{"id":"https://openalex.org/W2996817764","doi":"https://doi.org/10.1145/3303083","title":"Rich Visual and Language Representation with Complementary Semantics for Video Captioning","display_name":"Rich Visual and Language Representation with Complementary Semantics for Video Captioning","publication_year":2019,"publication_date":"2019-05-31","ids":{"openalex":"https://openalex.org/W2996817764","doi":"https://doi.org/10.1145/3303083","mag":"2996817764"},"language":"en","primary_location":{"id":"doi:10.1145/3303083","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3303083","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","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/A5019414690","display_name":"Pengjie Tang","orcid":"https://orcid.org/0000-0002-6220-7758"},"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"]},{"id":"https://openalex.org/I14748160","display_name":"Jinggangshan University","ror":"https://ror.org/04exd0a76","country_code":"CN","type":"education","lineage":["https://openalex.org/I14748160"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Pengjie Tang","raw_affiliation_strings":["Tongji University, P. R. China and Jinggangshan University, Shanghai, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University, P. R. China and Jinggangshan University, Shanghai, P. R. China","institution_ids":["https://openalex.org/I14748160","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":["Tongji University, Shanghai, P. R. China"],"raw_orcid":"https://orcid.org/0000-0002-9999-4871","affiliations":[{"raw_affiliation_string":"Tongji University, Shanghai, P. R. China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5119247506","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":["Tongji University, P. R. China and Lanzhou City University, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University, P. R. China and Lanzhou City University, P. R. China","institution_ids":["https://openalex.org/I116953780"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5019414690"],"corresponding_institution_ids":["https://openalex.org/I116953780","https://openalex.org/I14748160"],"apc_list":null,"apc_paid":null,"fwci":1.2253,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.84007504,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"15","issue":"2","first_page":"1","last_page":"23"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9970999956130981,"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":0.9965000152587891,"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":0.8856298923492432},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8653817176818848},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6350997686386108},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6278184056282043},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.6252841949462891},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5852525234222412},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5823054909706116},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.49588093161582947},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.48393183946609497},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4559917151927948},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.45333462953567505},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.4295696020126343},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2386678159236908},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.09362933039665222}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8856298923492432},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8653817176818848},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6350997686386108},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6278184056282043},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.6252841949462891},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5852525234222412},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5823054909706116},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.49588093161582947},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.48393183946609497},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4559917151927948},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.45333462953567505},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.4295696020126343},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2386678159236908},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.09362933039665222},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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:10.1145/3303083","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3303083","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6000000238418579}],"awards":[{"id":"https://openalex.org/G7824007637","display_name":null,"funder_award_id":"GZ2015005","funder_id":"https://openalex.org/F4320336023","funder_display_name":"Program