{"id":"https://openalex.org/W4316660552","doi":"https://doi.org/10.1109/vcip56404.2022.10008808","title":"STSI: Efficiently Mine Spatio- Temporal Semantic Information between Different Multimodal for Video Captioning","display_name":"STSI: Efficiently Mine Spatio- Temporal Semantic Information between Different Multimodal for Video Captioning","publication_year":2022,"publication_date":"2022-12-13","ids":{"openalex":"https://openalex.org/W4316660552","doi":"https://doi.org/10.1109/vcip56404.2022.10008808"},"language":"en","primary_location":{"id":"doi:10.1109/vcip56404.2022.10008808","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/vcip56404.2022.10008808","pdf_url":null,"source":{"id":"https://openalex.org/S4363608486","display_name":"2022 IEEE International Conference on Visual Communications and Image Processing (VCIP)","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 Conference on Visual Communications and Image Processing (VCIP)","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/A5109503011","display_name":"Huiyu Xiong","orcid":"https://orcid.org/0000-0002-3216-3643"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Huiyu Xiong","raw_affiliation_strings":["School of Information and Communication Engineering, University of Electronic Science and Technology of China,Chengdu,China","School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, University of Electronic Science and Technology of China,Chengdu,China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067691968","display_name":"Lanxiao Wang","orcid":"https://orcid.org/0000-0002-3745-0262"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lanxiao Wang","raw_affiliation_strings":["School of Information and Communication Engineering, University of Electronic Science and Technology of China,Chengdu,China","School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, University of Electronic Science and Technology of China,Chengdu,China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5109503011"],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1858691,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"28","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":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":0.9987999796867371,"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":0.9980999827384949,"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/computer-science","display_name":"Computer science","score":0.8878734111785889},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.8855918645858765},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6475581526756287},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5825652480125427},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5636465549468994},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.561416745185852},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5345980525016785},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.532001793384552},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5299621224403381},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.510202169418335},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.49591025710105896},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.457429975271225},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.21021798253059387}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8878734111785889},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8855918645858765},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6475581526756287},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5825652480125427},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5636465549468994},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.561416745185852},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5345980525016785},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.532001793384552},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5299621224403381},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.510202169418335},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49591025710105896},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.457429975271225},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.21021798253059387},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/vcip56404.2022.10008808","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/vcip56404.2022.10008808","pdf_url":null,"source":{"id":"https://openalex.org/S4363608486","display_name":"2022 IEEE International Conference on Visual Communications and Image Processing (VCIP)","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 Conference on Visual Communications and Image Processing (VCIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6600000262260437}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1522301498","https://openalex.org/W1586939924","https://openalex.org/W1596841185","https://openalex.org/W1601567445","https://openalex.org/W1607035479","https://openalex.org/W1889081078","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2117539524","https://openalex.org/W2133564696","https://openalex.org/W2139501017","https://openalex.org/W2142900973","https://openalex.org/W2154652894","https://openalex.org/W2425121537","https://openalex.org/W2527349934","https://openalex.org/W2547875792","https://openalex.org/W2600463316","https://openalex.org/W2619947201","https://openalex.org/W2745461083","https://openalex.org/W2766375149","https://openalex.org/W2948358897","https://openalex.org/W2950579554","https://openalex.org/W2962681491","https://openalex.org/W2962861647","https://openalex.org/W2962907269","https://openalex.org/W2962990649","https://openalex.org/W2963524571","https://openalex.org/W2963843052","https://openalex.org/W2964241990","https://openalex.org/W2964350391","https://openalex.org/W2988753485","https://openalex.org/W2990964949","https://openalex.org/W3035365026","https://openalex.org/W3035372819","https://openalex.org/W3035392611","https://openalex.org/W3093309253","https://openalex.org/W3209772048","https://openalex.org/W3217578129","https://openalex.org/W4200621741","https://openalex.org/W4205312796","https://openalex.org/W4225620527","https://openalex.org/W6620707391","https://openalex.org/W6678262379","https://openalex.org/W6682631176","https://openalex.org/W6684090549"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W3088136942","https://openalex.org/W2949362007","https://openalex.org/W2775506363","https://openalex.org/W4290852288","https://openalex.org/W4388893791","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393"],"abstract_inverted_index":{"As":[0],"one":[1],"of":[2,20,45,93,134],"the":[3,18,57,62,74,84,91,105,121,125,131,154,170],"challenging":[4],"tasks":[5],"in":[6,67,111],"computer":[7],"vision,":[8],"video":[9],"captioning":[10],"needs":[11],"to":[12,16,36,60,103,145,169],"use":[13,97],"natural":[14],"language":[15],"describe":[17],"content":[19],"video.":[21,68],"Video":[22],"contains":[23],"complex":[24],"information,":[25,29],"such":[26],"as":[27,130],"semantic":[28,99],"time":[30,113,127],"information":[31,46,100],"and":[32,42,78,108,114,177],"so":[33],"on.":[34],"How":[35],"synthesize":[37],"sentences":[38,148],"effectively":[39],"from":[40],"rich":[41],"different":[43,65],"kinds":[44],"is":[47,117,128,143,167],"very":[48],"significant.":[49],"The":[50,156],"existing":[51,75],"methods":[52,172],"often":[53],"cannot":[54],"well":[55],"integrate":[56],"multimodal":[58,88],"feature":[59],"predict":[61],"association":[63],"between":[64,87],"objects":[66],"In":[69],"this":[70],"paper,":[71],"we":[72,96],"improve":[73],"encoder-decoder":[76],"structure":[77],"propose":[79],"a":[80,139],"network":[81],"deeply":[82],"mining":[83,101],"spatio-temporal":[85,98],"correlation":[86],"features.":[89],"Through":[90],"analysis":[92],"sentence":[94],"components,":[95],"module":[102],"fuse":[104],"object,":[106],"2D":[107],"3D":[109],"features":[110],"both":[112],"space.":[115],"It":[116],"worth":[118],"mentioning":[119],"that":[120,149,164],"word":[122],"output":[123,146],"at":[124],"previous":[126],"added":[129],"prediction":[132],"branch":[133],"auxiliary":[135],"conjunctions.":[136],"After":[137],"that,":[138],"dynamic":[140],"gumbel":[141],"scorer":[142],"used":[144],"caption":[147],"are":[150],"more":[151,175],"consistent":[152],"with":[153],"facts.":[155],"experimental":[157],"results":[158],"on":[159],"two":[160],"benchmark":[161],"datasets":[162],"show":[163],"our":[165],"STSI":[166],"superior":[168],"state-of-the-art":[171],"while":[173],"generating":[174],"reasonable":[176],"semantic-logical":[178],"sentences.":[179]},"counts_by_year":[],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}