{"id":"https://openalex.org/W3217070527","doi":"https://doi.org/10.1109/access.2021.3131343","title":"Image Captioning With Positional and Geometrical Semantics","display_name":"Image Captioning With Positional and Geometrical Semantics","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3217070527","doi":"https://doi.org/10.1109/access.2021.3131343","mag":"3217070527"},"language":"en","primary_location":{"id":"doi:10.1109/access.2021.3131343","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3131343","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2021.3131343","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054155672","display_name":"Anwar ul Haque","orcid":"https://orcid.org/0000-0002-0188-2653"},"institutions":[{"id":"https://openalex.org/I4210165529","display_name":"University of Business and Technology","ror":"https://ror.org/05tcr1n44","country_code":"SA","type":"education","lineage":["https://openalex.org/I4210165529"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Anwar Ul Haque","raw_affiliation_strings":["Institute of Business Administration"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Business Administration","institution_ids":["https://openalex.org/I4210165529"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037233730","display_name":"Sayeed Ghani","orcid":"https://orcid.org/0000-0003-2938-2789"},"institutions":[{"id":"https://openalex.org/I4210165529","display_name":"University of Business and Technology","ror":"https://ror.org/05tcr1n44","country_code":"SA","type":"education","lineage":["https://openalex.org/I4210165529"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Sayeed Ghani","raw_affiliation_strings":["Institute of Business Administration"],"raw_orcid":"https://orcid.org/0000-0003-2938-2789","affiliations":[{"raw_affiliation_string":"Institute of Business Administration","institution_ids":["https://openalex.org/I4210165529"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101776229","display_name":"Muhammad Arif Saeed","orcid":"https://orcid.org/0000-0002-6818-7858"},"institutions":[{"id":"https://openalex.org/I193670377","display_name":"University of Karachi","ror":"https://ror.org/05bbbc791","country_code":"PK","type":"education","lineage":["https://openalex.org/I193670377"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Muhammad Saeed","raw_affiliation_strings":["Department of Computer Science, University of Karachi. (e-mail: saeed@uok.edu.pk)"],"raw_orcid":"https://orcid.org/0000-0002-6818-7858","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Karachi. (e-mail: saeed@uok.edu.pk)","institution_ids":["https://openalex.org/I193670377"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":1.1306,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.80618971,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"9","issue":null,"first_page":"160917","last_page":"160925"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9955999851226807,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9829000234603882,"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":0.9459962844848633},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7868428230285645},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6421103477478027},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5377011895179749},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5209195017814636},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5038203597068787},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4977162182331085},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4941911995410919},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.49332013726234436},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4511057138442993},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4436110258102417},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4320261776447296},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4162348508834839},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.07838720083236694}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9459962844848633},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7868428230285645},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6421103477478027},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5377011895179749},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5209195017814636},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5038203597068787},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4977162182331085},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4941911995410919},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.49332013726234436},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4511057138442993},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4436110258102417},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4320261776447296},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4162348508834839},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.07838720083236694},{"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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2021.3131343","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3131343","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:168c9afac3a24b11970defe5832f1692","is_oa":true,"landing_page_url":"https://doaj.org/article/168c9afac3a24b11970defe5832f1692","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 