{"id":"https://openalex.org/W3115684750","doi":"https://doi.org/10.1109/tcsvt.2020.3045735","title":"Adaptive Spatial Location With Balanced Loss for Video Captioning","display_name":"Adaptive Spatial Location With Balanced Loss for Video Captioning","publication_year":2020,"publication_date":"2020-12-18","ids":{"openalex":"https://openalex.org/W3115684750","doi":"https://doi.org/10.1109/tcsvt.2020.3045735","mag":"3115684750"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2020.3045735","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2020.3045735","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","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/A5101967550","display_name":"Linghui Li","orcid":"https://orcid.org/0000-0002-7614-3142"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Linghui Li","raw_affiliation_strings":["Key Laboratory of Trustworthy Distributed Computing and Service, Beijing University of Posts and Telecommunications, Ministry of Education, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Trustworthy Distributed Computing and Service, Beijing University of Posts and Telecommunications, Ministry of Education, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046305086","display_name":"Yongdong Zhang","orcid":"https://orcid.org/0000-0002-1151-1792"},"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":false,"raw_author_name":"Yongdong Zhang","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/A5056776177","display_name":"Sheng Tang","orcid":"https://orcid.org/0000-0003-3573-2407"},"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":false,"raw_author_name":"Sheng Tang","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/A5075290241","display_name":"Lingxi Xie","orcid":"https://orcid.org/0000-0003-4831-9451"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lingxi Xie","raw_affiliation_strings":["Huawei Technologies Inc., Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Huawei Technologies Inc., Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100673949","display_name":"Xiaoyong Li","orcid":"https://orcid.org/0000-0001-5597-9306"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyong Li","raw_affiliation_strings":["Key Laboratory of Trustworthy Distributed Computing and Service, Beijing University of Posts and Telecommunications, Ministry of Education, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Trustworthy Distributed Computing and Service, Beijing University of Posts and Telecommunications, Ministry of Education, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111504451","display_name":"Qi Tian","orcid":"https://orcid.org/0009-0003-2676-5300"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Tian","raw_affiliation_strings":["Huawei Technologies Inc., Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Huawei Technologies Inc., Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101967550"],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":1.1777,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.81943431,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"32","issue":"1","first_page":"17","last_page":"30"},"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":0.9987000226974487,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9898999929428101,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.8772069215774536},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.752966582775116},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.6994783878326416},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5564584136009216},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.542367160320282},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5237812399864197},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.4673479199409485},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4331764876842499},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.40389150381088257},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1611105501651764}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8772069215774536},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.752966582775116},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.6994783878326416},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5564584136009216},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.542367160320282},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5237812399864197},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.4673479199409485},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4331764876842499},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.40389150381088257},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1611105501651764},{"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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2020.3045735","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2020.3045735","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G3537652289","display_name":null,"funder_award_id":"61871004","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6702848871","display_name":null,"funder_award_id":"2020TQ0055","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"},{"id":"https://openalex.org/G7415212279","display_name":null,"funder_award_id":"U1836215","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8290336390","display_name":null,"funder_award_id":"61525206","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"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"},{"id":"https://openalex.org/F4320335800","display_name":"Key