{"id":"https://openalex.org/W4312260630","doi":"https://doi.org/10.1109/iscas48785.2022.9937852","title":"Spatio-temporal Super-resolution Network: Enhance Visual Representations for Video Captioning","display_name":"Spatio-temporal Super-resolution Network: Enhance Visual Representations for Video Captioning","publication_year":2022,"publication_date":"2022-05-28","ids":{"openalex":"https://openalex.org/W4312260630","doi":"https://doi.org/10.1109/iscas48785.2022.9937852"},"language":"en","primary_location":{"id":"doi:10.1109/iscas48785.2022.9937852","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscas48785.2022.9937852","pdf_url":null,"source":{"id":"https://openalex.org/S4363604393","display_name":"2022 IEEE International Symposium on Circuits and Systems (ISCAS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Symposium on Circuits and Systems (ISCAS)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5036640427","display_name":"Quanhui Cao","orcid":null},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Quanhui Cao","raw_affiliation_strings":["Tongji University,Department of Computer Science & Technology,Shanghai,P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University,Department of Computer Science & Technology,Shanghai,P. R. China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019414690","display_name":"Pengjie Tang","orcid":"https://orcid.org/0000-0002-6220-7758"},"institutions":[{"id":"https://openalex.org/I14748160","display_name":"Jinggangshan University","ror":"https://ror.org/04exd0a76","country_code":"CN","type":"education","lineage":["https://openalex.org/I14748160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengjie Tang","raw_affiliation_strings":["Jinggangshan University,College of Electronic and Information Engineering,Ji’an,P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jinggangshan University,College of Electronic and Information Engineering,Ji’an,P. R. China","institution_ids":["https://openalex.org/I14748160"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058982350","display_name":"Hanli Wang","orcid":"https://orcid.org/0000-0002-9999-4871"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanli Wang","raw_affiliation_strings":["Tongji University,Department of Computer Science & Technology,Shanghai,P. R. China","Frontiers Science Center for Intelligent Autonomous Systems, Shanghai, P. R. China","Key Laboratory of Embedded System & Service Computing, Ministry of Education, Tongji University, Shanghai, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University,Department of Computer Science & Technology,Shanghai,P. R. China","institution_ids":["https://openalex.org/I116953780"]},{"raw_affiliation_string":"Frontiers Science Center for Intelligent Autonomous Systems, Shanghai, P. R. China","institution_ids":[]},{"raw_affiliation_string":"Key Laboratory of Embedded System & Service Computing, Ministry of Education, Tongji University, Shanghai, P. R. China","institution_ids":["https://openalex.org/I116953780"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3125","last_page":"3129"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9969000220298767,"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":0.9969000220298767,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9951000213623047,"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":0.9873999953269958,"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":0.9242350459098816},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8542832136154175},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6719748377799988},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5840763449668884},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5567768812179565},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5221205949783325},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5115054845809937},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5006096363067627},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.5000772476196289},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.46339327096939087},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.41526538133621216},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2432335615158081},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.06438776850700378}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9242350459098816},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8542832136154175},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6719748377799988},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5840763449668884},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5567768812179565},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5221205949783325},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5115054845809937},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5006096363067627},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.5000772476196289},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.46339327096939087},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.41526538133621216},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2432335615158081},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06438776850700378},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscas48785.2022.9937852","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscas48785.2022.9937852","pdf_url":null,"source":{"id":"https://openalex.org/S4363604393","display_name":"2022 IEEE International Symposium on Circuits and Systems (ISCAS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Symposium on Circuits and Systems (ISCAS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1586939924","https://openalex.org/W1956340063","https://openalex.org/W2133459682","https://openalex.org/W2139501017","https://openalex.org/W2154652894","https://openalex.org/W2164290393","https://openalex.org/W2194775991","https://openalex.org/W2425121537","https://openalex.org/W2914587137","https://openalex.org/W2950579554","https://openalex.org/W2953461088","https://openalex.org/W2962990649","https://openalex.org/W2963524571","https://openalex.org/W2963843052","https://openalex.org/W2964065937","https://openalex.org/W2984862483","https://openalex.org/W3009192917","https://openalex.org/W3035017890","https://openalex.org/W3035236663","https://openalex.org/W3035365026","https://openalex.org/W3035392611","https://openalex.org/W3093013777","https://openalex.org/W3107848485","https://openalex.org/W3176425931","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6682631176","https://openalex.org/W6684090549","https://openalex.org/W6739901393","https://openalex.org/W6758859460","https://openalex.org/W6762586985","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W2547835662","https://openalex.org/W2607572884","https://openalex.org/W4210446059","https://openalex.org/W187484614","https://openalex.org/W2053675109","https://openalex.org/W2369698754","https://openalex.org/W2580345890","https://openalex.org/W2803822766","https://openalex.org/W1967456564","https://openalex.org/W4250616939"],"abstract_inverted_index":{"Video":[0],"captioning":[1,66,138],"is":[2,23,60],"a":[3,53,78],"sequence-to-sequence":[4],"task":[5,67,72,81],"of":[6,17,39,83,110],"automatically":[7],"generating":[8],"descriptions":[9],"for":[10,25,63],"given":[11],"videos.":[12],"Due":[13],"to":[14,117],"the":[15,37,64,69,133],"diversity":[16],"video":[18,26,65,70,79,137],"scenes,":[19],"learning":[20],"rich":[21],"representations":[22],"critical":[24],"captioning.":[27],"However,":[28],"previous":[29],"works":[30],"mainly":[31],"exploited":[32],"elaborate":[33],"features":[34,91,98],"but":[35],"neglected":[36],"loss":[38],"information":[40],"caused":[41],"by":[42],"frame":[43,97],"sampling":[44],"and":[45,68,122,141],"image":[46,90],"compression.":[47],"In":[48],"this":[49],"paper,":[50],"we":[51],"propose":[52],"novel":[54],"spatio-temporal":[55],"super-resolution":[56,71,80,87,94],"(STSR)":[57],"network":[58],"which":[59],"jointly":[61],"trained":[62],"in":[73],"an":[74],"end-to-end":[75],"fashion.":[76],"Specifically,":[77],"consists":[82],"two":[84,100,112,128],"subtasks:":[85],"spatial":[86],"restores":[88],"high-resolution":[89],"while":[92],"temporal":[93],"reconstructs":[95],"missing":[96],"between":[99],"adjacent":[101],"sampled":[102],"frames.":[103],"By":[104],"sharing":[105],"multi-modal":[106],"encoders":[107,116],"across":[108],"both":[109],"these":[111],"tasks,":[113],"STSR":[114,135],"encourages":[115],"capture":[118],"salient":[119],"visual":[120],"contents":[121],"learn":[123],"context-aware":[124],"representations.":[125],"Experiments":[126],"on":[127],"benchmark":[129],"datasets":[130],"demonstrate":[131],"that":[132],"proposed":[134],"boosts":[136],"performances":[139],"significantly":[140],"outperforms":[142],"most":[143],"state-of-the-art":[144],"approaches.":[145]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}