{"id":"https://openalex.org/W7143757965","doi":"https://doi.org/10.1016/j.neucom.2026.133497","title":"GTA: Geometric transform-attention network for enhanced spatial reasoning in image captioning","display_name":"GTA: Geometric transform-attention network for enhanced spatial reasoning in image captioning","publication_year":2026,"publication_date":"2026-03-31","ids":{"openalex":"https://openalex.org/W7143757965","doi":"https://doi.org/10.1016/j.neucom.2026.133497"},"language":"en","primary_location":{"id":"doi:10.1016/j.neucom.2026.133497","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.neucom.2026.133497","pdf_url":null,"source":{"id":"https://openalex.org/S45693802","display_name":"Neurocomputing","issn_l":"0925-2312","issn":["0925-2312","1872-8286"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neurocomputing","raw_type":"journal-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/A5131394467","display_name":"Mohammad Alamgir Hossain","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mohammad Alamgir Hossain","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0007-9339-4393","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5131198969","display_name":"Zhongfu Ye","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhongfu Ye","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5131402952","display_name":"Md.Bipul Hossen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Md. Bipul Hossen","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-8546-5426","affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Md Shohidul Islam","orcid":"https://orcid.org/0000-0002-2854-4419"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Md Shohidul Islam","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-2854-4419","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5131309164","display_name":"Md.Ibrahim Abdullah","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Md. Ibrahim Abdullah","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2470,"currency":"USD","value_usd":2470},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.43096676,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"683","issue":null,"first_page":"133497","last_page":"133497"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9635999798774719,"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":0.9635999798774719,"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/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.00430000014603138,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.0034000000450760126,"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":0.9031999707221985},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5827999711036682},{"id":"https://openalex.org/keywords/spatial-intelligence","display_name":"Spatial intelligence","score":0.39489999413490295},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3700000047683716},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.34360000491142273}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9031999707221985},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.770799994468689},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6942999958992004},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5827999711036682},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.52920001745224},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.39489999413490295},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3700000047683716},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.34360000491142273},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.30390000343322754},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.27230000495910645},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.25839999318122864}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.neucom.2026.133497","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.neucom.2026.133497","pdf_url":null,"source":{"id":"https://openalex.org/S45693802","display_name":"Neurocomputing","issn_l":"0925-2312","issn":["0925-2312","1872-8286"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neurocomputing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2277195237","https://openalex.org/W3131872037","https://openalex.org/W3201187808","https://openalex.org/W3203790606","https://openalex.org/W4213303451","https://openalex.org/W4220798700","https://openalex.org/W4226397058","https://openalex.org/W4285792275","https://openalex.org/W4311310217","https://openalex.org/W4320487288","https://openalex.org/W4396609326","https://openalex.org/W4400939036","https://openalex.org/W4401666710","https://openalex.org/W4402469082","https://openalex.org/W4407099375","https://openalex.org/W4408446156","https://openalex.org/W4412055419","https://openalex.org/W7127951571"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-04-01T00:00:00"}
