{"id":"https://openalex.org/W4415540605","doi":"https://doi.org/10.1145/3746027.3761837","title":"A Streamlined System for Multimodal Industrial Anomaly Detection via 2D and 3D Feature Fusion","display_name":"A Streamlined System for Multimodal Industrial Anomaly Detection via 2D and 3D Feature Fusion","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415540605","doi":"https://doi.org/10.1145/3746027.3761837"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3761837","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3761837","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","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/A5051800409","display_name":"Wenbing Zhu","orcid":"https://orcid.org/0000-0002-0494-0492"},"institutions":[{"id":"https://openalex.org/I4210119458","display_name":"Roche (China)","ror":"https://ror.org/02hv5e369","country_code":"CN","type":"company","lineage":["https://openalex.org/I118019719","https://openalex.org/I4210119458"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenbing Zhu","raw_affiliation_strings":["Rongcheer Co., Ltd., Suzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-0494-0492","affiliations":[{"raw_affiliation_string":"Rongcheer Co., Ltd., Suzhou, China","institution_ids":["https://openalex.org/I4210119458"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057267422","display_name":"Mingmin Chi","orcid":"https://orcid.org/0000-0003-2650-4146"},"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":"Mingmin Chi","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-2650-4146","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109971431","display_name":"Bo Peng","orcid":"https://orcid.org/0000-0001-5100-5344"},"institutions":[{"id":"https://openalex.org/I44675526","display_name":"Shanghai Ocean University","ror":"https://ror.org/04n40zv07","country_code":"CN","type":"education","lineage":["https://openalex.org/I44675526"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Peng","raw_affiliation_strings":["Shanghai Ocean University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-5100-5344","affiliations":[{"raw_affiliation_string":"Shanghai Ocean University, Shanghai, China","institution_ids":["https://openalex.org/I44675526"]}]}],"institutions":[],"countries_distinct_count":1,"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":0.27043641,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"14358","last_page":"14358"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9965999722480774,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9965999722480774,"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/T10876","display_name":"Fault Detection and Control Systems","score":0.9272000193595886,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.7190999984741211},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5705000162124634},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.5523999929428101},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5016999840736389},{"id":"https://openalex.org/keywords/point-cloud","display_name":"Point cloud","score":0.4659999907016754},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4099999964237213},{"id":"https://openalex.org/keywords/anomaly","display_name":"Anomaly (physics)","score":0.3889999985694885},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3774999976158142}],"concepts":[{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.7190999984741211},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6863999962806702},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6448000073432922},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5705000162124634},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.5523999929428101},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5016999840736389},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.47200000286102295},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.4659999907016754},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4099999964237213},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.3889999985694885},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3774999976158142},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.36649999022483826},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.3310999870300293},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.32409998774528503},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32089999318122864},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.2946000099182129},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.2883000075817108},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.2606000006198883},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.2581000030040741},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2558000087738037}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3761837","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3761837","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0],"demonstrate":[1],"an":[2],"end-to-end":[3],"system":[4,73],"for":[5,18,100],"real-time,":[6],"multimodal":[7],"industrial":[8],"anomaly":[9,69],"detection":[10],"(IAD),":[11],"built":[12],"upon":[13],"a":[14,29,65,97],"custom":[15],"hardware":[16],"platform":[17],"synchronized":[19],"2D":[20],"and":[21,43,67],"3D":[22],"data":[23],"acquisition.":[24],"Our":[25],"core":[26],"contribution":[27],"is":[28],"novel":[30],"cross-modal":[31],"residual":[32],"mechanism":[33],"that":[34,87],"identifies":[35],"defects":[36],"by":[37,82],"quantifying":[38],"predictive":[39],"errors":[40],"between":[41],"visual":[42],"geometric":[44],"feature":[45],"spaces.":[46],"Instead":[47],"of":[48,91],"traditional":[49],"concatenation,":[50],"our":[51],"dual-stream":[52],"architecture":[53],"mutually":[54],"predicts":[55],"features":[56],"across":[57],"modalities,":[58],"leveraging":[59],"the":[60,89],"prediction":[61],"residual's":[62],"magnitude":[63],"as":[64],"direct":[66,92],"robust":[68],"indicator.":[70],"The":[71],"entire":[72],"achieves":[74],"sub-second":[75],"inference":[76],"from":[77],"acquisition":[78],"to":[79],"decision,":[80],"enabled":[81],"efficient":[83],"depth":[84],"map":[85],"analysis":[86],"circumvents":[88],"complexity":[90],"point":[93],"cloud":[94],"processing,":[95],"offering":[96],"deployable":[98],"solution":[99],"high-speed":[101],"inspection.":[102]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-25T00:00:00"}