{"id":"https://openalex.org/W3096396720","doi":"https://doi.org/10.1145/3394171.3416288","title":"Multi-stage Tag Guidance Network in Video Caption","display_name":"Multi-stage Tag Guidance Network in Video Caption","publication_year":2020,"publication_date":"2020-10-12","ids":{"openalex":"https://openalex.org/W3096396720","doi":"https://doi.org/10.1145/3394171.3416288","mag":"3096396720"},"language":"en","primary_location":{"id":"doi:10.1145/3394171.3416288","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3416288","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","raw_type":"proceedings-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/A5067691968","display_name":"Lanxiao Wang","orcid":"https://orcid.org/0000-0002-3745-0262"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lanxiao Wang","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029041038","display_name":"Chao Shang","orcid":"https://orcid.org/0000-0003-3905-4631"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Shang","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066434602","display_name":"Heqian Qiu","orcid":"https://orcid.org/0000-0002-0963-0311"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heqian Qiu","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072221658","display_name":"Taijin Zhao","orcid":"https://orcid.org/0009-0008-5449-900X"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Taijin Zhao","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046642871","display_name":"Benliu Qiu","orcid":"https://orcid.org/0009-0000-8582-8576"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Benliu Qiu","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114378292","display_name":"Hongliang Li","orcid":"https://orcid.org/0000-0002-7481-095X"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongliang Li","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5067691968"],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":0.3908,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.62591584,"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":"4610","last_page":"4614"},"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":0.9997000098228455,"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":0.9958000183105469,"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":0.8621018528938293},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.7813833951950073},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.7652998566627502},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5694369673728943},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5139438509941101},{"id":"https://openalex.org/keywords/train","display_name":"Train","score":0.4774625599384308},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.46381017565727234},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.45786407589912415},{"id":"https://openalex.org/keywords/dropout","display_name":"Dropout (neural networks)","score":0.41523459553718567},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.33535510301589966},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3333313465118408},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32951581478118896},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2431454360485077},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.15190082788467407}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8621018528938293},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.7813833951950073},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.7652998566627502},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5694369673728943},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5139438509941101},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.4774625599384308},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.46381017565727234},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.45786407589912415},{"id":"https://openalex.org/C2776145597","wikidata":"https://www.wikidata.org/wiki/Q25339462","display_name":"Dropout (neural networks)","level":2,"score":0.41523459553718567},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.33535510301589966},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3333313465118408},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32951581478118896},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2431454360485077},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.15190082788467407},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3394171.3416288","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3416288","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6499999761581421,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G3672757813","display_name":null,"funder_award_id":"61525102, 61831005","funder_id":"https://openalex.org/F4320327720","funder_display_name":"Foundation for Innovative Research Groups of the National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320327720","display_name":"Foundation for Innovative Research Groups of the National Natural Science Foundation of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1573040851","https://openalex.org/W2064675550","https://openalex.org/W2139501017","https://openalex.org/W2142900973","https://openalex.org/W2292443655","https://openalex.org/W2507365558","https://openalex.org/W2605021547","https://openalex.org/W2963524571","https://openalex.org/W3089790101","https://openalex.org/W4293861233","https://openalex.org/W4300026658"],"related_works":["https://openalex.org/W2989932438","https://openalex.org/W3128220493","https://openalex.org/W3011996705","https://openalex.org/W2095705004","https://openalex.org/W3099765033","https://openalex.org/W3175189414","https://openalex.org/W4210794429","https://openalex.org/W2953328427","https://openalex.org/W2605524926","https://openalex.org/W3186919929"],"abstract_inverted_index":{"Recently,":[0],"video":[1,30],"caption":[2],"plays":[3],"an":[4],"important":[5],"role":[6],"in":[7,13,55,134],"computer":[8],"vision":[9],"tasks.":[10],"We":[11],"participate":[12],"Pre-training":[14,135],"for":[15,27,136],"Video":[16,137],"Captioning":[17,138],"Challenge":[18,139],"which":[19,49,140],"aims":[20],"to":[21,45,72,84,120],"produce":[22],"at":[23],"least":[24],"one":[25],"sentence":[26],"each":[28],"challenge":[29],"based":[31],"on":[32],"the":[33,53,75,90,107,123,142],"pretraining":[34],"models.":[35],"In":[36,127],"this":[37],"work,":[38],"we":[39,64,115,129],"propose":[40],"a":[41,47,111,117],"tag":[42],"guidance":[43],"module":[44],"learn":[46],"representation":[48],"can":[50],"better":[51],"build":[52],"interaction":[54],"cross-modal":[56],"between":[57],"visual":[58],"content":[59],"and":[60,80,87,106],"textual":[61],"sentences.":[62],"First,":[63],"utilize":[65],"three":[66],"types":[67],"of":[68,77,93,144],"features":[69],"extraction":[70],"networks":[71],"fully":[73],"capture":[74],"information":[76],"2D,":[78],"3D":[79],"object":[81],"information.":[82],"Second,":[83],"prevent":[85],"overfitting":[86],"time":[88],"issues,":[89],"entire":[91],"process":[92],"training":[94],"is":[95],"divided":[96],"into":[97],"two":[98],"stages.":[99],"The":[100],"first":[101],"stage":[102,109],"trains":[103],"all":[104],"data,":[105],"second":[108],"introduces":[110],"random":[112],"dropout.":[113],"Furthermore,":[114],"train":[116],"CNN-based":[118],"network":[119],"pick":[121],"out":[122],"best":[124],"candidate":[125],"results.":[126],"summary,":[128],"were":[130],"ranked":[131],"third":[132],"place":[133],"proved":[141],"effectiveness":[143],"our":[145],"model.":[146]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}