{"id":"https://openalex.org/W4405785573","doi":"https://doi.org/10.1109/iros58592.2024.10802429","title":"Disentangled Acoustic Fields For Multimodal Physical Scene Understanding","display_name":"Disentangled Acoustic Fields For Multimodal Physical Scene Understanding","publication_year":2024,"publication_date":"2024-10-14","ids":{"openalex":"https://openalex.org/W4405785573","doi":"https://doi.org/10.1109/iros58592.2024.10802429"},"language":"en","primary_location":{"id":"doi:10.1109/iros58592.2024.10802429","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10802429","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5005347029","display_name":"Jie Yin","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":"Jie Yin","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/A5112880088","display_name":"Andrew Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Luo","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101182304","display_name":"Yilun Du","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yilun Du","raw_affiliation_strings":["Massachusetts Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024613828","display_name":"Anoop Cherian","orcid":"https://orcid.org/0000-0002-5566-0351"},"institutions":[{"id":"https://openalex.org/I4210133125","display_name":"Mitsubishi Electric (Japan)","ror":"https://ror.org/033y26782","country_code":"JP","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Anoop Cherian","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories(MERL)"],"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories(MERL)","institution_ids":["https://openalex.org/I4210133125"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008369672","display_name":"Tim K. Marks","orcid":null},"institutions":[{"id":"https://openalex.org/I4210133125","display_name":"Mitsubishi Electric (Japan)","ror":"https://ror.org/033y26782","country_code":"JP","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tim K. Marks","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories(MERL)"],"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories(MERL)","institution_ids":["https://openalex.org/I4210133125"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064097430","display_name":"Jonathan Le Roux","orcid":"https://orcid.org/0000-0002-0158-2837"},"institutions":[{"id":"https://openalex.org/I4210133125","display_name":"Mitsubishi Electric (Japan)","ror":"https://ror.org/033y26782","country_code":"JP","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jonathan Le Roux","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories(MERL)"],"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories(MERL)","institution_ids":["https://openalex.org/I4210133125"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040877128","display_name":"Chuang Gan","orcid":"https://orcid.org/0000-0003-4031-5886"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chuang Gan","raw_affiliation_strings":["MIT-IBM AI Lab and UMass Amherst"],"affiliations":[{"raw_affiliation_string":"MIT-IBM AI Lab and UMass Amherst","institution_ids":["https://openalex.org/I24603500"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5005347029"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.375,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.61542992,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"557","last_page":"564"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9768000245094299,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9768000245094299,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9613999724388123,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.948199987411499,"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":0.6764686107635498},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.34023982286453247}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6764686107635498},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.34023982286453247}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros58592.2024.10802429","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10802429","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7599999904632568}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1969483458","https://openalex.org/W2511428026","https://openalex.org/W2619697695","https://openalex.org/W2962865004","https://openalex.org/W2962960500","https://openalex.org/W2962969419","https://openalex.org/W2963066677","https://openalex.org/W2963115079","https://openalex.org/W2963150697","https://openalex.org/W2963218389","https://openalex.org/W2963627347","https://openalex.org/W2964345931","https://openalex.org/W2989980422","https://openalex.org/W3089887959","https://openalex.org/W3108240585","https://openalex.org/W3108332675","https://openalex.org/W3108655859","https://openalex.org/W3116298410","https://openalex.org/W3154807520","https://openalex.org/W3176232375","https://openalex.org/W3201411247","https://openalex.org/W4200150166","https://openalex.org/W4285512293","https://openalex.org/W4289665794","https://openalex.org/W4297846303","https://openalex.org/W4312347618","https://openalex.org/W4312823237","https://openalex.org/W4386075904","https://openalex.org/W4401416115","https://openalex.org/W4402698362","https://openalex.org/W6640963894","https://openalex.org/W6741002519","https://openalex.org/W6753516098","https://openalex.org/W6756437543","https://openalex.org/W6763480078","https://openalex.org/W6771883515","https://openalex.org/W6780091408","https://openalex.org/W6780316881","https://openalex.org/W6780443396","https://openalex.org/W6784119104","https://openalex.org/W6796058780","https://openalex.org/W6796289742","https://openalex.org/W6801629112","https://openalex.org/W6803392726","https://openalex.org/W6810700606"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"We":[0,96,119],"study":[1],"the":[2,39,73,80,91,112,116,123,130,134],"problem":[3],"of":[4,25,61,115,136],"multimodal":[5],"physical":[6],"scene":[7],"understanding,":[8],"where":[9,90],"an":[10,26],"embodied":[11,81],"agent":[12,82],"needs":[13],"to":[14,36,44,65,71,83],"find":[15],"fallen":[16,137],"objects":[17,92,138],"by":[18,107,139],"inferring":[19],"object":[20],"properties,":[21],"direction,":[22],"and":[23,47,76,110],"distance":[24],"impact":[27],"sound":[28,74,105],"source.":[29],"Previous":[30],"works":[31],"adopt":[32],"feed-forward":[33],"neural":[34],"networks":[35],"directly":[37],"regress":[38],"variables":[40],"from":[41],"sound,":[42],"leading":[43],"poor":[45],"generalization":[46],"domain":[48],"adaptation":[49],"issues.":[50],"In":[51],"this":[52],"paper,":[53],"we":[54],"illustrate":[55],"that":[56,98,122],"learning":[57],"a":[58,85],"disentangled":[59,67,117],"model":[60],"acoustic":[62,68],"formation,":[63],"referred":[64],"as":[66],"field":[69],"(DAF),":[70],"capture":[72],"generation":[75],"propagation":[77],"process,":[78],"enables":[79],"construct":[84],"spatial":[86,124],"uncertainty":[87,125],"map":[88,126],"over":[89],"may":[93],"have":[94],"fallen.":[95],"demonstrate":[97],"our":[99],"analysis-by-synthesis":[100],"framework":[101],"can":[102,127],"jointly":[103],"infer":[104],"properties":[106],"explicitly":[108],"decomposing":[109],"factorizing":[111],"latent":[113],"space":[114],"model.":[118],"further":[120],"show":[121],"significantly":[128],"improve":[129],"success":[131],"rate":[132],"for":[133],"localization":[135],"proposing":[140],"multiple":[141],"plausible":[142],"exploration":[143],"locations.":[144]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}