{"id":"https://openalex.org/W4220790454","doi":"https://doi.org/10.1109/tip.2022.3158546","title":"Long Short-Term Relation Transformer With Global Gating for Video Captioning","display_name":"Long Short-Term Relation Transformer With Global Gating for Video Captioning","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4220790454","doi":"https://doi.org/10.1109/tip.2022.3158546","pmid":"https://pubmed.ncbi.nlm.nih.gov/35324439"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2022.3158546","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2022.3158546","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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":"Liang Li","orcid":"https://orcid.org/0000-0001-8437-4824"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Liang Li","raw_affiliation_strings":["Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004694827","display_name":"Xingyu Gao","orcid":"https://orcid.org/0000-0002-4660-8092"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210119392","display_name":"Institute of Microelectronics","ror":"https://ror.org/02s6gs133","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210119392"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingyu Gao","raw_affiliation_strings":["Institute of Microelectronics, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Microelectronics, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210119392","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088526694","display_name":"Jincan Deng","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jincan Deng","raw_affiliation_strings":["Kuaishou Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Kuaishou Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021557044","display_name":"Yunbin Tu","orcid":"https://orcid.org/0000-0002-9525-9060"},"institutions":[{"id":"https://openalex.org/I10660446","display_name":"Kunming University of Science and Technology","ror":"https://ror.org/00xyeez13","country_code":"CN","type":"education","lineage":["https://openalex.org/I10660446"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunbin Tu","raw_affiliation_strings":["Kunming University of Science and Technology, Yunnan, China"],"affiliations":[{"raw_affiliation_string":"Kunming University of Science and Technology, Yunnan, China","institution_ids":["https://openalex.org/I10660446"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003217535","display_name":"Zheng-Jun Zha","orcid":"https://orcid.org/0000-0003-2510-8993"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng-Jun Zha","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028597017","display_name":"Qingming Huang","orcid":"https://orcid.org/0000-0001-7542-296X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingming Huang","raw_affiliation_strings":["Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"],"apc_list":null,"apc_paid":null,"fwci":8.7789,"has_fulltext":false,"cited_by_count":92,"citation_normalized_percentile":{"value":0.98616998,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"31","issue":null,"first_page":"2726","last_page":"2738"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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":0.9987999796867371,"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":0.9933000206947327,"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":0.766467273235321},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.6913657188415527},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.5520890951156616},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5458711385726929},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.5077542066574097},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4643659293651581},{"id":"https://openalex.org/keywords/spatial-relation","display_name":"Spatial relation","score":0.4628976881504059},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.4608457088470459},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.4243176579475403},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4201597273349762},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3379392623901367},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.303519070148468}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.766467273235321},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.6913657188415527},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.5520890951156616},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5458711385726929},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.5077542066574097},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4643659293651581},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.4628976881504059},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.4608457088470459},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.4243176579475403},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4201597273349762},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3379392623901367},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.303519070148468},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2022.3158546","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2022.3158546","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},{"id":"pmid:35324439","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35324439","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2446480051","display_name":null,"funder_award_id":"2020108","funder_id":"https://openalex.org/F4320321133","funder_display_name":"Chinese Academy of Sciences"},{"id":"https://openalex.org/G4908610437","display_name":null,"funder_award_id":"2018AAA0102003","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G5801878730","display_name":null,"funder_award_id":"2021PP15002000","funder_id":"https://openalex.org/F4320316084","funder_display_name":"China Computer Federation"},{"id":"https://openalex.org/G8232626336","display_name":null,"funder_award_id":"61771457","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8641854563","display_name":null,"funder_award_id":"61702491","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320316084","display_name":"China Computer