{"id":"https://openalex.org/W4388736801","doi":"https://doi.org/10.1109/iecon51785.2023.10312358","title":"Enhancing Ocean Scene Video Captioning with Multimodal Pre-Training and Video-Swin-Transformer","display_name":"Enhancing Ocean Scene Video Captioning with Multimodal Pre-Training and Video-Swin-Transformer","publication_year":2023,"publication_date":"2023-10-16","ids":{"openalex":"https://openalex.org/W4388736801","doi":"https://doi.org/10.1109/iecon51785.2023.10312358"},"language":"en","primary_location":{"id":"doi:10.1109/iecon51785.2023.10312358","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iecon51785.2023.10312358","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IECON 2023- 49th Annual Conference of the IEEE Industrial Electronics Society","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/A5100443904","display_name":"Xinyu Chen","orcid":"https://orcid.org/0000-0003-2075-7193"},"institutions":[{"id":"https://openalex.org/I136765683","display_name":"Tianjin University of Technology","ror":"https://ror.org/00zbe0w13","country_code":"CN","type":"education","lineage":["https://openalex.org/I136765683"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xinyu Chen","raw_affiliation_strings":["School of Computer Science and Engineering, Tianjin University of Technology,Laboratory of Computer Vision and System of Ministry of Education,Tianjin,China,300384"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Tianjin University of Technology,Laboratory of Computer Vision and System of Ministry of Education,Tianjin,China,300384","institution_ids":["https://openalex.org/I136765683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070105853","display_name":"Meng Zhao","orcid":"https://orcid.org/0000-0002-5060-9223"},"institutions":[{"id":"https://openalex.org/I136765683","display_name":"Tianjin University of Technology","ror":"https://ror.org/00zbe0w13","country_code":"CN","type":"education","lineage":["https://openalex.org/I136765683"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Zhao","raw_affiliation_strings":["School of Computer Science and Engineering, Tianjin University of Technology,Laboratory of Computer Vision and System of Ministry of Education,Tianjin,China,300384"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Tianjin University of Technology,Laboratory of Computer Vision and System of Ministry of Education,Tianjin,China,300384","institution_ids":["https://openalex.org/I136765683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007910454","display_name":"Fan Shi","orcid":"https://orcid.org/0000-0003-2074-0228"},"institutions":[{"id":"https://openalex.org/I136765683","display_name":"Tianjin University of Technology","ror":"https://ror.org/00zbe0w13","country_code":"CN","type":"education","lineage":["https://openalex.org/I136765683"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Shi","raw_affiliation_strings":["School of Computer Science and Engineering, Tianjin University of Technology,Laboratory of Computer Vision and System of Ministry of Education,Tianjin,China,300384"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Tianjin University of Technology,Laboratory of Computer Vision and System of Ministry of Education,Tianjin,China,300384","institution_ids":["https://openalex.org/I136765683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109656187","display_name":"M Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I136765683","display_name":"Tianjin University of Technology","ror":"https://ror.org/00zbe0w13","country_code":"CN","type":"education","lineage":["https://openalex.org/I136765683"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng'en Zhang","raw_affiliation_strings":["School of Computer Science and Engineering, Tianjin University of Technology,Laboratory of Computer Vision and System of Ministry of Education,Tianjin,China,300384"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Tianjin University of Technology,Laboratory of Computer Vision and System of Ministry of Education,Tianjin,China,300384","institution_ids":["https://openalex.org/I136765683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073749322","display_name":"Yu He","orcid":"https://orcid.org/0000-0002-0357-681X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210086028","display_name":"Technology and Engineering Center for Space Utilization","ror":"https://ror.org/00cn03n83","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210086028"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu He","raw_affiliation_strings":["Technology and Engineering Center for Space Utilization, Chinese Academy of Sciences,Key Laboratory of Space Utilization,Beijing,China,100190"],"affiliations":[{"raw_affiliation_string":"Technology and Engineering Center for Space Utilization, Chinese Academy of Sciences,Key Laboratory of Space Utilization,Beijing,China,100190","institution_ids":["https://openalex.org/I4210086028","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055627037","display_name":"Shengyong Chen","orcid":"https://orcid.org/0000-0002-6705-3831"},"institutions":[{"id":"https://openalex.org/I136765683","display_name":"Tianjin University of Technology","ror":"https://ror.org/00zbe0w13","country_code":"CN","type":"education","lineage":["https://openalex.org/I136765683"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengyong Chen","raw_affiliation_strings":["School of Computer Science and Engineering, Tianjin University of Technology,Laboratory of Computer Vision and System of Ministry of Education,Tianjin,China,300384"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Tianjin University of Technology,Laboratory of Computer Vision and System of Ministry of Education,Tianjin,China,300384","institution_ids":["https://openalex.org/I136765683"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100443904"],"corresponding_institution_ids":["https://openalex.org/I136765683"],"apc_list":null,"apc_paid":null,"fwci":0.369,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.61152128,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.996999979019165,"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"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9750999808311462,"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":0.8542627096176147},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8489224314689636},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6091111898422241},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.578607439994812},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4907337427139282},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.391788125038147},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3249151110649109}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8542627096176147},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8489224314689636},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6091111898422241},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.578607439994812},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4907337427139282},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.391788125038147},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3249151110649109},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iecon51785.2023.10312358","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iecon51785.2023.10312358","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IECON 2023- 49th Annual Conference of the IEEE Industrial Electronics Society","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/14","display_name":"Life below water","score":0.8500000238418579}],"awards":[{"id":"https://openalex.org/G1190114359","display_name":null,"funder_award_id":"62020106004,62272342,92048301","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1956340063","https://openalex.org/W2060422862","https://openalex.org/W2101105183","https://openalex.org/W2600463316","https://openalex.org/W2952132648","https://openalex.org/W2981851019","https://openalex.org/W2984008963","https://openalex.org/W3035265375","https://openalex.org/W3112103703","https://openalex.org/W3138516171","https://openalex.org/W3217340782","https://openalex.org/W4308234126","https://openalex.org/W4312560592","https://openalex.org/W4313156423"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W3088136942","https://openalex.org/W2949362007","https://openalex.org/W2775506363","https://openalex.org/W4310447809","https://openalex.org/W4200243030","https://openalex.org/W2800782462","https://openalex.org/W3209117276","https://openalex.org/W4323777661","https://openalex.org/W4388184981"],"abstract_inverted_index":{"With":[0],"the":[1,8,78,119,124,145,151,176,181],"success":[2],"of":[3,64,80,87],"multimodal":[4,16,39],"pre-training":[5,40,112],"models":[6,17],"in":[7,28,58,130,155,188],"video-language":[9,135],"field":[10],"and":[11,30,51,73,99,113,133,153,159,180,192],"various":[12,92],"downstream":[13],"tasks,":[14],"previous":[15],"used":[18],"3DCNN":[19],"networks":[20],"as":[21,96],"video":[22,50,59,67,83,128,167],"feature":[23],"extractors,":[24],"which":[25],"have":[26],"limitations":[27],"interacting":[29],"fusing":[31],"with":[32],"text":[33,52,69],"features.":[34],"This":[35],"paper":[36],"proposes":[37],"a":[38,44],"model":[41,62,125,170],"that":[42,162],"utilizes":[43],"Video-Swin-Transformer-based":[45],"network":[46],"to":[47,54,76,122,126,148,164],"encode":[48],"both":[49,175],"data,":[53],"achieve":[55],"better":[56,149],"performance":[57],"understanding.":[60],"The":[61,104,138,169],"consists":[63],"four":[65],"modules:":[66],"encoder,":[68,70,72],"interact":[71],"caption":[74],"decoder":[75],"accomplish":[77],"task":[79],"ocean":[81,88,156,165],"scene":[82,89,157,166],"captioning.":[84],"A":[85],"dataset":[86,121,147,178,183],"videos,":[90],"including":[91],"content":[93,154],"types":[94],"such":[95],"sea":[97],"surfaces":[98],"shores,":[100],"is":[101,107,116,141],"also":[102],"constructed.":[103],"training":[105],"process":[106],"divided":[108],"into":[109],"two":[110],"stages:":[111],"fine-tuning.":[114],"Pre-training":[115],"performed":[117,143],"on":[118,144,174],"Howto100m":[120],"allow":[123],"learn":[127],"captions":[129,161],"natural":[131],"scenes":[132],"complete":[134],"matching":[136],"tasks.":[137],"fine-tuning":[139],"stage":[140],"then":[142],"ocean1000":[146],"understand":[150],"events":[152],"videos":[158],"generate":[160],"conform":[163],"descriptions.":[168],"achieves":[171],"satisfying":[172],"results":[173],"public":[177],"YouCook2":[179],"proprietary":[182],"Ocean1000,":[184],"demonstrating":[185],"its":[186],"ability":[187],"video-text":[189],"information":[190],"fusion":[191],"interaction.":[193]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}
