{"id":"https://openalex.org/W4414459554","doi":"https://doi.org/10.1109/iccv51701.2025.01959","title":"OVG-HQ: Online Video Grounding with Hybrid-Modal Queries","display_name":"OVG-HQ: Online Video Grounding with Hybrid-Modal Queries","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4414459554","doi":"https://doi.org/10.1109/iccv51701.2025.01959"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01959","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01959","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2508.11903","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018498977","display_name":"Runhao Zeng","orcid":"https://orcid.org/0000-0001-8694-4245"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]},{"id":"https://openalex.org/I4388482657","display_name":"Shenzhen MSU-BIT University","ror":"https://ror.org/02q963474","country_code":null,"type":"education","lineage":["https://openalex.org/I4388482657"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Runhao Zeng","raw_affiliation_strings":["Artificial Intelligence Research Institute, Shenzhen MSU-BIT University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Research Institute, Shenzhen MSU-BIT University","institution_ids":["https://openalex.org/I1343180700","https://openalex.org/I4388482657"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jiaqi Mao","orcid":null},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]},{"id":"https://openalex.org/I4388482657","display_name":"Shenzhen MSU-BIT University","ror":"https://ror.org/02q963474","country_code":null,"type":"education","lineage":["https://openalex.org/I4388482657"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiaqi Mao","raw_affiliation_strings":["Artificial Intelligence Research Institute, Shenzhen MSU-BIT University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Research Institute, Shenzhen MSU-BIT University","institution_ids":["https://openalex.org/I1343180700","https://openalex.org/I4388482657"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047025966","display_name":"Mallory Lai","orcid":"https://orcid.org/0000-0002-3519-5755"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]},{"id":"https://openalex.org/I4388482657","display_name":"Shenzhen MSU-BIT University","ror":"https://ror.org/02q963474","country_code":null,"type":"education","lineage":["https://openalex.org/I4388482657"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Minghao Lai","raw_affiliation_strings":["Artificial Intelligence Research Institute, Shenzhen MSU-BIT University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Research Institute, Shenzhen MSU-BIT University","institution_ids":["https://openalex.org/I1343180700","https://openalex.org/I4388482657"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086523266","display_name":"Vu Minh Hieu Phan","orcid":"https://orcid.org/0000-0003-3861-0296"},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Minh Hieu Phan","raw_affiliation_strings":["University of Adelaide"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Adelaide","institution_ids":["https://openalex.org/I5681781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033202374","display_name":"Yan Dong","orcid":"https://orcid.org/0000-0002-6208-2537"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]},{"id":"https://openalex.org/I4388482657","display_name":"Shenzhen MSU-BIT University","ror":"https://ror.org/02q963474","country_code":null,"type":"education","lineage":["https://openalex.org/I4388482657"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yanjie Dong","raw_affiliation_strings":["Artificial Intelligence Research Institute, Shenzhen MSU-BIT University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Research Institute, Shenzhen MSU-BIT University","institution_ids":["https://openalex.org/I1343180700","https://openalex.org/I4388482657"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100391664","display_name":"Wei Wang","orcid":"https://orcid.org/0000-0001-5493-3277"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]},{"id":"https://openalex.org/I4388482657","display_name":"Shenzhen MSU-BIT University","ror":"https://ror.org/02q963474","country_code":null,"type":"education","lineage":["https://openalex.org/I4388482657"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Wang","raw_affiliation_strings":["Artificial Intelligence Research Institute, Shenzhen MSU-BIT University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Research Institute, Shenzhen MSU-BIT University","institution_ids":["https://openalex.org/I1343180700","https://openalex.org/I4388482657"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100340166","display_name":"Qi Chen","orcid":"https://orcid.org/0000-0002-4978-1974"},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Qi Chen","raw_affiliation_strings":["University of Adelaide"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Adelaide","institution_ids":["https://openalex.org/I5681781"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007941489","display_name":"Xiping Hu","orcid":"https://orcid.org/0000-0002-4952-699X"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]},{"id":"https://openalex.org/I4388482657","display_name":"Shenzhen MSU-BIT University","ror":"https://ror.org/02q963474","country_code":null,"type":"education","lineage":["https://openalex.org/I4388482657"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiping Hu","raw_affiliation_strings":["Artificial Intelligence Research Institute, Shenzhen MSU-BIT University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Research Institute, Shenzhen MSU-BIT University","institution_ids":["https://openalex.org/I1343180700","https://openalex.org/I4388482657"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"21085","last_page":"21096"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9990000128746033,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9990000128746033,"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":0.9990000128746033,"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":0.9987000226974487,"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/task","display_name":"Task (project