{"id":"https://openalex.org/W4408351970","doi":"https://doi.org/10.1109/icassp49660.2025.10888715","title":"SlotFusion: Object-Centric Audiovisual Feature Fusion with Slot Attention for Remote Sensing Scene Recognition","display_name":"SlotFusion: Object-Centric Audiovisual Feature Fusion with Slot Attention for Remote Sensing Scene Recognition","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408351970","doi":"https://doi.org/10.1109/icassp49660.2025.10888715"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888715","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888715","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5035887742","display_name":"Fangzhou Han","orcid":"https://orcid.org/0000-0002-3641-1667"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fangzhou Han","raw_affiliation_strings":["Harbin Institute of Technology,Dept. of Information Engineering,Harbin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Dept. of Information Engineering,Harbin,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019744998","display_name":"Tianyi Yu","orcid":"https://orcid.org/0000-0001-8090-6512"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianyi Yu","raw_affiliation_strings":["Harbin Institute of Technology,Dept. of Information Engineering,Harbin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Dept. of Information Engineering,Harbin,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052182532","display_name":"Lamei Zhang","orcid":"https://orcid.org/0000-0002-3595-0001"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lamei Zhang","raw_affiliation_strings":["Harbin Institute of Technology,Dept. of Information Engineering,Harbin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Dept. of Information Engineering,Harbin,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003513450","display_name":"Lingyu Si","orcid":"https://orcid.org/0000-0002-7735-6676"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lingyu Si","raw_affiliation_strings":["Chinese Academy of Sciences,National Key Laboratory of Space Integrated Information System Institute of Software,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,National Key Laboratory of Space Integrated Information System Institute of Software,Beijing,China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100624503","display_name":"Yiqi Zhang","orcid":"https://orcid.org/0000-0003-4267-0144"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiqi Zhang","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Software,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Software,Beijing,China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10688","display_name":"Image and Signal Denoising Methods","score":0.9624999761581421,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9624999761581421,"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/T10689","display_name":"Remote-Sensing Image Classification","score":0.9613000154495239,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9433000087738037,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/computer-science","display_name":"Computer science","score":0.7926756143569946},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5865730047225952},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5620492696762085},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5589357614517212},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.5095920562744141},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4828948974609375},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.43316057324409485},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.43195831775665283},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.24162372946739197}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7926756143569946},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5865730047225952},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5620492696762085},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5589357614517212},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.5095920562744141},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4828948974609375},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.43316057324409485},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.43195831775665283},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.24162372946739197},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888715","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888715","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2987489329","https://openalex.org/W3004301609","https://openalex.org/W3083147600","https://openalex.org/W3109212767","https://openalex.org/W3190018318","https://openalex.org/W4366721399","https://openalex.org/W4380763457","https://openalex.org/W4384915783","https://openalex.org/W4387828735","https://openalex.org/W4388105150","https://openalex.org/W4389879943","https://openalex.org/W4395056520","https://openalex.org/W4399146296","https://openalex.org/W4401537492","https://openalex.org/W6779809370"],"related_works":["https://openalex.org/W3147584709","https://openalex.org/W2114275278","https://openalex.org/W4292830139","https://openalex.org/W4319309705","https://openalex.org/W1489511283","https://openalex.org/W2974914859","https://openalex.org/W2026565050","https://openalex.org/W2110244802","https://openalex.org/W2163728705","https://openalex.org/W949345935"],"abstract_inverted_index":{"Despite":[0],"significant":[1],"advancements":[2],"in":[3,9,29,130],"remote":[4,30,121],"sensing":[5,31,122],"multimodal":[6],"learning,":[7],"particularly":[8],"image-image":[10],"feature":[11,17,55,65,72,102],"fusion,":[12],"the":[13,22,41,106,116],"exploration":[14],"of":[15,26,86],"audio-image":[16],"fusion":[18,42,56,73],"remains":[19],"insufficient.":[20],"Given":[21],"complexity":[23],"and":[24,68,93],"redundancy":[25],"ground":[27],"objects":[28],"images,":[32],"accurately":[33],"aligning":[34],"audio":[35],"features":[36,39,78,88],"with":[37,79,126],"image":[38],"during":[40],"process":[43],"is":[44],"a":[45,62,69,84,127],"critical":[46],"challenge.":[47],"In":[48],"this":[49],"paper,":[50],"we":[51,75],"introduce":[52],"an":[53],"object-centric":[54,101],"method":[57],"named":[58],"SlotFusion.":[59],"By":[60],"employing":[61],"slot":[63,87],"attention-based":[64],"decoupling":[66],"module":[67],"slot-based":[70],"audiovisual":[71],"module,":[74],"transform":[76],"modality":[77],"complex":[80],"semantic":[81],"information":[82],"into":[83],"set":[85],"corresponding":[89],"to":[90,98,134],"object":[91],"units":[92,97],"use":[94],"gated":[95],"activation":[96],"adaptively":[99],"implement":[100],"fusion.":[103],"Experiments":[104],"on":[105],"Audio":[107],"Visual":[108],"Aerial":[109],"Scene":[110],"Recognition":[111],"dataset":[112],"(ADVANCE)":[113],"demonstrate":[114],"that":[115],"proposed":[117],"SlotFusion":[118],"significantly":[119],"improves":[120],"scene":[123],"recognition":[124],"performance,":[125],"7.04%":[128],"increase":[129],"overall":[131],"accuracy":[132],"compared":[133],"previous":[135],"methods,":[136],"achieving":[137],"state-of-the-art":[138],"results.":[139]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}