for Professor of Special Appointment (Eastern Scholar) at Shanghai Institutions of Higher Learning"},{"id":"https://openalex.org/G8240765861","display_name":null,"funder_award_id":"61622115, 61472281","funder_id":"https://openalex.org/F4320335595","funder_display_name":"National Natural Science Foundation of China-Yunnan Joint Fund"}],"funders":[{"id":"https://openalex.org/F4320335595","display_name":"National Natural Science Foundation of China-Yunnan Joint Fund","ror":null},{"id":"https://openalex.org/F4320336023","display_name":"Program for Professor of Special Appointment (Eastern Scholar) at Shanghai Institutions of Higher Learning","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1573040851","https://openalex.org/W1586939924","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1923211482","https://openalex.org/W1923404803","https://openalex.org/W1947481528","https://openalex.org/W1956340063","https://openalex.org/W2091812280","https://openalex.org/W2097117768","https://openalex.org/W2101105183","https://openalex.org/W2108325777","https://openalex.org/W2112429522","https://openalex.org/W2139501017","https://openalex.org/W2142900973","https://openalex.org/W2155893237","https://openalex.org/W2186222003","https://openalex.org/W2194775991","https://openalex.org/W2425121537","https://openalex.org/W2507365558","https://openalex.org/W2523937091","https://openalex.org/W2523993696","https://openalex.org/W2527349934","https://openalex.org/W2552161745","https://openalex.org/W2554906389","https://openalex.org/W2556388456","https://openalex.org/W2557264465","https://openalex.org/W2558834163","https://openalex.org/W2607119937","https://openalex.org/W2739107216","https://openalex.org/W2742570236","https://openalex.org/W2751153269","https://openalex.org/W2765621372","https://openalex.org/W2799013120","https://openalex.org/W2799176631","https://openalex.org/W2803620531","https://openalex.org/W2884326683","https://openalex.org/W2887712318","https://openalex.org/W2896874112","https://openalex.org/W2951365926","https://openalex.org/W2962681491","https://openalex.org/W2963524571","https://openalex.org/W2963576560","https://openalex.org/W2963843052","https://openalex.org/W2963971014","https://openalex.org/W2964018924","https://openalex.org/W2964241990","https://openalex.org/W3098682680","https://openalex.org/W3099884890"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2949362007","https://openalex.org/W2775506363","https://openalex.org/W4290852288","https://openalex.org/W3088136942","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2803345361","https://openalex.org/W3009270862"],"abstract_inverted_index":{"It":[0],"is":[1,24,50,98,104,141],"interesting":[2],"and":[3,31,64,95,100,114,117,136,154,162,175,177],"challenging":[4],"to":[5,9,26,68,106,123,158,188],"translate":[6],"a":[7,60,65,101,137],"video":[8,16,36],"natural":[10],"description":[11],"sentences":[12,28],"based":[13,148],"on":[14,169],"the":[15,55,75,83,86,90,125,132,183],"content.":[17],"In":[18,110],"this":[19],"work,":[20],"an":[21,46],"advanced":[22],"framework":[23],"built":[25],"generate":[27],"with":[29,45,59,89],"coherence":[30],"rich":[32],"semantic":[33],"expressions":[34],"for":[35,79,112],"captioning.":[37],"A":[38],"long":[39],"short":[40],"term":[41],"memory":[42],"(LSTM)":[43],"network":[44,88,134,140,147],"improved":[47,92],"factored":[48,62,93],"way":[49,63,94,97],"first":[51,76],"developed,":[52],"which":[53],"takes":[54],"inspiration":[56],"of":[57,85],"LSTM":[58,73,87,139],"conventional":[61],"common":[66],"practice":[67],"feed":[69],"multi-modal":[70],"features":[71,149],"into":[72],"at":[74],"time":[77],"step":[78],"visual":[80,116,164],"description.":[81],"Then,":[82],"incorporation":[84],"proposed":[91,184],"un-factored":[96],"exploited,":[99],"voting":[102],"strategy":[103],"utilized":[105],"predict":[107],"candidate":[108],"words.":[109],"addition,":[111],"robust":[113],"abstract":[115],"language":[118],"representation,":[119],"residuals":[120],"are":[121,129,156,167,180],"employed":[122],"enhance":[124],"gradient":[126],"signals":[127],"that":[128],"learned":[130],"from":[131,151],"residual":[133],"(ResNet),":[135],"deeper":[138],"constructed.":[142],"Furthermore,":[143],"three":[144],"convolutional":[145],"neural":[146],"extracted":[150],"GoogLeNet,":[152],"ResNet101,":[153],"ResNet152,":[155],"fused":[157],"catch":[159],"more":[160],"comprehensive":[161],"complementary":[163],"information.":[165],"Experiments":[166],"conducted":[168],"two":[170],"benchmark":[171],"datasets,":[172],"including":[173],"MSVD":[174],"MSR-VTT2016,":[176],"competitive":[178],"performances":[179],"obtained":[181],"by":[182],"techniques":[185],"as":[186],"compared":[187],"other":[189],"state-of-the-art":[190],"methods.":[191]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}