{"id":"https://openalex.org/W7158066449","doi":"https://doi.org/10.48550/arxiv.2604.25276","title":"OmniVTG: A Large-Scale Dataset and Training Paradigm for Open-World Video Temporal Grounding","display_name":"OmniVTG: A Large-Scale Dataset and Training Paradigm for Open-World Video Temporal Grounding","publication_year":2026,"publication_date":"2026-04-28","ids":{"openalex":"https://openalex.org/W7158066449","doi":"https://doi.org/10.48550/arxiv.2604.25276"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.25276","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.25276","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.25276","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071596230","display_name":"Minghang Zheng","orcid":"https://orcid.org/0000-0003-1612-975X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng, Minghang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134833365","display_name":"Zihao Yin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yin, Zihao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134845180","display_name":"Yi Yang","orcid":"https://orcid.org/0009-0006-2462-3327"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Yi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134853118","display_name":"Yuxin Peng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peng, Yuxin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5134865328","display_name":"Yang Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.987500011920929,"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":0.987500011920929,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.0024999999441206455,"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/T10028","display_name":"Topic Modeling","score":0.0013000000035390258,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.8185999989509583},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.734499990940094},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6527000069618225},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.598800003528595},{"id":"https://openalex.org/keywords/ground","display_name":"Ground","score":0.5273000001907349},{"id":"https://openalex.org/keywords/semantic-gap","display_name":"Semantic gap","score":0.46000000834465027},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4537000060081482},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4424999952316284},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4318000078201294}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8185999989509583},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8115000128746033},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.734499990940094},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6527000069618225},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.598800003528595},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5386000275611877},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.5273000001907349},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.49950000643730164},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.46000000834465027},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4537000060081482},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4424999952316284},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4318000078201294},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.39969998598098755},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.36820000410079956},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.35989999771118164},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.3513999879360199},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.34790000319480896},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3361000120639801},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.3328999876976013},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32679998874664307},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.30309998989105225},{"id":"https://openalex.org/C2777877512","wikidata":"https://www.wikidata.org/wiki/Q1116097","display_name":"Common ground","level":2,"score":0.29670000076293945},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.28139999508857727},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.26269999146461487},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.2574000060558319}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.25276","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.25276","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.25276","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.25276","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.42779022455215454}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Video":[0],"Temporal":[1],"Grounding":[2],"(VTG),":[3],"the":[4,58,84,106,134,182],"task":[5],"of":[6,61,86,208],"localizing":[7],"video":[8,160],"segments":[9],"from":[10],"text":[11],"queries,":[12],"struggles":[13],"in":[14,83,226],"open-world":[15,45,224],"settings":[16],"due":[17],"to":[18,56,96,125,128,184,192],"limited":[19],"dataset":[20,43,229],"scale":[21],"and":[22,30,89,119,151,195,212],"semantic":[23],"diversity,":[24],"causing":[25],"performance":[26,147,235],"gaps":[27,82],"between":[28,149],"common":[29,152],"rare":[31,150],"concepts.":[32,100],"To":[33],"overcome":[34],"these":[35,98],"limitations,":[36],"we":[37,104,136,172],"introduce":[38],"OmniVTG,":[39],"a":[40,49,72,121,146,174,205],"new":[41],"large-scale":[42],"for":[44],"VTG,":[46],"coupled":[47],"with":[48],"Self-Correction":[50,175],"Chain-of-Thought":[51,176],"(CoT)":[52,177],"training":[53,178],"paradigm":[54],"designed":[55],"enhance":[57],"grounding":[59,118,167,225],"capabilities":[60,191],"Multimodal":[62],"Large":[63],"Language":[64],"Models":[65],"(MLLMs).":[66],"Our":[67],"OmniVTG":[68,228],"is":[69,143,202,242],"constructed":[70],"via":[71,204],"novel":[73],"Semantic":[74],"Coverage":[75],"Iterative":[76],"Expansion":[77],"pipeline,":[78],"which":[79],"first":[80,185],"identifies":[81],"vocabulary":[85],"existing":[87,238],"datasets":[88],"collects":[90],"videos":[91],"that":[92,108,138,158],"are":[93],"highly":[94],"likely":[95],"contain":[97],"target":[99],"For":[101],"high-quality":[102],"annotation,":[103],"leverage":[105],"insight":[107],"modern":[109],"MLLMs":[110,127],"excel":[111],"at":[112,223,244],"dense":[113],"captioning":[114],"more":[115],"than":[116],"direct":[117,166],"design":[120],"caption-centric":[122],"data":[123],"engine":[124],"prompt":[126],"generate":[129],"dense,":[130],"timestamped":[131],"descriptions.":[132],"Beyond":[133],"dataset,":[135],"observe":[137],"simple":[139],"supervised":[140],"finetuning":[141],"(SFT)":[142],"insufficient,":[144],"as":[145],"gap":[148],"concepts":[153],"still":[154],"persists.":[155],"We":[156,180],"find":[157],"MLLMs'":[159],"understanding":[161,190],"ability":[162],"significantly":[163],"surpasses":[164],"their":[165],"ability.":[168],"Based":[169],"on":[170,194,236],"this,":[171],"propose":[173],"paradigm.":[179],"train":[181],"MLLM":[183],"predict,":[186],"then":[187],"use":[188],"its":[189,197],"reflect":[193],"refine":[196],"own":[198],"predictions.":[199],"This":[200],"capability":[201],"instilled":[203],"three-stage":[206],"pipeline":[207],"SFT,":[209],"CoT":[210],"finetuning,":[211],"reinforcement":[213],"learning.":[214],"Extensive":[215],"experiments":[216],"show":[217],"our":[218,227],"approach":[219],"not":[220],"only":[221],"excels":[222],"but":[230],"also":[231],"achieves":[232],"state-of-the-art":[233],"zero-shot":[234],"four":[237],"VTG":[239],"benchmarks.":[240],"Code":[241],"available":[243],"https://github.com/oceanflowlab/OmniVTG.":[245]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-04-30T00:00:00"}