{"id":"https://openalex.org/W4210268062","doi":"https://doi.org/10.1109/tpami.2022.3144984","title":"Switchable Novel Object Captioner","display_name":"Switchable Novel Object Captioner","publication_year":2022,"publication_date":"2022-01-25","ids":{"openalex":"https://openalex.org/W4210268062","doi":"https://doi.org/10.1109/tpami.2022.3144984","pmid":"https://pubmed.ncbi.nlm.nih.gov/35077354"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2022.3144984","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tpami.2022.3144984","pdf_url":"https://ieeexplore.ieee.org/ielx7/34/9970415/09693277.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/34/9970415/09693277.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yu Wu","orcid":"https://orcid.org/0000-0002-1680-8253"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yu Wu","raw_affiliation_strings":["Baidu Research, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1680-8253","affiliations":[{"raw_affiliation_string":"Baidu Research, Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Lu Jiang","orcid":"https://orcid.org/0000-0003-0286-8439"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lu Jiang","raw_affiliation_strings":["Google Research, Mountain View, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-0286-8439","affiliations":[{"raw_affiliation_string":"Google Research, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":null,"display_name":"Yi Yang","orcid":"https://orcid.org/0000-0002-0512-880X"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Yang","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0002-0512-880X","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I168879160"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98301712"],"apc_list":null,"apc_paid":null,"fwci":2.6531,"has_fulltext":true,"cited_by_count":26,"citation_normalized_percentile":{"value":0.91143264,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"45","issue":"1","first_page":"1162","last_page":"1173"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9952999949455261,"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":0.9952999949455261,"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":0.00039999998989515007,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.00039999998989515007,"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":0.9718999862670898},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6481999754905701},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6413999795913696},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5767999887466431},{"id":"https://openalex.org/keywords/noun","display_name":"Noun","score":0.4934000074863434},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.42289999127388},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.37380000948905945},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3587000072002411}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9718999862670898},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8536999821662903},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6934000253677368},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6481999754905701},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6413999795913696},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6104000210762024},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5767999887466431},{"id":"https://openalex.org/C121934690","wikidata":"https://www.wikidata.org/wiki/Q1084","display_name":"Noun","level":2,"score":0.4934000074863434},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.42289999127388},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4081000089645386},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.37380000948905945},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3587000072002411},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.358599990606308},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.35019999742507935},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.3237999975681305},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.31679999828338623},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3151000142097473},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3091000020503998},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.3018999993801117},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2962000072002411},{"id":"https://openalex.org/C3019973339","wikidata":"https://www.wikidata.org/wiki/Q899523","display_name":"Object based","level":3,"score":0.2856000065803528},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.28519999980926514},{"id":"https://openalex.org/C20894473","wikidata":"https://www.wikidata.org/wiki/Q1116105","display_name":"Object model","level":3,"score":0.2815000116825104},{"id":"https://openalex.org/C2780103172","wikidata":"https://www.wikidata.org/wiki/Q1309721","display_name":"Visual Objects","level":3,"score":0.2578999996185303}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2022.3144984","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tpami.2022.3144984","pdf_url":"https://ieeexplore.ieee.org/ielx7/34/9970415/09693277.