{"id":"https://openalex.org/W4414607018","doi":"https://doi.org/10.1145/3769088","title":"Learning Prediction-aware Prior in Transformer Network for Accurate Spatio-Temporal Video Grounding","display_name":"Learning Prediction-aware Prior in Transformer Network for Accurate Spatio-Temporal Video Grounding","publication_year":2025,"publication_date":"2025-09-29","ids":{"openalex":"https://openalex.org/W4414607018","doi":"https://doi.org/10.1145/3769088"},"language":"en","primary_location":{"id":"doi:10.1145/3769088","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3769088","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3769088","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Xin Wang","orcid":"https://orcid.org/0009-0005-8143-244X"},"institutions":[{"id":"https://openalex.org/I44445938","display_name":"Shandong Jianzhu University","ror":"https://ror.org/01gbfax37","country_code":"CN","type":"education","lineage":["https://openalex.org/I44445938"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Wang","raw_affiliation_strings":["School of Sciences, Shandong Jianzhu University, Jinan, China","Shandong Jianzhu University, China"],"raw_orcid":"https://orcid.org/0009-0005-8143-244X","affiliations":[{"raw_affiliation_string":"School of Sciences, Shandong Jianzhu University, Jinan, China","institution_ids":["https://openalex.org/I44445938"]},{"raw_affiliation_string":"Shandong Jianzhu University, China","institution_ids":["https://openalex.org/I44445938"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114833240","display_name":"Tong Zhang","orcid":"https://orcid.org/0000-0001-8163-3050"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tong Zhang","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, Hangzhou, China","Zhejiang University, China"],"raw_orcid":"https://orcid.org/0000-0001-8163-3050","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]},{"raw_affiliation_string":"Zhejiang University, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040047825","display_name":"Yongshun Gong","orcid":"https://orcid.org/0000-0003-3948-4471"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongshun Gong","raw_affiliation_strings":["School of Software, Shandong University, Jinan, China","Shandong University, China"],"raw_orcid":"https://orcid.org/0000-0003-3948-4471","affiliations":[{"raw_affiliation_string":"School of Software, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]},{"raw_affiliation_string":"Shandong University, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076814111","display_name":"Jialin Gao","orcid":"https://orcid.org/0000-0002-8554-7827"},"institutions":[{"id":"https://openalex.org/I4210087373","display_name":"Meizu (China)","ror":"https://ror.org/0067g4302","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210087373"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jialin Gao","raw_affiliation_strings":["Meituan, Beijing, China","Meituan, China"],"raw_orcid":"https://orcid.org/0000-0002-8554-7827","affiliations":[{"raw_affiliation_string":"Meituan, Beijing, China","institution_ids":["https://openalex.org/I4210087373"]},{"raw_affiliation_string":"Meituan, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036903821","display_name":"Yanyu Xu","orcid":"https://orcid.org/0000-0001-8926-7833"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanyu Xu","raw_affiliation_strings":["School of Software, Shandong University, Jinan, China","Shandong University, China"],"raw_orcid":"https://orcid.org/0000-0001-8926-7833","affiliations":[{"raw_affiliation_string":"School of Software, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]},{"raw_affiliation_string":"Shandong University, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jin Qian","orcid":"https://orcid.org/0009-0008-3925-1997"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin Qian","raw_affiliation_strings":["School of Software, Shandong University, Jinan, China","Shandong University, China"],"raw_orcid":"https://orcid.org/0009-0008-3925-1997","affiliations":[{"raw_affiliation_string":"School of Software, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]},{"raw_affiliation_string":"Shandong University, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019824207","display_name":"Xiushan Nie","orcid":"https://orcid.org/0000-0001-9644-9723"},"institutions":[{"id":"https://openalex.org/I44445938","display_name":"Shandong Jianzhu University","ror":"https://ror.org/01gbfax37","country_code":"CN","type":"education","lineage":["https://openalex.org/I44445938"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiushan Nie","raw_affiliation_strings":["School of Computer and Artificial Intelligence, Shandong Jianzhu University, Jinan, China and Shandong Yunhai Guochuang Cloud Computing Equipment Industry Innovation Co., Ltd., Jinan, China","Shandong Jianzhu University, China"],"raw_orcid":"https://orcid.org/0000-0001-9644-9723","affiliations":[{"raw_affiliation_string":"School of Computer and Artificial Intelligence, Shandong Jianzhu University, Jinan, China and Shandong Yunhai Guochuang Cloud Computing Equipment Industry Innovation Co., Ltd., Jinan, China","institution_ids":["https://openalex.org/I44445938"]},{"raw_affiliation_string":"Shandong Jianzhu University, China","institution_ids":["https://openalex.org/I44445938"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101414718","display_name":"Lizhen Cui","orcid":"https://orcid.org/0000-0002-8262-8883"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lizhen Cui","raw_affiliation_strings":["School of Software, Shandong University, Jinan, China  and Joint SDU-NTU Centre for Artificial Intelligence Research (C-FAIR), Shandong University, Jinan, China","Shandong University, China"],"raw_orcid":"https://orcid.org/0000-0002-8262-8883","affiliations":[{"raw_affiliation_string":"School of Software, Shandong University, Jinan, China  and Joint SDU-NTU Centre for Artificial Intelligence Research (C-FAIR), Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]},{"raw_affiliation_string":"Shandong University, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100438525","display_name":"Chengqi Zhang","orcid":"https://orcid.org/0000-0001-5715-7154"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Chengqi Zhang","raw_affiliation_strings":["The Hong Kong Polytechnic University, Hong Kong, Hong