{"id":"https://openalex.org/W4402389794","doi":"https://doi.org/10.1109/mapr63514.2024.10660775","title":"InstSynth: Instance-wise Prompt-guided Style Masked Conditional Data Synthesis for Scene Understanding","display_name":"InstSynth: Instance-wise Prompt-guided Style Masked Conditional Data Synthesis for Scene Understanding","publication_year":2024,"publication_date":"2024-08-15","ids":{"openalex":"https://openalex.org/W4402389794","doi":"https://doi.org/10.1109/mapr63514.2024.10660775"},"language":"en","primary_location":{"id":"doi:10.1109/mapr63514.2024.10660775","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mapr63514.2024.10660775","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/A5103193545","display_name":"Thanh-Danh Nguyen","orcid":"https://orcid.org/0000-0001-6577-2122"},"institutions":[{"id":"https://openalex.org/I127591826","display_name":"University of Dayton","ror":"https://ror.org/021v3qy27","country_code":"US","type":"education","lineage":["https://openalex.org/I127591826"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Thanh-Danh Nguyen","raw_affiliation_strings":["University of Dayton,Dayton,OH,United States,45469","University of Information Technology,Ho Chi Minh City,Vietnam"],"affiliations":[{"raw_affiliation_string":"University of Dayton,Dayton,OH,United States,45469","institution_ids":["https://openalex.org/I127591826"]},{"raw_affiliation_string":"University of Information Technology,Ho Chi Minh City,Vietnam","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108982821","display_name":"Bich-Nga Pham","orcid":"https://orcid.org/0009-0008-3031-1711"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bich-Nga Pham","raw_affiliation_strings":["University of Information Technology,Ho Chi Minh City,Vietnam"],"affiliations":[{"raw_affiliation_string":"University of Information Technology,Ho Chi Minh City,Vietnam","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111321161","display_name":"Trong-Tai Dam Vu","orcid":"https://orcid.org/0009-0005-1549-989X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Trong-Tai Dam Vu","raw_affiliation_strings":["University of Information Technology,Ho Chi Minh City,Vietnam"],"affiliations":[{"raw_affiliation_string":"University of Information Technology,Ho Chi Minh City,Vietnam","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054588832","display_name":"Vinh-Tiep Nguyen","orcid":"https://orcid.org/0000-0003-4260-7874"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vinh-Tiep Nguyen","raw_affiliation_strings":["University of Information Technology,Ho Chi Minh City,Vietnam"],"affiliations":[{"raw_affiliation_string":"University of Information Technology,Ho Chi Minh City,Vietnam","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081841048","display_name":"Thanh Duc Ngo","orcid":"https://orcid.org/0000-0001-6882-0070"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thanh Duc Ngo","raw_affiliation_strings":["University of Information Technology,Ho Chi Minh City,Vietnam"],"affiliations":[{"raw_affiliation_string":"University of Information Technology,Ho Chi Minh City,Vietnam","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022799473","display_name":"Tam Nguyen","orcid":"https://orcid.org/0000-0003-0236-7992"},"institutions":[{"id":"https://openalex.org/I127591826","display_name":"University of Dayton","ror":"https://ror.org/021v3qy27","country_code":"US","type":"education","lineage":["https://openalex.org/I127591826"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tam V. Nguyen","raw_affiliation_strings":["University of Dayton,Dayton,OH,United States,45469","University of Information Technology,Ho Chi Minh City,Vietnam"],"affiliations":[{"raw_affiliation_string":"University of Dayton,Dayton,OH,United States,45469","institution_ids":["https://openalex.org/I127591826"]},{"raw_affiliation_string":"University of Information Technology,Ho Chi Minh