{"id":"https://openalex.org/W3117184563","doi":"https://doi.org/10.1109/ivcnz51579.2020.9290719","title":"Leveraging Linguistically-aware Object Relations and NASNet for Image Captioning","display_name":"Leveraging Linguistically-aware Object Relations and NASNet for Image Captioning","publication_year":2020,"publication_date":"2020-11-25","ids":{"openalex":"https://openalex.org/W3117184563","doi":"https://doi.org/10.1109/ivcnz51579.2020.9290719","mag":"3117184563"},"language":"en","primary_location":{"id":"doi:10.1109/ivcnz51579.2020.9290719","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ivcnz51579.2020.9290719","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 35th International Conference on Image and Vision Computing New Zealand (IVCNZ)","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/A5044043482","display_name":"Naeha Sharif","orcid":"https://orcid.org/0000-0001-8351-6288"},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"The University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Naeha Sharif","raw_affiliation_strings":["The University of Western Australia, Perth, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Western Australia, Perth, Australia","institution_ids":["https://openalex.org/I177877127"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023326215","display_name":"Mohammad A. A. K. Jalwana","orcid":"https://orcid.org/0000-0002-5184-1884"},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"The University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Mohammad A. A. K. Jalwana","raw_affiliation_strings":["The University of Western Australia, Perth, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Western Australia, Perth, Australia","institution_ids":["https://openalex.org/I177877127"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009750573","display_name":"Mohammed Bennamoun","orcid":"https://orcid.org/0000-0002-6603-3257"},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"The University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Mohammed Bennamoun","raw_affiliation_strings":["The University of Western Australia, Perth, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Western Australia, Perth, Australia","institution_ids":["https://openalex.org/I177877127"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100641142","display_name":"Wei Liu","orcid":"https://orcid.org/0000-0002-7409-0948"},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"The University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Wei Liu","raw_affiliation_strings":["The University of Western Australia, Perth, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Western Australia, Perth, Australia","institution_ids":["https://openalex.org/I177877127"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049303874","display_name":"Syed Afaq Ali Shah","orcid":"https://orcid.org/0000-0003-2181-8445"},"institutions":[{"id":"https://openalex.org/I176790772","display_name":"Murdoch University","ror":"https://ror.org/00r4sry34","country_code":"AU","type":"education","lineage":["https://openalex.org/I176790772"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Syed Afaq Ali Shah","raw_affiliation_strings":["Murdoch University, Perth, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Murdoch University, Perth, Australia","institution_ids":["https://openalex.org/I176790772"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1915,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.51359615,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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":0.9927999973297119,"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":0.9861999750137329,"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":0.9898147583007812},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.810283899307251},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6762441396713257},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.654528021812439},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5603388547897339},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5524510741233826},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5412473678588867},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5369007587432861},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5297086238861084},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4915529191493988},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.38937920331954956},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.35342735052108765},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11283442378044128}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9898147583007812},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.810283899307251},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6762441396713257},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.654528021812439},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5603388547897339},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5524510741233826},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5412473678588867},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5369007587432861},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5297086238861084},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4915529191493988},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.38937920331954956},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.35342735052108765},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11283442378044128},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/ivcnz51579.2020.9290719","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ivcnz51579.2020.9290719","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 