{"id":"https://openalex.org/W4293061975","doi":"https://doi.org/10.1049/cvi2.12103","title":"Exploring the Spatio\u2010Temporal Aware Graph for video captioning","display_name":"Exploring the Spatio\u2010Temporal Aware Graph for video captioning","publication_year":2022,"publication_date":"2022-05-24","ids":{"openalex":"https://openalex.org/W4293061975","doi":"https://doi.org/10.1049/cvi2.12103"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1049/cvi2.12103","pdf_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1049/cvi2.12103","source":{"id":"https://openalex.org/S166929102","display_name":"IET Computer Vision","issn_l":"1751-9632","issn":["1751-9632","1751-9640"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311714","host_organization_name":"Institution of Engineering and Technology","host_organization_lineage":["https://openalex.org/P4310311714"],"host_organization_lineage_names":["Institution of Engineering and Technology"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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://onlinelibrary.wiley.com/doi/pdfdirect/10.1049/cvi2.12103","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013517923","display_name":"Ping Xue","orcid":"https://orcid.org/0000-0003-0013-7923"},"institutions":[{"id":"https://openalex.org/I100188998","display_name":"Harbin University of Science and Technology","ror":"https://ror.org/04e6y1282","country_code":"CN","type":"education","lineage":["https://openalex.org/I100188998"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ping Xue","raw_affiliation_strings":["School of Measurement and Communication Engineering, Harbin University of Science and Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"School of Measurement and Communication Engineering, Harbin University of Science and Technology, Harbin, China","institution_ids":["https://openalex.org/I100188998"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004576894","display_name":"Bing Zhou","orcid":"https://orcid.org/0000-0001-8966-7423"},"institutions":[{"id":"https://openalex.org/I100188998","display_name":"Harbin University of Science and Technology","ror":"https://ror.org/04e6y1282","country_code":"CN","type":"education","lineage":["https://openalex.org/I100188998"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing Zhou","raw_affiliation_strings":["Institute of Automation, Harbin University of Science and Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Harbin University of Science and Technology, Harbin, China","institution_ids":["https://openalex.org/I100188998"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5013517923"],"corresponding_institution_ids":["https://openalex.org/I100188998"],"apc_list":{"value":2000,"currency":"EUR","value_usd":2200,"provenance":"doaj"},"apc_paid":{"value":2000,"currency":"EUR","value_usd":2200,"provenance":"doaj"},"fwci":0.149,"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":1,"citation_normalized_percentile":{"value":0.356739,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":60,"max":70},"biblio":{"volume":"16","issue":"5","first_page":"456","last_page":"467"},"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":0.9996,"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":0.9951,"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/discriminative-model","display_name":"Discriminative model","score":0.5288989},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.50250196},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.44116676}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8535518},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6836489},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.64565575},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5417486},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5288989},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.50250196},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.44236267},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.44116676},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.42990285},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4187461},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.41671482},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.35544753},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.09662077},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.08990443},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"is_oa":true,"landing_page_url":"https://doi.org/10.1049/cvi2.12103","pdf_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1049/cvi2.12103","source":{"id":"https://openalex.org/S166929102","display_name":"IET Computer Vision","issn_l":"1751-9632","issn":["1751-9632","1751-9640"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311714","host_organization_name":"Institution of Engineering and Technology","host_organization_lineage":["https://openalex.org/P4310311714"],"host_organization_lineage_names":["Institution of Engineering and Technology"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":false,"landing_page_url":"https://doaj.org/article/49a322594e9141f482e95640413566e1","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_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/10.1049/cvi2.12103","pdf_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1049/cvi2.12103","source":{"id":"https://openalex.org/S166929102","display_name":"IET