{"id":"https://openalex.org/W3198583350","doi":"https://doi.org/10.1145/3461353.3461386","title":"Divided Caption Model with Global Attention","display_name":"Divided Caption Model with Global Attention","publication_year":2021,"publication_date":"2021-03-05","ids":{"openalex":"https://openalex.org/W3198583350","doi":"https://doi.org/10.1145/3461353.3461386","mag":"3198583350"},"language":"en","primary_location":{"id":"doi:10.1145/3461353.3461386","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3461353.3461386","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 the 5th International Conference on Innovation in Artificial Intelligence","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/A5031364544","display_name":"Yamin Cheng","orcid":null},"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":"Cheng Yamin","raw_affiliation_strings":["University of Electronic Science and Technology of China, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102079217","display_name":"Hancong Duan","orcid":"https://orcid.org/0000-0002-7721-7422"},"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":"Duan Hancong","raw_affiliation_strings":["University of Electronic Science and Technology of China, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084729575","display_name":"Zitian Zhao","orcid":"https://orcid.org/0000-0001-8605-0938"},"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":"Zhao Zitian","raw_affiliation_strings":["University of Electronic Science and Technology of China, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100376399","display_name":"Zhi Wang","orcid":"https://orcid.org/0000-0002-5462-6178"},"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":"Wang Zhi","raw_affiliation_strings":["University of Electronic Science and Technology of China, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5031364544"],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11019608,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"69","last_page":"75"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9972000122070312,"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":0.996399998664856,"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":0.9520870447158813},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8772660493850708},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6529067158699036},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5448818206787109},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5354487895965576},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5180037617683411},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.42964601516723633},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.42205724120140076},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4162471294403076},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.15149709582328796}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9520870447158813},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8772660493850708},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6529067158699036},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5448818206787109},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5354487895965576},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5180037617683411},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.42964601516723633},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.42205724120140076},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4162471294403076},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.15149709582328796},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3461353.3461386","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3461353.3461386","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 the 5th International Conference on Innovation in Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2139501017","https://openalex.org/W2156798932","https://openalex.org/W2461621749","https://openalex.org/W2519328139","https://openalex.org/W2597958930","https://openalex.org/W2607119937","https://openalex.org/W2755876276","https://openalex.org/W2784025607","https://openalex.org/W2788713610","https://openalex.org/W2952132648","https://openalex.org/W2962799512","https://openalex.org/W2963351113","https://openalex.org/W2963576560","https://openalex.org/W2963645879","https://openalex.org/W2963686907","https://openalex.org/W2963753226","https://openalex.org/W2963916161","https://openalex.org/W2964214371","https://openalex.org/W2964265128","https://openalex.org/W2968104955","https://openalex.org/W3123077146"],"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/W4399485860"],"abstract_inverted_index":{"Dense":[0],"video":[1,87,122,140],"captioning":[2,72],"is":[3],"a":[4,18,57,75,81,96,109],"newly":[5],"emerging":[6],"task":[7],"that":[8],"aims":[9],"at":[10],"both":[11],"locating":[12],"and":[13,22,43,119,138,154],"describing":[14],"all":[15],"events":[16],"in":[17,74,89,125,142],"video.":[19],"We":[20],"identify":[21],"tackle":[23],"two":[24,63],"challenges":[25],"on":[26,176],"this":[27,53],"task,":[28],"namely,":[29],"1)":[30],"the":[31,39,49,71,90,149,160,164,177],"limitation":[32],"of":[33,163],"just":[34],"attending":[35],"local":[36],"features;":[37],"2)":[38],"severely":[40],"degraded":[41,152],"description":[42,153],"increased":[44,155],"training":[45],"complexity":[46],"caused":[47],"by":[48],"redundant":[50],"information.":[51],"In":[52],"paper,":[54],"we":[55,79,101,135],"propose":[56],"new":[58],"divided":[59],"caption":[60,126],"model,":[61],"where":[62],"different":[64],"attention":[65,83,121],"mechanisms":[66],"are":[67],"introduced":[68],"to":[69,85,112,128,147],"rectify":[70],"process":[73],"unified":[76],"framework.":[77],"Firstly,":[78],"employ":[80],"global":[82,120],"mechanism":[84,111],"encode":[86],"features":[88,118,141],"proposal":[91],"module,":[92],"which":[93],"can":[94],"obtain":[95],"better":[97],"temporal":[98],"boundary.":[99],"Second,":[100],"design":[102],"bidirectional":[103],"Long":[104],"short-term":[105],"memory":[106],"(LSTM)":[107],"with":[108,169],"common-attention":[110],"counterpoise":[113],"3d-convolutional":[114],"neural":[115],"network":[116],"(c3d)":[117],"content":[123],"effectively":[124],"module":[127],"generate":[129],"coherent":[130],"natural":[131],"language":[132],"descriptions.":[133],"Besides,":[134],"divide":[136],"forward":[137],"backward":[139],"an":[143],"event":[144],"into":[145],"segments":[146],"relieve":[148],"stress":[150],"for":[151],"complexity.":[156],"Extensive":[157],"experiments":[158],"demonstrate":[159],"competitive":[161],"performance":[162],"proposed":[165],"Divided":[166],"Caption":[167],"Model":[168],"Global":[170],"Attention":[171],"(DCM-GA)":[172],"over":[173],"state-of-the-art":[174],"methods":[175],"ActivityNet":[178],"Captions":[179],"dataset.":[180]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}