{"id":"https://openalex.org/W4402402615","doi":"https://doi.org/10.1109/mapr63514.2024.10660805","title":"Rethinking Text-to-Image as Semantic-Aware Data Augmentation for Indoor Scene Recognition","display_name":"Rethinking Text-to-Image as Semantic-Aware Data Augmentation for Indoor Scene Recognition","publication_year":2024,"publication_date":"2024-08-15","ids":{"openalex":"https://openalex.org/W4402402615","doi":"https://doi.org/10.1109/mapr63514.2024.10660805"},"language":"en","primary_location":{"id":"doi:10.1109/mapr63514.2024.10660805","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/mapr63514.2024.10660805","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Conference on Multimedia Analysis and Pattern Recognition (MAPR)","raw_type":"proceedings-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/A5075898211","display_name":"Trong-Vu Hoang","orcid":"https://orcid.org/0000-0001-7367-1401"},"institutions":[{"id":"https://openalex.org/I23582244","display_name":"Ho Chi Minh City University of Science","ror":"https://ror.org/05jfbgm49","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023","https://openalex.org/I23582244"]},{"id":"https://openalex.org/I123565023","display_name":"Vietnam National University Ho Chi Minh City","ror":"https://ror.org/00waaqh38","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023"]}],"countries":["VN"],"is_corresponding":true,"raw_author_name":"Trong-Vu Hoang","raw_affiliation_strings":["University of Science, VNU-HCM,Vietnam"],"affiliations":[{"raw_affiliation_string":"University of Science, VNU-HCM,Vietnam","institution_ids":["https://openalex.org/I23582244","https://openalex.org/I123565023"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033391110","display_name":"Quang-Binh Nguyen","orcid":"https://orcid.org/0000-0003-1199-3661"},"institutions":[{"id":"https://openalex.org/I123565023","display_name":"Vietnam National University Ho Chi Minh City","ror":"https://ror.org/00waaqh38","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023"]},{"id":"https://openalex.org/I23582244","display_name":"Ho Chi Minh City University of Science","ror":"https://ror.org/05jfbgm49","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023","https://openalex.org/I23582244"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Quang-Binh Nguyen","raw_affiliation_strings":["University of Science, VNU-HCM,Vietnam"],"affiliations":[{"raw_affiliation_string":"University of Science, VNU-HCM,Vietnam","institution_ids":["https://openalex.org/I23582244","https://openalex.org/I123565023"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104258631","display_name":"Dinh-Khoi Vo","orcid":null},"institutions":[{"id":"https://openalex.org/I23582244","display_name":"Ho Chi Minh City University of Science","ror":"https://ror.org/05jfbgm49","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023","https://openalex.org/I23582244"]},{"id":"https://openalex.org/I123565023","display_name":"Vietnam National University Ho Chi Minh City","ror":"https://ror.org/00waaqh38","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Dinh-Khoi Vo","raw_affiliation_strings":["University of Science, VNU-HCM,Vietnam"],"affiliations":[{"raw_affiliation_string":"University of Science, VNU-HCM,Vietnam","institution_ids":["https://openalex.org/I23582244","https://openalex.org/I123565023"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025298148","display_name":"Hoai-Danh Vo","orcid":"https://orcid.org/0009-0006-6774-2123"},"institutions":[{"id":"https://openalex.org/I123565023","display_name":"Vietnam National University Ho Chi Minh City","ror":"https://ror.org/00waaqh38","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023"]},{"id":"https://openalex.org/I23582244","display_name":"Ho Chi Minh City University of Science","ror":"https://ror.org/05jfbgm49","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023","https://openalex.org/I23582244"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Hoai-Danh Vo","raw_affiliation_strings":["University of Science, VNU-HCM,Vietnam"],"affiliations":[{"raw_affiliation_string":"University of Science, VNU-HCM,Vietnam","institution_ids":["https://openalex.org/I23582244","https://openalex.org/I123565023"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053495766","display_name":"Minh\u2013Triet Tran","orcid":"https://orcid.org/0000-0003-3046-3041"},"institutions":[{"id":"https://openalex.org/I123565023","display_name":"Vietnam National University Ho Chi Minh City","ror":"https://ror.org/00waaqh38","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023"]},{"id":"https://openalex.org/I23582244","display_name":"Ho Chi Minh City University of Science","ror":"https://ror.org/05jfbgm49","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023","https://openalex.org/I23582244"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Minh-Triet Tran","raw_affiliation_strings":["University of Science, VNU-HCM,Vietnam"],"affiliations":[{"raw_affiliation_string":"University of Science, VNU-HCM,Vietnam","institution_ids":["https://openalex.org/I23582244","https://openalex.org/I123565023"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062359795","display_name":"Trung-Nghia Le","orcid":"https://orcid.org/0000-0002-7363-2610"},"institutions":[{"id":"https://openalex.org/I23582244","display_name":"Ho Chi Minh City University of Science","ror":"https://ror.org/05jfbgm49","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023","https://openalex.org/I23582244"]},{"id":"https://openalex.org/I123565023","display_name":"Vietnam National University Ho Chi Minh City","ror":"https://ror.org/00waaqh38","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Trung-Nghia Le","raw_affiliation_strings":["University of