{"id":"https://openalex.org/W3135656708","doi":"https://doi.org/10.1109/iscslp49672.2021.9362117","title":"Audio Caption in a Car Setting with a Sentence-Level Loss","display_name":"Audio Caption in a Car Setting with a Sentence-Level Loss","publication_year":2021,"publication_date":"2021-01-24","ids":{"openalex":"https://openalex.org/W3135656708","doi":"https://doi.org/10.1109/iscslp49672.2021.9362117","mag":"3135656708"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp49672.2021.9362117","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp49672.2021.9362117","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 12th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5025827045","display_name":"Xuenan Xu","orcid":"https://orcid.org/0000-0001-8718-1278"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xuenan Xu","raw_affiliation_strings":["Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence SpeechLab, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence SpeechLab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080154283","display_name":"Heinrich Dinkel","orcid":"https://orcid.org/0000-0003-4330-8980"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heinrich Dinkel","raw_affiliation_strings":["Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence SpeechLab, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence SpeechLab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081865665","display_name":"Mengyue Wu","orcid":"https://orcid.org/0000-0002-5599-8707"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengyue Wu","raw_affiliation_strings":["Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence SpeechLab, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence SpeechLab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043098653","display_name":"Kai Yu","orcid":"https://orcid.org/0000-0002-7102-9826"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Yu","raw_affiliation_strings":["Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence SpeechLab, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence SpeechLab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5025827045"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":1.2489,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.81361111,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9940999746322632,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9922000169754028,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.9547735452651978},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8735674619674683},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6589760184288025},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.6028817892074585},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5963371992111206},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5937753915786743},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5690728425979614},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5404452085494995},{"id":"https://openalex.org/keywords/natural-language-generation","display_name":"Natural language generation","score":0.5201297402381897},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.519980251789093},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.4513890743255615},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.41569432616233826},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4100547730922699},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.21683910489082336},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11161977052688599}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9547735452651978},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8735674619674683},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6589760184288025},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.6028817892074585},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5963371992111206},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5937753915786743},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5690728425979614},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5404452085494995},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.5201297402381897},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.519980251789093},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.4513890743255615},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.41569432616233826},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4100547730922699},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.21683910489082336},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11161977052688599},{"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp49672.2021.9362117","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp49672.2021.9362117","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 12th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8100000023841858,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W68733909","https://openalex.org/W1514535095","https://openalex.org/W1522301498","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W2131744502","https://openalex.org/W2176263492","https://openalex.org/W2250539671","https://openalex.org/W2584992898","https://openalex.org/W2605035112","https://openalex.org/W2607119937","https://openalex.org/W2786670585","https://openalex.org/W2896457183","https://openalex.org/W2899024931","https://openalex.org/W2902469875","https://openalex.org/W2916103538","https://openalex.org/W2945761034","https://openalex.org/W2962739339","https://openalex.org/W2963084599","https://openalex.org/W2963248296","https://openalex.org/W2963341956","https://openalex.org/W2963747784","https://openalex.org/W2963756346","https://openalex.org/W2964065937","https://openalex.org/W2964121744","https://openalex.org/W2970971581","https://openalex.org/W3015591594","https://openalex.org/W3038899388","https://openalex.org/W4295312788","https://openalex.org/W4302343710","https://openalex.org/W6630875275","https://openalex.org/W6631190155","https://openalex.org/W6679775712","https://openalex.org/W6685322675","https://openalex.org/W6742080785","https://openalex.org/W6755207826","https://openalex.org/W6757163628","https://openalex.org/W6766978945","https://openalex.org/W6780379688"],"related_works":["https://openalex.org/W3009270862","https://openalex.org/W382594479","https://openalex.org/W2152921782","https://openalex.org/W2470045054","https://openalex.org/W2575772232","https://openalex.org/W2140902089","https://openalex.org/W2030298461","https://openalex.org/W3014316498","https://openalex.org/W1510553545","https://openalex.org/W3020827637"],"abstract_inverted_index":{"Captioning":[0],"has":[1],"attracted":[2],"much":[3],"attention":[4],"in":[5,40,85],"image":[6],"and":[7,72,100],"video":[8],"understanding":[9],"while":[10],"a":[11,22,29,43,66],"small":[12],"amount":[13],"of":[14],"work":[15],"examines":[16],"audio":[17,26,107],"captioning.":[18],"This":[19],"paper":[20],"contributes":[21],"Mandarin-annotated":[23],"dataset":[24,71],"for":[25],"captioning":[27],"within":[28],"car":[30],"scene.":[31],"A":[32],"sentence-level":[33],"loss":[34],"is":[35],"proposed":[36],"to":[37,47,54],"be":[38,89,111],"used":[39],"tandem":[41],"with":[42,50],"GRU":[44],"encoder-decoder":[45],"model":[46,60,118],"generate":[48],"captions":[49,108,119],"higher":[51],"semantic":[52],"similarity":[53],"human":[55,101,114],"annotations.":[56],"We":[57],"evaluate":[58],"the":[59,62,73],"on":[61,120],"newly-proposed":[63],"Car":[64],"dataset,":[65,75],"previously":[67],"published":[68],"Mandarin":[69],"Hospital":[70],"Joint":[74],"indicating":[76],"its":[77],"generalization":[78],"capability":[79],"across":[80],"different":[81],"scenes.":[82],"An":[83],"improvement":[84],"all":[86],"metrics":[87],"can":[88,109],"observed,":[90],"including":[91],"classical":[92],"natural":[93],"language":[94],"generation":[95],"(NLG)":[96],"metrics,":[97],"sentence":[98],"richness":[99],"evaluation":[102],"ratings.":[103],"However,":[104],"though":[105],"detailed":[106],"now":[110],"automatically":[112],"generated,":[113],"annotations":[115],"still":[116],"outperform":[117],"many":[121],"aspects.":[122]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
