{"id":"https://openalex.org/W2899879331","doi":"https://doi.org/10.1109/access.2018.2879642","title":"A Fine-Grained Spatial-Temporal Attention Model for Video Captioning","display_name":"A Fine-Grained Spatial-Temporal Attention Model for Video Captioning","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2899879331","doi":"https://doi.org/10.1109/access.2018.2879642","mag":"2899879331"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2018.2879642","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_indexed_in_scopus":true,"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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true},"type":"article","type_crossref":"journal-article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2018.2879642","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081485810","display_name":"An-An Liu","orcid":"https://orcid.org/0000-0001-5755-9145"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"funder","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"An-An Liu","raw_affiliation_strings":["School of Electrical and Information Engineering, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058955781","display_name":"Yurui Qiu","orcid":null},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"funder","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yurui Qiu","raw_affiliation_strings":["School of Electrical and Information Engineering, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020006712","display_name":"Yongkang Wong","orcid":"https://orcid.org/0000-0002-1239-4428"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"funder","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yongkang Wong","raw_affiliation_strings":["Smart Systems Institute, National University of Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Smart Systems Institute, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033713097","display_name":"Yuting Su","orcid":"https://orcid.org/0000-0001-5165-204X"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"funder","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu-Ting Su","raw_affiliation_strings":["School of Electrical and Information Engineering, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016415049","display_name":"Mohan Kankanhalli","orcid":"https://orcid.org/0000-0002-4846-2015"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"funder","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Mohan Kankanhalli","raw_affiliation_strings":["School of Computing, National University of Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institution_assertions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":1.81,"has_fulltext":true,"fulltext_origin":"ngrams","cited_by_count":24,"citation_normalized_percentile":{"value":0.801967,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":92,"max":93},"biblio":{"volume":"6","issue":null,"first_page":"68463","last_page":"68471"},"is_retracted":false,"is_paratext":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":0.9982,"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":0.9971,"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":0.9443973},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.5868082},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5614278}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9443973},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.89730346},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.60011256},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.5868082},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5614278},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5194137},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.43976825},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.15124702},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2018.2879642","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_indexed_in_scopus":true,"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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":false,"landing_page_url":"https://doaj.org/article/ca1457f3a56e495ebc2d01044b7abccd","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2018.2879642","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_indexed_in_scopus":true,"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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.66,"display_name":"Quality education"}],"grants":[{"funder":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China","award_id":"61472275"},{"funder":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China","award_id":"61772359"}],"datasets":[],"versions":[],"referenced_works_count":45,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1573040851","https://openalex.org/W1586939924","https://openalex.org/W1799366690","https://openalex.org/W1956340063","https://openalex.org/W2095705004","https://openalex.org/W2101105183","https://openalex.org/W2110933980","https://openalex.org/W2133459682","https://openalex.org/W2133564696","https://openalex.org/W2139501017","https://openalex.org/W2142900973","https://openalex.org/W2157331557","https://openalex.org/W2164290393","https://openalex.org/W2194775991","https://openalex.org/W2251353663","https://openalex.org/W2294130536","https://openalex.org/W2327894203","https://openalex.org/W2425121537","https://openalex.org/W2520861906","https://openalex.org/W2556388456","https://openalex.org/W2558834163","https://openalex.org/W2565639579","https://openalex.org/W2565656701","https://openalex.org/W2594785588","https://openalex.org/W2613718673","https://openalex.org/W2613964630","https://openalex.org/W2621571501","https://openalex.org/W2740388348","https://openalex.org/W2742570236","https://openalex.org/W2766375149","https://openalex.org/W2766520430","https://openalex.org/W2767073696","https://openalex.org/W2799256316","https://openalex.org/W2800791174","https://openalex.org/W2962958773","https://openalex.org/W2963037989","https://openalex.org/W2963150697","https://openalex.org/W2963576560","https://openalex.org/W2963630207","https://openalex.org/W2963811219","https://openalex.org/W2964018924","https://openalex.org/W2964241990","https://openalex.org/W639708223","https://openalex.org/W6908809"],"related_works":["https://openalex.org/W4290852288","https://openalex.org/W4289422896","https://openalex.org/W4283207562","https://openalex.org/W4210416330","https://openalex.org/W3088136942","https://openalex.org/W2963177403","https://openalex.org/W2949522393","https://openalex.org/W2949362007","https://openalex.org/W2775506363","https://openalex.org/W2330246314"],"abstract_inverted_index":{"Attention":[0],"mechanism":[1,27,118],"has":[2],"been":[3],"extensively":[4],"used":[5],"in":[6,75],"video":[7,21,77],"captioning":[8,22],"tasks,":[9],"which":[10,32],"enables":[11],"further":[12],"development":[13],"of":[14,72,97,150],"deeper":[15],"visual":[16,50],"understanding.":[17],"However,":[18],"most":[19],"existing":[20],"methods":[23],"apply":[24],"the":[25,29,35,43,54,69,76,84,89,100,106,124,148,151],"attention":[26,65,91,109,117],"on":[28,127,153],"frame":[30],"level,":[31],"only":[33],"model":[34,66,126,142],"temporal":[36,107],"structure":[37],"and":[38,68,104,133],"generated":[39],"words,":[40],"but":[41],"ignore":[42],"region-level":[44],"spatial":[45,70],"information":[46,71],"that":[47,138],"provides":[48],"accurate":[49],"features":[51],"corresponding":[52],"to":[53,119],"semantic":[55],"content.":[56],"In":[57,83],"this":[58],"paper,":[59],"we":[60,87],"propose":[61],"a":[62,93,112],"fine-grained":[63,94],"spatial-temporal":[64],"(FSTA),":[67],"objects":[73,98],"appearing":[74],"will":[78],"be":[79],"our":[80,139],"main":[81],"concern.":[82],"proposed":[85,125,140],"FSTA,":[86],"achieve":[88,144],"spatial-hard":[90],"at":[92],"region":[95],"level":[96],"through":[99],"mask":[101],"pooling":[102],"module":[103],"compute":[105],"soft":[108],"by":[110],"using":[111],"two-layer":[113],"LSTM":[114],"network":[115],"with":[116],"generate":[120],"sentences.":[121],"We":[122],"test":[123],"two":[128],"benchmark":[129],"datasets,":[130],"namely,":[131],"MSVD":[132],"MSR-VTT.":[134],"The":[135],"results":[136],"indicate":[137],"FSTA":[141],"can":[143],"competitive":[145],"performance":[146],"against":[147],"state":[149],"arts":[152],"both":[154],"datasets.":[155]},"abstract_inverted_index_v3":null,"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2899879331","counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":5}],"updated_date":"2025-05-03T13:01:38.630397","created_date":"2018-11-16"}