Computer Vision","issn_l":"1751-9632","issn":["1751-9632","1751-9640"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311714","host_organization_name":"Institution of Engineering and Technology","host_organization_lineage":["https://openalex.org/P4310311714"],"host_organization_lineage_names":["Institution of Engineering and Technology"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},"sustainable_development_goals":[{"score":0.72,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":60,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1522734439","https://openalex.org/W1573040851","https://openalex.org/W1586939924","https://openalex.org/W1607035479","https://openalex.org/W1861492603","https://openalex.org/W1889081078","https://openalex.org/W1904365287","https://openalex.org/W1956340063","https://openalex.org/W2110933980","https://openalex.org/W2133512280","https://openalex.org/W2133564696","https://openalex.org/W2139501017","https://openalex.org/W2142900973","https://openalex.org/W2152984213","https://openalex.org/W2194775991","https://openalex.org/W2425121537","https://openalex.org/W2507009361","https://openalex.org/W2559655401","https://openalex.org/W2565639579","https://openalex.org/W2604272474","https://openalex.org/W2608988379","https://openalex.org/W2612690371","https://openalex.org/W2766520430","https://openalex.org/W2806331055","https://openalex.org/W2807834696","https://openalex.org/W2808203533","https://openalex.org/W2883429621","https://openalex.org/W2886970679","https://openalex.org/W2890531016","https://openalex.org/W2911590702","https://openalex.org/W2948358897","https://openalex.org/W2951390634","https://openalex.org/W2953461088","https://openalex.org/W2954137266","https://openalex.org/W2962907269","https://openalex.org/W2963076818","https://openalex.org/W2963091558","https://openalex.org/W2963150697","https://openalex.org/W2963155035","https://openalex.org/W2963524571","https://openalex.org/W2963820951","https://openalex.org/W2964015378","https://openalex.org/W2964241990","https://openalex.org/W2981699264","https://openalex.org/W2981750519","https://openalex.org/W2984862483","https://openalex.org/W2986407524","https://openalex.org/W2988753485","https://openalex.org/W2990152177","https://openalex.org/W3034221024","https://openalex.org/W3035392611","https://openalex.org/W3041874265","https://openalex.org/W3104915307","https://openalex.org/W3117344638","https://openalex.org/W3151123052","https://openalex.org/W3190318906","https://openalex.org/W3205898187","https://openalex.org/W4287231898","https://openalex.org/W4295312788"],"related_works":["https://openalex.org/W4388893791","https://openalex.org/W4290852288","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":{"Describing":[0],"video":[1,129,135],"content":[2],"automatically":[3],"in":[4,12,28,172],"natural":[5],"language":[6],"sentences":[7],"is":[8,54,83,104,138],"a":[9,49,100],"long-standing":[10],"challenge":[11],"computer":[13],"vision.":[14],"Although":[15],"existing":[16],"methods":[17],"that":[18,120,137,165],"capture":[19,57,127],"relational":[20],"information":[21,37,119],"among":[22,91],"objects":[23,39,92],"have":[24],"made":[25],"significant":[26],"strides":[27],"the":[29,32,67,72,80,89,95,117,121,151,166],"past":[30],"years,":[31],"detailed":[33,68,96],"geometrical":[34],"and":[35,140,158,181],"temporal":[36],"of":[38,71,85],"remains":[40],"to":[41,56,65,109,115,126,145,162],"be":[42],"further":[43],"explored.":[44],"To":[45],"address":[46],"this":[47],"problem,":[48],"novel":[50],"Spatio-Temporal":[51],"Aware":[52],"Graph":[53,103],"proposed":[55,81,167],"more":[58],"elaborate":[59],"visual":[60],"representations,":[61,112,136],"which":[62,113],"are":[63,143],"able":[64],"exploit":[66],"spatio-temporal":[69,97],"clues":[70],"extracted":[73],"object":[74,122],"features.":[75],"By":[76],"performing":[77],"graph-structured":[78],"aggregation,":[79],"model":[82],"capable":[84],"capturing":[86],"not":[87],"only":[88],"interactions":[90],"but":[93],"also":[94],"relations.":[98],"Meanwhile,":[99],"Frame":[101],"Similarity":[102],"constructed":[105],"on":[106,150],"frame":[107],"features":[108],"learn":[110,146],"comprehensive":[111],"aim":[114],"extract":[116],"global":[118],"feature":[123],"lacks.":[124],"Moreover,":[125],"rich":[128],"semantics":[130],"from":[131],"different":[132],"perspectives,":[133],"multiple":[134],"appearance":[139],"motion":[141],"information,":[142],"utilised":[144],"discriminative":[147],"representations.":[148],"Experiments":[149],"prevalent":[152],"benchmarks:":[153],"Microsoft":[154,159],"Video":[155,161],"Description":[156],"Corpus":[157],"Research":[160],"Text":[163],"demonstrate":[164],"approach":[168],"achieves":[169],"state-of-the-art":[170],"performance":[171],"several":[173],"widely":[174],"used":[175],"evaluation":[176],"metrics:":[177],"BLEU-4,":[178],"METEOR,":[179],"ROUGE,":[180],"CIDEr.":[182]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4293061975","counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2024-12-13T16:35:43.025176","created_date":"2022-08-26"}