{"id":"https://openalex.org/W7134933472","doi":"https://doi.org/10.1007/s11263-026-02767-6","title":"Sample-efficient Audio-Visual Learning of Scene Acoustics","display_name":"Sample-efficient Audio-Visual Learning of Scene Acoustics","publication_year":2026,"publication_date":"2026-03-11","ids":{"openalex":"https://openalex.org/W7134933472","doi":"https://doi.org/10.1007/s11263-026-02767-6"},"language":"en","primary_location":{"id":"doi:10.1007/s11263-026-02767-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-026-02767-6","pdf_url":null,"source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1007/s11263-026-02767-6","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056056745","display_name":"Arjun Somayazulu","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Arjun Somayazulu","raw_affiliation_strings":["University of Texas at Austin, Austin, United States"],"raw_orcid":"https://orcid.org/0009-0005-1647-298X","affiliations":[{"raw_affiliation_string":"University of Texas at Austin, Austin, United States","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064099733","display_name":"Sagnik Majumder","orcid":"https://orcid.org/0000-0002-2851-1510"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sagnik Majumder","raw_affiliation_strings":["University of Texas at Austin, Austin, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Austin, Austin, United States","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127791337","display_name":"Changan Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Changan Chen","raw_affiliation_strings":["University of Texas at Austin, Austin, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Austin, Austin, United States","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128692702","display_name":"Ziad Al-Halah","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ziad Al-Halah","raw_affiliation_strings":["University of Texas at Austin, Austin, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Austin, Austin, United States","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5128728391","display_name":"Kristen Grauman","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kristen Grauman","raw_affiliation_strings":["University of Texas at Austin, Austin, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Austin, Austin, United States","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5056056745"],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":{"value":3690,"currency":"USD","value_usd":3690},"apc_paid":{"value":3690,"currency":"USD","value_usd":3690},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.27734899,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"134","issue":"4","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.6195999979972839,"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":0.6195999979972839,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.056699998676776886,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.053300000727176666,"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/rendering","display_name":"Rendering (computer graphics)","score":0.7251999974250793},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4767000079154968},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4377000033855438},{"id":"https://openalex.org/keywords/impulse-response","display_name":"Impulse response","score":0.4180999994277954},{"id":"https://openalex.org/keywords/room-acoustics","display_name":"Room acoustics","score":0.4081000089645386},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4043999910354614},{"id":"https://openalex.org/keywords/mobile-device","display_name":"Mobile device","score":0.39500001072883606}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7973999977111816},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.7251999974250793},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4878000020980835},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4767000079154968},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4431999921798706},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4377000033855438},{"id":"https://openalex.org/C72279823","wikidata":"https://www.wikidata.org/wiki/Q1139726","display_name":"Impulse response","level":2,"score":0.4180999994277954},{"id":"https://openalex.org/C178432105","wikidata":"https://www.wikidata.org/wiki/Q2182127","display_name":"Room acoustics","level":3,"score":0.4081000089645386},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4043999910354614},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.39500001072883606},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.37459999322891235},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.36169999837875366},{"id":"https://openalex.org/C70836080","wikidata":"https://www.wikidata.org/wiki/Q837940","display_name":"Impulse (physics)","level":2,"score":0.3479999899864197},{"id":"https://openalex.org/C2776009117","wikidata":"https://www.wikidata.org/wiki/Q2305951","display_name":"Architectural