{"id":"https://openalex.org/W3187583865","doi":"https://doi.org/10.1109/icaica52286.2021.9497899","title":"Video Captioning Method Based on Multi-Modal Information Fusion","display_name":"Video Captioning Method Based on Multi-Modal Information Fusion","publication_year":2021,"publication_date":"2021-06-28","ids":{"openalex":"https://openalex.org/W3187583865","doi":"https://doi.org/10.1109/icaica52286.2021.9497899","mag":"3187583865"},"language":"en","primary_location":{"id":"doi:10.1109/icaica52286.2021.9497899","doi":"https://doi.org/10.1109/icaica52286.2021.9497899","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icaica52286.2021.9497899","pdf_url":null,"source":{"id":"https://openalex.org/S4363608013","display_name":"IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA)","raw_type":"proceedings-article"},"parent_works":[],"lineage":["https://openalex.org/W3187583865"],"child_works_count":0,"type":"conference-paper","is_traditional":true,"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":null,"display_name":"Xin Ai","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Ai","raw_affiliation_strings":["College of Computer Science and Technology, Beijing Jiaotong University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101786222","display_name":"Hao Wang","orcid":"https://orcid.org/0000-0002-3035-3064","observed_orcids":["https://orcid.org/0000-0002-3035-3064"]},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Wang","raw_affiliation_strings":["College of Computer Science and Technology, Beijing Jiaotong University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100697327","display_name":"Haiyang Chen","orcid":"https://orcid.org/0000-0002-7556-6741","observed_orcids":["https://orcid.org/0000-0002-7556-6741"]},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haiyang Chen","raw_affiliation_strings":["College of Computer Science and Technology, Beijing Jiaotong University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071889746","display_name":"Wanru Xu","orcid":"https://orcid.org/0000-0003-2206-5051","observed_orcids":["https://orcid.org/0000-0003-2206-5051"]},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wanru Xu","raw_affiliation_strings":["College of Computer Science and Technology, Beijing Jiaotong University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I21193070"],"apc_list":null,"apc_paid":null,"fwci":0.2311,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.51220104,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"820","last_page":"824"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994999766349792,"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":0.9994999766349792,"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":0.00019999999494757503,"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":9.999999747378752e-05,"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/video-captioning","display_name":"video captioning","score":0.9990000128746033},{"id":"https://openalex.org/keywords/multimodal-fusion","display_name":"multimodal fusion","score":0.7940000295639038},{"id":"https://openalex.org/keywords/attention-mechanism","display_name":"attention mechanism","score":0.7689999938011169},{"id":"https://openalex.org/keywords/optical-flow","display_name":"optical flow","score":0.824999988079071},{"id":"https://openalex.org/keywords/rgb-features","display_name":"RGB features","score":0.6050000190734863},{"id":"https://openalex.org/keywords/feature-concatenation","display_name":"feature concatenation","score":0.7260000109672546}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9325602650642395},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8626145720481873},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.7007944583892822},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6007426977157593},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4969806969165802},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.4824986457824707},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.4584599733352661},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.45244166254997253},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.44233396649360657},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.42835739254951477},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.16101351380348206},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icaica52286.2021.9497899","doi":"https://doi.org/10.1109/icaica52286.2021.9497899","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icaica52286.2021.9497899","pdf_url":null,"source":{"id":"https://openalex.org/S4363608013","display_name":"IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"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":15,"referenced_works":["https://openalex.org/W1573040851","https://openalex.org/W1895577753","https://openalex.org/W2016589492","https://openalex.org/W2119717200","https://openalex.org/W2159243025","https://openalex.org/W2425121537","https://openalex.org/W2558834163","https://openalex.org/W2609138599","https://openalex.org/W2742943414","https://openalex.org/W2895845501","https://openalex.org/W2951390634","https://openalex.org/W2962990649","https://openalex.org/W2972281329","https://openalex.org/W3035365026","https://openalex.org/W3035392611"],"related_works":["https://openalex.org/W4225155274","https://openalex.org/W4405755673","https://openalex.org/W2935973931","https://openalex.org/W3031435312","https://openalex.org/W4385270576","https://openalex.org/W3131045228","https://openalex.org/W2527349934","https://openalex.org/W2584992898","https://openalex.org/W4387587644","https://openalex.org/W2972589507"],"abstract_inverted_index":{"Video":[0],"captioning":[1,156],"is":[2,47,93],"a":[3,70],"challenging":[4],"problem":[5],"in":[6,90],"the":[7,28,33,38,52,56,60,91,109,113,118,123,128,139,143,153],"field":[8],"of":[9,37,55,86,127],"computer":[10,16],"vision,":[11],"which":[12,107],"aims":[13],"at":[14],"using":[15],"to":[17,24,41,50,75,101,137],"automatically":[18],"generate":[19,42,102],"human-readable":[20],"natural":[21],"language":[22],"sentences":[23],"describe":[25,51,59],"video":[26,39,61,82,92,155],"content.However,":[27],"traditional":[29],"method":[30,145],"only":[31],"uses":[32],"single":[34],"mode":[35],"information":[36,85,116,132,136],"sequence":[40],"description":[43,105],"sentences,":[44],"and":[45,65,77,98,117,133,148],"it":[46],"not":[48],"enough":[49],"whole":[53],"content":[54,62],"video.":[57,140],"To":[58],"more":[63,103],"accurately":[64],"detailed,":[66],"this":[67],"paper":[68],"designs":[69],"multi-modal":[71],"fusion":[72],"based":[73],"model":[74,124],"capture":[76],"integrate":[78],"multiple":[79],"cues":[80],"for":[81],"captioning.":[83],"The":[84],"different":[87],"modes":[88],"contained":[89],"fused":[94],"through":[95],"feature":[96],"concatenation":[97],"attention":[99],"mechanism":[100],"detailed":[104],"sequences,":[106],"including":[108],"original":[110],"RGB":[111],"information,":[112,130],"optical":[114],"flow":[115],"attribute":[119],"tag":[120],"information.":[121],"Thus,":[122],"extracts":[125],"all":[126],"appearance":[129],"motion":[131],"high-level":[134],"semantic":[135],"represent":[138],"In":[141],"experiment,":[142],"proposed":[144],"achieves":[146],"comparable":[147],"even":[149],"better":[150],"results":[151],"on":[152],"public":[154],"dataset.":[157]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":3}],"updated_date":"2026-11-14T11:04:58.165337","created_date":"2021-08-16T00:00:00"}
