{"id":"https://openalex.org/W2910068805","doi":"https://doi.org/10.1109/dicta.2018.8615810","title":"Image Caption Generator with Novel Object Injection","display_name":"Image Caption Generator with Novel Object Injection","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2910068805","doi":"https://doi.org/10.1109/dicta.2018.8615810","mag":"2910068805"},"language":"en","primary_location":{"id":"doi:10.1109/dicta.2018.8615810","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dicta.2018.8615810","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Digital Image Computing: Techniques and Applications (DICTA)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5066847863","display_name":"Mirza Muhammad Ali Baig","orcid":null},"institutions":[{"id":"https://openalex.org/I929597975","display_name":"National University of Sciences and Technology","ror":"https://ror.org/03w2j5y17","country_code":"PK","type":"education","lineage":["https://openalex.org/I929597975"]}],"countries":["PK"],"is_corresponding":true,"raw_author_name":"Mirza Muhammad Ali Baig","raw_affiliation_strings":["School of Electrical Engineering and Computer Science, National University of Sciences and Technology, Islamabad, Pakistan"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Computer Science, National University of Sciences and Technology, Islamabad, Pakistan","institution_ids":["https://openalex.org/I929597975"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079850649","display_name":"Mian Ihtisham Shah","orcid":null},"institutions":[{"id":"https://openalex.org/I929597975","display_name":"National University of Sciences and Technology","ror":"https://ror.org/03w2j5y17","country_code":"PK","type":"education","lineage":["https://openalex.org/I929597975"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Mian Ihtisham Shah","raw_affiliation_strings":["School of Electrical Engineering and Computer Science, National University of Sciences and Technology, Islamabad, Pakistan"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Computer Science, National University of Sciences and Technology, Islamabad, Pakistan","institution_ids":["https://openalex.org/I929597975"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040237988","display_name":"Muhammad Abdullah Wajahat","orcid":"https://orcid.org/0000-0002-2995-8234"},"institutions":[{"id":"https://openalex.org/I929597975","display_name":"National University of Sciences and Technology","ror":"https://ror.org/03w2j5y17","country_code":"PK","type":"education","lineage":["https://openalex.org/I929597975"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Muhammad Abdullah Wajahat","raw_affiliation_strings":["School of Electrical Engineering and Computer Science, National University of Sciences and Technology, Islamabad, Pakistan"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Computer Science, National University of Sciences and Technology, Islamabad, Pakistan","institution_ids":["https://openalex.org/I929597975"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036178166","display_name":"Nauman Zafar","orcid":null},"institutions":[{"id":"https://openalex.org/I929597975","display_name":"National University of Sciences and Technology","ror":"https://ror.org/03w2j5y17","country_code":"PK","type":"education","lineage":["https://openalex.org/I929597975"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Nauman Zafar","raw_affiliation_strings":["School of Electrical Engineering and Computer Science, National University of Sciences and Technology, Islamabad, Pakistan"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Computer Science, National University of Sciences and Technology, Islamabad, Pakistan","institution_ids":["https://openalex.org/I929597975"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071393061","display_name":"Omar Arif","orcid":"https://orcid.org/0000-0001-6648-3787"},"institutions":[{"id":"https://openalex.org/I929597975","display_name":"National University of Sciences and Technology","ror":"https://ror.org/03w2j5y17","country_code":"PK","type":"education","lineage":["https://openalex.org/I929597975"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Omar Arif","raw_affiliation_strings":["School of Electrical Engineering and Computer Science, National University of Sciences and Technology, Islamabad, Pakistan"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Computer Science, National University of Sciences and Technology, Islamabad, Pakistan","institution_ids":["https://openalex.org/I929597975"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5066847863"],"corresponding_institution_ids":["https://openalex.org/I929597975"],"apc_list":null,"apc_paid":null,"fwci":0.3134,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.63935055,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"2","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9973999857902527,"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":0.9961000084877014,"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":0.9734749794006348},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8426803350448608},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.8026962280273438},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.656156063079834},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6547938585281372},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6538054347038269},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6323721408843994},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6057257056236267},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5658854842185974},