management)","score":0.6574000120162964},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5874000191688538},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5180000066757202},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.4717000126838684},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.4616999924182892},{"id":"https://openalex.org/keywords/internet-video","display_name":"Internet video","score":0.4487999975681305},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.4431999921798706},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.42820000648498535}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8416000008583069},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6574000120162964},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5874000191688538},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5180000066757202},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4717000126838684},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.4616999924182892},{"id":"https://openalex.org/C2779789524","wikidata":"https://www.wikidata.org/wiki/Q16885149","display_name":"Internet video","level":3,"score":0.4487999975681305},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.4431999921798706},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.439300000667572},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.42820000648498535},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41190001368522644},{"id":"https://openalex.org/C2988167200","wikidata":"https://www.wikidata.org/wiki/Q16885149","display_name":"Online video","level":2,"score":0.4068000018596649},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.38989999890327454},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3840999901294708},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.37689998745918274},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.3495999872684479},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.30329999327659607},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2962000072002411},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.296099990606308},{"id":"https://openalex.org/C2983174267","wikidata":"https://www.wikidata.org/wiki/Q3775098","display_name":"Video retrieval","level":2,"score":0.29440000653266907},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.2757999897003174},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.26919999718666077},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.26179999113082886},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.25870001316070557},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.2549000084400177}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01959","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01959","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2508.11903","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.11903","pdf_url":"https://arxiv.org/pdf/2508.11903","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2508.11903","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2508.11903","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2508.11903","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.11903","pdf_url":"https://arxiv.org/pdf/2508.11903","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4860469773","display_name":null,"funder_award_id":"62202311","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G657063301","display_name":null,"funder_award_id":"2023A1515011512","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Video":[0,46],"grounding":[1],"(VG)":[2],"task":[3,43,66],"focuses":[4],"on":[5,13],"locating":[6],"specific":[7],"moments":[8],"in":[9,17,73],"a":[10,14,41,93,97,112,126,188],"video":[11,29,60,194],"based":[12],"query,":[15],"usually":[16],"text":[18],"form.":[19],"However,":[20],"traditional":[21],"VG":[22],"struggles":[23],"with":[24,48,147],"some":[25],"scenarios":[26],"like":[27],"streaming":[28],"or":[30],"queries":[31],"using":[32,57],"visual":[33],"cues.":[34],"To":[35,87],"fill":[36],"this":[37],"gap,":[38],"we":[39,90,141,157],"present":[40],"new":[42,69],"named":[44],"Online":[45],"Grounding":[47],"Hybrid-modal":[49],"Queries":[50],"(OVG-HQ),":[51],"which":[52],"enables":[53,125],"online":[54,74,162,168],"segment":[55],"localization":[56],"text,":[58],"images,":[59],"segments,":[61],"and":[62,76,111,167,177,198],"their":[63],"combinations.":[64],"This":[65,123],"poses":[67],"two":[68],"challenges:":[70],"limited":[71],"context":[72],"settings":[75],"modality":[77],"imbalance":[78],"during":[79],"training,":[80],"where":[81],"dominant":[82],"modalities":[83],"overshadow":[84],"weaker":[85],"ones.":[86],"address":[88],"these,":[89],"propose":[91],"OVG-HQ-Unify,":[92],"unified":[94],"framework":[95],"featuring":[96],"Parametric":[98],"Memory":[99],"Block":[100],"(PMB)":[101],"that":[102,116,181],"retain":[103],"previously":[104],"learned":[105],"knowledge":[106],"to":[107,129,135,160,173],"enhance":[108],"current":[109],"decision":[110],"cross-modal":[113],"distillation":[114],"strategy":[115],"guides":[117],"the":[118,136,161],"learning":[119],"of":[120,138],"non-dominant":[121],"modalities.":[122],"design":[124],"single":[127],"model":[128],"effectively":[130],"handle":[131],"hybrid-modal":[132,193],"queries.":[133,149],"Due":[134],"lack":[137],"suitable":[139],"datasets,":[140],"construct":[142],"QVHighlights-Unify,":[143],"an":[144],"expanded":[145],"dataset":[146],"multi-modal":[148],"Besides,":[150],"since":[151],"offline":[152],"metrics":[153],"overlook":[154],"prediction":[155],"timeliness,":[156],"adapt":[158],"them":[159],"setting,":[163],"introducing":[164],"oR@n,":[165],"IoU=m,":[166],"mean":[169],"Average":[170],"Precision":[171],"(omAP)":[172],"evaluate":[174],"both":[175],"accuracy":[176],"efficiency.":[178],"Experiments":[179],"show":[180],"our":[182],"OVG-HQ-Unify":[183],"outperforms":[184],"existing":[185],"models,":[186],"offering":[187],"robust":[189],"solution":[190],"for":[191],"online,":[192],"grounding.":[195],"Source":[196],"code":[197],"datasets":[199],"are":[200],"available":[201],"at":[202],"https://github.com/maojiaqi2324/OVG-HQ.":[203]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