Science, VNU-HCM,Vietnam"],"affiliations":[{"raw_affiliation_string":"University of Science, VNU-HCM,Vietnam","institution_ids":["https://openalex.org/I23582244","https://openalex.org/I123565023"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5075898211"],"corresponding_institution_ids":["https://openalex.org/I123565023","https://openalex.org/I23582244"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14877557,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"1","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":0.9991000294685364,"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":0.9991000294685364,"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":0.9976999759674072,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9976000189781189,"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/computer-science","display_name":"Computer science","score":0.7275539040565491},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5449321866035461},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5022573471069336},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40259164571762085},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.39701250195503235},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3747346103191376}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7275539040565491},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5449321866035461},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5022573471069336},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40259164571762085},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.39701250195503235},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3747346103191376}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mapr63514.2024.10660805","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/mapr63514.2024.10660805","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Conference on Multimedia Analysis and Pattern Recognition (MAPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W1994956562","https://openalex.org/W2025183033","https://openalex.org/W2067912884","https://openalex.org/W2108598243","https://openalex.org/W2152161678","https://openalex.org/W2187089797","https://openalex.org/W2194775991","https://openalex.org/W2775795276","https://openalex.org/W2803187616","https://openalex.org/W2809598685","https://openalex.org/W2908510526","https://openalex.org/W2954996726","https://openalex.org/W2957455763","https://openalex.org/W2971296908","https://openalex.org/W2982083293","https://openalex.org/W2992308087","https://openalex.org/W3013004221","https://openalex.org/W3094502228","https://openalex.org/W3096831136","https://openalex.org/W3141117710","https://openalex.org/W4224035735","https://openalex.org/W4226125322","https://openalex.org/W4281485151","https://openalex.org/W4288279014","https://openalex.org/W4306820534","https://openalex.org/W4308163867","https://openalex.org/W4312933868","https://openalex.org/W4312977351","https://openalex.org/W4317951215","https://openalex.org/W4375839990","https://openalex.org/W4380551079","https://openalex.org/W4386065752","https://openalex.org/W4386076458","https://openalex.org/W4386076532","https://openalex.org/W4390873235","https://openalex.org/W6747218270","https://openalex.org/W6751420435","https://openalex.org/W6757817989","https://openalex.org/W6766543368","https://openalex.org/W6784333009","https://openalex.org/W6790978476","https://openalex.org/W6791353385","https://openalex.org/W6792155083","https://openalex.org/W6793164127","https://openalex.org/W6809885388","https://openalex.org/W6810940779","https://openalex.org/W6838639034","https://openalex.org/W6846007759","https://openalex.org/W6846655393","https://openalex.org/W6849119191","https://openalex.org/W6853387682"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"In":[0],"the":[1,13,29,45,75,88,94,102,115,157],"realm":[2],"of":[3,16,31,47,60,96,104,117,159],"computer":[4],"vision,":[5],"indoor":[6,33,71,81],"image":[7,82],"recognition":[8,83],"presents":[9],"challenges":[10],"due":[11],"to":[12,113],"intricate":[14],"interplay":[15],"lighting":[17],"conditions,":[18],"occlusions,":[19],"and":[20,69],"diverse":[21,68],"object":[22],"arrangements":[23],"within":[24],"confined":[25],"spaces.":[26],"To":[27],"address":[28],"lacks":[30],"training":[32,76,103,137],"images,":[34,49,120],"we":[35,121],"introduce":[36,122],"a":[37,53,63,123],"novel":[38],"approach":[39,99,149],"leveraging":[40],"Stable":[41],"Diffusion":[42],"(SD)":[43],"for":[44,66,79],"generation":[46],"synthetic":[48,119],"which":[50],"serve":[51],"as":[52],"powerful":[54,133],"data":[55,77,109],"augmentation":[56],"tool.":[57],"The":[58,132],"utilization":[59],"SD":[61,118,153],"offers":[62],"principled":[64],"framework":[65],"synthesizing":[67],"realistic":[70],"scenes,":[72],"thereby":[73],"enriching":[74],"pool":[78],"robust":[80,138],"models.":[84,144],"Experimental":[85],"findings":[86],"on":[87,127],"MIT":[89],"Indoor":[90],"Scene":[91],"dataset":[92],"reveal":[93],"potential":[95],"our":[97,148],"proposed":[98],"in":[100],"enhancing":[101],"deep":[105,143],"models":[106],"when":[107],"authentic":[108],"is":[110],"limited.":[111],"Furthermore,":[112],"prevent":[114],"misuse":[116],"counter":[124],"measure":[125],"based":[126],"DIffusion":[128],"Reconstruction":[129],"Error":[130],"(DIRE).":[131],"DIRE":[134],"presentation":[135],"enables":[136],"classifiers":[139],"only":[140],"using":[141,161],"lightweight":[142],"Experiments":[145],"show":[146],"that":[147],"can":[150],"perfectly":[151],"recognize":[152],"generated":[154],"images":[155],"with":[156],"accuracy":[158],"100%":[160],"MobilenetV3.":[162]},"counts_by_year":[],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}