{"id":"https://openalex.org/W7208765778","doi":"https://doi.org/10.1145/3801438.3801459","title":"CDMA-VP: A Cross-Domain Multi-Agent Visual Perception Engine with Diffusion-Based Adaptation","display_name":"CDMA-VP: A Cross-Domain Multi-Agent Visual Perception Engine with Diffusion-Based Adaptation","publication_year":2026,"publication_date":"2026-04-24","ids":{"openalex":"https://openalex.org/W7208765778","doi":"https://doi.org/10.1145/3801438.3801459"},"language":"en","primary_location":{"id":"doi:10.1145/3801438.3801459","doi":"https://doi.org/10.1145/3801438.3801459","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3801438.3801459","pdf_url":null,"source":{"id":"https://openalex.org/S7407086067","display_name":"International Conference on Machine Intelligence and Digital Applications (MIDA)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd International Conference on Machine Intelligence and Digital Applications","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3801438.3801459","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137781967","display_name":"Jianmin Wang","orcid":"https://orcid.org/0009-0003-5266-9611","observed_orcids":["https://orcid.org/0009-0003-5266-9611"]},"institutions":[{"id":"https://openalex.org/I4405260334","display_name":"Dongying Vocational Institute","ror":"https://ror.org/03kbxzp97","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210096525","https://openalex.org/I4387155179","https://openalex.org/I4405260334"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianmin Wang","raw_affiliation_strings":["School of Information and Future Technology, Dongying Vocational College, Dongying, China"],"raw_orcid":"https://orcid.org/0009-0003-5266-9611","affiliations":[{"raw_affiliation_string":"School of Information and Future Technology, Dongying Vocational College, Dongying, China","institution_ids":["https://openalex.org/I4405260334"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5150024419","display_name":"Jiahui Cao","orcid":"https://orcid.org/0009-0009-9648-185X","observed_orcids":["https://orcid.org/0009-0009-9648-185X"]},"institutions":[{"id":"https://openalex.org/I38877650","display_name":"Zhengzhou University","ror":"https://ror.org/04ypx8c21","country_code":"CN","type":"education","lineage":["https://openalex.org/I38877650"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiahui Cao","raw_affiliation_strings":["School of Fine Arts, Zhengzhou University, Zhengzhou, China"],"raw_orcid":"https://orcid.org/0009-0009-9648-185X","affiliations":[{"raw_affiliation_string":"School of Fine Arts, Zhengzhou University, Zhengzhou, China","institution_ids":["https://openalex.org/I38877650"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123392206","display_name":"Tianzuo Yuan","orcid":"https://orcid.org/0009-0006-5122-2799","observed_orcids":["https://orcid.org/0009-0006-5122-2799"]},"institutions":[{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Tianzuo Yuan","raw_affiliation_strings":["Faculty of Health Sciences, University of Macau, Macau S.A.R., Macao"],"raw_orcid":"https://orcid.org/0009-0006-5122-2799","affiliations":[{"raw_affiliation_string":"Faculty of Health Sciences, University of Macau, Macau S.A.R., Macao","institution_ids":["https://openalex.org/I204512498"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1781","last_page":"1785"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9990000128746033,"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"}},"topics":[{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9990000128746033,"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"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.0010000000474974513,"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":0.0,"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/domain-adaptation","display_name":"domain adaptation","score":0.6909999847412109},{"id":"https://openalex.org/keywords/diffusion-models","display_name":"diffusion models","score":0.7210000157356262},{"id":"https://openalex.org/keywords/domain-shift","display_name":"domain shift","score":0.6129999756813049},{"id":"https://openalex.org/keywords/adaptive-feature-fusion","display_name":"adaptive feature fusion","score":0.6850000023841858},{"id":"https://openalex.org/keywords/semantic-segmentation","display_name":"semantic segmentation","score":0.6990000009536743},{"id":"https://openalex.org/keywords/agent-selection","display_name":"agent selection","score":0.6779999732971191},{"id":"https://openalex.org/keywords/computational-efficiency","display_name":"computational