{"id":"https://openalex.org/W4400019297","doi":"https://doi.org/10.1109/mmul.2024.3415643","title":"The Multimodal Scene Recognition Method Based on Self-Attention and Distillation","display_name":"The Multimodal Scene Recognition Method Based on Self-Attention and Distillation","publication_year":2024,"publication_date":"2024-06-25","ids":{"openalex":"https://openalex.org/W4400019297","doi":"https://doi.org/10.1109/mmul.2024.3415643"},"language":"en","primary_location":{"id":"doi:10.1109/mmul.2024.3415643","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmul.2024.3415643","pdf_url":null,"source":{"id":"https://openalex.org/S72873717","display_name":"IEEE Multimedia","issn_l":"1070-986X","issn":["1070-986X","1941-0166"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE MultiMedia","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/A5041345011","display_name":"Ning Sun","orcid":"https://orcid.org/0000-0002-6907-3756"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ning Sun","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-6907-3756","affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wei Xu","orcid":"https://orcid.org/0009-0003-7585-9418"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Xu","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0003-7585-9418","affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081669641","display_name":"Jixin Liu","orcid":"https://orcid.org/0000-0001-8414-4199"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jixin Liu","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-8414-4199","affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Lei Chai","orcid":"https://orcid.org/0000-0001-9120-0339"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Chai","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-9120-0339","affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036049204","display_name":"Haian Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haian Sun","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I41198531"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08216758,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"31","issue":"4","first_page":"25","last_page":"36"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13717","display_name":"Advanced Algorithms and Applications","score":0.7897999882698059,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T13717","display_name":"Advanced Algorithms and Applications","score":0.7897999882698059,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13890","display_name":"Remote Sensing and Land Use","score":0.7684999704360962,"subfield":{"id":"https://openalex.org/subfields/1902","display_name":"Atmospheric Science"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T14270","display_name":"Simulation and Modeling Applications","score":0.6933000087738037,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8371735215187073},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.5578391551971436},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5130668878555298},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4667978882789612},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41453659534454346},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.38456565141677856},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3282879590988159}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8371735215187073},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.5578391551971436},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5130668878555298},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4667978882789612},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41453659534454346},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.38456565141677856},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3282879590988159},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mmul.2024.3415643","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmul.2024.3415643","pdf_url":null,"source":{"id":"https://openalex.org/S72873717","display_name":"IEEE Multimedia","issn_l":"1070-986X","issn":["1070-986X","1941-0166"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE MultiMedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1057750671","display_name":null,"funder_award_id":"BK20180088","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"},{"id":"https://openalex.org/G7564392077","display_name":"\u9762\u5411\u667a\u80fd\u89c6\u9891\u76d1\u63a7\u7cfb\u7edf\u4e2d\u76ee\u6807\u7406\u89e3\u7684\u957f\u65f6\u7a0b\u6df1\u5ea6\u5b66\u4e60\u6a21\u578b\u7814\u7a76","funder_award_id":"61471206","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"},{"id":"https://openalex.org/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W125693051","https://openalex.org/W1923184257","https://openalex.org/W2592613168","https://openalex.org/W2901505625","https://openalex.org/W2905312384","https://openalex.org/W2911247705","https://openalex.org/W2939308562","https://openalex.org/W2968004941","https://openalex.org/W2976689776","https://openalex.org/W3019632826","https://openalex.org/W3034429256","https://openalex.org/W3088307280","https://openalex.org/W3125237740","https://openalex.org/W3162750720","https://openalex.org/W3173799170","https://openalex.org/W3197292052","https://openalex.org/W4224084679","https://openalex.org/W4226426325","https://openalex.org/W4312372834","https://openalex.org/W4386275868","https://openalex.org/W6762287338","https://openalex.org/W6781725879","https://openalex.org/W6784333009","https://openalex.org/W6788135285","https://openalex.org/W6789503006"],"related_works":["https://openalex.org/W3026162553","https://openalex.org/W2768175398","https://openalex.org/W2344382886","https://openalex.org/W19111321","https://openalex.org/W2412887479","https://openalex.org/W32245304","https://openalex.org/W2953684491","https://openalex.org/W4285338581","https://openalex.org/W2015158429","https://openalex.org/W2080290893"],"abstract_inverted_index":{"Scene":[0],"recognition":[1,57,160,179],"is":[2,60,138],"a":[3,135,145],"challenging":[4],"task":[5],"in":[6,15,62,98,111,130],"computer":[7],"vision":[8],"because":[9],"of":[10,13,21,29,67,75,85,103,144,148,171],"the":[11,19,27,51,68,71,100,112,116,121,131,142,169],"diversity":[12],"objects":[14],"scene":[16,31,38,56,87,159,178],"images":[17],"and":[18,53,81,164],"ambiguity":[20],"object":[22],"layouts.":[23],"In":[24],"recent":[25],"years,":[26],"emergence":[28],"multimodal":[30,55,86,158,177],"data":[32],"has":[33,42],"provided":[34],"new":[35,45],"solutions":[36],"for":[37,95],"recognition,":[39],"but":[40],"it":[41],"also":[43],"brought":[44],"problems.":[46],"To":[47],"address":[48],"these":[49],"challenges,":[50],"self-attention":[52,110],"distillation-based":[54],"network":[58],"(SAD-MSR)":[59],"proposed":[61],"this":[63,96],"article.":[64],"The":[65],"backbone":[66],"model":[69,97],"adopts":[70],"pure":[72],"transformer":[73],"structure":[74],"self-attention,":[76],"which":[77,99],"can":[78,183],"extract":[79],"local":[80],"global":[82],"spatial":[83],"features":[84,118],"images.":[88],"A":[89],"multistage":[90],"fusion":[91],"mechanism":[92,137],"was":[93],"developed":[94],"concatenated":[101],"tokens":[102],"two":[104,122,157],"modalities":[105,123],"are":[106,124],"fused":[107,125],"based":[108,126],"on":[109,127,156],"early":[113],"stage,":[114],"while":[115],"high-level":[117],"extracted":[119],"from":[120],"cross":[128],"attention":[129],"late":[132],"stage.":[133],"Furthermore,":[134],"distillation":[136],"introduced":[139],"to":[140,167],"alleviate":[141],"problem":[143],"limited":[146],"number":[147],"training":[149],"samples.":[150],"Finally,":[151],"we":[152],"conducted":[153],"extensive":[154],"experiments":[155],"databases,":[161],"SUN":[162],"RGB-D":[163],"NYU":[165],"Depth,":[166],"show":[168],"effectiveness":[170],"SAD-MSR.":[172],"Compared":[173],"with":[174],"other":[175],"state-of-the-art":[176],"methods,":[180],"our":[181],"method":[182],"achieve":[184],"better":[185],"experimental":[186],"results.":[187]},"counts_by_year":[],"updated_date":"2025-12-26T23:08:49.675405","created_date":"2025-10-10T00:00:00"}