City,Vietnam","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5103193545"],"corresponding_institution_ids":["https://openalex.org/I127591826"],"apc_list":null,"apc_paid":null,"fwci":0.275,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.5339213,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9983999729156494,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9983999729156494,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9980999827384949,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9966999888420105,"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":0.7355687618255615},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.5232048034667969},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38717541098594666},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3340054154396057},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.05427852272987366}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7355687618255615},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.5232048034667969},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38717541098594666},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3340054154396057},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.05427852272987366},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mapr63514.2024.10660775","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mapr63514.2024.10660775","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":44,"referenced_works":["https://openalex.org/W2064076387","https://openalex.org/W2133665775","https://openalex.org/W2171943915","https://openalex.org/W2340897893","https://openalex.org/W2781228439","https://openalex.org/W2963150697","https://openalex.org/W2963857746","https://openalex.org/W2964057616","https://openalex.org/W2964241181","https://openalex.org/W2990032492","https://openalex.org/W2993182889","https://openalex.org/W3034355852","https://openalex.org/W3096609285","https://openalex.org/W3097065222","https://openalex.org/W3107443479","https://openalex.org/W3116529608","https://openalex.org/W3153469116","https://openalex.org/W3211490618","https://openalex.org/W3216352822","https://openalex.org/W4214893857","https://openalex.org/W4224035735","https://openalex.org/W4281485151","https://openalex.org/W4301206121","https://openalex.org/W4312615272","https://openalex.org/W4312815172","https://openalex.org/W4312933868","https://openalex.org/W4362707108","https://openalex.org/W4383472654","https://openalex.org/W4385245566","https://openalex.org/W4386066020","https://openalex.org/W4386071839","https://openalex.org/W4386076027","https://openalex.org/W4387951062","https://openalex.org/W4392341509","https://openalex.org/W6739901393","https://openalex.org/W6765779288","https://openalex.org/W6786095906","https://openalex.org/W6790978476","https://openalex.org/W6797399245","https://openalex.org/W6809885388","https://openalex.org/W6838639034","https://openalex.org/W6852041589","https://openalex.org/W6854511533","https://openalex.org/W6861363789"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Scene":[0],"understanding":[1,110],"at":[2,32,165],"the":[3,30,33,63,86,104,107,115,118,135,158],"instance":[4,34,95,120],"level":[5,35],"is":[6,36],"an":[7,53,80,141],"essential":[8],"task":[9],"in":[10,155],"computer":[11],"vision":[12],"to":[13,39,61,75,93,102],"support":[14],"modern":[15],"Advanced":[16],"Driver":[17],"Assistance":[18],"Systems.":[19],"Solutions":[20],"have":[21],"been":[22],"proposed":[23],"with":[24,97,147,157],"abundant":[25],"annotated":[26],"training":[27,64],"data.":[28,65],"However,":[29],"annotation":[31],"high-cost":[37],"due":[38],"huge":[40],"manual":[41],"efforts.":[42],"In":[43],"this":[44,48],"work,":[45],"we":[46,139],"solve":[47],"problem":[49],"by":[50,127],"introducing":[51],"InstSynth,":[52],"advanced":[54],"framework":[55],"leveraging":[56],"instance-wise":[57],"annotations":[58],"as":[59],"conditions":[60],"enrich":[62],"Existing":[66],"methods":[67],"focused":[68],"on":[69,134],"semantic":[70],"segmentation":[71,121],"via":[72],"using":[73],"prompts":[74],"synthesize":[76,94],"image-annotation":[77],"pairs,":[78],"facing":[79],"unrealistic":[81],"manner.":[82],"Our":[83],"proposals":[84],"utilize":[85],"strength":[87],"of":[88,106,117,123,153],"such":[89],"large":[90],"generative":[91],"models":[92],"data":[96],"prompt-guided":[98],"and":[99,125,129],"mask-based":[100],"mechanisms":[101],"boost":[103],"performance":[105,116],"instance-level":[108,142],"scene":[109],"models.":[111],"We":[112],"empirically":[113],"improve":[114],"latest":[119],"architectures":[122],"FastInst":[124],"OneFormer":[126],"14.49%":[128],"11.59%":[130],"AP,":[131],"respectively,":[132],"evaluated":[133],"Cityscapes":[136],"benchmark.":[137],"Accordingly,":[138],"construct":[140],"synthesized":[143],"dataset,":[144],"dubbed":[145],"IS-Cityscapes,":[146],"over":[148],"a":[149],"4\u00d7":[150],"larger":[151],"number":[152],"instances":[154],"comparison":[156],"vanilla":[159],"Cityscapes.":[160],"Code":[161],"can":[162],"be":[163],"found":[164],"https://github.com/danhntd/InstSynth.":[166]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}