{"id":"https://openalex.org/W2765621372","doi":"https://doi.org/10.1145/3123266.3127895","title":"Richer Semantic Visual and Language Representation for Video Captioning","display_name":"Richer Semantic Visual and Language Representation for Video Captioning","publication_year":2017,"publication_date":"2017-10-20","ids":{"openalex":"https://openalex.org/W2765621372","doi":"https://doi.org/10.1145/3123266.3127895","mag":"2765621372"},"language":"en","primary_location":{"id":"doi:10.1145/3123266.3127895","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3123266.3127895","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM international conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","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/A5102827532","display_name":"Pengjie Tang","orcid":"https://orcid.org/0000-0001-7523-0175"},"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":"Pengjie Tang","raw_affiliation_strings":["Tongji University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"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":["Tongji University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101670955","display_name":"Hanzhang Wang","orcid":"https://orcid.org/0009-0006-4088-5984"},"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":"Hanzhang Wang","raw_affiliation_strings":["Tongji University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101839579","display_name":"Kaisheng Xu","orcid":"https://orcid.org/0000-0002-7455-8352"},"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":"Kaisheng Xu","raw_affiliation_strings":["Tongji University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"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":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1871","last_page":"1876"},"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":0.998199999332428,"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":0.996999979019165,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.9197605848312378},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8800092935562134},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.6308030486106873},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6298989057540894},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.628990650177002},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5839762687683105},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.503983199596405},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4851149320602417},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.48053961992263794},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4569568634033203},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.43372708559036255},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.4262404441833496},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.4181619882583618},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.41781002283096313},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2550661563873291},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.17055585980415344}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9197605848312378},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8800092935562134},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.6308030486106873},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6298989057540894},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.628990650177002},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5839762687683105},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.503983199596405},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4851149320602417},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.48053961992263794},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4569568634033203},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.43372708559036255},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.4262404441833496},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4181619882583618},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.41781002283096313},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2550661563873291},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.17055585980415344},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3123266.3127895","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3123266.3127895","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM international conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7599999904632568}],"awards":[{"id":"https://openalex.org/G4555171464","display_name":null,"funder_award_id":"61472281, 61622115","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":15,"referenced_works":["https://openalex.org/W1573040851","https://openalex.org/W1586939924","https://openalex.org/W2064675550","https://openalex.org/W2101105183","https://openalex.org/W2108325777","https://openalex.org/W2112429522","https://openalex.org/W2117539524","https://openalex.org/W2139501017","https://openalex.org/W2142900973","https://openalex.org/W2152984213","https://openalex.org/W2507365558","https://openalex.org/W2523937091","https://openalex.org/W2523993696","https://openalex.org/W2527349934","https://openalex.org/W2963843052"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393","https://openalex.org/W3009270862"],"abstract_inverted_index":{"Translating":[0],"and":[1,11,31,56,82,87,114,140,150],"summarizing":[2],"a":[3,18,57,88,115],"video":[4,71],"into":[5],"natural":[6],"language":[7],"is":[8,21,45,85,91,100,108,119],"an":[9,41],"interesting":[10],"challenging":[12],"visual":[13,142],"task.":[14],"In":[15],"this":[16],"work,":[17],"novel":[19],"framework":[20],"built":[22],"to":[23,93,102,136,155,169],"generate":[24],"sentences":[25],"for":[26,70],"videos":[27],"with":[28,40,76,131],"more":[29,138],"coherence":[30],"semantics.":[32],"A":[33],"long":[34],"short":[35],"term":[36],"memory":[37],"(LSTM)":[38],"network":[39,75,112,118,125],"improved":[42,80],"factored":[43,54,81],"way":[44,55],"first":[46,66],"developed,":[47],"which":[48,107],"takes":[49],"inspiration":[50],"of":[51,60,79,159],"the":[52,65,77,95,98,104,148,157,166],"conventional":[53],"common":[58],"practice":[59],"presenting":[61],"multi-modal":[62],"features":[63,127],"at":[64],"time":[67],"in":[68],"LSTM":[69,74,117],"captioning.":[72],"An":[73],"combination":[78],"un-factored":[83],"ways":[84],"exploited,":[86],"voting":[89],"strategy":[90],"employed":[92],"predict":[94],"words.":[96],"Then,":[97],"residual":[99,111],"used":[101],"enhance":[103],"gradient":[105],"signals":[106],"learned":[109],"from":[110,128],"(ResNet),":[113],"deeper":[116],"constructed.":[120],"Furthermore,":[121],"several":[122],"convolutional":[123],"neural":[124],"(CNN)":[126],"deep":[129],"models":[130],"different":[132],"architectures":[133],"are":[134,145],"fused":[135],"catch":[137],"comprehensive":[139],"complementary":[141],"information.":[143],"Experiments":[144],"conducted":[146],"on":[147],"MSR-VTT2016":[149],"MSR-VTT2017":[151],"grand":[152],"challenge":[153],"datasets":[154],"demonstrate":[156],"effectiveness":[158],"each":[160],"presented":[161],"techniques":[162],"as":[163,165],"well":[164],"superiority":[167],"compared":[168],"other":[170],"state-of-the-art":[171],"methods.":[172]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}