{"id":"https://openalex.org/W7162313882","doi":"https://doi.org/10.48550/arxiv.2605.23304","title":"General Hazard Detection","display_name":"General Hazard Detection","publication_year":2026,"publication_date":"2026-05-22","ids":{"openalex":"https://openalex.org/W7162313882","doi":"https://doi.org/10.48550/arxiv.2605.23304"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.23304","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.23304","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.23304","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136976131","display_name":"Stephanie Ng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ng, Stephanie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136899726","display_name":"CP Lim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lim, CP","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136950174","display_name":"SueJen Looi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Looi, SueJen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053372432","display_name":"Hendrik Zurlinden","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zurlinden, Hendrik","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136931867","display_name":"David Nguyen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nguyen, David","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136918955","display_name":"Lei Wei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei, Lei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015293969","display_name":"Saeid Nahavandi","orcid":"https://orcid.org/0000-0002-0360-5270"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nahavandi, Saeid","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5018875718","display_name":"Hailing Zhou","orcid":"https://orcid.org/0000-0001-5009-4330"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Hailing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.5595999956130981,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.5595999956130981,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.08919999748468399,"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/T10809","display_name":"Occupational Health and Safety Research","score":0.0731000006198883,"subfield":{"id":"https://openalex.org/subfields/3614","display_name":"Radiological and Ultrasound Technology"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/hazard","display_name":"Hazard","score":0.7138000130653381},{"id":"https://openalex.org/keywords/decoupling","display_name":"Decoupling (probability)","score":0.46939998865127563},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.46650001406669617},{"id":"https://openalex.org/keywords/hazard-analysis","display_name":"Hazard analysis","score":0.4336000084877014},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.42489999532699585},{"id":"https://openalex.org/keywords/system-safety","display_name":"System safety","score":0.3750999867916107}],"concepts":[{"id":"https://openalex.org/C49261128","wikidata":"https://www.wikidata.org/wiki/Q1132455","display_name":"Hazard","level":2,"score":0.7138000130653381},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6017000079154968},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5220000147819519},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.46939998865127563},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.46650001406669617},{"id":"https://openalex.org/C206355099","wikidata":"https://www.wikidata.org/wiki/Q3614972","display_name":"Hazard analysis","level":2,"score":0.4336000084877014},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.42489999532699585},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.4020000100135803},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3785000145435333},{"id":"https://openalex.org/C132835097","wikidata":"https://www.wikidata.org/wiki/Q7663745","display_name":"System safety","level":2,"score":0.3750999867916107},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3691999912261963},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33059999346733093},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.26260000467300415},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.26190000772476196},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.25999999046325684}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.23304","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.23304","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.23304","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.23304","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Hazard,":[0],"as":[1],"an":[2,177],"abstract":[3,47],"concept,":[4],"is":[5,105],"typically":[6],"defined":[7],"through":[8,117],"cognitive-level":[9],"logical":[10],"reasoning":[11,226],"rather":[12],"than":[13],"concrete":[14],"examples.":[15],"In":[16],"contrast,":[17],"existing":[18],"hazard":[19,25,87,100,108,134,191,215],"detection":[20,35,216],"systems":[21],"rely":[22],"on":[23],"predefined":[24],"categories":[26],"and":[27,52,64,66,128,148,185],"require":[28],"intensive":[29],"collection":[30],"of":[31],"labelled":[32],"examples":[33,112],"within":[34],"or":[36,72],"classification":[37],"architectures.":[38],"This":[39],"approach":[40,123],"faces":[41],"three":[42],"fundamental":[43],"challenges":[44],"when":[45],"addressing":[46],"safety":[48,115,159,209],"concepts:":[49],"(1)":[50],"noisy":[51],"sparse":[53],"training":[54],"data,":[55],"(2)":[56],"dynamically":[57],"evolving":[58],"definitions":[59],"that":[60],"change":[61],"across":[62,136],"contexts":[63],"time,":[65],"(3)":[67],"limited":[68],"generalisation":[69],"to":[70,131,181,218],"unseen":[71],"novel":[73],"scenarios.":[74],"To":[75,171],"address":[76,219],"these":[77],"limitations,":[78],"we":[79,175],"present":[80],"the":[81,84,107,167,202],"CompliVision":[82,140],"dataset,":[83],"first":[85],"general-purpose":[86],"dataset":[88,141],"designed":[89],"for":[90,99,155,207],"rule-based":[91],"compliance":[92,156],"assessment,":[93],"along":[94],"with":[95,151,201,227,228],"a":[96,213],"baseline":[97],"framework":[98,180,217],"evaluation.":[101],"Our":[102],"key":[103],"innovation":[104],"decoupling":[106],"concept":[109],"from":[110],"image-based":[111],"by":[113,162],"expressing":[114],"requirements":[116],"language-based":[118],"rules.":[119],"We":[120,211],"ground":[121],"our":[122],"in":[124,189],"authoritative":[125],"domain":[126],"regulations":[127],"ISO":[129],"standards":[130],"define":[132],"diverse":[133],"concepts":[135],"multiple":[137],"domains.":[138],"The":[139],"comprises":[142],"3,006":[143],"images":[144],"spanning":[145],"traffic,":[146],"construction,":[147],"warehouse":[149],"environments,":[150],"each":[152],"image":[153],"annotated":[154],"against":[157],"specific":[158],"rules,":[160],"accompanied":[161],"natural":[163],"language":[164],"explanations":[165],"highlighting":[166],"supporting":[168],"visual":[169,225],"evidence.":[170],"achieve":[172],"robust":[173],"generalisation,":[174],"develop":[176],"active":[178],"learning":[179],"more":[182],"effectively":[183],"guide":[184],"refine":[186],"vision-language":[187],"models":[188],"assessing":[190],"compliance.":[192],"While":[193],"state-of-the-art":[194],"VLMs":[195],"demonstrate":[196],"strong":[197],"capabilities,":[198],"they":[199],"struggle":[200],"fine-grained,":[203],"context-dependent":[204],"interpretation":[205],"required":[206],"accurate":[208],"assessment.":[210],"proposed":[212],"general":[214],"this":[220],"limitation":[221],"which":[222],"combines":[223],"LLaVA-based":[224],"human-in-the-loop":[229],"feedback.":[230]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-26T00:00:00"}