{"id":"https://openalex.org/W7118853953","doi":"https://doi.org/10.1007/s13735-025-00394-4","title":"CSAM: Capsule spatial attention mask network for visual question answering","display_name":"CSAM: Capsule spatial attention mask network for visual question answering","publication_year":2026,"publication_date":"2026-01-07","ids":{"openalex":"https://openalex.org/W7118853953","doi":"https://doi.org/10.1007/s13735-025-00394-4"},"language":"en","primary_location":{"id":"doi:10.1007/s13735-025-00394-4","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s13735-025-00394-4","pdf_url":null,"source":{"id":"https://openalex.org/S2496055428","display_name":"International Journal of Multimedia Information Retrieval","issn_l":"2192-6611","issn":["2192-6611","2192-662X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Multimedia Information Retrieval","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/A5112905513","display_name":"Lixia Xue","orcid":"https://orcid.org/0009-0000-4841-5318"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lixia Xue","raw_affiliation_strings":["School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, 230601, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, 230601, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077521090","display_name":"Yi Huang","orcid":"https://orcid.org/0000-0001-9259-8123"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Huang","raw_affiliation_strings":["School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, 230601, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, 230601, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079086221","display_name":"Ronggui Wang","orcid":"https://orcid.org/0009-0007-7547-5659"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ronggui Wang","raw_affiliation_strings":["School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, 230601, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, 230601, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109533304","display_name":"Juan Yang","orcid":"https://orcid.org/0000-0001-6538-4381"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Juan Yang","raw_affiliation_strings":["School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, 230601, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, 230601, China","institution_ids":["https://openalex.org/I16365422"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5109533304"],"corresponding_institution_ids":["https://openalex.org/I16365422"],"apc_list":{"value":3090,"currency":"USD","value_usd":3090},"apc_paid":null,"fwci":4.6258,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.89398394,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"15","issue":"1","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":0.9937000274658203,"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":0.9937000274658203,"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/T10028","display_name":"Topic Modeling","score":0.0010999999940395355,"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":0.0006000000284984708,"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/question-answering","display_name":"Question answering","score":0.820900022983551},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.7263000011444092},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.48190000653266907},{"id":"https://openalex.org/keywords/attention-network","display_name":"Attention network","score":0.47679999470710754},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.47600001096725464},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.46209999918937683},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.45579999685287476},{"id":"https://openalex.org/keywords/mobile-device","display_name":"Mobile device","score":0.38659998774528503},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3758000135421753}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8784999847412109},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.820900022983551},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.7263000011444092},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.565500020980835},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.48190000653266907},{"id":"https://openalex.org/C2993807640","wikidata":"https://www.wikidata.org/wiki/Q103709453","display_name":"Attention network","level":2,"score":0.47679999470710754},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.47600001096725464},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.46209999918937683},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.45579999685287476},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4074999988079071},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.38659998774528503},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3758000135421753},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3675999939441681},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3635999858379364},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.3495999872684479},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34790000319480896},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.33889999985694885},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.3328000009059906},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.32330000400543213},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.32249999046325684},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.31209999322891235},{"id":"https://openalex.org/C200873422","wikidata":"https://www.wikidata.org/wiki/Q5448821","display_name":"Filling-in","level":2,"score":0.30410000681877136},{"id":"https://openalex.org/C205372480","wikidata":"https://www.wikidata.org/wiki/Q210521","display_name":"Image resolution","level":2,"score":0.2971999943256378},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2915000021457672},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2863999903202057},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.2734000086784363},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.26820001006126404},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.25679999589920044},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.25529998540878296}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s13735-025-00394-4","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s13735-025-00394-4","pdf_url":null,"source":{"id":"https://openalex.org/S2496055428","display_name":"International Journal of Multimedia Information Retrieval","issn_l":"2192-6611","issn":["2192-6611","2192-662X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Multimedia Information Retrieval","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4368614928","display_name":null,"funder_award_id":"62106064","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W2277195237","https://openalex.org/W2546696630","https://openalex.org/W2561715562","https://openalex.org/W2747623286","https://openalex.org/W2793546384","https://openalex.org/W2799142693","https://openalex.org/W2963176022","https://openalex.org/W2963954913","https://openalex.org/W2964067226","https://openalex.org/W2964345214","https://openalex.org/W2966683369","https://openalex.org/W2969679616","https://openalex.org/W3035497460","https://openalex.org/W3108982874","https://openalex.org/W3167939936","https://openalex.org/W3174377922","https://openalex.org/W3185066916","https://openalex.org/W3203354307","https://openalex.org/W4224217283","https://openalex.org/W4310092748","https://openalex.org/W4311773928","https://openalex.org/W4312554250","https://openalex.org/W4312950730","https://openalex.org/W4320487288","https://openalex.org/W4385413584","https://openalex.org/W4388181804","https://openalex.org/W4388209340","https://openalex.org/W4390874447","https://openalex.org/W4393150006","https://openalex.org/W4396547305","https://openalex.org/W4400767105","https://openalex.org/W4401631528","https://openalex.org/W4404544349","https://openalex.org/W4406501268","https://openalex.org/W4406681426"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2026-01-08T00:00:00"}