35th International Conference on Image and Vision Computing New Zealand (IVCNZ)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:publications/bf888cd1-e8c8-49c0-a321-a9c5c6190973","is_oa":false,"landing_page_url":"https://research-repository.uwa.edu.au/en/publications/bf888cd1-e8c8-49c0-a321-a9c5c6190973","pdf_url":null,"source":{"id":"https://openalex.org/S4306402523","display_name":"UWA Profiles and Research Repository (University of Western Australia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I177877127","host_organization_name":"The University of Western Australia","host_organization_lineage":["https://openalex.org/I177877127"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sharif , N , Jalwana , M A A K , Bennamoun , M , Liu , W &amp; Shah , S A A 2020 , Leveraging Linguistically-aware Object Relations and NASNet for Image Captioning . in 2020 35th International Conference on Image and Vision Computing New Zealand (IVCNZ) . , 9290719 , International Conference Image and Vision Computing New Zealand , vol. 2020-November , IEEE, Institute of Electrical and Electronics Engineers , pp. 1-6 , 35th International Conference on Image and Vision Computing New Zealand, IVCNZ , Wellington , New Zealand , 25/11/20 . https://doi.org/10.1109/IVCNZ51579.2020.9290719","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:researchrepository.murdoch.edu.au:59413","is_oa":false,"landing_page_url":"https://researchrepository.murdoch.edu.au/id/eprint/59413/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400274","display_name":"Murdoch Research Repository (Murdoch University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I176790772","host_organization_name":"Murdoch University","host_organization_lineage":["https://openalex.org/I176790772"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"  Sharif, N., Jalwana, M.A.A.K., Bennamoun, M., Liu, W. and Shah, S.A.A. &lt;https://researchrepository.murdoch.edu.au/view/author/Shah, Syed Afaq Ali.html&gt;   (2020)  Leveraging Linguistically-aware Object Relations and NASNet for Image Captioning.     In: 35th International Conference on Image and Vision Computing New Zealand (IVCNZ), 25 - 27 November 2020, Wellington, New Zealand   ","raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6800000071525574,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W658020064","https://openalex.org/W1514535095","https://openalex.org/W1686810756","https://openalex.org/W1773149199","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1956340063","https://openalex.org/W2064675550","https://openalex.org/W2097117768","https://openalex.org/W2101105183","https://openalex.org/W2108598243","https://openalex.org/W2123301721","https://openalex.org/W2154652894","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2302086703","https://openalex.org/W2460442863","https://openalex.org/W2493916176","https://openalex.org/W2506483933","https://openalex.org/W2531409750","https://openalex.org/W2552161745","https://openalex.org/W2588822708","https://openalex.org/W2745461083","https://openalex.org/W2796347433","https://openalex.org/W2803408761","https://openalex.org/W2890531016","https://openalex.org/W2896348597","https://openalex.org/W2945472816","https://openalex.org/W2953641512","https://openalex.org/W2963446712","https://openalex.org/W2963565375","https://openalex.org/W2964081807","https://openalex.org/W2969047925","https://openalex.org/W3010982166","https://openalex.org/W3045097470","https://openalex.org/W3098325931","https://openalex.org/W4293584584","https://openalex.org/W6621906925","https://openalex.org/W6630875275","https://openalex.org/W6637373629","https://openalex.org/W6678262379","https://openalex.org/W6682631176","https://openalex.org/W6750227808","https://openalex.org/W6784955093","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393","https://openalex.org/W4289422896"],"abstract_inverted_index":{"Image":[0],"captioning":[1],"is":[2],"a":[3,10],"challenging":[4],"vision-to-language":[5],"task,":[6],"which":[7,48],"has":[8,53],"garnered":[9],"lot":[11],"of":[12,20,34,68,81,98,129],"attention":[13],"over":[14],"the":[15,25,32,35,63,78,82,106,111,127],"past":[16],"decade.":[17],"The":[18],"introduction":[19],"Encoder-Decoder":[21],"based":[22],"architectures":[23],"expedited":[24],"research":[26],"in":[27,49,95],"this":[28],"area":[29],"and":[30,65,116],"provided":[31],"backbone":[33],"most":[36,112],"recent":[37],"systems.":[38],"Moreover,":[39,75],"leveraging":[40],"relationships":[41],"between":[42],"objects":[43],"for":[44,139],"holistic":[45],"scene":[46],"understanding,":[47],"turn":[50],"improves":[51],"captioning,":[52],"recently":[54],"sparked":[55],"interest":[56],"among":[57],"researchers.":[58],"Our":[59,124],"proposed":[60],"model":[61],"encodes":[62],"spatial":[64],"semantic":[66,89],"proximity":[67],"object":[69,114,131],"pairs":[70],"into":[71],"linguistically-aware":[72,130],"relationship":[73],"embeddings.":[74],"it":[76],"captures":[77],"global":[79],"semantics":[80],"image":[83,100,140],"using":[84],"NASNet.":[85],"This":[86],"way,":[87],"true":[88],"relations":[90,115,132],"that":[91,105],"are":[92],"not":[93],"apparent":[94],"visual":[96,117,137],"content":[97],"an":[99],"can":[101,108],"be":[102],"learned,":[103],"such":[104],"decoder":[107],"attend":[109],"to":[110,119],"relevant":[113],"features":[118,138],"generate":[120],"more":[121],"semantically-meaningful":[122],"captions.":[123],"experiments":[125],"highlight":[126],"usefulness":[128],"as":[133,135],"well":[134],"NASNet":[136],"captioning.":[141]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}
