{"id":"https://openalex.org/W4387171925","doi":"https://doi.org/10.3233/faia230381","title":"Reasoning Guided by a Manual: Context-Aware Image Captioning with Novel Objects","display_name":"Reasoning Guided by a Manual: Context-Aware Image Captioning with Novel Objects","publication_year":2023,"publication_date":"2023-09-28","ids":{"openalex":"https://openalex.org/W4387171925","doi":"https://doi.org/10.3233/faia230381"},"language":"en","primary_location":{"id":"doi:10.3233/faia230381","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia230381","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230381","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230381","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034545673","display_name":"Peiyao Hua","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]},{"id":"https://openalex.org/I918919364","display_name":"Switch","ror":"https://ror.org/02yw51758","country_code":"CH","type":"nonprofit","lineage":["https://openalex.org/I918919364"]}],"countries":["CH","CN"],"is_corresponding":false,"raw_author_name":"Peiyao Hua","raw_affiliation_strings":["State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216","https://openalex.org/I918919364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008194128","display_name":"Haifeng Sun","orcid":"https://orcid.org/0000-0003-3072-7422"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]},{"id":"https://openalex.org/I918919364","display_name":"Switch","ror":"https://ror.org/02yw51758","country_code":"CH","type":"nonprofit","lineage":["https://openalex.org/I918919364"]}],"countries":["CH","CN"],"is_corresponding":true,"raw_author_name":"Haifeng Sun","raw_affiliation_strings":["State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216","https://openalex.org/I918919364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070546688","display_name":"Jiachang Hao","orcid":"https://orcid.org/0000-0001-6842-4721"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]},{"id":"https://openalex.org/I918919364","display_name":"Switch","ror":"https://ror.org/02yw51758","country_code":"CH","type":"nonprofit","lineage":["https://openalex.org/I918919364"]}],"countries":["CH","CN"],"is_corresponding":false,"raw_author_name":"Jiachang Hao","raw_affiliation_strings":["State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216","https://openalex.org/I918919364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014006906","display_name":"Cong Liu","orcid":"https://orcid.org/0009-0009-0184-5965"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cong Liu","raw_affiliation_strings":["China Mobile"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Mobile","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100432460","display_name":"Jingyu Wang","orcid":"https://orcid.org/0000-0002-2182-2228"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]},{"id":"https://openalex.org/I918919364","display_name":"Switch","ror":"https://ror.org/02yw51758","country_code":"CH","type":"nonprofit","lineage":["https://openalex.org/I918919364"]}],"countries":["CH","CN"],"is_corresponding":false,"raw_author_name":"Jingyu Wang","raw_affiliation_strings":["State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216","https://openalex.org/I918919364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100406584","display_name":"Qi Qi","orcid":"https://orcid.org/0000-0003-0829-4624"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]},{"id":"https://openalex.org/I918919364","display_name":"Switch","ror":"https://ror.org/02yw51758","country_code":"CH","type":"nonprofit","lineage":["https://openalex.org/I918919364"]}],"countries":["CH","CN"],"is_corresponding":false,"raw_author_name":"Qi Qi","raw_affiliation_strings":["State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216","https://openalex.org/I918919364"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055685073","display_name":"Jianxin Liao","orcid":"https://orcid.org/0000-0003-1486-0573"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]},{"id":"https://openalex.org/I918919364","display_name":"Switch","ror":"https://ror.org/02yw51758","country_code":"CH","type":"nonprofit","lineage":["https://openalex.org/I918919364"]}],"countries":["CH","CN"],"is_corresponding":false,"raw_author_name":"Jianxin Liao","raw_affiliation_strings":["State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216","https://openalex.org/I918919364"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5008194128"],"corresponding_institution_ids":["https://openalex.org/I139759216","https://openalex.org/I918919364"],"apc_list":null,"apc_paid":null,"fwci":0.3823,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.66190193,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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/T10028","display_name":"Topic Modeling","score":0.9487000107765198,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9301999807357788,"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":0.9756672382354736},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8179803490638733},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6894761323928833},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6752668619155884},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6428910493850708},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5966082811355591},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5120673775672913},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.45622190833091736},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4273976683616638},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.42018574476242065},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3449617624282837},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07261323928833008}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9756672382354736},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8179803490638733},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6894761323928833},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6752668619155884},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