Laboratory of Trustworthy Distributed Computing and Service of Ministry of Education","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":86,"referenced_works":["https://openalex.org/W179875071","https://openalex.org/W877909479","https://openalex.org/W1573040851","https://openalex.org/W1586939924","https://openalex.org/W1595717062","https://openalex.org/W1686810756","https://openalex.org/W1810943226","https://openalex.org/W1956340063","https://openalex.org/W1993229407","https://openalex.org/W1995820507","https://openalex.org/W2016053056","https://openalex.org/W2101105183","https://openalex.org/W2110933980","https://openalex.org/W2133512280","https://openalex.org/W2139501017","https://openalex.org/W2142900973","https://openalex.org/W2152984213","https://openalex.org/W2157331557","https://openalex.org/W2176091656","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2213342961","https://openalex.org/W2274862467","https://openalex.org/W2425121537","https://openalex.org/W2507365558","https://openalex.org/W2508429489","https://openalex.org/W2523937091","https://openalex.org/W2523993696","https://openalex.org/W2554906389","https://openalex.org/W2555186239","https://openalex.org/W2556388456","https://openalex.org/W2558834163","https://openalex.org/W2560346187","https://openalex.org/W2604201385","https://openalex.org/W2604729005","https://openalex.org/W2621571501","https://openalex.org/W2625940279","https://openalex.org/W2737030113","https://openalex.org/W2739107216","https://openalex.org/W2754689878","https://openalex.org/W2766237723","https://openalex.org/W2798725893","https://openalex.org/W2803620531","https://openalex.org/W2806224701","https://openalex.org/W2884561390","https://openalex.org/W2887712318","https://openalex.org/W2889418103","https://openalex.org/W2896380152","https://openalex.org/W2918626955","https://openalex.org/W2951390634","https://openalex.org/W2962681491","https://openalex.org/W2962907269","https://openalex.org/W2962990649","https://openalex.org/W2963177403","https://openalex.org/W2963351113","https://openalex.org/W2963410018","https://openalex.org/W2963576560","https://openalex.org/W2963699792","https://openalex.org/W2963843052","https://openalex.org/W2963916161","https://openalex.org/W2963971014","https://openalex.org/W2964241990","https://openalex.org/W2984287396","https://openalex.org/W2996794639","https://openalex.org/W3019301826","https://openalex.org/W3034221024","https://openalex.org/W3034467781","https://openalex.org/W3034593503","https://openalex.org/W3034600407","https://openalex.org/W3034636873","https://openalex.org/W3035365026","https://openalex.org/W3035392611","https://openalex.org/W4288083805","https://openalex.org/W6607974698","https://openalex.org/W6637373629","https://openalex.org/W6638273328","https://openalex.org/W6677326919","https://openalex.org/W6679434410","https://openalex.org/W6682631176","https://openalex.org/W6684090549","https://openalex.org/W6685342604","https://openalex.org/W6686164453","https://openalex.org/W6691419566","https://openalex.org/W6695711977","https://openalex.org/W6754478056","https://openalex.org/W6768853884"],"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/W4289422896"],"abstract_inverted_index":{"Many":[0],"pioneering":[1],"approaches":[2],"have":[3,21],"verified":[4],"the":[5,9,45,64,79,83,111,120,134,156,170,177],"effectiveness":[6],"of":[7,74,81,122,152],"utilizing":[8],"global":[10],"temporal":[11,112],"and":[12,20,50,106,118,172],"local":[13,99],"object":[14,29,100],"information":[15,46],"for":[16,63],"video":[17,36,65,76,116],"understanding":[18],"tasks":[19],"achieved":[22],"significant":[23],"progress.":[24],"However,":[25],"existing":[26,138],"methods":[27],"utilize":[28],"detectors":[30],"to":[31,44,132,149,184],"extract":[32],"all":[33],"objects":[34],"overall":[35],"frames.":[37],"This":[38],"may":[39],"bring":[40],"performance":[41,182],"degradation":[42],"due":[43],"redundancy":[47,113],"both":[48],"spatially":[49],"temporally.":[51],"To":[52],"address":[53,133],"this":[54],"problem,":[55],"we":[56,126],"propose":[57,127],"an":[58,71],"adaptive":[59,88],"spatial":[60,89],"location":[61,90],"module":[62],"captioning":[66],"task":[67],"which":[68,159],"dynamically":[69],"predicts":[70],"important":[72],"position":[73],"each":[75,150],"frame":[77],"in":[78,114,139,155],"procedure":[80],"generating":[82],"description":[84,164],"sentence.":[85],"The":[86,142],"proposed":[87,143,178],"method":[91,179],"not":[92],"only":[93],"makes":[94],"our":[95],"model":[96],"focus":[97],"on":[98,169],"information,":[101],"but":[102],"also":[103],"reduces":[104],"time":[105],"memory":[107],"consumption":[108],"brought":[109],"by":[110],"extensive":[115],"frames":[117],"improves":[119],"accuracy":[121],"generated":[123],"description.":[124],"Besides,":[125],"a":[128],"balanced":[129,144],"loss":[130,145],"function":[131],"class":[135],"imbalance":[136],"problem":[137],"training":[140,157],"data.":[141],"assigns":[146],"different":[147],"weight":[148],"word":[151],"ground-truth":[153],"sentence":[154],"process":[158],"can":[160],"generate":[161],"more":[162],"diversified":[163],"sentences.":[165],"Extensive":[166],"experimental":[167],"results":[168],"MSVD":[171],"MSR-VTT":[173],"dataset":[174],"show":[175],"that":[176],"achieves":[180],"competitive":[181],"compared":[183],"state-of-the-art":[185],"methods.":[186]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}