{"id":"https://openalex.org/W3092714093","doi":"https://doi.org/10.1145/3394171.3414023","title":"Look, Listen and Infer","display_name":"Look, Listen and Infer","publication_year":2020,"publication_date":"2020-10-12","ids":{"openalex":"https://openalex.org/W3092714093","doi":"https://doi.org/10.1145/3394171.3414023","mag":"3092714093"},"language":"en","primary_location":{"id":"doi:10.1145/3394171.3414023","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3414023","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","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/A5024477290","display_name":"Ruijian Jia","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruijian Jia","raw_affiliation_strings":["Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021472684","display_name":"Xinsheng Wang","orcid":"https://orcid.org/0000-0003-1826-7419"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinsheng Wang","raw_affiliation_strings":["Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006557413","display_name":"Shanmin Pang","orcid":"https://orcid.org/0000-0001-7217-864X"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shanmin Pang","raw_affiliation_strings":["Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068185614","display_name":"Jihua Zhu","orcid":"https://orcid.org/0000-0002-3081-8781"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jihua Zhu","raw_affiliation_strings":["Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024309592","display_name":"Jianru Xue","orcid":"https://orcid.org/0000-0002-4994-9343"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianru Xue","raw_affiliation_strings":["Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I87445476"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3911","last_page":"3919"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9991000294685364,"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/T11309","display_name":"Music and Audio Processing","score":0.9991000294685364,"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/T10860","display_name":"Speech and Audio Processing","score":0.9973000288009644,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9914000034332275,"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":0.8090994358062744},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.7238754034042358},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6942214965820312},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5938581824302673},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5796411633491516},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5532231330871582},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.48642778396606445},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.47534772753715515},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.45578163862228394},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.4180225431919098},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.11627832055091858},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0683881938457489}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8090994358062744},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.7238754034042358},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6942214965820312},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5938581824302673},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5796411633491516},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5532231330871582},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.48642778396606445},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.47534772753715515},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.45578163862228394},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.4180225431919098},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.11627832055091858},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0683881938457489},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"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/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3394171.3414023","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3414023","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5199999809265137}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1996309403","https://openalex.org/W2098411764","https://openalex.org/W2108598243","https://openalex.org/W2125560515","https://openalex.org/W2145215286","https://openalex.org/W2153579005","https://openalex.org/W2186222003","https://openalex.org/W2194775991","https://openalex.org/W2302255633","https://openalex.org/W2405223529","https://openalex.org/W2526050071","https://openalex.org/W2552383788","https://openalex.org/W2556930864","https://openalex.org/W2593116425","https://openalex.org/W2596142952","https://openalex.org/W2611632661","https://openalex.org/W2619697695","https://openalex.org/W2623327532","https://openalex.org/W2889587173","https://openalex.org/W2894786240","https://openalex.org/W2900759294","https://openalex.org/W2951748488","https://openalex.org/W2956018683","https://openalex.org/W2962714319","https://openalex.org/W2962865004","https://openalex.org/W2962960500","https://openalex.org/W2962964995","https://openalex.org/W2963115079","https://openalex.org/W2963430933","https://openalex.org/W2963495494","https://openalex.org/W2963680395","https://openalex.org/W2964105864","https://openalex.org/W2967957126","https://openalex.org/W2971709506","https://openalex.org/W2975813532","https://openalex.org/W2985951359","https://openalex.org/W2988823324","https://openalex.org/W3143107425"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2271369634","https://openalex.org/W2366718574","https://openalex.org/W3147472394","https://openalex.org/W2047100085"],"abstract_inverted_index":{"Inspired":[0],"by":[1],"the":[2,9,35,55,162],"ability":[3],"of":[4,57,164],"human":[5],"beings":[6],"on":[7,147,152,158],"recognizing":[8],"relations":[10,56],"between":[11],"visual":[12,58,171],"scenes":[13,59,172],"and":[14,28,41,60,81,105,138,173],"sounds,":[15],"many":[16],"cross-modal":[17,79,109,136],"learning":[18,169],"methods":[19],"have":[20],"been":[21],"developed":[22],"for":[23,34,74,103,170,180],"modeling":[24],"images":[25,104],"or":[26],"videos":[27],"associated":[29],"sounds.":[30],"In":[31],"this":[32,88,132,153],"work,":[33],"first":[36],"time,":[37],"a":[38,49,94,100,108,123,141],"Look,":[39],"Listen":[40],"Infer":[42],"Network":[43],"(LLINet)":[44],"is":[45,69,91,112,129,149,175,182],"proposed":[46,113],"to":[47,72,116],"learn":[48],"zero-shot":[50,135,142,168],"model":[51],"that":[52,98,167],"can":[53],"infer":[54],"sounds":[61,148,174],"from":[62],"novel":[63],"categories":[64],"never":[65],"appeared":[66],"before.":[67],"LLINet":[68,115,181],"mainly":[70],"desired":[71],"qualify":[73],"two":[75],"tasks,":[76],"i.e.,":[77],"image-audio":[78],"retrieval":[80,137],"sound":[82,118,139],"localization":[83],"in":[84,114,131],"each":[85],"image.":[86],"Towards":[87],"end,":[89],"it":[90],"designed":[92],"as":[93],"two-branch":[95],"encoding":[96],"network":[97],"builds":[99],"common":[101],"space":[102],"audios.":[106],"Besides,":[107],"attention":[110],"mechanism":[111],"localize":[117],"objects.":[119],"To":[120],"evaluate":[121],"LLINet,":[122,165],"new":[124],"data":[125],"set,":[126],"named":[127],"INSTRUMENT-32CLASS,":[128],"collected":[130],"work.":[133],"Besides":[134],"localization,":[140],"image":[143],"recognition":[144],"task":[145],"based":[146],"also":[150],"conducted":[151],"database.":[154],"All":[155],"experimental":[156],"results":[157],"these":[159],"tasks":[160],"demonstrate":[161],"effectiveness":[163],"indicating":[166],"feasible.":[176],"The":[177],"project":[178],"page":[179],"available":[183],"at":[184],"https://llinet.github.io/.":[185]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