efficiency","score":0.578000009059906}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5268999934196472},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4629000127315521},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4587000012397766},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4074999988079071},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.39410001039505005},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.37070000171661377},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.321399986743927},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3167000114917755},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.2962999939918518},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2791999876499176},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.2680000066757202},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3801438.3801459","doi":"https://doi.org/10.1145/3801438.3801459","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3801438.3801459","pdf_url":null,"source":{"id":"https://openalex.org/S7407086067","display_name":"International Conference on Machine Intelligence and Digital Applications (MIDA)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd International Conference on Machine Intelligence and Digital Applications","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3801438.3801459","doi":"https://doi.org/10.1145/3801438.3801459","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3801438.3801459","pdf_url":null,"source":{"id":"https://openalex.org/S7407086067","display_name":"International Conference on Machine Intelligence and Digital Applications (MIDA)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd International Conference on Machine Intelligence and Digital Applications","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2340897893","https://openalex.org/W2431874326","https://openalex.org/W2487365028","https://openalex.org/W3035564946","https://openalex.org/W3217147624","https://openalex.org/W4386047746","https://openalex.org/W4394625700","https://openalex.org/W4414494379","https://openalex.org/W7124906074"],"related_works":["https://openalex.org/W4415540034","https://openalex.org/W4383108477","https://openalex.org/W4411535491","https://openalex.org/W7165898138","https://openalex.org/W4403938688","https://openalex.org/W4387609210","https://openalex.org/W7128774069","https://openalex.org/W1904548169","https://openalex.org/W7154569735","https://openalex.org/W2057266281"],"abstract_inverted_index":{"Visual":[0],"perception":[1,32],"systems":[2],"face":[3],"critical":[4],"challenges":[5],"when":[6],"deployed":[7],"across":[8],"diverse":[9,48],"scenarios":[10],"due":[11],"to":[12,85],"domain":[13,54,103],"shift":[14],"from":[15],"varying":[16],"imaging":[17],"conditions,":[18],"device":[19],"configurations,":[20],"and":[21,61,82,117,128,136],"data":[22],"distributions.":[23],"This":[24],"paper":[25],"proposes":[26],"CDMA-VP,":[27],"a":[28,52],"cross-domain":[29,36],"multi-agent":[30,74,111],"visual":[31,45,88],"engine":[33],"that":[34],"addresses":[35],"adaptation":[37,55,92],"through":[38,98],"three":[39],"key":[40],"components:":[41],"(1)":[42],"six":[43],"heterogeneous":[44],"agents":[46],"for":[47,57],"feature":[49,58,96],"extraction,":[50],"(2)":[51],"diffusion-based":[53,91],"module":[56,93],"distribution":[59],"alignment,":[60],"(3)":[62],"an":[63],"adaptive":[64,106,140],"fusion":[65,71,107],"mechanism":[66,108,143],"based":[67,113],"on":[68,114],"Chair-Varshney":[69],"optimal":[70],"theory.":[72],"The":[73,90,105,139],"architecture":[75],"integrates":[76],"ResNet-50,":[77],"FPN,":[78],"MobileNetV3,":[79],"DenseNet-121,":[80],"EfficientNet-B3,":[81],"Vision":[83],"Transformer":[84],"capture":[86],"complementary":[87],"features.":[89],"progressively":[94],"aligns":[95],"distributions":[97],"iterative":[99],"denoising,":[100],"effectively":[101],"mitigating":[102],"shift.":[104],"dynamically":[109],"combines":[110],"predictions":[112],"confidence":[115],"scores":[116],"historical":[118],"performance.":[119],"On":[120],"standard":[121],"benchmarks":[122],"(GTA5\u2192Cityscapes,":[123],"SYNTHIA\u2192Cityscapes),":[124],"CDMA-VP":[125],"achieves":[126],"72.5%":[127],"64.8%":[129],"mIoU,":[130],"improving":[131],"over":[132],"DAFormer":[133],"by":[134,147],"4.2%":[135],"3.9%,":[137],"respectively.":[138],"agent":[141],"selection":[142],"reduces":[144],"computational":[145],"overhead":[146],"50.0%":[148],"while":[149],"maintaining":[150],"near-optimal":[151],"performance":[152],"with":[153],"only":[154],"0.6%":[155],"mIoU":[156],"degradation.":[157]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-09-05T00:00:00"}