9, Pp 160917-160925 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2021.3131343","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3131343","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.47999998927116394,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W68733909","https://openalex.org/W2302086703","https://openalex.org/W2463955103","https://openalex.org/W2481240925","https://openalex.org/W2607151106","https://openalex.org/W2807697862","https://openalex.org/W2890531016","https://openalex.org/W2895420168","https://openalex.org/W2914163459","https://openalex.org/W2946450307","https://openalex.org/W2963703618","https://openalex.org/W2963743213","https://openalex.org/W2965597639","https://openalex.org/W2965697393","https://openalex.org/W2965820511","https://openalex.org/W2972818416","https://openalex.org/W2978613765","https://openalex.org/W2979739834","https://openalex.org/W2981165461","https://openalex.org/W2983141445","https://openalex.org/W2986670728","https://openalex.org/W2990307191","https://openalex.org/W2994144150","https://openalex.org/W2997056851","https://openalex.org/W2997248215","https://openalex.org/W3007328579","https://openalex.org/W3011932950","https://openalex.org/W3012183480","https://openalex.org/W3025875705","https://openalex.org/W3034984754","https://openalex.org/W3035160838","https://openalex.org/W3047564907","https://openalex.org/W3093735614","https://openalex.org/W3103651098","https://openalex.org/W3106925514","https://openalex.org/W3133717587","https://openalex.org/W3152988074","https://openalex.org/W6743446608"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W3088136942","https://openalex.org/W2949362007","https://openalex.org/W2775506363","https://openalex.org/W4310447809","https://openalex.org/W4200243030","https://openalex.org/W2800782462","https://openalex.org/W4323777661","https://openalex.org/W3209117276","https://openalex.org/W4388184981"],"abstract_inverted_index":{"The":[0,65,159,186,216],"last":[1],"5":[2],"to":[3,29,43,60,113,132,232,253,261,270],"6":[4],"years":[5],"have":[6],"seen":[7],"tremendous":[8],"progress":[9],"in":[10,195,212],"automatic":[11],"image":[12,25,32,108,123,148,168,218,225],"captioning":[13,96,109,149,257],"using":[14],"deep":[15],"learning.":[16],"Initial":[17],"research":[18,38,52,68],"focused":[19],"on":[20,70],"the":[21,31,36,90,115,122,133,157,171,177,229,247,263],"attribute-to-attribute":[22],"comparison":[23],"of":[24,50,67,93,118,167,173,188,197,224],"features":[26,219],"and":[27,45,62,84,102,124,142,200,227,237,242,250,265],"texts":[28],"describe":[30],"as":[33,128,156,268],"a":[34,145,209,221],"sentence,":[35],"current":[37,48,272],"is":[39,180],"handling":[40],"issues":[41],"related":[42],"semantics":[44],"correlations.":[46],"However,":[47],"state":[49],"art":[51],"suffers":[53],"from":[54],"insufficient":[55],"concepts":[56],"when":[57,258],"it":[58,259],"comes":[59,260],"positional":[61,236,264],"geometrical":[63,116,143,165,201,238,266],"attributes.":[64],"majority":[66],"relying":[69],"CNN\u2019s":[71,106],"(Convolutional":[72],"Neural":[73,184],"Networks)":[74],"for":[75,95],"object":[76,119,193,206],"feature":[77],"extractions":[78],"has":[79],"no":[80],"clue":[81],"about":[82],"equivariance":[83],"rotational":[85],"invariance":[86],"which":[87],"leads":[88],"towards":[89],"orientation-less":[91],"understanding":[92,194,207,223],"objects":[94,169,226],"along":[97,151],"with":[98,140,152,170,203,235],"longer":[99],"training":[100],"time,":[101],"larger":[103],"dataset.":[104],"Furthermore,":[105],"based":[107],"encoders":[110],"also":[111],"fail":[112],"understand":[114],"alignment":[117],"attributes":[120],"within":[121],"hence":[125],"mislabels":[126],"distorted":[127],"correct.":[129],"To":[130],"cater":[131],"above":[134],"issues,":[135],"we":[136],"propose":[137],"ICPS":[138,161,245],"(Captioning":[139],"Positional":[141],"Semantics)":[144],"capsule":[146],"network-based":[147],"technique":[150],"transformer":[153],"neural":[154],"networks":[155],"decoder.":[158],"proposed":[160],"architecture":[162],"handles":[163],"various":[164],"properties":[166],"help":[172,228],"parallelized":[174],"capsules":[175,190],"while":[176],"object-to-text":[178],"decoding":[179,230],"done":[181],"by":[182],"Transformer":[183],"Networks.":[185],"inclusion":[187],"cluster":[189],"provides":[191],"better":[192,222,255],"terms":[196],"position,":[198],"equivariance,":[199],"orientation":[202],"more":[204],"augmented":[205],"over":[208,246],"small":[210],"dataset":[211,249],"comparatively":[213],"less":[214],"time.":[215],"extracted":[217],"provide":[220],"stage":[231],"narrate":[233],"effectively":[234],"details.":[239],"We":[240],"trained":[241],"tested":[243],"our":[244],"Flickr8k":[248],"found":[251],"ourselves":[252],"be":[254],"at":[256],"describing":[262],"transitions":[267],"compared":[269],"other":[271],"state-of-the-art":[273],"research.":[274]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}