{"id":"https://openalex.org/W4386108345","doi":"https://doi.org/10.1109/tmm.2023.3307972","title":"Global-Shared Text Representation Based Multi-Stage Fusion Transformer Network for Multi-Modal Dense Video Captioning","display_name":"Global-Shared Text Representation Based Multi-Stage Fusion Transformer Network for Multi-Modal Dense Video Captioning","publication_year":2023,"publication_date":"2023-08-23","ids":{"openalex":"https://openalex.org/W4386108345","doi":"https://doi.org/10.1109/tmm.2023.3307972"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2023.3307972","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3307972","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-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/A5051731173","display_name":"Yulai Xie","orcid":"https://orcid.org/0000-0003-0764-6579"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yulai Xie","raw_affiliation_strings":["Hitachi China Research Laboratory, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-0764-6579","affiliations":[{"raw_affiliation_string":"Hitachi China Research Laboratory, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005095177","display_name":"Jingjing Niu","orcid":"https://orcid.org/0000-0001-9515-1079"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingjing Niu","raw_affiliation_strings":["School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9515-1079","affiliations":[{"raw_affiliation_string":"School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100354625","display_name":"Yang Zhang","orcid":"https://orcid.org/0000-0002-0523-8478"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang Zhang","raw_affiliation_strings":["Hitachi China Research Laboratory, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0523-8478","affiliations":[{"raw_affiliation_string":"Hitachi China Research Laboratory, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100652923","display_name":"Fang Ren","orcid":"https://orcid.org/0000-0002-2251-9220"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fang Ren","raw_affiliation_strings":["School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2251-9220","affiliations":[{"raw_affiliation_string":"School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5051731173"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.471,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.6460155,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"26","issue":null,"first_page":"3164","last_page":"3179"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9993000030517578,"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":0.9973000288009644,"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":0.9041712284088135},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8602687120437622},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5681630969047546},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5165273547172546},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.49854397773742676},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4442993998527527},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4252159595489502},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4056193232536316},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.090535968542099}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9041712284088135},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8602687120437622},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5681630969047546},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5165273547172546},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.49854397773742676},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4442993998527527},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4252159595489502},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4056193232536316},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.090535968542099},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2023.3307972","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3307972","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":66,"referenced_works":["https://openalex.org/W1596841185","https://openalex.org/W1821462560","https://openalex.org/W1849277567","https://openalex.org/W1947481528","https://openalex.org/W1956340063","https://openalex.org/W2064675550","https://openalex.org/W2101105183","https://openalex.org/W2133459682","https://openalex.org/W2139501017","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2526050071","https://openalex.org/W2619383789","https://openalex.org/W2747920239","https://openalex.org/W2763440627","https://openalex.org/W2766375149","https://openalex.org/W2767249564","https://openalex.org/W2767989436","https://openalex.org/W2785892019","https://openalex.org/W2883409523","https://openalex.org/W2883910824","https://openalex.org/W2885775891","https://openalex.org/W2899879331","https://openalex.org/W2905139236","https://openalex.org/W2951098185","https://openalex.org/W2962799512","https://openalex.org/W2962990649","https://openalex.org/W2962994439","https://openalex.org/W2963177403","https://openalex.org/W2963351113","https://openalex.org/W2963504927","https://openalex.org/W2963524571","https://openalex.org/W2963576560","https://openalex.org/W2963811641","https://openalex.org/W2963843052","https://openalex.org/W2963916161","https://openalex.org/W2964010806","https://openalex.org/W2964051877","https://openalex.org/W2964241990","https://openalex.org/W2968104955","https://openalex.org/W2972589507","https://openalex.org/W2982770724","https://openalex.org/W2985144848","https://openalex.org/W2985185987","https://openalex.org/W3034815696","https://openalex.org/W3037572520","https://openalex.org/W3043840704","https://openalex.org/W3173549566","https://openalex.org/W3176724088","https://openalex.org/W3206529771","https://openalex.org/W3214432797","https://openalex.org/W4281391284","https://openalex.org/W4283219253","https://openalex.org/W4294576248","https://openalex.org/W4321793515","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6638523607","https://openalex.org/W6738806211","https://openalex.org/W6746213830","https://openalex.org/W6754478056","https://openalex.org/W6757408916","https://openalex.org/W6766978945","https://openalex.org/W6775036685","https://openalex.org/W6777481484","https://openalex.org/W6784761581"],"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":{"Dense":[0],"video":[1,11,64,75,96,209],"captioning":[2,97],"aims":[3],"to":[4,24,70,92,141,159],"detect":[5],"all":[6],"events":[7],"of":[8,28,74,145,164,177],"an":[9,152],"uncropped":[10],"and":[12,104,121,128,190],"generate":[13,142,161],"corresponding":[14],"textual":[15],"captions":[16],"for":[17,206],"each":[18],"event.":[19],"Multi-modal":[20],"information":[21],"is":[22,68,157,203],"essential":[23],"improve":[25],"the":[26,32,38,49,55,71,86,100,102,105,168,175,178,194,199],"performance":[27,72,189],"this":[29,78],"task,":[30],"but":[31],"existing":[33],"methods":[34],"mainly":[35],"rely":[36],"on":[37,174],"single":[39],"visual":[40,106,122],"or":[41],"dual":[42],"audio-visual":[43],"modal":[44,51],"input,":[45],"while":[46],"completely":[47],"ignoring":[48],"text":[50,56,135,201],"input":[52],"(subtitle).":[53],"Since":[54],"data":[57,61],"has":[58],"a":[59,82,112,125,133,138,143,162],"similar":[60],"representation":[62,136,202],"as":[63],"caption":[65],"words,":[66],"it":[67],"conducive":[69],"improvement":[73],"captioning.":[76,210],"In":[77,150],"article,":[79],"we":[80],"propose":[81],"novel":[83],"framework,":[84],"called":[85],"multi-stage":[87,113],"fusion":[88,115],"transformer":[89],"network":[90],"(MS-FTN),":[91],"realize":[93],"multi-modal":[94,146,207],"dense":[95,208],"by":[98],"fusing":[99],"text,":[101],"audio,":[103],"features":[107],"in":[108],"stages.":[109],"We":[110],"present":[111],"feature":[114],"encoder":[116],"that":[117,183,198],"first":[118],"fuses":[119,130],"audio":[120],"modalities":[123],"at":[124,137],"lower":[126],"level":[127,140],"then":[129],"them":[131],"with":[132],"global-shared":[134,200],"higher":[139],"set":[144,163],"complementary":[147],"context":[148],"features.":[149],"addition,":[151],"anchor-free":[153],"event":[154,165],"proposal":[155],"module":[156],"proposed":[158,185],"efficiently":[160],"proposals":[166],"without":[167],"complex":[169],"anchor":[170],"calculation.":[171],"Extensive":[172],"experiments":[173],"subsets":[176],"ActivityNet":[179],"Captions":[180],"dataset":[181],"show":[182],"our":[184],"MS-FTN":[186],"achieves":[187],"superior":[188],"efficient":[191],"computation.":[192],"Moreover,":[193],"ablation":[195],"studies":[196],"demonstrate":[197],"more":[204],"suitable":[205]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}