Federation","ror":"https://ror.org/015xj5w40"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321133","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":83,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W877909479","https://openalex.org/W1522734439","https://openalex.org/W1586939924","https://openalex.org/W1632013789","https://openalex.org/W1956340063","https://openalex.org/W2064675550","https://openalex.org/W2101105183","https://openalex.org/W2133459682","https://openalex.org/W2142900973","https://openalex.org/W2157331557","https://openalex.org/W2194775991","https://openalex.org/W2425121537","https://openalex.org/W2506483933","https://openalex.org/W2554906389","https://openalex.org/W2558834163","https://openalex.org/W2560346187","https://openalex.org/W2625940279","https://openalex.org/W2737030113","https://openalex.org/W2745461083","https://openalex.org/W2765658575","https://openalex.org/W2806331055","https://openalex.org/W2885520603","https://openalex.org/W2887712318","https://openalex.org/W2890531016","https://openalex.org/W2905145027","https://openalex.org/W2909502737","https://openalex.org/W2945223572","https://openalex.org/W2948358897","https://openalex.org/W2951390634","https://openalex.org/W2962681491","https://openalex.org/W2962899219","https://openalex.org/W2962990649","https://openalex.org/W2963076818","https://openalex.org/W2963101956","https://openalex.org/W2963349562","https://openalex.org/W2963351113","https://openalex.org/W2963524571","https://openalex.org/W2963971014","https://openalex.org/W2964051675","https://openalex.org/W2964101993","https://openalex.org/W2964350391","https://openalex.org/W2970768710","https://openalex.org/W2979437663","https://openalex.org/W2979739834","https://openalex.org/W2981663434","https://openalex.org/W2982515679","https://openalex.org/W2983256121","https://openalex.org/W2984862483","https://openalex.org/W2988753485","https://openalex.org/W2993235622","https://openalex.org/W3001208314","https://openalex.org/W3009192917","https://openalex.org/W3019301826","https://openalex.org/W3034221024","https://openalex.org/W3035365026","https://openalex.org/W3035372819","https://openalex.org/W3035392611","https://openalex.org/W3093225449","https://openalex.org/W3093309253","https://openalex.org/W3110761028","https://openalex.org/W3125154076","https://openalex.org/W3175933895","https://openalex.org/W3205898195","https://openalex.org/W4206621053","https://openalex.org/W6631190155","https://openalex.org/W6639432524","https://openalex.org/W6679434410","https://openalex.org/W6680145277","https://openalex.org/W6682631176","https://openalex.org/W6684090549","https://openalex.org/W6726873649","https://openalex.org/W6739901393","https://openalex.org/W6746451923","https://openalex.org/W6758859460","https://openalex.org/W6761628794","https://openalex.org/W6768853884","https://openalex.org/W6772565011","https://openalex.org/W6775054590","https://openalex.org/W6776048684","https://openalex.org/W6796767996","https://openalex.org/W6798016242","https://openalex.org/W6803023527"],"related_works":["https://openalex.org/W4320016117","https://openalex.org/W2547835662","https://openalex.org/W3183824823","https://openalex.org/W3008515501","https://openalex.org/W2923366293","https://openalex.org/W3025136821","https://openalex.org/W3035237998","https://openalex.org/W2036778696","https://openalex.org/W4372266864","https://openalex.org/W4309795810"],"abstract_inverted_index":{"Video":[0],"captioning":[1],"aims":[2],"to":[3,9,58,91,118,143,170],"generate":[4],"a":[5,15,75,101,127,136],"natural":[6],"language":[7],"sentence":[8],"describe":[10],"the":[11,28,44,69,80,93,123,164,186,208],"main":[12],"content":[13],"of":[14,27,68,74,82,160,204,210],"video.":[16],"Since":[17],"there":[18],"are":[19],"multiple":[20],"objects":[21,46,148],"in":[22,96],"videos,":[23],"taking":[24],"full":[25,66],"exploration":[26],"spatial":[29,70,110],"and":[30,50,71,77,86,113,149,181,206],"temporal":[31,72],"relationships":[32],"among":[33],"them":[34],"is":[35],"crucial":[36],"for":[37,175],"this":[38,97],"task.":[39],"The":[40,195],"previous":[41],"methods":[42],"wrap":[43],"detected":[45],"as":[47],"input":[48],"sequences,":[49],"leverage":[51],"vanilla":[52],"self-attention":[53],"or":[54],"graph":[55,104,130],"neural":[56],"network":[57],"reason":[59],"about":[60],"visual":[61],"relations.":[62],"This":[63],"cannot":[64],"make":[65],"use":[67],"nature":[73],"video,":[76],"suffers":[78],"from":[79],"problems":[81],"redundant":[83],"connections,":[84],"over-smoothing,":[85],"relation":[87,151,167],"ambiguity.":[88,152],"In":[89],"order":[90],"address":[92],"above":[94],"problems,":[95],"paper":[98],"we":[99,125,162],"construct":[100],"long":[102,165],"short-term":[103,109,166],"(LSTG)":[105],"that":[106,185,199],"simultaneously":[107],"captures":[108],"semantic":[111],"relations":[112,174],"long-term":[114],"transformation":[115],"dependencies.":[116],"Further,":[117],"perform":[119],"relational":[120,211],"reasoning":[121,131],"over":[122],"LSTG,":[124],"design":[126],"global":[128,137,141],"gated":[129],"module":[132],"(G3RM),":[133],"which":[134],"introduces":[135],"gating":[138],"based":[139],"on":[140,179],"context":[142],"control":[144],"information":[145],"propagation":[146],"between":[147],"alleviate":[150],"Finally,":[153],"by":[154],"introducing":[155],"G3RM":[156],"into":[157],"Transformer":[158],"instead":[159],"self-attention,":[161],"propose":[163],"transformer":[168],"(LSRT)":[169],"fully":[171],"mine":[172],"objects'":[173],"caption":[176],"generation.":[177],"Experiments":[178],"MSVD":[180],"MSR-VTT":[182],"datasets":[183],"show":[184],"LSRT":[187],"achieves":[188],"superior":[189],"performance":[190],"compared":[191],"with":[192],"state-of-the-art":[193],"methods.":[194],"visualization":[196],"results":[197],"indicate":[198],"our":[200],"method":[201],"alleviates":[202],"problem":[203],"over-smoothing":[205],"strengthens":[207],"ability":[209],"reasoning.":[212]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":19},{"year":2024,"cited_by_count":33},{"year":2023,"cited_by_count":27},{"year":2022,"cited_by_count":7}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}