{"id":"https://openalex.org/W4417289319","doi":"https://doi.org/10.1109/wacv61042.2026.00135","title":"Explaining the Unseen: Multimodal Vision-Language Reasoning for Situational Awareness in Underground Mining Disasters","display_name":"Explaining the Unseen: Multimodal Vision-Language Reasoning for Situational Awareness in Underground Mining Disasters","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W4417289319","doi":"https://doi.org/10.1109/wacv61042.2026.00135"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00135","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00135","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2512.09092","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114761467","display_name":"Mizanur Rahman Jewel","orcid":null},"institutions":[{"id":"https://openalex.org/I20382870","display_name":"Missouri University of Science and Technology","ror":"https://ror.org/00scwqd12","country_code":"US","type":"education","lineage":["https://openalex.org/I20382870"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mizanur Rahman Jewel","raw_affiliation_strings":["Missouri University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Missouri University of Science and Technology","institution_ids":["https://openalex.org/I20382870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052668861","display_name":"Mohamed Elmahallawy","orcid":null},"institutions":[{"id":"https://openalex.org/I72951846","display_name":"Washington State University","ror":"https://ror.org/05dk0ce17","country_code":"US","type":"education","lineage":["https://openalex.org/I72951846"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohamed Elmahallawy","raw_affiliation_strings":["Washington State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Washington State University","institution_ids":["https://openalex.org/I72951846"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012569039","display_name":"Sanjay Madria","orcid":"https://orcid.org/0000-0002-2768-3660"},"institutions":[{"id":"https://openalex.org/I20382870","display_name":"Missouri University of Science and Technology","ror":"https://ror.org/00scwqd12","country_code":"US","type":"education","lineage":["https://openalex.org/I20382870"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanjay Madria","raw_affiliation_strings":["Missouri University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Missouri University of Science and Technology","institution_ids":["https://openalex.org/I20382870"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090136374","display_name":"Samuel Frimpong","orcid":"https://orcid.org/0000-0002-8300-6824"},"institutions":[{"id":"https://openalex.org/I20382870","display_name":"Missouri University of Science and Technology","ror":"https://ror.org/00scwqd12","country_code":"US","type":"education","lineage":["https://openalex.org/I20382870"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Samuel Frimpong","raw_affiliation_strings":["Missouri University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Missouri University of Science and Technology","institution_ids":["https://openalex.org/I20382870"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.03144474,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1324","last_page":"1333"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9706000089645386,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9706000089645386,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.00570000009611249,"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":0.0019000000320374966,"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/situation-awareness","display_name":"Situation awareness","score":0.8406000137329102},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.6482999920845032},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5241000056266785},{"id":"https://openalex.org/keywords/situational-ethics","display_name":"Situational ethics","score":0.515999972820282},{"id":"https://openalex.org/keywords/emergency-management","display_name":"Emergency management","score":0.4259999990463257},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.3959999978542328},{"id":"https://openalex.org/keywords/language-understanding","display_name":"Language understanding","score":0.38179999589920044}],"concepts":[{"id":"https://openalex.org/C145804949","wikidata":"https://www.wikidata.org/wiki/Q478123","display_name":"Situation awareness","level":2,"score":0.8406000137329102},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6499000191688538},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.6482999920845032},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5241000056266785},{"id":"https://openalex.org/C9114305","wikidata":"https://www.wikidata.org/wiki/Q1428317","display_name":"Situational ethics","level":2,"score":0.515999972820282},{"id":"https://openalex.org/C62555980","wikidata":"https://www.wikidata.org/wiki/Q1460420","display_name":"Emergency management","level":2,"score":0.4259999990463257},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4253000020980835},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3959999978542328},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.38179999589920044},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3785000145435333},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33820000290870667},{"id":"https://openalex.org/C3018653863","wikidata":"https://www.wikidata.org/wiki/Q5281355","display_name":"Disaster response","level":3,"score":0.3239000141620636},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3091000020503998},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.3066999912261963},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3021000027656555},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.3012000024318695},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2957000136375427},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.2632000148296356},{"id":"https://openalex.org/C14911803","wikidata":"https://www.wikidata.org/wiki/Q7532148","display_name":"Situation analysis","level":2,"score":0.262800008058548},{"id":"https://openalex.org/C2777877512","wikidata":"https://www.wikidata.org/wiki/Q1116097","display_name":"Common ground","level":2,"score":0.26080000400543213},{"id":"https://openalex.org/C95713431","wikidata":"https://www.wikidata.org/wiki/Q631425","display_name":"Vulnerability (computing)","level":2,"score":0.2583000063896179}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/wacv61042.2026.00135","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00135","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2512.09092","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.09092","pdf_url":"https://arxiv.org/pdf/2512.09092","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2512.09092","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.09092","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"pmh:oai:arXiv.org:2512.09092","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.09092","pdf_url":"https://arxiv.org/pdf/2512.09092","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"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":{"Underground":[0,98],"mining":[1],"disasters":[2],"produce":[3],"pervasive":[4],"darkness,":[5],"dust,":[6],"and":[7,12,19,58,74,77,113,119,133],"collapses":[8],"that":[9,36,71,123,137],"obscure":[10],"vision":[11],"make":[13],"situational":[14,145],"awareness":[15,146],"difficult":[16],"for":[17,53,83,147],"humans":[18],"conventional":[20],"systems.":[21],"To":[22,91],"address":[23],"this,":[24],"we":[25,95],"propose":[26],"MDSE,":[27],"Multimodal":[28],"Disaster":[29,100],"Situation":[30],"Explainer,":[31],"a":[32],"novel":[33],"vision-language":[34],"framework":[35],"automatically":[37],"generates":[38],"detailed":[39],"textual":[40,59],"explanations":[41],"of":[42,56,106],"post-disaster":[43],"underground":[44,108,148],"scenes.":[45],"MDSE":[46,124],"has":[47],"three-fold":[48],"innovations:":[49],"(i)":[50],"Context-Aware":[51],"Cross-Attention":[52],"robust":[54],"alignment":[55],"visual":[57,69],"features":[60],"even":[61],"under":[62],"severe":[63],"degradation;":[64],"(ii)":[65],"Segmentation-aware":[66],"dual":[67],"pathway":[68],"encoding":[70],"fuses":[72],"global":[73],"region-specific":[75],"embeddings;":[76],"(iii)":[78],"Resource-Efficient":[79],"Transformer-Based":[80],"Language":[81],"Model":[82],"expressive":[84],"caption":[85],"generation":[86],"with":[87],"minimal":[88],"compute":[89],"cost.":[90],"support":[92],"this":[93],"task,":[94],"present":[96],"the":[97],"Mine":[99],"(UMD)":[101],"dataset\u2014the":[102],"first":[103],"image\u2013caption":[104],"corpus":[105],"real":[107],"disaster":[109],"scenes\u2014enabling":[110],"rigorous":[111],"training":[112],"evaluation.":[114],"Extensive":[115],"experiments":[116],"on":[117],"UMD":[118],"related":[120],"benchmarks":[121],"show":[122],"substantially":[125],"outperforms":[126],"state-of-the-art":[127],"captioning":[128],"models,":[129],"producing":[130],"more":[131],"accurate":[132],"contextually":[134],"relevant":[135],"descriptions":[136],"capture":[138],"crucial":[139],"details":[140],"in":[141],"obscured":[142],"environments,":[143],"improving":[144],"emergency":[149],"response.":[150],"The":[151],"code":[152],"is":[153],"at":[154],"Github.":[155]},"counts_by_year":[],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-12-12T00:00:00"}