{"id":"https://openalex.org/W4406857473","doi":"https://doi.org/10.1109/tmm.2025.3535394","title":"Vision-Language Relational Transformer for Video-to-Text Generation","display_name":"Vision-Language Relational Transformer for Video-to-Text Generation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4406857473","doi":"https://doi.org/10.1109/tmm.2025.3535394"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2025.3535394","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3535394","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/A5013006794","display_name":"Tengpeng Li","orcid":null},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tengpeng Li","raw_affiliation_strings":["College of Electronic and Information Engineering, Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0007-2244-0567","affiliations":[{"raw_affiliation_string":"College of Electronic and Information Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058982350","display_name":"Hanli Wang","orcid":"https://orcid.org/0000-0002-9999-4871"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanli Wang","raw_affiliation_strings":["College of Electronic and Information Engineering, Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-9999-4871","affiliations":[{"raw_affiliation_string":"College of Electronic and Information Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Qinyu Li","orcid":"https://orcid.org/0009-0001-1519-0914"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qinyu Li","raw_affiliation_strings":["College of Electronic and Information Engineering, Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0001-1519-0914","affiliations":[{"raw_affiliation_string":"College of Electronic and Information Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032273272","display_name":"Zhangkai Ni","orcid":"https://orcid.org/0000-0003-3682-6288"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhangkai Ni","raw_affiliation_strings":["College of Electronic and Information Engineering, Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-3682-6288","affiliations":[{"raw_affiliation_string":"College of Electronic and Information Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I116953780"],"apc_list":null,"apc_paid":null,"fwci":3.0621,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.90543888,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"27","issue":null,"first_page":"4584","last_page":"4596"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9930999875068665,"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":0.991100013256073,"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":0.847943902015686},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.590346097946167},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4976814091205597},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4588940143585205},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.34385088086128235},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3407435417175293},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.1293521523475647}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.847943902015686},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.590346097946167},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4976814091205597},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4588940143585205},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34385088086128235},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3407435417175293},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.1293521523475647},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2025.3535394","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3535394","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":[{"id":"https://openalex.org/G2125127483","display_name":null,"funder_award_id":"62371343","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":65,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1586939924","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2139501017","https://openalex.org/W2425121537","https://openalex.org/W2554320282","https://openalex.org/W2604178507","https://openalex.org/W2613964630","https://openalex.org/W2752782242","https://openalex.org/W2883910824","https://openalex.org/W2896457183","https://openalex.org/W2905145027","https://openalex.org/W2948358897","https://openalex.org/W2953461088","https://openalex.org/W2963177403","https://openalex.org/W2963552819","https://openalex.org/W2963916161","https://openalex.org/W2964137974","https://openalex.org/W2964241990","https://openalex.org/W2969844053","https://openalex.org/W2996817764","https://openalex.org/W3009149353","https://openalex.org/W3009960797","https://openalex.org/W3018388102","https://openalex.org/W3025796084","https://openalex.org/W3034815696","https://openalex.org/W3035237998","https://openalex.org/W3035365026","https://openalex.org/W3035392611","https://openalex.org/W3131477521","https://openalex.org/W3166366124","https://openalex.org/W3173909648","https://openalex.org/W3176689360","https://openalex.org/W3216659302","https://openalex.org/W3217340782","https://openalex.org/W4210668396","https://openalex.org/W4214692497","https://openalex.org/W4221163941","https://openalex.org/W4285200050","https://openalex.org/W4303443398","https://openalex.org/W4308234126","https://openalex.org/W4312463400","https://openalex.org/W4312825258","https://openalex.org/W4322718191","https://openalex.org/W4323717348","https://openalex.org/W4384918448","https://openalex.org/W4385245566","https://openalex.org/W4386057717","https://openalex.org/W4386066385","https://openalex.org/W4391128821","https://openalex.org/W4394659899","https://openalex.org/W6678262379","https://openalex.org/W6682631176","https://openalex.org/W6682889407","https://openalex.org/W6684090549","https://openalex.org/W6791353385","https://openalex.org/W6809975043","https://openalex.org/W6811013733","https://openalex.org/W6846002521","https://openalex.org/W6849177959","https://openalex.org/W6850071225","https://openalex.org/W6850625674","https://openalex.org/W6854866820","https://openalex.org/W6864544085"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Video-to-text":[0],"generation":[1],"is":[2,53,70,91,107],"a":[3,48,65,87,103,165],"challenging":[4],"task":[5],"that":[6,141],"involves":[7],"translating":[8],"video":[9,35,170],"contents":[10],"into":[11],"accurate":[12],"and":[13,29,77,83,98,124,138,163],"expressive":[14],"sentences.":[15,43],"Existing":[16],"methods":[17],"often":[18],"ignore":[19],"the":[20,115,142,150,154,158],"importance":[21],"of":[22],"establishing":[23],"fine-grained":[24],"semantics":[25],"within":[26],"visual":[27,66,119],"representations":[28,76],"exploring":[30],"textual":[31,96],"knowledge":[32,88,122],"implied":[33],"by":[34,113],"contents,":[36],"leading":[37],"to":[38,72,93,109],"difficulty":[39],"in":[40],"generating":[41],"satisfactory":[42],"To":[44],"address":[45],"these":[46],"problems,":[47],"vision-language":[49],"relational":[50],"transformer":[51],"model":[52],"proposed":[54,116,143],"for":[55,168],"video-to-text":[56],"generation.":[57,126],"Three":[58],"key":[59],"novel":[60],"aspects":[61],"are":[62],"investigated.":[63],"First,":[64],"relation":[67,120],"modeling":[68],"block":[69,90],"designed":[71],"obtain":[73],"higher-order":[74],"feature":[75],"establish":[78],"semantic":[79],"relationships":[80],"between":[81],"regional":[82],"global":[84],"features.":[85],"Second,":[86],"attention":[89,123],"developed":[92],"explore":[94],"hierarchical":[95],"information":[97],"capture":[99],"cross-modal":[100],"dependencies.":[101],"Third,":[102],"video-centric":[104],"conversation":[105,161],"system":[106],"constructed":[108],"complete":[110],"multi-round":[111],"dialogues":[112],"incorporating":[114],"modules":[117],"including":[118,133],"modeling,":[121],"text":[125],"Extensive":[127],"experiments":[128],"on":[129],"five":[130],"benchmark":[131],"datasets":[132],"MSVD,":[134],"MSRVTT,":[135],"ActivityNet,":[136],"Charades":[137],"EMVPC":[139],"demonstrate":[140],"scheme":[144],"achieves":[145],"remarkable":[146],"performance":[147],"compared":[148],"with":[149],"state-of-the-art":[151],"methods.":[152],"Besides,":[153],"qualitative":[155],"experiment":[156],"reveals":[157],"system's":[159],"favorable":[160],"capability":[162],"provides":[164],"valuable":[166],"exemplar":[167],"future":[169],"understanding":[171],"works.":[172]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}