Kong","The Hong Kong Polytechnic University, China"],"raw_orcid":"https://orcid.org/0000-0001-5715-7154","affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"The Hong Kong Polytechnic University, China","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.23164243,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"22","issue":"7","first_page":"1","last_page":"17"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9979000091552734,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9979000091552734,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9955000281333923,"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":0.9948999881744385,"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/ground","display_name":"Ground","score":0.6247000098228455},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6114000082015991},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.5138999819755554},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.5026000142097473},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.42170000076293945},{"id":"https://openalex.org/keywords/spatial-contextual-awareness","display_name":"Spatial contextual awareness","score":0.3806000053882599},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.3723999857902527},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.349700003862381}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8795999884605408},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6274999976158142},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.6247000098228455},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6114000082015991},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.5138999819755554},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.5026000142097473},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4787999987602234},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.42170000076293945},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.3806000053882599},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.3723999857902527},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.349700003862381},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.3402000069618225},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.3357999920845032},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.3246999979019165},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.3122999966144562},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.3059999942779541},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.2987000048160553},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.29280000925064087},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.27869999408721924},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2734000086784363},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2709999978542328},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2687000036239624},{"id":"https://openalex.org/C73752529","wikidata":"https://www.wikidata.org/wiki/Q79872","display_name":"Object-oriented programming","level":2,"score":0.26499998569488525},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.250900000333786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3769088","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3769088","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3769088","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3769088","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5968890584","display_name":null,"funder_award_id":"62476154","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2912512851","https://openalex.org/W2962766617","https://openalex.org/W2997429269","https://openalex.org/W3025323587","https://openalex.org/W3096609285","https://openalex.org/W3116510459","https://openalex.org/W3159619744","https://openalex.org/W3166712493","https://openalex.org/W3183241772","https://openalex.org/W4226048133","https://openalex.org/W4236965008","https://openalex.org/W4297947337","https://openalex.org/W4301409532","https://openalex.org/W4322706621","https://openalex.org/W4386074813","https://openalex.org/W4386289268","https://openalex.org/W4394896927","https://openalex.org/W4400900379","https://openalex.org/W4402188147","https://openalex.org/W4403982114"],"related_works":[],"abstract_inverted_index":{"Spatio-temporal":[0],"video":[1,14],"grounding":[2,28,82],"(STVG)":[3],"aims":[4],"to":[5,16,56,74,94,119,130],"precisely":[6],"locate":[7],"a":[8,17,62,88,126],"spatio-temporal":[9,58],"tube":[10,137],"in":[11],"an":[12],"untrimmed":[13],"corresponding":[15],"given":[18],"language":[19],"description.":[20],"Many":[21],"existing":[22],"methods":[23],"decouple":[24],"spatial":[25,45,81,121],"and":[26,99,139],"temporal":[27,70,89,104,112],"as":[29,48,72,115],"separate":[30],"tasks,":[31],"missing":[32],"the":[33,37,108,149],"strong":[34],"interdependencies":[35],"between":[36,97],"two,":[38],"which":[39],"are":[40],"crucial":[41],"for":[42,79],"accurately":[43],"aligning":[44],"regions":[46],"(such":[47],"objects)":[49],"with":[50,68],"their":[51],"motion":[52],"over":[53,83],"time.":[54,84],"Thus,":[55],"enhance":[57,95],"associations,":[59],"we":[60],"introduce":[61,125],"new":[63],"Prior-Driven":[64],"Transformer":[65],"Network":[66],"(PDTNet)":[67],"predicted":[69,111],"boundaries":[71,113],"priors":[73],"guide":[75],"object":[76,132,141],"bounding":[77],"boxes":[78],"improved":[80],"Firstly,":[85],"PDTNet":[86],"employs":[87],"prior,":[90],"termed":[91],"reference":[92],"query,":[93],"discriminability":[96],"language-related":[98],"language-irrelevant":[100],"visual":[101],"content,":[102],"improving":[103],"boundary":[105],"localization.":[106,133,142],"Further,":[107],"context":[109],"within":[110],"serves":[114],"another":[116],"prior":[117,129],"knowledge":[118],"modulate":[120],"features.":[122],"We":[123],"also":[124],"prediction-aware":[127],"Gaussian":[128],"precise":[131],"This":[134],"ensures":[135],"consistent":[136],"construction":[138],"accurate":[140],"Extensive":[143],"experiments":[144],"on":[145],"STVG":[146],"benchmarks":[147],"validate":[148],"effectiveness":[150],"of":[151],"PDTNet.":[152],"Code":[153],"is":[154],"available":[155],"at":[156],"https://github.com/tongzhang111/PDTNet":[157],".":[158]},"counts_by_year":[],"updated_date":"2026-06-25T06:16:34.145877","created_date":"2025-10-10T00:00:00"}
