{"id":"https://openalex.org/W2966917182","doi":"https://doi.org/10.1109/icra.2019.8794166","title":"Sound-Indicated Visual Object Detection for Robotic Exploration","display_name":"Sound-Indicated Visual Object Detection for Robotic Exploration","publication_year":2019,"publication_date":"2019-05-01","ids":{"openalex":"https://openalex.org/W2966917182","doi":"https://doi.org/10.1109/icra.2019.8794166","mag":"2966917182"},"language":"en","primary_location":{"id":"doi:10.1109/icra.2019.8794166","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2019.8794166","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"conference-paper","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/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":["State Key Laboratory of Intelligent Technology and Systems, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Intelligent Technology and Systems, Beijing National Research Center 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":["State Key Laboratory of Intelligent Technology and Systems, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Intelligent Technology and Systems, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","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":["State Key Laboratory of Intelligent Technology and Systems, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Intelligent Technology and Systems, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111387505","display_name":"Junfeng Zhou","orcid":"https://orcid.org/0000-0002-8201-6799"},"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":"Junfeng Zhou","raw_affiliation_strings":["State Key Laboratory of Intelligent Technology and Systems, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Intelligent Technology and Systems, Beijing National Research Center for Information Science and Technology, 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":["State Key Laboratory of Intelligent Technology and Systems, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Intelligent Technology and Systems, Beijing National Research Center 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":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8070","last_page":"8076"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9962999820709229,"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":0.9962999820709229,"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":0.9958999752998352,"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/T11309","display_name":"Music and Audio Processing","score":0.9785000085830688,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7639247179031372},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.7191964387893677},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.7074114084243774},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7068542242050171},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5771048665046692},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5667663812637329},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5601736903190613},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5408928394317627},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.43731629848480225},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4346630573272705},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3609105944633484},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.14050373435020447},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.12165340781211853}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7639247179031372},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.7191964387893677},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.7074114084243774},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7068542242050171},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5771048665046692},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5667663812637329},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5601736903190613},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5408928394317627},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.43731629848480225},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4346630573272705},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3609105944633484},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.14050373435020447},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.12165340781211853},{"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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"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/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra.2019.8794166","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2019.8794166","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on Robotics and Automation (ICRA)","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":32,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W854541894","https://openalex.org/W1686810756","https://openalex.org/W2078855514","https://openalex.org/W2100235303","https://openalex.org/W2147704751","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2207851367","https://openalex.org/W2217431788","https://openalex.org/W2402272455","https://openalex.org/W2546190447","https://openalex.org/W2561787614","https://openalex.org/W2567353838","https://openalex.org/W2593116425","https://openalex.org/W2613718673","https://openalex.org/W2726368908","https://openalex.org/W2765440071","https://openalex.org/W2796992393","https://openalex.org/W2798453914","https://openalex.org/W2962865004","https://openalex.org/W2962960500","https://openalex.org/W2963037989","https://openalex.org/W2963115079","https://openalex.org/W2963680395","https://openalex.org/W6620707391","https://openalex.org/W6623517193","https://openalex.org/W6637373629","https://openalex.org/W6684191040","https://openalex.org/W6728854242","https://openalex.org/W6750591037","https://openalex.org/W6751130187"],"related_works":["https://openalex.org/W2271369634","https://openalex.org/W2185469136","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2949096641","https://openalex.org/W2970686063","https://openalex.org/W4320729701","https://openalex.org/W3210378990","https://openalex.org/W3034745255","https://openalex.org/W4254103348"],"abstract_inverted_index":{"Robots":[0],"are":[1,80],"usually":[2],"equipped":[3],"with":[4],"microphones":[5],"and":[6,10,44,56,76],"cameras":[7],"to":[8,52,71],"perceive":[9],"understand":[11],"the":[12,24,54,61,69,73],"physical":[13],"world.":[14],"Though":[15],"visual":[16,40,55],"object":[17,41],"detection":[18,25,42],"technology":[19],"has":[20],"achieved":[21],"great":[22],"success,":[23],"in":[26],"other":[27],"modalities":[28,58],"remains":[29],"unsolved.":[30],"In":[31],"this":[32],"paper,":[33],"we":[34],"establish":[35],"a":[36,46],"novel":[37],"robotic":[38,83],"sound-indicated":[39],"framework,":[43],"develop":[45],"two-stream":[47],"weakly-supervised":[48],"deep":[49],"learning":[50],"architecture":[51],"connect":[53],"audio":[57],"for":[59],"localizing":[60],"sounding":[62],"object.":[63],"A":[64],"dataset":[65],"is":[66],"constructed":[67],"from":[68],"AudioSet":[70],"validate":[72],"proposed":[74],"method":[75],"some":[77],"promising":[78],"applications":[79],"demonstrated":[81],"on":[82],"platforms.":[84]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
