{"id":"https://openalex.org/W3209267444","doi":"https://doi.org/10.1109/icspcc52875.2021.9564796","title":"The Video Captioning Method Based On The Spatial- Temporal Information and Attention Mechanism","display_name":"The Video Captioning Method Based On The Spatial- Temporal Information and Attention Mechanism","publication_year":2021,"publication_date":"2021-08-17","ids":{"openalex":"https://openalex.org/W3209267444","doi":"https://doi.org/10.1109/icspcc52875.2021.9564796","mag":"3209267444"},"language":"en","primary_location":{"id":"doi:10.1109/icspcc52875.2021.9564796","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icspcc52875.2021.9564796","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC)","raw_type":"proceedings-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/A5085280616","display_name":"Ou Ye","orcid":"https://orcid.org/0000-0002-4134-9191"},"institutions":[{"id":"https://openalex.org/I110440473","display_name":"Xi'an University of Science and Technology","ror":"https://ror.org/046fkpt18","country_code":"CN","type":"education","lineage":["https://openalex.org/I110440473"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ou Ye","raw_affiliation_strings":["Xi&#x0027;an University of Science and Technology,School of Computer Science and Technology,Xi&#x0027;an,China"],"affiliations":[{"raw_affiliation_string":"Xi&#x0027;an University of Science and Technology,School of Computer Science and Technology,Xi&#x0027;an,China","institution_ids":["https://openalex.org/I110440473"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101706896","display_name":"Tao Liu","orcid":"https://orcid.org/0000-0003-3897-9085"},"institutions":[{"id":"https://openalex.org/I110440473","display_name":"Xi'an University of Science and Technology","ror":"https://ror.org/046fkpt18","country_code":"CN","type":"education","lineage":["https://openalex.org/I110440473"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Liu","raw_affiliation_strings":["Xi&#x0027;an University of Science and Technology,School of Computer Science and Technology,Xi&#x0027;an,China"],"affiliations":[{"raw_affiliation_string":"Xi&#x0027;an University of Science and Technology,School of Computer Science and Technology,Xi&#x0027;an,China","institution_ids":["https://openalex.org/I110440473"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102773413","display_name":"Yan Fu","orcid":"https://orcid.org/0000-0001-9943-7656"},"institutions":[{"id":"https://openalex.org/I110440473","display_name":"Xi'an University of Science and Technology","ror":"https://ror.org/046fkpt18","country_code":"CN","type":"education","lineage":["https://openalex.org/I110440473"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Fu","raw_affiliation_strings":["Xi&#x0027;an University of Science and Technology,School of Computer Science and Technology,Xi&#x0027;an,China"],"affiliations":[{"raw_affiliation_string":"Xi&#x0027;an University of Science and Technology,School of Computer Science and Technology,Xi&#x0027;an,China","institution_ids":["https://openalex.org/I110440473"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112907329","display_name":"Jun Deng","orcid":null},"institutions":[{"id":"https://openalex.org/I110440473","display_name":"Xi'an University of Science and Technology","ror":"https://ror.org/046fkpt18","country_code":"CN","type":"education","lineage":["https://openalex.org/I110440473"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Deng","raw_affiliation_strings":["Xi&#x0027;an University of Science and Technology,School of Computer Science and Technology,Xi&#x0027;an,China"],"affiliations":[{"raw_affiliation_string":"Xi&#x0027;an University of Science and Technology,School of Computer Science and Technology,Xi&#x0027;an,China","institution_ids":["https://openalex.org/I110440473"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101469245","display_name":"Jian Feng","orcid":"https://orcid.org/0000-0003-1154-3695"},"institutions":[{"id":"https://openalex.org/I110440473","display_name":"Xi'an University of Science and Technology","ror":"https://ror.org/046fkpt18","country_code":"CN","type":"education","lineage":["https://openalex.org/I110440473"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Feng","raw_affiliation_strings":["Xi&#x0027;an University of Science and Technology,School of Computer Science and Technology,Xi&#x0027;an,China"],"affiliations":[{"raw_affiliation_string":"Xi&#x0027;an University of Science and Technology,School of Computer Science and Technology,Xi&#x0027;an,China","institution_ids":["https://openalex.org/I110440473"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048577121","display_name":"Yun