{"id":"https://openalex.org/W4372259812","doi":"https://doi.org/10.1109/icassp49357.2023.10094965","title":"Flowgrad: Using Motion for Visual Sound Source Localization","display_name":"Flowgrad: Using Motion for Visual Sound Source Localization","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372259812","doi":"https://doi.org/10.1109/icassp49357.2023.10094965"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10094965","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10094965","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5019039668","display_name":"Rajsuryan Singh","orcid":"https://orcid.org/0009-0002-7962-6462"},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Pompeu Fabra University","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Rajsuryan Singh","raw_affiliation_strings":["Universitat Pompeu Fabra,MTG,Barcelona,Spain","MTG, Universitat Pompeu Fabra, Barcelona, Spain"],"affiliations":[{"raw_affiliation_string":"Universitat Pompeu Fabra,MTG,Barcelona,Spain","institution_ids":["https://openalex.org/I170486558"]},{"raw_affiliation_string":"MTG, Universitat Pompeu Fabra, Barcelona, Spain","institution_ids":["https://openalex.org/I170486558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075959503","display_name":"Pablo Zinemanas","orcid":"https://orcid.org/0000-0002-9372-730X"},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Pompeu Fabra University","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Pablo Zinemanas","raw_affiliation_strings":["Universitat Pompeu Fabra,MTG,Barcelona,Spain","MTG, Universitat Pompeu Fabra, Barcelona, Spain"],"affiliations":[{"raw_affiliation_string":"Universitat Pompeu Fabra,MTG,Barcelona,Spain","institution_ids":["https://openalex.org/I170486558"]},{"raw_affiliation_string":"MTG, Universitat Pompeu Fabra, Barcelona, Spain","institution_ids":["https://openalex.org/I170486558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006479715","display_name":"Xavier Serra","orcid":"https://orcid.org/0000-0003-1395-2345"},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Pompeu Fabra University","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Xavier Serra","raw_affiliation_strings":["Universitat Pompeu Fabra,MTG,Barcelona,Spain","MTG, Universitat Pompeu Fabra, Barcelona, Spain"],"affiliations":[{"raw_affiliation_string":"Universitat Pompeu Fabra,MTG,Barcelona,Spain","institution_ids":["https://openalex.org/I170486558"]},{"raw_affiliation_string":"MTG, Universitat Pompeu Fabra, Barcelona, Spain","institution_ids":["https://openalex.org/I170486558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031398497","display_name":"Juan Pablo Bello","orcid":"https://orcid.org/0000-0001-8561-5204"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Juan Pablo Bello","raw_affiliation_strings":["New York University,MARL,New York,USA","MARL, New York University, New York, USA"],"affiliations":[{"raw_affiliation_string":"New York University,MARL,New York,USA","institution_ids":["https://openalex.org/I57206974"]},{"raw_affiliation_string":"MARL, New York University, New York, USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021235229","display_name":"Magdalena Fuentes","orcid":"https://orcid.org/0000-0003-4506-6639"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Magdalena Fuentes","raw_affiliation_strings":["New York University,MARL,New York,USA","MARL, New York University, New York, USA","IDM, New York University, New York, USA"],"affiliations":[{"raw_affiliation_string":"New York University,MARL,New York,USA","institution_ids":["https://openalex.org/I57206974"]},{"raw_affiliation_string":"MARL, New York University, New York, USA","institution_ids":["https://openalex.org/I57206974"]},{"raw_affiliation_string":"IDM, New York University, New York, USA","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5019039668"],"corresponding_institution_ids":["https://openalex.org/I170486558"],"apc_list":null,"apc_paid":null,"fwci":0.8133,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.69913,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"12","issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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":0.9995999932289124,"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/T11309","display_name":"Music and Audio Processing","score":0.9984999895095825,"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/T11665","display_name":"Animal Vocal Communication and Behavior","score":0.9833999872207642,"subfield":{"id":"https://openalex.org/subfields/1309","display_name":"Developmental Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8342297077178955},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6695743799209595},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.5828901529312134},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.5727781057357788},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.559248685836792},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5022132396697998},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4591604471206665},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.45907044410705566},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.44730302691459656},{"id":"https://openalex.org/keywords/acoustic-source-localization","display_name":"Acoustic