{"id":"https://openalex.org/W4414141704","doi":"https://doi.org/10.1109/icmew68306.2025.11152172","title":"RIASA: Enhancing Reasoning Industrial Anomaly Segmentation via Large Vision-Language Models","display_name":"RIASA: Enhancing Reasoning Industrial Anomaly Segmentation via Large Vision-Language Models","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4414141704","doi":"https://doi.org/10.1109/icmew68306.2025.11152172"},"language":"en","primary_location":{"id":"doi:10.1109/icmew68306.2025.11152172","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmew68306.2025.11152172","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)","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/A5018742547","display_name":"Zongyun Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zongyun Zhang","raw_affiliation_strings":["Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003889945","display_name":"Xian Gao","orcid":"https://orcid.org/0000-0002-5301-0515"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xian Gao","raw_affiliation_strings":["Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020776216","display_name":"Jiacheng Ruan","orcid":"https://orcid.org/0009-0002-1590-1955"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiacheng Ruan","raw_affiliation_strings":["Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100418165","display_name":"Ting Liu","orcid":"https://orcid.org/0000-0003-3489-4578"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ting Liu","raw_affiliation_strings":["Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101704886","display_name":"Yuzhuo Fu","orcid":"https://orcid.org/0000-0001-5516-3016"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuzhuo Fu","raw_affiliation_strings":["Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5018742547"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13281785,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9991999864578247,"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":0.9991999864578247,"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/T14470","display_name":"Advanced Data Processing Techniques","score":0.9496999979019165,"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"}},{"id":"https://openalex.org/T10876","display_name":"Fault Detection and Control Systems","score":0.9304999709129333,"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/segmentation","display_name":"Segmentation","score":0.7433000206947327},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.6700000166893005},{"id":"https://openalex.org/keywords/anomaly","display_name":"Anomaly (physics)","score":0.6462000012397766},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5419999957084656},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4781000018119812},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.47609999775886536},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.3921000063419342}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7433000206947327},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.6700000166893005},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6618000268936157},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.6462000012397766},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5861999988555908},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5419999957084656},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4781000018119812},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.47609999775886536},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.3921000063419342},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37290000915527344},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3483000099658966},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3285999894142151},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2856000065803528},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.27549999952316284},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.26910001039505005},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.2606000006198883},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.25110000371932983}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icmew68306.2025.11152172","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmew68306.2025.11152172","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)","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":20,"referenced_works":["https://openalex.org/W2948982773","https://openalex.org/W3034314048","https://openalex.org/W3092704883","https://openalex.org/W3159648608","https://openalex.org/W3168867926","https://openalex.org/W4212919149","https://openalex.org/W4221143046","https://openalex.org/W4307079201","https://openalex.org/W4312605624","https://openalex.org/W4365460740","https://openalex.org/W4366330503","https://openalex.org/W4380994575","https://openalex.org/W4386065385","https://openalex.org/W4386351457","https://openalex.org/W4388093086","https://openalex.org/W4388093160","https://openalex.org/W4390874575","https://openalex.org/W4393158476","https://openalex.org/W4402702916","https://openalex.org/W4402754134"],"related_works":["https://openalex.org/W2806741695","https://openalex.org/W4290647774","https://openalex.org/W3189286258","https://openalex.org/W3207797160","https://openalex.org/W3210364259","https://openalex.org/W4300558037","https://openalex.org/W2667207928","https://openalex.org/W2912112202","https://openalex.org/W4377864969","https://openalex.org/W3120251014"],"abstract_inverted_index":{"Industrial":[0,90],"anomaly":[1,37,41,54,130,164],"detection":[2],"(IAD)":[3],"is":[4],"crucial":[5],"for":[6],"maintaining":[7],"product":[8],"quality":[9],"in":[10,162],"manufacturing,":[11],"but":[12],"it":[13],"faces":[14],"challenges":[15],"due":[16],"to":[17,48],"limited":[18],"data":[19],"and":[20,58,61,75,124,152,166],"diverse":[21],"defect":[22],"semantics.":[23],"Zero-shot":[24],"IAD":[25,99,154,179],"has":[26,112],"seen":[27],"rapid":[28],"development,":[29],"while":[30],"current":[31],"methods":[32],"mainly":[33],"rely":[34],"on":[35,103,148],"pixel-level":[36],"scores,":[38],"lacking":[39],"thorough":[40],"region":[42],"definition.":[43],"The":[44],"explanatory":[45],"details":[46],"related":[47],"domain":[49,114],"knowledge,":[50],"such":[51],"as":[52],"the":[53,104,178],"categories,":[55],"visual":[56,80,126,175],"semantics,":[57],"potential":[59],"causes":[60],"consequences,":[62],"are":[63],"often":[64],"overlooked.":[65],"Recently,":[66],"Large":[67],"Vision-Language":[68],"Models":[69],"(LVLMs)":[70],"have":[71],"exhibited":[72],"remarkable":[73],"perception":[74],"generalization":[76],"abilities":[77],"across":[78],"various":[79],"tasks.":[81],"In":[82],"this":[83],"paper,":[84],"we":[85],"introduce":[86],"RIASA,":[87],"a":[88,134],"Reasoning":[89],"Anomaly":[91],"Segmentation":[92],"Assistant,":[93],"which":[94],"integrates":[95],"reasoning":[96,107],"segmentation":[97,108,123,165],"into":[98],"via":[100],"LVLMs.":[101],"Building":[102],"foundation":[105],"of":[106],"framework":[109],"LISA,":[110],"RIASA":[111,158],"made":[113],"alignment":[115],"enhancements":[116],"through":[117],"instruction-supervised":[118],"fine-tuning":[119],"on:":[120],"(1)":[121],"semantic":[122],"(2)":[125],"question":[127],"answering":[128],"regarding":[129],"details.":[131],"We":[132],"construct":[133],"multi-modal":[135,170],"question-answering":[136],"instruction":[137],"dataset":[138],"using":[139],"GPT-4V,":[140],"containing":[141],"1,890":[142],"high-quality":[143],"question-answer":[144],"pairs.":[145],"Extensive":[146],"experiments":[147],"several":[149],"public":[150],"2D":[151],"3D":[153],"benchmarks":[155],"demonstrate":[156],"that":[157],"achieves":[159],"superior":[160],"performance":[161],"zero-shot":[163],"generalization.":[167],"Additionally,":[168],"RIASA\u2019s":[169],"interaction":[171],"capability":[172],"provides":[173],"professional":[174],"descriptions":[176],"within":[177],"domain.":[180]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}