acoustics","level":3,"score":0.29989999532699585},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.295199990272522},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.2824000120162964},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.25220000743865967},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.25189998745918274}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s11263-026-02767-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-026-02767-6","pdf_url":null,"source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s11263-026-02767-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-026-02767-6","pdf_url":null,"source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":66,"referenced_works":["https://openalex.org/W1559975096","https://openalex.org/W1901129140","https://openalex.org/W1950843348","https://openalex.org/W1988526405","https://openalex.org/W2034314942","https://openalex.org/W2052666245","https://openalex.org/W2098950531","https://openalex.org/W2112261915","https://openalex.org/W2117678320","https://openalex.org/W2128141288","https://openalex.org/W2137123220","https://openalex.org/W2194775991","https://openalex.org/W2410879554","https://openalex.org/W2551677029","https://openalex.org/W2788241093","https://openalex.org/W2810259310","https://openalex.org/W2898519127","https://openalex.org/W2900429685","https://openalex.org/W2911483584","https://openalex.org/W2962960500","https://openalex.org/W2963680395","https://openalex.org/W2964171275","https://openalex.org/W2964339842","https://openalex.org/W2965390715","https://openalex.org/W2966966150","https://openalex.org/W2981851635","https://openalex.org/W2981905048","https://openalex.org/W2982624843","https://openalex.org/W3009928773","https://openalex.org/W3026094182","https://openalex.org/W3089887959","https://openalex.org/W3089944088","https://openalex.org/W3096780661","https://openalex.org/W3097930518","https://openalex.org/W3108332675","https://openalex.org/W3108655859","https://openalex.org/W3109585842","https://openalex.org/W3110885542","https://openalex.org/W3116298410","https://openalex.org/W3121594710","https://openalex.org/W3136499730","https://openalex.org/W3139813613","https://openalex.org/W3168060631","https://openalex.org/W3172944499","https://openalex.org/W3174854700","https://openalex.org/W3176232375","https://openalex.org/W3198454118","https://openalex.org/W3202387331","https://openalex.org/W3206257526","https://openalex.org/W4214681287","https://openalex.org/W4214759869","https://openalex.org/W4226373941","https://openalex.org/W4281264304","https://openalex.org/W4289665794","https://openalex.org/W4312356258","https://openalex.org/W4312498304","https://openalex.org/W4312779270","https://openalex.org/W4372348432","https://openalex.org/W4385767322","https://openalex.org/W4386076216","https://openalex.org/W4389666183","https://openalex.org/W4390590981","https://openalex.org/W4390872419","https://openalex.org/W4394805515","https://openalex.org/W4402716236","https://openalex.org/W7133238248"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"An":[1],"environment":[2,130,165],"acoustic":[3,89,116,131,155,222],"model":[4,132],"represents":[5],"how":[6,41,64],"sound":[7,34],"is":[8],"transformed":[9],"by":[10,104],"the":[11,37,59,93,129,163,177],"physical":[12,106],"characteristics":[13],"of":[14,53,95],"an":[15,204],"indoor":[16,172],"environment,":[17,38],"for":[18,26,162],"any":[19],"given":[20,211],"source/receiver":[21],"location.":[22],"Whereas":[23],"traditional":[24,184,217],"methods":[25],"constructing":[27],"such":[28],"models":[29],"assume":[30],"dense":[31],"geometry":[32],"and/or":[33],"measurements":[35],"throughout":[36],"we":[39,76,112],"explore":[40],"to":[42,65,68,85,186,207],"infer":[43],"room":[44],"impulse":[45],"responses":[46],"(RIRs)":[47],"based":[48],"on":[49,168],"a":[50,79,87,119,124,144,180,190],"sparse":[51,139],"set":[52],"images":[54],"and":[55,133,220],"echoes":[56],"observed":[57],"in":[58,108,122,189],"space,":[60],"as":[61,63],"well":[62],"choose":[66],"where":[67],"collect":[69],"these":[70,110],"audio-visual":[71,140],"observations.":[72,141],"Towards":[73],"that":[74,82,149],"goal,":[75],"first":[77],"introduce":[78,114],"transformer-based":[80],"method":[81,175],"uses":[83],"self-attention":[84],"build":[86],"rich":[88],"context,":[90],"then":[91],"infers":[92],"RIRs":[94],"arbitrary":[96],"query":[97],"source-receiver":[98],"locations":[99],"through":[100],"cross-attention.":[101],"Then,":[102],"motivated":[103],"real-world":[105,212],"constraints":[107],"collecting":[109],"observations,":[111],"further":[113],"active":[115,198],"sampling":[117,157,199],",":[118],"new":[120],"task":[121],"which":[123],"mobile":[125],"agent":[126,151,206],"jointly":[127],"constructs":[128],"spatial":[134],"occupancy":[135],"map":[136],"on-the-fly":[137],"from":[138,183],"We":[142],"train":[143],"reinforcement":[145],"learning":[146],"(RL)":[147],"policy":[148],"guides":[150,203],"navigation":[152,218],"toward":[153],"optimal":[154],"data":[156],"positions,":[158],"rewarding":[159],"information":[160],"gain":[161],"full":[164],"model.":[166],"Evaluating":[167],"diverse":[169],"unseen":[170],"3D":[171],"environments,":[173],"our":[174,197],"outperforms":[176],"state-of-the-art":[178],"and\u2014in":[179],"major":[181],"departure":[182],"methods\u2014generalizes":[185],"novel":[187],"environments":[188],"few-shot":[191],"manner.":[192],"Furthermore,":[193],"when":[194],"augmented":[195],"with":[196],"policy,":[200],"it":[201],"successfully":[202],"embodied":[205],"acoustically":[208],"informative":[209],"positions":[210],"exploration":[213],"constraints,":[214],"outperforming":[215],"both":[216],"agents":[219],"prior":[221],"rendering":[223],"methods.":[224],"Project:":[225],"http://vision.cs.utexas.edu/projects/fewShot-RIR":[226],".":[227]},"counts_by_year":[],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2026-03-12T00:00:00"}