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5615099668502808},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.44891247153282166},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42530009150505066},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4009944498538971},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32480907440185547}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9734749794006348},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8426803350448608},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.8026962280273438},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.656156063079834},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6547938585281372},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6538054347038269},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6323721408843994},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6057257056236267},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5658854842185974},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5615099668502808},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.44891247153282166},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42530009150505066},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4009944498538971},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32480907440185547},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"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},{"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:10.1109/dicta.2018.8615810","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dicta.2018.8615810","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Digital Image Computing: Techniques and Applications (DICTA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W12634471","https://openalex.org/W93016980","https://openalex.org/W189277179","https://openalex.org/W1514535095","https://openalex.org/W1614298861","https://openalex.org/W1686810756","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1947481528","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2117539524","https://openalex.org/W2119775030","https://openalex.org/W2139380585","https://openalex.org/W2154652894","https://openalex.org/W2173180041","https://openalex.org/W2176412452","https://openalex.org/W2183341477","https://openalex.org/W2185175083","https://openalex.org/W2194775991","https://openalex.org/W2302086703","https://openalex.org/W2530422462","https://openalex.org/W2552161745","https://openalex.org/W2570343428","https://openalex.org/W2575842049","https://openalex.org/W2583892095","https://openalex.org/W2950577311","https://openalex.org/W2953116809","https://openalex.org/W2962830213","https://openalex.org/W2963285578","https://openalex.org/W2963745697","https://openalex.org/W2964018924","https://openalex.org/W2964086552","https://openalex.org/W2964350391","https://openalex.org/W6630875275","https://openalex.org/W6639102338","https://openalex.org/W6677994088","https://openalex.org/W6682631176","https://openalex.org/W6729624334","https://openalex.org/W6766314179","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W3217195652","https://openalex.org/W3164229987","https://openalex.org/W3215212336","https://openalex.org/W4290852288","https://openalex.org/W3217388757","https://openalex.org/W3122720459","https://openalex.org/W4298897568","https://openalex.org/W4289422896","https://openalex.org/W1938708284","https://openalex.org/W4380190185"],"abstract_inverted_index":{"Image":[0,130],"captioning":[1],"is":[2,9,27,34,49,71],"a":[3,15,101,137],"field":[4,26],"within":[5],"artificial":[6],"intelligence":[7],"that":[8,33,82,103,152],"progressing":[10],"rapidly":[11],"and":[12,114,121,141,172,177],"it":[13],"has":[14],"lot":[16],"of":[17,31,88,146],"potentials.":[18],"A":[19],"major":[20],"problem":[21],"when":[22],"working":[23],"in":[24,54,108,156],"this":[25,97],"the":[28,47,50,86,89,144,147,157,160,164,180],"limited":[29,84],"amount":[30,74],"data":[32,90],"available":[35],"to":[36,78,85,95,110,149],"us":[37],"as":[38],"is.":[39],"The":[40,174],"only":[41],"dataset":[42,158],"considered":[43],"suitable":[44],"enough":[45],"for":[46],"task":[48],"Microsoft:":[51],"Common":[52],"Objects":[53],"Context":[55],"(MSCOCO)":[56],"dataset,":[57],"which":[58,70],"contains":[59],"about":[60,66],"120,000":[61],"training":[62],"images.":[63],"This":[64],"covers":[65],"80":[67],"object":[68,124],"classes,":[69],"an":[72],"insufficient":[73],"if":[75],"we":[76,99],"want":[77],"create":[79],"robust":[80],"solutions":[81],"aren't":[83],"constraints":[87],"at":[91],"hand.":[92],"In":[93],"order":[94,109],"overcome":[96],"problem,":[98],"propose":[100],"solution":[102],"incorporates":[104],"Zero-Shot":[105],"Learning":[106],"concepts":[107],"identify":[111],"unknown":[112],"objects":[113,151],"classes":[115],"by":[116],"using":[117,132],"semantic":[118],"word":[119],"embeddings":[120],"existing":[122],"state-of-the-art":[123],"identification":[125],"algorithms.":[126],"Our":[127],"proposed":[128],"model,":[129],"Captioning":[131],"Novel":[133],"Word":[134],"Injection,":[135],"uses":[136],"pre-trained":[138],"caption":[139],"generator":[140,148],"works":[142],"on":[143,166],"output":[145],"inject":[150],"are":[153],"not":[154],"present":[155],"into":[159],"caption.":[161],"We":[162],"evaluate":[163],"model":[165],"standardized":[167],"metrics,":[168],"namely,":[169],"BLEU,":[170],"CIDEr":[171],"ROUGE-L.":[173],"results,":[175],"qualitatively":[176],"quantitatively,":[178],"outperform":[179],"underlying":[181],"model.":[182]},"counts_by_year":[{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
