{"id":"https://openalex.org/W4392903523","doi":"https://doi.org/10.1109/icassp48485.2024.10447433","title":"Semantic-Guided Network with Contrastive Learning for Video Caption","display_name":"Semantic-Guided Network with Contrastive Learning for Video Caption","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903523","doi":"https://doi.org/10.1109/icassp48485.2024.10447433"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447433","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10447433","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5100632847","display_name":"Kaixuan Chen","orcid":"https://orcid.org/0000-0002-2492-5230"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaixuan Chen","raw_affiliation_strings":["Xiamen University,Fujian Key Laboratory of Sensing and Computing for Smart City,School of Informatics,Xiamen,China,361005","Ministry of Education of China, The Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Xiamen University, Xiamen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,Fujian Key Laboratory of Sensing and Computing for Smart City,School of Informatics,Xiamen,China,361005","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"Ministry of Education of China, The Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089981551","display_name":"Qianji Di","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qianji Di","raw_affiliation_strings":["Xiamen University,Fujian Key Laboratory of Sensing and Computing for Smart City,School of Informatics,Xiamen,China,361005","Ministry of Education of China, The Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Xiamen University, Xiamen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,Fujian Key Laboratory of Sensing and Computing for Smart City,School of Informatics,Xiamen,China,361005","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"Ministry of Education of China, The Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100454257","display_name":"Lu Yang","orcid":"https://orcid.org/0000-0002-5428-7874"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Lu","raw_affiliation_strings":["Xiamen University,Fujian Key Laboratory of Sensing and Computing for Smart City,School of Informatics,Xiamen,China,361005","Ministry of Education of China, The Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Xiamen University, Xiamen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,Fujian Key Laboratory of Sensing and Computing for Smart City,School of Informatics,Xiamen,China,361005","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"Ministry of Education of China, The Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044594971","display_name":"Hanzi Wang","orcid":"https://orcid.org/0000-0002-6913-9786"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanzi Wang","raw_affiliation_strings":["Xiamen University,Fujian Key Laboratory of Sensing and Computing for Smart City,School of Informatics,Xiamen,China,361005","Ministry of Education of China, The Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Xiamen University, Xiamen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,Fujian Key Laboratory of Sensing and Computing for Smart City,School of Informatics,Xiamen,China,361005","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"Ministry of Education of China, The Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I191208505"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3830","last_page":"3884"},"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":0.9959999918937683,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9919000267982483,"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":0.8971134424209595},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.837383508682251},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6806116104125977},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6616146564483643},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6465144753456116},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5910173654556274},{"id":"https://openalex.org/keywords/syntax","display_name":"Syntax","score":0.5323593616485596},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4328542947769165},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4320891499519348},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.19947651028633118},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07632917165756226}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8971134424209595},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.837383508682251},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6806116104125977},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6616146564483643},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6465144753456116},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5910173654556274},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.5323593616485596},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4328542947769165},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4320891499519348},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.19947651028633118},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07632917165756226},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447433","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10447433","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2022121445","display_name":null,"funder_award_id":"U21A20514","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G590298258","display_name":null,"funder_award_id":"62376233","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2108325777","https://openalex.org/W2133459682","https://openalex.org/W2425121537","https://openalex.org/W2948358897","https://openalex.org/W2951390634","https://openalex.org/W2984862483","https://openalex.org/W3034221024","https://openalex.org/W3035365026","https://openalex.org/W3035392611","https://openalex.org/W3134875898","https://openalex.org/W3176425931","https://openalex.org/W3216659302","https://openalex.org/W4236965008","https://openalex.org/W4313483475","https://openalex.org/W4382464395","https://openalex.org/W4385245566","https://openalex.org/W4385617545","https://openalex.org/W4386057717","https://openalex.org/W6684090549","https://openalex.org/W6791353385"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W4391150403","https://openalex.org/W2081749821","https://openalex.org/W1968572830","https://openalex.org/W2090814745","https://openalex.org/W2029896371","https://openalex.org/W2136497797"],"abstract_inverted_index":{"Video":[0],"captioning":[1],"is":[2],"a":[3,10,17,82],"challenging":[4],"task,":[5],"which":[6,90],"aims":[7],"at":[8],"generating":[9],"sentence":[11],"to":[12,33,99,116,125],"describe":[13],"the":[14,20,53,61,73,101,108,118,136],"content":[15],"of":[16,55,93],"video":[18],"using":[19],"natural":[21],"language.":[22],"Many":[23],"existing":[24],"methods":[25],"model":[26,128],"visual":[27,42],"features":[28,43,102],"(2D/3D)":[29],"extracted":[30],"from":[31,72],"videos":[32],"generate":[34],"captions,":[35],"but":[36],"they":[37],"neglect":[38],"semantic":[39,62,131],"guidance.":[40,105,132],"Empirically,":[41],"contain":[44],"fine-grained":[45],"information":[46,98],"such":[47],"as":[48],"color":[49],"and":[50,63,96,138],"shape,":[51],"while":[52],"generation":[54],"captions":[56],"requires":[57],"more":[58],"emphasis":[59],"on":[60,86,107,135],"syntax":[64],"clues":[65],"that":[66,142],"cannot":[67],"be":[68],"studied":[69],"adequately":[70],"only":[71],"caption":[74],"loss.":[75],"To":[76],"alleviate":[77],"this":[78],"problem,":[79],"we":[80],"propose":[81],"semantic-guided":[83],"network":[84],"based":[85],"contrastive":[87],"learning":[88],"(SNCL),":[89],"makes":[91],"use":[92],"both":[94],"vision":[95],"text":[97],"enrich":[100],"with":[103,129],"contextual":[104],"Based":[106],"meaningful":[109],"features,":[110],"hierarchical":[111],"reasoning":[112],"modules":[113],"are":[114],"employed":[115],"perform":[117],"key":[119],"phrase":[120],"prediction":[121],"task":[122],"in":[123],"order":[124],"enhance":[126],"our":[127,143],"specific":[130],"Experimental":[133],"results":[134],"MSVD":[137],"MSR-VTT":[139],"datasets":[140],"show":[141],"SNCL":[144],"outperforms":[145],"recent":[146],"state-of-the-art":[147],"methods.":[148]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
