{"id":"https://openalex.org/W4408353608","doi":"https://doi.org/10.1109/icassp49660.2025.10888725","title":"Spatiotemporal-Aware Visual Captioning using Vision-Language Pre-Training Model","display_name":"Spatiotemporal-Aware Visual Captioning using Vision-Language Pre-Training Model","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353608","doi":"https://doi.org/10.1109/icassp49660.2025.10888725"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888725","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888725","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5066900102","display_name":"Shuai Wu","orcid":"https://orcid.org/0000-0001-7713-1808"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]},{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Wu","raw_affiliation_strings":["Fudan University,School of Computer Science,China","Xi’an Jiaotong University,Faculty of Electronic and Information Engineering,Xi’an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University,School of Computer Science,China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Xi’an Jiaotong University,Faculty of Electronic and Information Engineering,Xi’an,China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108059888","display_name":"Weidong Yang","orcid":"https://orcid.org/0000-0003-1170-3847"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weidong Yang","raw_affiliation_strings":["Fudan University,School of Computer Science,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University,School of Computer Science,China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114225623","display_name":"Shuyan Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]},{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuyan Wu","raw_affiliation_strings":["Fudan University,School of Computer Science,China","Xi’an Jiaotong University,Faculty of Electronic and Information Engineering,Xi’an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University,School of Computer Science,China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Xi’an Jiaotong University,Faculty of Electronic and Information Engineering,Xi’an,China","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4136,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.76760236,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"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":0.996999979019165,"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":0.996999979019165,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9858999848365784,"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":0.9830999970436096,"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":0.9799792766571045},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8309600353240967},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5748658776283264},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5657041072845459},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.48172977566719055},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.45569294691085815},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.45185887813568115},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3683839440345764},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3421829044818878},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2398035228252411}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9799792766571045},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8309600353240967},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5748658776283264},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5657041072845459},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.48172977566719055},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45569294691085815},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.45185887813568115},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3683839440345764},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3421829044818878},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2398035228252411},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888725","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888725","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2886641317","https://openalex.org/W3096935578","https://openalex.org/W3167366812","https://openalex.org/W4402671548","https://openalex.org/W6639432524","https://openalex.org/W6684090549","https://openalex.org/W6717767745","https://openalex.org/W6739901393","https://openalex.org/W6770434407","https://openalex.org/W6772619176","https://openalex.org/W6774102634","https://openalex.org/W6791353385","https://openalex.org/W6793987055","https://openalex.org/W6804001748","https://openalex.org/W6810819044","https://openalex.org/W6850512150","https://openalex.org/W6851592950","https://openalex.org/W6851950068","https://openalex.org/W6857162426","https://openalex.org/W6858817466","https://openalex.org/W6859407189"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W2963177403","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4283207562","https://openalex.org/W2330246314","https://openalex.org/W2949522393","https://openalex.org/W4289422896"],"abstract_inverted_index":{"Current":[0],"visual":[1,7,29,60,64,114],"captioning":[2],"technologies":[3],"typically":[4],"transform":[5],"3D/2D":[6],"information":[8,27,61],"into":[9],"one-dimensional":[10],"sequential":[11],"data":[12],"and":[13,40,76,110,146],"employ":[14],"language":[15,79],"models":[16,35],"to":[17,36,67,120,136],"generate":[18],"corresponding":[19],"descriptions.":[20],"This":[21],"approach,":[22],"however,":[23],"compromises":[24],"the":[25,41,63,68,94,102,118],"spatiotemporal":[26,96],"in":[28,143],"data,":[30],"making":[31],"it":[32],"difficult":[33],"for":[34],"capture":[37],"temporal":[38],"variations":[39],"relative":[42,95],"spatial":[43],"relationships":[44],"between":[45],"objects.":[46],"To":[47],"address":[48],"this":[49],"issue,":[50],"we":[51,100],"propose":[52],"STPos-VC,":[53],"a":[54,73,82,105,113],"pre-trained":[55],"vision-language":[56],"model":[57,103,119],"that":[58],"maps":[59],"from":[62],"vector":[65,70],"space":[66,71],"textual":[69],"through":[72,112],"visual-text":[74],"mapper":[75,85],"generates":[77],"natural":[78],"descriptions":[80],"using":[81],"decoder.":[83],"The":[84],"incorporates":[86],"three-dimensional":[87],"rotational":[88],"position":[89],"encoding,":[90],"which":[91],"effectively":[92],"preserves":[93],"positional":[97],"relationships.":[98],"Furthermore,":[99],"pre-train":[101],"on":[104],"mixed":[106],"dataset":[107],"comprising":[108],"images":[109],"videos":[111],"question-answering":[115],"framework,":[116],"enabling":[117],"perform":[121],"well":[122],"even":[123],"with":[124],"small":[125],"sample":[126],"sizes.":[127],"Experimental":[128],"results":[129],"across":[130],"multiple":[131],"datasets":[132],"demonstrate":[133],"that,":[134],"compared":[135],"existing":[137],"methods,":[138],"STPos-VC":[139],"achieves":[140],"superior":[141],"performance":[142],"both":[144],"general-purpose":[145],"domain-specific":[147],"applications.":[148]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}