{"id":"https://openalex.org/W3005427955","doi":"https://doi.org/10.1109/icassp40776.2020.9054690","title":"Audio-Visual Calibration with Polynomial Regression for 2-D Projection Using SVD-PHAT","display_name":"Audio-Visual Calibration with Polynomial Regression for 2-D Projection Using SVD-PHAT","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3005427955","doi":"https://doi.org/10.1109/icassp40776.2020.9054690","mag":"3005427955"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054690","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054690","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2002.01440","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045901453","display_name":"Fran\u00e7ois Grondin","orcid":"https://orcid.org/0000-0002-0563-4251"},"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":true,"raw_author_name":"Francois Grondin","raw_affiliation_strings":["Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA","Massachusetts Institute of Technology,Computer Science & Artificial Intelligence Laboratory,Cambridge,MA,USA,02139"],"affiliations":[{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Massachusetts Institute of Technology,Computer Science & Artificial Intelligence Laboratory,Cambridge,MA,USA,02139","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100662192","display_name":"Hao Tang","orcid":"https://orcid.org/0000-0002-6877-0226"},"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":"Hao Tang","raw_affiliation_strings":["Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA","Massachusetts Institute of Technology,Computer Science & Artificial Intelligence Laboratory,Cambridge,MA,USA,02139"],"affiliations":[{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Massachusetts Institute of Technology,Computer Science & Artificial Intelligence Laboratory,Cambridge,MA,USA,02139","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112758056","display_name":"James Glass","orcid":"https://orcid.org/0000-0002-3097-360X"},"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":"James Glass","raw_affiliation_strings":["Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA","Massachusetts Institute Of Technology#TAB#"],"affiliations":[{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Massachusetts Institute Of Technology#TAB#","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5045901453"],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":0.1524,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.39540666,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"7443","issue":null,"first_page":"4856","last_page":"4860"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.996399998664856,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.994700014591217,"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/computer-science","display_name":"Computer science","score":0.6315634250640869},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.584496796131134},{"id":"https://openalex.org/keywords/projection","display_name":"Projection (relational algebra)","score":0.5838603973388672},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5774064660072327},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5677648186683655},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5008318424224854},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.49431347846984863},{"id":"https://openalex.org/keywords/polynomial","display_name":"Polynomial","score":0.48679158091545105},{"id":"https://openalex.org/keywords/calibration","display_name":"Calibration","score":0.4371107518672943},{"id":"https://openalex.org/keywords/singular-value-decomposition","display_name":"Singular value decomposition","score":0.41845205426216125},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.26271307468414307},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21179533004760742},{"id":"https://openalex.org/keywords/sound-pressure","display_name":"Sound pressure","score":0.09886690974235535}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6315634250640869},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.584496796131134},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.5838603973388672},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5774064660072327},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5677648186683655},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5008318424224854},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.49431347846984863},{"id":"https://openalex.org/C90119067","wikidata":"https://www.wikidata.org/wiki/Q43260","display_name":"Polynomial","level":2,"score":0.48679158091545105},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.4371107518672943},{"id":"https://openalex.org/C22789450","wikidata":"https://www.wikidata.org/wiki/Q420904","display_name":"Singular value decomposition","level":2,"score":0.41845205426216125},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26271307468414307},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21179533004760742},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.09886690974235535},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054690","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054690","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2002.01440","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2002.01440","pdf_url":"https://arxiv.org/pdf/2002.01440","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3005427955","is_oa":true,"landing_page_url":"http://arxiv.org/pdf/2002.01440.pdf","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2002.01440","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2002.01440","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":"article"},{"id":"doi:10.17023/c1yw-x078","is_oa":true,"landing_page_url":"https://doi.org/10.17023/c1yw-x078","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2002.01440","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2002.01440","pdf_url":"https://arxiv.org/pdf/2002.01440","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3005427955.pdf","grobid_xml":"https://content.openalex.org/works/W3005427955.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W1555217905","https://openalex.org/W2054852564","https://openalex.org/W2076462394","https://openalex.org/W2084637638","https://openalex.org/W2102767076","https://openalex.org/W2113638573","https://openalex.org/W2120275602","https://openalex.org/W2150678643","https://openalex.org/W2151227854","https://openalex.org/W2289480995","https://openalex.org/W2410809048","https://openalex.org/W2903420265","https://openalex.org/W2914926710","https://openalex.org/W2921997986","https://openalex.org/W2962946733","https://openalex.org/W2963058659","https://openalex.org/W2972395415","https://openalex.org/W3123318516","https://openalex.org/W4289665794","https://openalex.org/W6678053734","https://openalex.org/W6760606803"],"related_works":["https://openalex.org/W3015877553","https://openalex.org/W2011789996","https://openalex.org/W2114976455","https://openalex.org/W2156954690","https://openalex.org/W2137192709","https://openalex.org/W1969299255","https://openalex.org/W2131669377","https://openalex.org/W2127386624","https://openalex.org/W1981607703","https://openalex.org/W2515217432","https://openalex.org/W2272108674","https://openalex.org/W3176928964","https://openalex.org/W2149498121","https://openalex.org/W2200782450","https://openalex.org/W2247271586","https://openalex.org/W1776993573","https://openalex.org/W2537586743","https://openalex.org/W1998316398","https://openalex.org/W2158412868","https://openalex.org/W2063708263"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,14,36,58],"straightforward":[4],"2-D":[5],"method":[6,64],"to":[7],"spatially":[8],"calibrate":[9],"the":[10,17],"visual":[11],"field":[12,19],"of":[13,20],"camera":[15,54],"with":[16,52],"auditory":[18],"an":[21,28,32,41],"array":[22,39],"microphone":[23,38],"by":[24],"generating":[25],"and":[26,40,56],"overlaying":[27],"acoustic":[29],"image":[30],"over":[31],"optical":[33],"image.":[34],"Using":[35],"low-cost":[37],"off-the-shelf":[42],"camera,":[43],"we":[44],"show":[45],"that":[46,57],"polynomial":[47],"regression":[48],"can":[49,69],"deal":[50],"efficiently":[51],"non-linear":[53],"distortion,":[55],"recently":[59],"proposed":[60],"sound":[61],"source":[62],"localization":[63],"for":[65,72],"real-time":[66],"processing,":[67],"SVD-PHAT,":[68],"be":[70],"adapted":[71],"this":[73],"task.":[74]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
