"62132012","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2542400961","display_name":null,"funder_award_id":"U21A20469","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2855469915","display_name":null,"funder_award_id":"61936002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4486898","display_name":null,"funder_award_id":"2020YFB2104100","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W37400329","https://openalex.org/W2007241592","https://openalex.org/W2037227137","https://openalex.org/W2080133951","https://openalex.org/W2117539524","https://openalex.org/W2138180870","https://openalex.org/W2141569821","https://openalex.org/W2150512498","https://openalex.org/W2161581092","https://openalex.org/W2180041965","https://openalex.org/W2250539671","https://openalex.org/W2333322610","https://openalex.org/W2343061342","https://openalex.org/W2510932841","https://openalex.org/W2524925309","https://openalex.org/W2597908760","https://openalex.org/W2753137392","https://openalex.org/W2904982178","https://openalex.org/W2962996306","https://openalex.org/W2963296620","https://openalex.org/W2963603913","https://openalex.org/W2969224142","https://openalex.org/W2969653330","https://openalex.org/W2969980980","https://openalex.org/W2972458663","https://openalex.org/W2981613027","https://openalex.org/W2988916019","https://openalex.org/W2992843368","https://openalex.org/W3000384001","https://openalex.org/W3005587429","https://openalex.org/W3005984470","https://openalex.org/W3043666678","https://openalex.org/W3091002423","https://openalex.org/W3092806605","https://openalex.org/W3094617751","https://openalex.org/W3097722521","https://openalex.org/W3118244215","https://openalex.org/W3164124914","https://openalex.org/W3184021524","https://openalex.org/W3202786858","https://openalex.org/W3204925778","https://openalex.org/W4205930639","https://openalex.org/W4251646134","https://openalex.org/W6620707391","https://openalex.org/W6639102338","https://openalex.org/W6679390333","https://openalex.org/W6749916090","https://openalex.org/W6755207826","https://openalex.org/W6762319049","https://openalex.org/W6766773940","https://openalex.org/W6767507553","https://openalex.org/W6777046832","https://openalex.org/W6781989493","https://openalex.org/W6785652829","https://openalex.org/W6785700261","https://openalex.org/W6802323406"],"related_works":[],"abstract_inverted_index":{"As":[0],"training":[1],"high-performance":[2],"object":[3,52,61,95,164],"detectors":[4,18],"requires":[5],"expensive":[6],"bounding":[7],"box":[8],"annotations,":[9],"recent":[10],"methods":[11],"resort":[12],"to":[13,54,71,111,149],"free-available":[14],"image":[15],"captions.":[16],"However,":[17],"trained":[19],"on":[20],"caption":[21,49,84],"supervision":[22,50,85],"perform":[23],"poorly":[24],"because":[25],"captions":[26],"are":[27,63,69,81,147],"usually":[28],"noisy":[29],"and":[30,119,130,138,143,153],"cannot":[31],"provide":[32],"precise":[33],"location":[34],"information.":[35],"To":[36,89],"tackle":[37],"this":[38],"issue,":[39],"we":[40],"present":[41],"a":[42,98,104,144],"visual":[43],"analysis":[44],"method,":[45],"which":[46,68],"tightly":[47],"integrates":[48],"with":[51,122],"detection":[53,96],"mutually":[55],"enhance":[56],"each":[57],"other.":[58],"In":[59],"particular,":[60],"labels":[62,118,129],"first":[64],"extracted":[65,117],"from":[66,79],"captions,":[67],"utilized":[70],"train":[72],"the":[73,76,94,113,116,120,151,156,161],"detectors.":[74,165],"Then,":[75],"objects":[77],"detected":[78,123],"images":[80,121,131],"fed":[82],"into":[83,93],"for":[86],"further":[87],"improvement.":[88],"effectively":[90],"loop":[91],"users":[92],"process,":[97],"node-link-based":[99],"set":[100],"visualization":[101],"supported":[102],"by":[103,133],"multi-type":[105],"relational":[106],"co-clustering":[107,126],"algorithm":[108,127],"is":[109],"developed":[110,157],"explain":[112],"relationships":[114],"between":[115],"objects.":[124],"The":[125],"clusters":[128],"simultaneously":[132],"utilizing":[134],"both":[135],"their":[136,139],"representations":[137],"relationships.":[140],"Quantitative":[141],"evaluations":[142],"case":[145],"study":[146],"conducted":[148],"demonstrate":[150],"efficiency":[152],"effectiveness":[154],"of":[155,163],"method":[158],"in":[159],"improving":[160],"performance":[162]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":8}],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2021-12-31T00:00:00"}