{"id":"https://openalex.org/W4411553096","doi":"https://doi.org/10.1145/3733566.3734430","title":"Towards Integrated Multimodal Interaction: Merging Immersive 3D Worlds with Language Based Retrieval for 3D Scene Understanding","display_name":"Towards Integrated Multimodal Interaction: Merging Immersive 3D Worlds with Language Based Retrieval for 3D Scene Understanding","publication_year":2025,"publication_date":"2025-06-23","ids":{"openalex":"https://openalex.org/W4411553096","doi":"https://doi.org/10.1145/3733566.3734430"},"language":"en","primary_location":{"id":"doi:10.1145/3733566.3734430","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3733566.3734430","pdf_url":null,"source":null,"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 6th Workshop on Intelligent Cross-Data Analysis and Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3733566.3734430","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042165813","display_name":"Shawn Bowser","orcid":null},"institutions":[{"id":"https://openalex.org/I166416128","display_name":"DEVCOM Army Research Laboratory","ror":"https://ror.org/011hc8f90","country_code":"US","type":"government","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I166416128","https://openalex.org/I2802705668","https://openalex.org/I4210154437"]},{"id":"https://openalex.org/I2802705668","display_name":"United States Army Combat Capabilities Development Command","ror":"https://ror.org/02rdkx920","country_code":"US","type":"other","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I2802705668","https://openalex.org/I4210154437"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Shawn Bowser","raw_affiliation_strings":["DEVCOM Army Research Laboratory, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"DEVCOM Army Research Laboratory, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I166416128","https://openalex.org/I2802705668"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019767181","display_name":"Cynthia Matuszek","orcid":"https://orcid.org/0000-0003-1383-8120"},"institutions":[{"id":"https://openalex.org/I126744593","display_name":"University of Maryland, Baltimore","ror":"https://ror.org/04rq5mt64","country_code":"US","type":"education","lineage":["https://openalex.org/I126744593"]},{"id":"https://openalex.org/I79272384","display_name":"University of Maryland, Baltimore County","ror":"https://ror.org/02qskvh78","country_code":"US","type":"education","lineage":["https://openalex.org/I79272384"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cynthia Matuszek","raw_affiliation_strings":["University of Maryland, Baltimore, County Baltimore, MD, USA"],"affiliations":[{"raw_affiliation_string":"University of Maryland, Baltimore, County Baltimore, MD, USA","institution_ids":["https://openalex.org/I79272384","https://openalex.org/I126744593"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053316502","display_name":"Stephanie M. Lukin","orcid":"https://orcid.org/0000-0001-8761-167X"},"institutions":[{"id":"https://openalex.org/I166416128","display_name":"DEVCOM Army Research Laboratory","ror":"https://ror.org/011hc8f90","country_code":"US","type":"government","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I166416128","https://openalex.org/I2802705668","https://openalex.org/I4210154437"]},{"id":"https://openalex.org/I2802705668","display_name":"United States Army Combat Capabilities Development Command","ror":"https://ror.org/02rdkx920","country_code":"US","type":"other","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I2802705668","https://openalex.org/I4210154437"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stephanie Lukin","raw_affiliation_strings":["DEVCOM Army Research Laboratory, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"DEVCOM Army Research Laboratory, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I166416128","https://openalex.org/I2802705668"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5042165813"],"corresponding_institution_ids":["https://openalex.org/I166416128","https://openalex.org/I2802705668"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16157315,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"32","last_page":"37"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.998199999332428,"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"}},"topics":[{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.998199999332428,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9966999888420105,"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/T12031","display_name":"Speech and dialogue systems","score":0.9950000047683716,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7828167080879211},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.46454572677612305},{"id":"https://openalex.org/keywords/multimodal-interaction","display_name":"Multimodal interaction","score":0.44324856996536255},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43353524804115295},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.32357460260391235}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7828167080879211},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.46454572677612305},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.44324856996536255},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43353524804115295},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32357460260391235}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3733566.3734430","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3733566.3734430","pdf_url":null,"source":null,"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 6th Workshop on Intelligent Cross-Data Analysis and Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3733566.3734430","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3733566.3734430","pdf_url":null,"source":null,"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 6th Workshop on Intelligent Cross-Data Analysis and Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5400000214576721}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2133585725","https://openalex.org/W2902857859","https://openalex.org/W2964487155","https://openalex.org/W2970641574","https://openalex.org/W4236965008","https://openalex.org/W4385318467","https://openalex.org/W4392633877","https://openalex.org/W4402716423","https://openalex.org/W4402772489","https://openalex.org/W4402776116","https://openalex.org/W4403706477","https://openalex.org/W4404781309"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"We":[0,36,62],"propose":[1],"a":[2,43,88,101,117],"novel":[3,89],"multimodal":[4],"interactive":[5],"system":[6],"for":[7,13,24,91,139,157],"3D":[8,34,102,106],"scene":[9,56,103],"understanding":[10,57],"and":[11,16,58,75,96,126,137,152],"question-answering":[12],"disaster":[14],"scenarios":[15],"related":[17],"tasks.":[18],"Our":[19],"approach":[20],"creates":[21],"open-domain":[22],"annotations":[23],"arbitrary":[25],"RGB":[26],"image":[27],"sequences,":[28],"enabling":[29],"natural":[30,133],"language-based":[31],"retrieval":[32],"of":[33,66],"scenes.":[35],"incorporate":[37],"an":[38],"automated":[39],"evaluation":[40],"strategy":[41],"using":[42,132],"vision-language":[44],"model":[45],"(VLM)":[46],"to":[47,93,166],"identify":[48],"temporal":[49],"differences":[50],"between":[51],"two":[52],"scenes,":[53,71],"significantly":[54],"increasing":[55],"same-place":[59],"recognition":[60],"accuracy.":[61],"demonstrate":[63],"the":[64,124,150],"robustness":[65],"our":[67,81],"method":[68,82,151],"on":[69,116],"dynamic":[70],"including":[72],"indoor":[73],"environments":[74],"real-world":[76],"disasters.":[77],"Finally,":[78],"we":[79],"test":[80],"within":[83],"human-agent":[84],"collaboration":[85],"by":[86],"designing":[87],"interface":[90,154],"users":[92],"ask":[94],"questions":[95],"retrieve":[97],"visual":[98,130],"evidence":[99,131],"from":[100],"rendered":[104],"with":[105,123,141],"Gaussian":[107],"Splatting":[108],"(3DGS)":[109],"as":[110,112],"well":[111],"navigate":[113],"through":[114],"it":[115],"desktop.":[118],"Users":[119],"were":[120],"highly":[121],"engaged":[122],"interface,":[125],"succeeded":[127],"in":[128,146],"providing":[129],"language":[134],"based":[135],"queries":[136],"navigation":[138],"tasks":[140],"properties":[142],"that":[143,163],"may":[144],"appear":[145],"emergency":[147,160],"responses.":[148],"Both":[149],"task-based":[153],"lay":[155],"foundations":[156],"more":[158],"resilient":[159],"management":[161],"technologies":[162],"can":[164],"adapt":[165],"rapidly":[167],"changing":[168],"environments.":[169]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}