{"id":"https://openalex.org/W4402981486","doi":"https://doi.org/10.1109/icme57554.2024.10687875","title":"Fine-Grained Scene Image Classification with Modality-Agnostic Adapter","display_name":"Fine-Grained Scene Image Classification with Modality-Agnostic Adapter","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402981486","doi":"https://doi.org/10.1109/icme57554.2024.10687875"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10687875","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10687875","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","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/A5100355047","display_name":"Yiqun Wang","orcid":"https://orcid.org/0000-0003-1942-5597"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiqun Wang","raw_affiliation_strings":["Fudan University,School of Computer Science,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University,School of Computer Science,China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100665357","display_name":"Zhao Zhou","orcid":"https://orcid.org/0000-0001-7069-6275"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhao Zhou","raw_affiliation_strings":["Fudan University,School of Computer Science,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University,School of Computer Science,China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047942518","display_name":"Xiangcheng Du","orcid":"https://orcid.org/0000-0002-4268-6114"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangcheng Du","raw_affiliation_strings":["Fudan University,School of Computer Science,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University,School of Computer Science,China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043728985","display_name":"Xingjiao Wu","orcid":"https://orcid.org/0000-0001-9146-051X"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingjiao Wu","raw_affiliation_strings":["Fudan University,School of Computer Science,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University,School of Computer Science,China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056833841","display_name":"Yingbin Zheng","orcid":"https://orcid.org/0000-0002-5590-9292"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yingbin Zheng","raw_affiliation_strings":["Videt Technology,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Videt Technology,China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100625873","display_name":"Cheng Jin","orcid":"https://orcid.org/0000-0003-3063-1957"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng Jin","raw_affiliation_strings":["Fudan University,School of Computer Science,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University,School of Computer Science,China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.7559999823570251,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.7559999823570251,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.7439000010490417,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.7357000112533569,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7516257166862488},{"id":"https://openalex.org/keywords/adapter","display_name":"Adapter (computing)","score":0.7435325980186462},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6700229644775391},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6212851405143738},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5146849751472473},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.4356893301010132},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4022884666919708},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33298707008361816},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.11058434844017029}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7516257166862488},{"id":"https://openalex.org/C177284502","wikidata":"https://www.wikidata.org/wiki/Q1005390","display_name":"Adapter (computing)","level":2,"score":0.7435325980186462},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6700229644775391},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6212851405143738},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5146849751472473},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.4356893301010132},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4022884666919708},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33298707008361816},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.11058434844017029}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme57554.2024.10687875","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10687875","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","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":25,"referenced_works":["https://openalex.org/W1567302070","https://openalex.org/W2046519698","https://openalex.org/W2097117768","https://openalex.org/W2138011018","https://openalex.org/W2194775991","https://openalex.org/W2493916176","https://openalex.org/W2521365688","https://openalex.org/W2565591417","https://openalex.org/W2727586675","https://openalex.org/W2745461083","https://openalex.org/W2904601236","https://openalex.org/W2963114696","https://openalex.org/W2970986510","https://openalex.org/W3024152176","https://openalex.org/W3043840704","https://openalex.org/W3090449556","https://openalex.org/W3119160127","https://openalex.org/W3176824248","https://openalex.org/W3205519684","https://openalex.org/W3212266429","https://openalex.org/W4288058182","https://openalex.org/W4312658754","https://openalex.org/W4312746376","https://openalex.org/W4386075667","https://openalex.org/W4386160550"],"related_works":["https://openalex.org/W2133028525","https://openalex.org/W4229060448","https://openalex.org/W4306381730","https://openalex.org/W2981692913","https://openalex.org/W3044188621","https://openalex.org/W3184035966","https://openalex.org/W2160602540","https://openalex.org/W2485605994","https://openalex.org/W2291489469","https://openalex.org/W2546503577"],"abstract_inverted_index":{"When":[0],"dealing":[1],"with":[2,117],"the":[3,37,60,63,78,85,114,138],"task":[4],"of":[5,39,65],"fine-grained":[6],"scene":[7],"image":[8],"classification,":[9],"most":[10],"previous":[11,118],"works":[12],"lay":[13],"much":[14],"emphasis":[15],"on":[16,33,110],"global":[17],"visual":[18],"features":[19],"when":[20,132],"doing":[21],"multi-modal":[22,49],"feature":[23,50,100],"fusion.":[24,101],"In":[25,42],"other":[26],"words,":[27],"models":[28],"are":[29],"deliberately":[30],"designed":[31],"based":[32],"prior":[34,75],"intuitions":[35],"about":[36],"importance":[38,64],"different":[40,66,69],"modalities.":[41],"this":[43],"paper,":[44],"we":[45,83],"present":[46],"a":[47,74,93,98],"new":[48,126],"fusion":[51],"approach":[52],"named":[53],"MAA":[54,106,134],"(Modality-Agnostic":[55],"Adapter),":[56],"trying":[57],"to":[58],"make":[59],"model":[61,79],"learn":[62],"modalities":[67,116,127],"in":[68,77,88],"cases":[70],"adaptively,":[71],"without":[72],"giving":[73],"setting":[76],"architecture.":[80],"More":[81],"specifically,":[82],"eliminate":[84],"modal":[86],"differences":[87],"distribution":[89],"and":[90,135],"then":[91],"use":[92],"modality-agnostic":[94],"Transformer":[95],"encoder":[96],"for":[97],"semantic-level":[99],"Our":[102],"experiments":[103],"demonstrate":[104],"that":[105,125],"achieves":[107],"state-of-the-art":[108],"results":[109],"benchmarks":[111],"by":[112],"applying":[113],"same":[115],"methods.":[119],"Besides,":[120],"it":[121],"is":[122],"worth":[123],"mentioning":[124],"can":[128],"be":[129],"easily":[130],"added":[131],"using":[133],"further":[136],"boost":[137],"performance.":[139]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}