{"id":"https://openalex.org/W3158565912","doi":"https://doi.org/10.1109/iscas51556.2021.9401232","title":"Learning Fine-Grained Semantics in Spoken Language Using Visual Grounding","display_name":"Learning Fine-Grained Semantics in Spoken Language Using Visual Grounding","publication_year":2021,"publication_date":"2021-04-27","ids":{"openalex":"https://openalex.org/W3158565912","doi":"https://doi.org/10.1109/iscas51556.2021.9401232","mag":"3158565912"},"language":"en","primary_location":{"id":"doi:10.1109/iscas51556.2021.9401232","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscas51556.2021.9401232","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Symposium on Circuits and Systems (ISCAS)","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/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":true,"raw_author_name":"Xinsheng Wang","raw_affiliation_strings":["School of Software Engineering, Xi\u2019an Jiaotong University, Xi\u2019an, China","School of Software Engineering, Xi'an Jiaotong University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"School of Software Engineering, Xi\u2019an Jiaotong University, Xi\u2019an, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"School of Software Engineering, Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100419137","display_name":"Tian Tian","orcid":"https://orcid.org/0000-0003-0148-4900"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Tian Tian","raw_affiliation_strings":["Multimedia Computing Group, Delft University of Technology, Delft, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Multimedia Computing Group, Delft University of Technology, Delft, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"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":["School of Software Engineering, Xi\u2019an Jiaotong University, Xi\u2019an, China","School of Software Engineering, Xi'an Jiaotong University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"School of Software Engineering, Xi\u2019an Jiaotong University, Xi\u2019an, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"School of Software Engineering, Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048860892","display_name":"Odette Scharenborg","orcid":"https://orcid.org/0000-0003-0693-8852"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Odette Scharenborg","raw_affiliation_strings":["Multimedia Computing Group, Delft University of Technology, Delft, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Multimedia Computing Group, Delft University of Technology, Delft, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5021472684"],"corresponding_institution_ids":["https://openalex.org/I87445476"],"apc_list":null,"apc_paid":null,"fwci":0.3884,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.59701083,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"9","issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.996999979019165,"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":0.8640516996383667},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6210135817527771},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6164838075637817},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.580702006816864},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.5265626907348633},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5116024613380432},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.4792337715625763},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.46605998277664185},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.40646088123321533}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8640516996383667},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6210135817527771},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6164838075637817},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.580702006816864},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.5265626907348633},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5116024613380432},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.4792337715625763},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.46605998277664185},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40646088123321533},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iscas51556.2021.9401232","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscas51556.2021.9401232","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Symposium on Circuits and Systems (ISCAS)","raw_type":"proceedings-article"},{"id":"pmh:oai:tudelft.nl:uuid:fc3c1730-e0ac-4b53-b606-31596c780dea","is_oa":false,"landing_page_url":"http://resolver.tudelft.nl/uuid:fc3c1730-e0ac-4b53-b606-31596c780dea","pdf_url":null,"source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.800000011920929}],"awards":[{"id":"https://openalex.org/G2300736770","display_name":null,"funder_award_id":"(CSC)","funder_id":"https://openalex.org/F4320322725","funder_display_name":"China Scholarship Council"},{"id":"https://openalex.org/G8589651859","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320322725","funder_display_name":"China Scholarship Council"}],"funders":[{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W68733909","https://openalex.org/W1522301498","https://openalex.org/W1797268635","https://openalex.org/W2099471712","https://openalex.org/W2117539524","https://openalex.org/W2157331557","https://openalex.org/W2187089797","https://openalex.org/W2194775991","https://openalex.org/W2327501763","https://openalex.org/W2347145335","https://openalex.org/W2398118205","https://openalex.org/W2405756170","https://openalex.org/W2533598788","https://openalex.org/W2556930864","https://openalex.org/W2765440071","https://openalex.org/W2796315435","https://openalex.org/W2894786240","https://openalex.org/W2950133079","https://openalex.org/W2962793481","https://openalex.org/W2962845008","https://openalex.org/W2962862718","https://openalex.org/W2963163163","https://openalex.org/W2963373786","https://openalex.org/W2963680395","https://openalex.org/W2963902314","https://openalex.org/W2963966654","https://openalex.org/W2963981733","https://openalex.org/W2964001192","https://openalex.org/W2964121744","https://openalex.org/W2964243274","https://openalex.org/W2967957126","https://openalex.org/W2971709506","https://openalex.org/W2985951359","https://openalex.org/W2988907666","https://openalex.org/W2995680346","https://openalex.org/W3102219307","https://openalex.org/W4301206121","https://openalex.org/W4320013936","https://openalex.org/W6631190155","https://openalex.org/W6638319203","https://openalex.org/W6713645886","https://openalex.org/W6718379498","https://openalex.org/W6729977899","https://openalex.org/W6750651883","https://openalex.org/W6765779288","https://openalex.org/W6770596778","https://openalex.org/W6779669310"],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W2183306018","https://openalex.org/W2549990292","https://openalex.org/W2345479200","https://openalex.org/W2951819827","https://openalex.org/W2849310602","https://openalex.org/W2419146053","https://openalex.org/W2088247287","https://openalex.org/W3006008237","https://openalex.org/W4313153715"],"abstract_inverted_index":{"In":[0],"the":[1,12,52,123,147],"case":[2],"of":[3,77],"unwritten":[4],"languages,":[5],"acoustic":[6],"models":[7],"cannot":[8],"be":[9,59,152],"trained":[10],"in":[11],"standard":[13],"way,":[14],"i.e.,":[15,33,115],"using":[16,31,34,112],"speech":[17,29,108,149],"and":[18,56,102,119,137,157],"textual":[19],"transcriptions.":[20],"Recently,":[21],"several":[22],"methods":[23,130],"have":[24,39],"been":[25],"proposed":[26],"to":[27,154],"learn":[28],"representations":[30,76,109,150],"images,":[32],"visual":[35,168],"grounding.":[36],"Existing":[37],"studies":[38],"focused":[40],"on":[41,131],"scene":[42,134],"images.":[43,160],"Here,":[44],"we":[45,88],"investigate":[46],"whether":[47],"fine-grained":[48,82,139,159,162],"semantic":[49,75],"information,":[50],"reflecting":[51],"relationship":[53],"between":[54],"attributes":[55],"objects,":[57],"can":[58,151],"learned":[60,107,148],"from":[61,164],"spoken":[62,78,165],"language.":[63],"To":[64],"this":[65],"end,":[66],"a":[67,96,103,133],"Fine-grained":[68],"Semantic":[69],"Embedding":[70],"Network":[71],"(FSEN)":[72],"for":[73],"learning":[74],"language":[79,166],"grounded":[80],"by":[81],"images":[83],"is":[84,170],"proposed.":[85],"For":[86],"training,":[87],"propose":[89],"an":[90,99],"efficient":[91],"objective":[92],"function,":[93],"which":[94],"includes":[95],"matching":[97],"constraint,":[98],"adversarial":[100],"objective,":[101],"classification":[104],"constraint.":[105],"The":[106,141],"are":[110],"evaluated":[111],"two":[113,138],"tasks,":[114],"speech-image":[116],"cross-modal":[117],"retrieval":[118,124],"speech-to-image":[120],"generation.":[121],"On":[122],"task,":[125],"FSEN":[126],"outperforms":[127],"other":[128],"state-of-the-art":[129],"both":[132],"image":[135,142],"dataset":[136],"datasets.":[140],"generation":[143],"task":[144],"shows":[145],"that":[146],"used":[153],"generate":[155],"high-quality":[156],"semantic-consistent":[158],"Learning":[161],"semantics":[163],"via":[167],"grounding":[169],"thus":[171],"possible.":[172]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}