source localization","score":0.4470224976539612},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.44256240129470825},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.43096432089805603},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.4277753233909607},{"id":"https://openalex.org/keywords/strengths-and-weaknesses","display_name":"Strengths and weaknesses","score":0.4165293872356415},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.08744916319847107}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8342297077178955},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6695743799209595},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5828901529312134},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.5727781057357788},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.559248685836792},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5022132396697998},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4591604471206665},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.45907044410705566},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.44730302691459656},{"id":"https://openalex.org/C93240960","wikidata":"https://www.wikidata.org/wiki/Q217270","display_name":"Acoustic source localization","level":3,"score":0.4470224976539612},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.44256240129470825},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.43096432089805603},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.4277753233909607},{"id":"https://openalex.org/C63882131","wikidata":"https://www.wikidata.org/wiki/Q17122954","display_name":"Strengths and weaknesses","level":2,"score":0.4165293872356415},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.08744916319847107},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10094965","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10094965","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8399999737739563,"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1755205674","https://openalex.org/W1861492603","https://openalex.org/W2105582566","https://openalex.org/W2106488367","https://openalex.org/W2164899449","https://openalex.org/W2619697695","https://openalex.org/W2962858109","https://openalex.org/W2963115079","https://openalex.org/W2963680395","https://openalex.org/W2981851635","https://openalex.org/W3015371781","https://openalex.org/W3110268547","https://openalex.org/W3116298410","https://openalex.org/W3164612304","https://openalex.org/W3170088426","https://openalex.org/W4212847156","https://openalex.org/W4224919395","https://openalex.org/W4297841849","https://openalex.org/W6639102338","https://openalex.org/W6684193366","https://openalex.org/W6766263406","https://openalex.org/W6781140265","https://openalex.org/W6796223860"],"related_works":["https://openalex.org/W2468279273","https://openalex.org/W2354198838","https://openalex.org/W1989130879","https://openalex.org/W2103419012","https://openalex.org/W2988126442","https://openalex.org/W4295769391","https://openalex.org/W2972220648","https://openalex.org/W2271369634","https://openalex.org/W1974414866","https://openalex.org/W3147472394"],"abstract_inverted_index":{"Most":[0],"recent":[1],"work":[2,49],"in":[3,14,25,61],"visual":[4,88],"sound":[5,58,89],"source":[6,59,90],"localization":[7,60,91],"relies":[8],"on":[9,95],"semantic":[10],"audio-visual":[11,99],"representations":[12],"learned":[13],"a":[15],"self-supervised":[16],"manner":[17],"and,":[18],"by":[19],"design,":[20],"excludes":[21],"temporal":[22,51],"information":[23],"present":[24],"videos.":[26],"While":[27],"it":[28],"proves":[29],"to":[30,67],"be":[31],"effective":[32],"for":[33,42,57,98],"widely":[34],"used":[35],"benchmark":[36],"datasets,":[37],"the":[38,54,74,85],"method":[39],"falls":[40],"short":[41],"challenging":[43],"scenarios":[44],"like":[45],"urban":[46,62],"traffic.":[47],"This":[48],"introduces":[50],"context":[52],"into":[53],"state-of-the-art":[55],"methods":[56,80],"scenes":[63],"using":[64],"optical":[65],"flow":[66],"encode":[68],"motion":[69],"information.":[70],"An":[71],"analysis":[72],"of":[73,78,87],"strengths":[75],"and":[76,92,104],"weaknesses":[77],"our":[79],"helps":[81],"us":[82],"better":[83],"understand":[84],"problem":[86],"sheds":[93],"light":[94],"open":[96],"challenges":[97],"scene":[100],"understanding.":[101],"The":[102],"code":[103],"pretrained":[105],"models":[106],"are":[107],"publicly":[108],"available":[109],"at":[110],"https://github.com/rrrajjjj/flowgrad":[111]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3}],"updated_date":"2025-12-24T23:09:58.560324","created_date":"2025-10-10T00:00:00"}