{"id":"https://openalex.org/W2402272455","doi":"https://doi.org/10.1109/icassp.2016.7472179","title":"Eigen and multimodal analysis for localizing moving sounding objects","display_name":"Eigen and multimodal analysis for localizing moving sounding objects","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2402272455","doi":"https://doi.org/10.1109/icassp.2016.7472179","mag":"2402272455"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472179","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472179","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5003885291","display_name":"Shreya Khare","orcid":null},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"facility","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Shreya Khare","raw_affiliation_strings":["Indian Institute of Technology Madras, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Madras, India","institution_ids":["https://openalex.org/I24676775"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061718357","display_name":"Akshay Bhandari","orcid":"https://orcid.org/0000-0001-9684-3376"},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"facility","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Akshay Bhandari","raw_affiliation_strings":["Indian Institute of Technology Madras, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Madras, India","institution_ids":["https://openalex.org/I24676775"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032418366","display_name":"Hema A. Murthy","orcid":"https://orcid.org/0000-0003-3611-6550"},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"facility","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Hema A. Murthy","raw_affiliation_strings":["Indian Institute of Technology Madras, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Madras, India","institution_ids":["https://openalex.org/I24676775"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5003885291"],"corresponding_institution_ids":["https://openalex.org/I24676775"],"apc_list":null,"apc_paid":null,"fwci":0.2522,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.50601405,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"2757","last_page":"2761"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9994999766349792,"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":0.9994999766349792,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9990000128746033,"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/T11439","display_name":"Video Analysis and Summarization","score":0.998199999332428,"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/artificial-intelligence","display_name":"Artificial intelligence","score":0.7280101776123047},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.716774582862854},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6623175740242004},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6454464793205261},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.6276673078536987},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5938482880592346},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.4634653627872467},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45275095105171204},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.44129207730293274},{"id":"https://openalex.org/keywords/motion-analysis","display_name":"Motion analysis","score":0.4106540381908417},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.2899973392486572}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7280101776123047},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.716774582862854},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6623175740242004},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6454464793205261},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.6276673078536987},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5938482880592346},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.4634653627872467},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45275095105171204},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.44129207730293274},{"id":"https://openalex.org/C2777036941","wikidata":"https://www.wikidata.org/wiki/Q6917771","display_name":"Motion analysis","level":2,"score":0.4106540381908417},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2899973392486572},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2016.7472179","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472179","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W159595522","https://openalex.org/W290456254","https://openalex.org/W1507500984","https://openalex.org/W1591726647","https://openalex.org/W1797158261","https://openalex.org/W1987111416","https://openalex.org/W1999478155","https://openalex.org/W2025341678","https://openalex.org/W2065274193","https://openalex.org/W2081432165","https://openalex.org/W2081841744","https://openalex.org/W2090994663","https://openalex.org/W2100152238","https://openalex.org/W2105582566","https://openalex.org/W2115213191","https://openalex.org/W2118246710","https://openalex.org/W2148154194","https://openalex.org/W2164899449","https://openalex.org/W2168010845","https://openalex.org/W2170502958","https://openalex.org/W2171819471","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2349769824","https://openalex.org/W2914532148","https://openalex.org/W2372625757","https://openalex.org/W4313178214","https://openalex.org/W3093766508","https://openalex.org/W2012393389","https://openalex.org/W2970653563","https://openalex.org/W2899717399","https://openalex.org/W3165027275","https://openalex.org/W2072289174"],"abstract_inverted_index":{"This":[0],"paper":[1],"identifies":[2],"moving":[3,37,58,64,72,92],"objects":[4,38],"in":[5],"a":[6],"video":[7,22,87],"that":[8,109],"are":[9],"associated":[10],"to":[11,54,89,118],"the":[12,17,30,56,103,110,113,121],"corresponding":[13],"audio,":[14],"by":[15],"exploiting":[16],"correlation":[18,31,48],"of":[19,32,35,112,120],"audio":[20,40],"and":[21,67,97],"features.":[23],"The":[24],"proposed":[25,114],"technique":[26],"is":[27,116],"based":[28,86],"on":[29],"motion":[33],"features":[34,45],"eigen":[36,57,63,71,91],"with":[39],"mel":[41],"frequency":[42],"cepstral":[43],"coefficients":[44],"using":[46,80],"canonical":[47],"analysis.":[49],"We":[50],"propose":[51],"two":[52],"strategies":[53],"detect":[55],"objects:":[59],"(i)":[60],"Per-frame":[61],"mapped":[62],"object":[65,73],"(PFEMO)":[66],"(ii)":[68],"Temporally":[69],"coherent":[70],"(TCEMO).":[74],"While":[75],"PFEMO":[76],"segments":[77],"each":[78],"frame":[79],"superpixel":[81],"segmentation,":[82],"TCEMO":[83],"exploits":[84],"supervoxel":[85],"segmentation":[88],"identify":[90],"objects.":[93],"Qualitative":[94],"(mean-opinion":[95],"score)":[96],"quantitative":[98],"(precision,":[99],"recall,":[100],"area":[101],"under":[102],"curve,":[104],"hit":[105],"ratio)":[106],"analysis":[107],"shows":[108],"performance":[111],"techniques":[115],"superior":[117],"those":[119],"state-of-the-art":[122],"methods.":[123]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}