{"id":"https://openalex.org/W3086339795","doi":null,"title":"Weakly Supervised Content Selection for Improved Image Captioning","display_name":"Weakly Supervised Content Selection for Improved Image Captioning","publication_year":2020,"publication_date":"2020-09-10","ids":{"openalex":"https://openalex.org/W3086339795","mag":"3086339795"},"language":"en","primary_location":{"id":"mag:3086339795","doi":null,"is_oa":false,"landing_page_url":"http://export.arxiv.org/pdf/2009.05175","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5007169600","display_name":"Khyathi Raghavi Chandu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Khyathi Raghavi Chandu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100679058","display_name":"Piyush Kumar Sharma","orcid":"https://orcid.org/0009-0003-0372-4303","observed_orcids":["https://orcid.org/0009-0003-0372-4303"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Piyush Sharma","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0003-0372-4303","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075518871","display_name":"Soravit Changpinyo","orcid":"https://orcid.org/0000-0002-4013-1190","observed_orcids":["https://orcid.org/0000-0002-4013-1190"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Soravit Changpinyo","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-4013-1190","affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Ashish Thapliyal","orcid":"https://orcid.org/0000-0002-1116-8349","observed_orcids":["https://orcid.org/0000-0002-1116-8349"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ashish Thapliyal","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-1116-8349","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5089152779","display_name":"Radu Soricut","orcid":"https://orcid.org/0000-0003-1565-3365","observed_orcids":["https://orcid.org/0000-0003-1565-3365"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Radu Soricut","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-1565-3365","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.168,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.41682256,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"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":0.9994999766349792,"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":0.9994999766349792,"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":9.999999747378752e-05,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":9.999999747378752e-05,"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/image-captioning","display_name":"image captioning","score":0.9890000224113464},{"id":"https://openalex.org/keywords/weakly-supervised-learning","display_name":"weakly supervised learning","score":0.8460000157356262}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9365126490592957},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8351907730102539},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6593577861785889},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6225765347480774},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.6157230138778687},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5403232574462891},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.48521044850349426},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.45431044697761536},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.44247958064079285},{"id":"https://openalex.org/C519982507","wikidata":"https://www.wikidata.org/wiki/Q1568","display_name":"Hindi","level":2,"score":0.42888033390045166},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4238080084323883},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.41960567235946655},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3659522235393524},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3086339795","doi":null,"is_oa":false,"landing_page_url":"http://export.arxiv.org/pdf/2009.05175","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1516517152","https://openalex.org/W1821462560","https://openalex.org/W1931639407","https://openalex.org/W1969616664","https://openalex.org/W2117539524","https://openalex.org/W2143449221","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2296385829","https://openalex.org/W2626778328","https://openalex.org/W2745461083","https://openalex.org/W2886641317","https://openalex.org/W2890531016","https://openalex.org/W2890550430","https://openalex.org/W2892087592","https://openalex.org/W2901988662","https://openalex.org/W2916754336","https://openalex.org/W2962793481","https://openalex.org/W2963048642","https://openalex.org/W2968660381","https://openalex.org/W2970608575","https://openalex.org/W2971310675","https://openalex.org/W2986670728","https://openalex.org/W2989377923","https://openalex.org/W2990818246","https://openalex.org/W2992478697","https://openalex.org/W2995753487","https://openalex.org/W2998317510","https://openalex.org/W3010124057","https://openalex.org/W3023544735","https://openalex.org/W3023584964","https://openalex.org/W3034984754","https://openalex.org/W3035532688"],"related_works":["https://openalex.org/W3153988949","https://openalex.org/W2969295463","https://openalex.org/W2890550430","https://openalex.org/W2978202471","https://openalex.org/W7161044174","https://openalex.org/W3046196303","https://openalex.org/W3116367518","https://openalex.org/W4407137110","https://openalex.org/W7099712403","https://openalex.org/W2760496796"],"abstract_inverted_index":{"Image":[0],"captioning":[1,57,163],"involves":[2],"identifying":[3],"semantic":[4,23],"concepts":[5,24],"in":[6,12,114],"the":[7,22,27,31,56,76,92,98,110,115,142,146,165,173,182,194],"scene":[8],"and":[9,25,41,63,70,90,118,157,202],"describing":[10],"them":[11],"fluent":[13],"natural":[14],"language.":[15],"Recent":[16],"approaches":[17],"do":[18],"not":[19],"explicitly":[20],"model":[21,28,122],"train":[26],"only":[29],"for":[30,94],"end":[32],"goal":[33],"of":[34,108,130,145,162,167,184,193],"caption":[35,72,111],"generation.":[36,73],"Such":[37],"models":[38],"lack":[39],"interpretability":[40],"controllability,":[42],"primarily":[43],"due":[44],"to":[45,149,189],"sub-optimal":[46],"content":[47],"selection.":[48],"We":[49,74,104],"address":[50],"this":[51],"problem":[52],"by":[53,136],"breaking":[54],"down":[55],"task":[58],"into":[59],"two":[60],"simpler,":[61],"manageable":[62],"more":[64],"controllable":[65],"tasks":[66],"--":[67],"skeleton":[68,113,148],"prediction":[69],"skeleton-based":[71],"approach":[75],"former":[77],"as":[78,134,186,199],"a":[79,84,101,187],"weakly":[80],"supervised":[81],"task,":[82],"using":[83],"simple":[85],"off-the-shelf":[86],"language":[87],"syntax":[88],"parser":[89],"avoiding":[91],"need":[93],"additional":[95],"human":[96,137],"annotations;":[97],"latter":[99],"uses":[100],"supervised-learning":[102],"approach.":[103],"investigate":[105,181],"three":[106],"methods":[107],"conditioning":[109],"on":[112,128,175],"encoder,":[116],"decoder":[117],"both.":[119],"Our":[120],"compositional":[121,160],"generates":[123],"significantly":[124],"better":[125],"quality":[126],"captions":[127],"out":[129],"domain":[131],"test":[132],"images,":[133],"judged":[135],"annotators.":[138],"Additionally,":[139],"we":[140,180],"demonstrate":[141],"cross-language":[143],"effectiveness":[144],"English":[147],"other":[150],"languages":[151],"including":[152],"French,":[153],"Italian,":[154],"German,":[155],"Spanish":[156],"Hindi.":[158],"This":[159],"nature":[161],"exhibits":[164],"potential":[166],"unpaired":[168],"image":[169,196],"captioning,":[170],"thereby":[171],"reducing":[172],"dependence":[174],"expensive":[176],"image-caption":[177],"pairs.":[178],"Furthermore,":[179],"use":[183],"skeletons":[185],"knob":[188],"control":[190],"certain":[191],"properties":[192],"generated":[195],"caption,":[197],"such":[198],"length,":[200],"content,":[201],"gender":[203],"expression.":[204]},"counts_by_year":[{"year":2021,"cited_by_count":2}],"updated_date":"2026-09-29T14:09:16.559479","created_date":"2020-09-21T00:00:00"}