6428910493850708},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5966082811355591},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5120673775672913},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.45622190833091736},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4273976683616638},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.42018574476242065},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3449617624282837},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07261323928833008},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/faia230381","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia230381","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230381","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.3233/faia230381","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia230381","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230381","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7599999904632568,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G3591376991","display_name":null,"funder_award_id":"62171057","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3829840669","display_name":null,"funder_award_id":"MCM20200202","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4255581185","display_name":"\u9762\u5411\u7f51\u8054\u81ea\u52a8\u9a7e\u9a76\u7684\u6682\u6001\u8fb9\u7f18\u8d44\u6e90\u534f\u4f5c\u673a\u7406\u7814\u7a76","funder_award_id":"62071067","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4300471285","display_name":null,"funder_award_id":"62001054","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8615917232","display_name":null,"funder_award_id":"62201072","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"},{"id":"https://openalex.org/F4320321470","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59"},{"id":"https://openalex.org/F4320329515","display_name":"China Mobile Research Institute","ror":null}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4387171925.pdf"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1861492603","https://openalex.org/W1956340063","https://openalex.org/W2139380585","https://openalex.org/W2141364309","https://openalex.org/W2173180041","https://openalex.org/W2277195237","https://openalex.org/W2506483933","https://openalex.org/W2560207749","https://openalex.org/W2743573407","https://openalex.org/W2745461083","https://openalex.org/W2775315796","https://openalex.org/W2787560479","https://openalex.org/W2797733588","https://openalex.org/W2808503835","https://openalex.org/W2904565150","https://openalex.org/W2941236977","https://openalex.org/W2962739339","https://openalex.org/W2963088515","https://openalex.org/W2963175879","https://openalex.org/W2963877622","https://openalex.org/W2964080601","https://openalex.org/W2966162142","https://openalex.org/W2979747405","https://openalex.org/W2998116350","https://openalex.org/W3009628218","https://openalex.org/W3016923549","https://openalex.org/W3021190596","https://openalex.org/W3035058125","https://openalex.org/W3091588028","https://openalex.org/W3104279398","https://openalex.org/W3125115471","https://openalex.org/W3134249459","https://openalex.org/W3134873017","https://openalex.org/W3153841200","https://openalex.org/W3169793270","https://openalex.org/W3173220247","https://openalex.org/W3174476431","https://openalex.org/W3188318562","https://openalex.org/W4221156084","https://openalex.org/W4225702709","https://openalex.org/W4241200240","https://openalex.org/W4297823579","https://openalex.org/W4310627598","https://openalex.org/W4312522167","https://openalex.org/W4389665269"],"related_works":["https://openalex.org/W2975200075","https://openalex.org/W2007544051","https://openalex.org/W1837097281","https://openalex.org/W1966410754","https://openalex.org/W2363840281","https://openalex.org/W2325242284","https://openalex.org/W2789220062","https://openalex.org/W2030539674","https://openalex.org/W2095705906","https://openalex.org/W2732308154"],"abstract_inverted_index":{"Novel":[0,82,102],"object":[1,49,96],"captioning":[2,50],"task":[3],"aims":[4],"at":[5],"describing":[6],"objects":[7,110,114,127],"that":[8,65,87],"are":[9],"absent":[10],"from":[11,63],"training":[12],"data.":[13],"Due":[14],"to":[15,23,27,31,93,106,124,132],"the":[16,116,142,156,163,175],"scarcity":[17],"of":[18,115,177],"novel":[19,48,76,95,109,126],"objects,":[20],"it\u2019s":[21],"challenging":[22,143],"find":[24],"a":[25,42,61,100,120],"way":[26],"utilize":[28],"external":[29,73],"data":[30],"improve":[32],"model\u2019s":[33,171],"reasoning":[34,53,172],"ability.":[35],"While":[36],"previously":[37],"designed":[38],"methods":[39],"all":[40],"follow":[41],"deep":[43,56],"learning":[44,57],"approach,":[45],"we":[46,154],"boost":[47],"by":[51,159],"incorporating":[52],"with":[54,69,138],"traditional":[55],"framework.":[58],"We":[59,78,135],"design":[60],"manual":[62],"dictionaries":[64],"provides":[66],"our":[67,170],"model":[68,85],"sufficient":[70],"and":[71,90,119,146,174],"accurate":[72],"information":[74],"on":[75,112,141,162],"objects.":[77],"propose":[79],"Manual-guided":[80],"Context-aware":[81],"Object":[83,103],"Captioning":[84],"(MC-NOC)":[86],"utilizes":[88],"image":[89,118],"caption":[91,133],"context":[92],"generate":[94],"captions.":[97,179],"It":[98],"contains":[99],"Manual-Guided":[101],"Reasoning":[104],"module":[105,123],"reason":[107],"about":[108],"based":[111],"other":[113],"given":[117],"Caption":[121],"Reconstruction":[122],"incorporate":[125],"into":[128],"generated":[129,178],"captions":[130],"according":[131],"context.":[134],"validate":[136],"MC-NOC":[137],"state-of-the-art":[139],"performance":[140],"Held-out":[144],"COCO":[145],"Nocaps":[147],"dataset,":[148],"leading":[149],"their":[150],"leaderboard.":[151],"In":[152],"particular,":[153],"improved":[155],"CIDER":[157],"metric":[158],"6.4":[160],"points":[161],"held-out":[164],"coco":[165],"dataset.":[166],"Comprehensive":[167],"experiments":[168],"demonstrate":[169],"capability":[173],"quality":[176]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-06T09:05:17.133730","created_date":"2025-10-10T00:00:00"}