Zhang","orcid":"https://orcid.org/0000-0002-2369-440X"},"institutions":[{"id":"https://openalex.org/I110440473","display_name":"Xi'an University of Science and Technology","ror":"https://ror.org/046fkpt18","country_code":"CN","type":"education","lineage":["https://openalex.org/I110440473"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yun Zhang","raw_affiliation_strings":["Xi&#x0027;an University of Science and Technology,School of Computer Science and Technology,Xi&#x0027;an,China"],"affiliations":[{"raw_affiliation_string":"Xi&#x0027;an University of Science and Technology,School of Computer Science and Technology,Xi&#x0027;an,China","institution_ids":["https://openalex.org/I110440473"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5085280616"],"corresponding_institution_ids":["https://openalex.org/I110440473"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13852941,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"56","issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9983000159263611,"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":0.991599977016449,"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":0.9167279005050659},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8665633201599121},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6387848854064941},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5579530000686646},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.45717647671699524},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.39052534103393555},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3620821237564087},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.17899075150489807}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9167279005050659},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8665633201599121},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6387848854064941},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5579530000686646},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.45717647671699524},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.39052534103393555},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3620821237564087},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.17899075150489807},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icspcc52875.2021.9564796","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icspcc52875.2021.9564796","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1586939924","https://openalex.org/W1969616664","https://openalex.org/W2109586012","https://openalex.org/W2152984213","https://openalex.org/W2251353663","https://openalex.org/W2493727926","https://openalex.org/W2584535601","https://openalex.org/W2740284552","https://openalex.org/W2963843052","https://openalex.org/W2964241990","https://openalex.org/W3000890708"],"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/W4388913932","https://openalex.org/W4309130263","https://openalex.org/W2138022083"],"abstract_inverted_index":{"In":[0,102],"order":[1],"to":[2,47,75,92,117],"utilize":[3],"the":[4,18,33,40,49,53,60,66,77,87,94,103,107,119,122,130,147,159],"complementarity":[5],"of":[6,13,20,52,72,81,106,121,149],"different":[7,11],"level":[8],"features":[9,51,71,97,124],"in":[10,23,59],"regions":[12,55],"videos":[14],"effectively,":[15],"and":[16,36,42,56,100,128,152],"improve":[17,146],"accuracy":[19,148],"text":[21,131],"description":[22,132],"videos,":[24],"we":[25,85],"propose":[26],"a":[27,82],"video":[28,61,73,126,150],"captioning":[29],"method":[30,143],"based":[31],"on":[32],"spatiotemporal":[34],"information":[35],"attention":[37,113],"mechanism.":[38],"First,":[39],"Faster-RCNN":[41],"VGG-16":[43],"networks":[44],"are":[45],"used":[46],"extract":[48,93],"high-level":[50],"interesting":[54],"significant":[57],"targets":[58],"frames,":[62,127],"respectively.":[63],"Second,":[64],"combing":[65],"low-level":[67],"dense":[68],"traj":[69],"ectory":[70],"frames":[74,99],"represent":[76],"spatial":[78],"appearance":[79],"feature":[80],"video.":[83],"Finally,":[84],"adopt":[86],"long":[88,108],"short-term":[89,109],"memory":[90],"network":[91],"temporal":[95],"association":[96],"between":[98],"texts.":[101],"hidden":[104],"layer":[105],"memory,":[110],"an":[111],"adaptive":[112],"mechanism":[114],"is":[115,133,155],"introduced":[116],"enhance":[118],"representation":[120],"salient":[123],"for":[125],"then":[129],"generated":[134],"automatically.":[135],"The":[136],"experimental":[137],"results":[138],"show":[139],"that":[140],"our":[141],"proposed":[142],"can":[144],"effectively":[145],"captioning,":[151],"its":[153],"performance":[154],"better":[156],"than":[157],"several":[158],"state-of-the-art":[160],"approaches.":[161]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
