{"id":"https://openalex.org/W4386590370","doi":"https://doi.org/10.1109/icip49359.2023.10223075","title":"Semantic Learning Network for Controllable Video Captioning","display_name":"Semantic Learning Network for Controllable Video Captioning","publication_year":2023,"publication_date":"2023-09-11","ids":{"openalex":"https://openalex.org/W4386590370","doi":"https://doi.org/10.1109/icip49359.2023.10223075"},"language":"en","primary_location":{"id":"doi:10.1109/icip49359.2023.10223075","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip49359.2023.10223075","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Image Processing (ICIP)","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/A5010775700","display_name":"Kaixuan Chen","orcid":"https://orcid.org/0000-0003-3904-0395"},"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","The Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, 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":"The Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, 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","The Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, 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":"The Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015745132","display_name":"Yang Lu","orcid":"https://orcid.org/0000-0002-3497-9611"},"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","The Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, 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":"The Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, 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","The Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, 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":"The Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, 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":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"880","last_page":"884"},"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":0.9969000220298767,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9948999881744385,"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/closed-captioning","display_name":"Closed captioning","score":0.9403964281082153},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8762226104736328},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6551908254623413},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5975236892700195},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5869815945625305},{"id":"https://openalex.org/keywords/predicate","display_name":"Predicate (mathematical logic)","score":0.5445634722709656},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.5001091957092285},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.45835769176483154},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.44663000106811523},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4337750971317291},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.4207271933555603},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.17550769448280334},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07832890748977661}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9403964281082153},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8762226104736328},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6551908254623413},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5975236892700195},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5869815945625305},{"id":"https://openalex.org/C140146324","wikidata":"https://www.wikidata.org/wiki/Q1144319","display_name":"Predicate (mathematical logic)","level":2,"score":0.5445634722709656},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.5001091957092285},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.45835769176483154},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.44663000106811523},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4337750971317291},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.4207271933555603},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.17550769448280334},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07832890748977661},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/icip49359.2023.10223075","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip49359.2023.10223075","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.800000011920929,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"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/W2891955747","https://openalex.org/W2895845501","https://openalex.org/W2905145027","https://openalex.org/W2948358897","https://openalex.org/W2949789546","https://openalex.org/W2951390634","https://openalex.org/W2963971014","https://openalex.org/W2984862483","https://openalex.org/W3034221024","https://openalex.org/W3035392611","https://openalex.org/W3096609285","https://openalex.org/W3176425931","https://openalex.org/W3216659302","https://openalex.org/W4242177601","https://openalex.org/W4312463400","https://openalex.org/W4394659899","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/W2949362007","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393","https://openalex.org/W3009270862"],"abstract_inverted_index":{"Video":[0],"captioning":[1,88],"is":[2,97],"fundamental":[3],"for":[4],"visual":[5,25,55,75],"understanding,":[6],"which":[7],"aims":[8],"at":[9],"describing":[10],"the":[11,30,34,51,62,74,91,106,113,120,123,126,131],"content":[12],"of":[13,54,72,122],"a":[14,38],"video":[15,87,96,114],"using":[16],"natural":[17],"language.":[18],"Previous":[19],"works":[20],"make":[21],"great":[22],"efforts":[23],"to":[24,44,50,84,99,111,115],"representation":[26],"learning":[27,53],"by":[28,77],"comparing":[29],"generated":[31],"sentences":[32],"and":[33,80,89,133],"ground":[35],"truth":[36],"in":[37,125],"supervised":[39],"way.":[40],"However,":[41],"they":[42],"neglect":[43],"explore":[45],"linguistic":[46],"semantics":[47,71],"adequately":[48],"due":[49],"insufficient":[52],"words.":[56],"In":[57],"this":[58],"paper,":[59],"we":[60,104],"propose":[61,105],"Semantic":[63],"Learning":[64],"Network":[65],"(SLN)":[66],"that":[67,93,137],"explicitly":[68],"learns":[69],"specific":[70],"all":[73],"words":[76],"aggregating":[78],"static":[79],"dynamic":[81],"features.":[82],"Besides,":[83],"achieve":[85],"controllable":[86],"alleviate":[90],"problem":[92],"one":[94],"identical":[95],"mapped":[98],"multiple":[100],"annotations":[101],"during":[102],"training,":[103],"predicate-based":[107],"feature":[108],"selection":[109],"approach":[110],"convert":[112],"different":[116],"textual":[117],"features":[118],"under":[119],"guidance":[121],"predicate":[124],"captions.":[127],"Experimental":[128],"results":[129],"on":[130],"MSVD":[132],"MSR-VTT":[134],"datasets":[135],"show":[136],"our":[138],"SLN":[139],"outperforms":[140],"recent":[141],"state-of-the-art":[142],"methods.":[143]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}