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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:35077354","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35077354","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":{"id":"doi:10.1109/tpami.2022.3144984","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tpami.2022.3144984","pdf_url":"https://ieeexplore.ieee.org/ielx7/34/9970415/09693277.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4210268062.pdf","grobid_xml":"https://content.openalex.org/works/W4210268062.grobid-xml"},"referenced_works_count":51,"referenced_works":["https://openalex.org/W1895577753","https://openalex.org/W1897761818","https://openalex.org/W1905882502","https://openalex.org/W1947481528","https://openalex.org/W1969616664","https://openalex.org/W1999970330","https://openalex.org/W2028502081","https://openalex.org/W2064675550","https://openalex.org/W2077071968","https://openalex.org/W2128532956","https://openalex.org/W2139501017","https://openalex.org/W2173180041","https://openalex.org/W2302086703","https://openalex.org/W2463955103","https://openalex.org/W2557728737","https://openalex.org/W2560920409","https://openalex.org/W2735159761","https://openalex.org/W2745461083","https://openalex.org/W2753232960","https://openalex.org/W2795151422","https://openalex.org/W2797733588","https://openalex.org/W2904565150","https://openalex.org/W2927812634","https://openalex.org/W2963084599","https://openalex.org/W2963088515","https://openalex.org/W2963175879","https://openalex.org/W2963327853","https://openalex.org/W2963398599","https://openalex.org/W2963499153","https://openalex.org/W2963877622","https://openalex.org/W2964138343","https://openalex.org/W2964350391","https://openalex.org/W2966162142","https://openalex.org/W2990113535","https://openalex.org/W2998116350","https://openalex.org/W3091588028","https://openalex.org/W3174873881","https://openalex.org/W3175335326","https://openalex.org/W4205474609","https://openalex.org/W6600334730","https://openalex.org/W6620707391","https://openalex.org/W6621543089","https://openalex.org/W6630875275","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6638742206","https://openalex.org/W6676497082","https://openalex.org/W6678262379","https://openalex.org/W6685230081","https://openalex.org/W6685322675","https://openalex.org/W6713134421"],"related_works":[],"abstract_inverted_index":{"Image":[0],"captioning":[1,21,45],"aims":[2],"at":[3],"automatically":[4],"describing":[5,186],"images":[6],"by":[7,92],"sentences.":[8,58],"It":[9],"often":[10],"requires":[11,181],"lots":[12],"of":[13,78,113,197],"paired":[14],"image-sentence":[15],"data":[16],"for":[17,101],"training.":[18],"However,":[19],"trained":[20],"models":[22],"can":[23],"hardly":[24],"be":[25],"applied":[26],"to":[27,122,172,200],"new":[28],"domains":[29],"in":[30,103,185],"which":[31],"some":[32],"novel":[33,43,53,108,187,202],"words":[34,100,112,121],"exist.":[35],"In":[36],"this":[37,84],"paper,":[38],"we":[39,64,86,110],"introduce":[40],"the":[41,48,61,66,76,104,124,137,153,164,195],"zero-shot":[42],"object":[44,90,138],"task,":[46,63],"where":[47],"machine":[49],"generates":[50],"descriptions":[51],"about":[52,71],"objects":[54,102,117],"without":[55],"extra":[56],"training":[57,178,183],"To":[59],"tackle":[60],"challenging":[62],"mimic":[65],"way":[67],"that":[68,133],"babies":[69],"talk":[70],"something":[72],"unknown,":[73],"i.e.,":[74,150],"using":[75],"word":[77],"a":[79,88,130],"similar":[80,115],"known":[81],"object.":[82],"Following":[83],"motivation,":[85],"build":[87],"key-value":[89,165],"memory":[91,139],"detection":[93],"models,":[94],"containing":[95],"visual":[96,120],"information":[97],"and":[98,158,180],"corresponding":[99],"image.":[105],"For":[106],"those":[107],"objects,":[109,179],"use":[111],"most":[114],"seen":[116],"as":[118],"proxy":[119],"solve":[123],"out-of-vocabulary":[125],"issue.":[126],"We":[127],"then":[128],"propose":[129],"Switchable":[131],"LSTM":[132],"incorporates":[134],"knowledge":[135],"from":[136,163,177],"into":[140],"sentence":[141,184],"generation.":[142],"The":[143],"model":[144,169],"has":[145],"two":[146],"switchable":[147],"working":[148],"modes,":[149],"1)":[151],"generating":[152],"sentences":[154],"like":[155],"standard":[156],"LSTMs":[157],"2)":[159],"retrieving":[160],"proper":[161],"nouns":[162],"memory.":[166],"Thus":[167],"our":[168,198],"is":[170],"learned":[171],"fully":[173],"disentangle":[174],"language":[175],"generation":[176],"zero":[182],"objects.":[188],"Experiments":[189],"on":[190],"three":[191],"large-scale":[192],"datasets":[193],"demonstrate":[194],"ability":[196],"method":[199],"describe":[201],"concepts.":[203]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2022-02-08T00:00:00"}