{"id":"https://openalex.org/W3033520894","doi":"https://doi.org/10.1109/tii.2020.3000240","title":"Active Object Discovery and Localization Using Sound-Induced Attention","display_name":"Active Object Discovery and Localization Using Sound-Induced Attention","publication_year":2020,"publication_date":"2020-06-05","ids":{"openalex":"https://openalex.org/W3033520894","doi":"https://doi.org/10.1109/tii.2020.3000240","mag":"3033520894"},"language":"en","primary_location":{"id":"doi:10.1109/tii.2020.3000240","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tii.2020.3000240","pdf_url":null,"source":{"id":"https://openalex.org/S184777250","display_name":"IEEE Transactions on Industrial Informatics","issn_l":"1551-3203","issn":["1551-3203","1941-0050"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Industrial Informatics","raw_type":"journal-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/A5041101317","display_name":"Huaping Liu","orcid":"https://orcid.org/0000-0002-4042-6044"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huaping Liu","raw_affiliation_strings":["Beijing National Research Centre for Information Science and Technology, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4042-6044","affiliations":[{"raw_affiliation_string":"Beijing National Research Centre for Information Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100431251","display_name":"Feng Wang","orcid":"https://orcid.org/0000-0002-4556-5326"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Wang","raw_affiliation_strings":["Beijing National Research Centre for Information Science and Technology, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing National Research Centre for Information Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101833400","display_name":"Di Guo","orcid":"https://orcid.org/0000-0002-9816-0103"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Di Guo","raw_affiliation_strings":["Beijing National Research Centre for Information Science and Technology, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9816-0103","affiliations":[{"raw_affiliation_string":"Beijing National Research Centre for Information Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101470788","display_name":"Xinzhu Liu","orcid":"https://orcid.org/0000-0002-6447-2926"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinzhu Liu","raw_affiliation_strings":["Beijing National Research Centre for Information Science and Technology, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing National Research Centre for Information Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100390719","display_name":"Xinyu Zhang","orcid":"https://orcid.org/0000-0003-0034-9037"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyu Zhang","raw_affiliation_strings":["State Key Laboratory of Automotive Safety and Energy, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-0034-9037","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Automotive Safety and Energy, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055546056","display_name":"Fuchun Sun","orcid":"https://orcid.org/0000-0003-3546-6305"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fuchun Sun","raw_affiliation_strings":["Beijing National Research Centre for Information Science and Technology, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing National Research Centre for Information Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":{"value":2645,"currency":"USD","value_usd":2645},"apc_paid":null,"fwci":0.4381,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.61448671,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"17","issue":"3","first_page":"2021","last_page":"2029"},"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/T11309","display_name":"Music and Audio Processing","score":0.9979000091552734,"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/T10914","display_name":"Tactile and Sensory Interactions","score":0.992900013923645,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7472582459449768},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.7383695840835571},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.654006838798523},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6213715076446533},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5730202794075012},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5629786252975464},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5230282545089722},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5073911547660828},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4560929834842682},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4254893660545349},{"id":"https://openalex.org/keywords/depth-sounding","display_name":"Depth sounding","score":0.4178146719932556},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.2341001033782959},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.1294671893119812}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7472582459449768},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.7383695840835571},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.654006838798523},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6213715076446533},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5730202794075012},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5629786252975464},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5230282545089722},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5073911547660828},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4560929834842682},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4254893660545349},{"id":"https://openalex.org/C55510283","wikidata":"https://www.wikidata.org/wiki/Q1382947","display_name":"Depth sounding","level":2,"score":0.4178146719932556},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2341001033782959},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.1294671893119812},{"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/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tii.2020.3000240","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tii.2020.3000240","pdf_url":null,"source":{"id":"https://openalex.org/S184777250","display_name":"IEEE Transactions on Industrial Informatics","issn_l":"1551-3203","issn":["1551-3203","1941-0050"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Industrial Informatics","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.5400000214576721,"display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G2802338391","display_name":null,"funder_award_id":"2018YFB1305102","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G8844373132","display_name":null,"funder_award_id":"61703284","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W854541894","https://openalex.org/W1967140145","https://openalex.org/W2022904055","https://openalex.org/W2057967659","https://openalex.org/W2078855514","https://openalex.org/W2100235303","https://openalex.org/W2147704751","https://openalex.org/W2207851367","https://openalex.org/W2217431788","https://openalex.org/W2402272455","https://openalex.org/W2511428026","https://openalex.org/W2518246700","https://openalex.org/W2546190447","https://openalex.org/W2561787614","https://openalex.org/W2593116425","https://openalex.org/W2613718673","https://openalex.org/W2619697695","https://openalex.org/W2726368908","https://openalex.org/W2765440071","https://openalex.org/W2783074568","https://openalex.org/W2796096089","https://openalex.org/W2798453914","https://openalex.org/W2888836575","https://openalex.org/W2901937360","https://openalex.org/W2962756039","https://openalex.org/W2962865004","https://openalex.org/W2962960500","https://openalex.org/W2963037989","https://openalex.org/W2963115079","https://openalex.org/W2963680395","https://openalex.org/W2966917182","https://openalex.org/W2978706708","https://openalex.org/W2987388689","https://openalex.org/W3003820461","https://openalex.org/W4293665662","https://openalex.org/W6623517193","https://openalex.org/W6729831399","https://openalex.org/W6751130187"],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W2167701463","https://openalex.org/W2110287964","https://openalex.org/W4307407935","https://openalex.org/W649759291"],"abstract_inverted_index":{"Industrial":[0],"intelligent":[1],"devices":[2],"are":[3,89],"usually":[4],"equipped":[5],"with":[6,30],"both":[7],"microphones":[8],"and":[9,13,51,64,85],"cameras":[10],"to":[11,60,80,91],"perceive":[12],"understand":[14],"the":[15,47,62,69,77,82,93,96],"physical":[16],"world.":[17],"Though":[18],"visual":[19,48,63],"object":[20,49],"detection":[21],"technology":[22],"has":[23],"achieved":[24],"a":[25,41,53],"great":[26],"success,":[27],"its":[28],"combination":[29],"other":[31],"sensing":[32],"modalities":[33,66],"remains":[34],"unsolved.":[35],"In":[36],"this":[37],"article,":[38],"we":[39],"establish":[40],"novel":[42],"sound-induced":[43],"attention":[44],"framework":[45],"for":[46,67],"detection,":[50],"develop":[52],"two-stream":[54],"weakly":[55],"supervised":[56],"deep":[57],"learning":[58],"architecture":[59],"combine":[61],"audio":[65],"localizing":[68],"sounding":[70],"object.":[71],"A":[72],"dataset":[73],"is":[74],"constructed":[75],"from":[76],"Audio":[78],"Set":[79],"validate":[81],"proposed":[83,97],"method":[84],"some":[86],"realistic":[87],"experiments":[88],"conducted":[90],"demonstrate":[92],"effectiveness":[94],"of":[95],"system.":[98]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}
