{"id":"https://openalex.org/W7171531399","doi":"https://doi.org/10.48550/arxiv.2607.23951","title":"TimePLE: Rethinking Temporal Representation for Video Temporal Grounding","display_name":"TimePLE: Rethinking Temporal Representation for Video Temporal Grounding","publication_year":2026,"publication_date":"2026-07-27","ids":{"openalex":"https://openalex.org/W7171531399","doi":"https://doi.org/10.48550/arxiv.2607.23951"},"language":null,"primary_location":{"id":"pmh:oai:arXiv.org:2607.23951","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2607.23951","pdf_url":"https://arxiv.org/pdf/2607.23951","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,"listed_in":[],"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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2607.23951","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5127883592","display_name":"Yuhui Zeng","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]},{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zeng, Yuhui","raw_affiliation_strings":["Kling Team , Kuaishou Technology , China","Media Analytics and Computing Lab , Xiamen University , Xiamen , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kling Team , Kuaishou Technology , China","institution_ids":[]},{"raw_affiliation_string":"Media Analytics and Computing Lab , Xiamen University , Xiamen , China","institution_ids":["https://openalex.org/I191208505","https://openalex.org/I75867142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128693999","display_name":"Xinyu Mao","orcid":"https://orcid.org/0009-0000-6110-6659","observed_orcids":["https://orcid.org/0009-0000-6110-6659","https://orcid.org/0009-0003-6531-7148"]},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Mao, Xinyu","raw_affiliation_strings":["Kling Team , Kuaishou Technology , China","The Chinese University of Hong Kong , HKSAR , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kling Team , Kuaishou Technology , China","institution_ids":[]},{"raw_affiliation_string":"The Chinese University of Hong Kong , HKSAR , China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125151232","display_name":"Xiaokun Liu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Xiaokun","raw_affiliation_strings":["Kling Team , Kuaishou Technology , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kling Team , Kuaishou Technology , China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047247059","display_name":"Xin Tao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tao, Xin","raw_affiliation_strings":["Kling Team , Kuaishou Technology , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kling Team , Kuaishou Technology , China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110947034","display_name":"Jinfa Huang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huang, Jinfa","raw_affiliation_strings":["Department of Computer Science , University of Rochester , Rochester , NY , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , University of Rochester , Rochester , NY , USA","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5144691245","display_name":"Jiayi Ji","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]},{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ji, Jiayi","raw_affiliation_strings":["Media Analytics and Computing Lab , Xiamen University , Xiamen , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Media Analytics and Computing Lab , Xiamen University , Xiamen , China","institution_ids":["https://openalex.org/I191208505","https://openalex.org/I75867142"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054226277","display_name":"Xiawu Zheng","orcid":"https://orcid.org/0000-0002-6855-5403","observed_orcids":["https://orcid.org/0000-0002-6855-5403"]},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]},{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng, Xiawu","raw_affiliation_strings":["Media Analytics and Computing Lab , Xiamen University , Xiamen , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Media Analytics and Computing Lab , Xiamen University , Xiamen , China","institution_ids":["https://openalex.org/I191208505","https://openalex.org/I75867142"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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":0.9951000213623047,"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":0.9951000213623047,"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":0.0017999999690800905,"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":0.0010000000474974513,"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/video-temporal-grounding","display_name":"video temporal grounding","score":1.0},{"id":"https://openalex.org/keywords/temporal-representation","display_name":"representation of time","score":0.6510000228881836},{"id":"https://openalex.org/keywords/interval-prediction","display_name":"interval prediction","score":0.5350000262260437},{"id":"https://openalex.org/keywords/temporal-anchors","display_name":"temporal anchors","score":0.4449999928474426},{"id":"https://openalex.org/keywords/video-language-models","display_name":"video-language models","score":0.6650000214576721}],"concepts":[{"id":"https://openalex.org/C2778067643","wikidata":"https://www.wikidata.org/wiki/Q166507","display_name":"Interval (graph theory)","level":2,"score":0.722599983215332},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6152999997138977},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.605400025844574},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5595999956130981},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.508400022983551},{"id":"https://openalex.org/C113954288","wikidata":"https://www.wikidata.org/wiki/Q186885","display_name":"Timestamp","level":2,"score":0.47620001435279846},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.4657000005245209},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4537999927997589},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.4359000027179718},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43209999799728394},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.42649999260902405},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.4156999886035919},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4138000011444092},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.4088999927043915},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3952000141143799},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.38519999384880066},{"id":"https://openalex.org/C88871306","wikidata":"https://www.wikidata.org/wiki/Q7208287","display_name":"Point process","level":2,"score":0.37709999084472656},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.37689998745918274},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.34130001068115234},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.32659998536109924},{"id":"https://openalex.org/C2778753569","wikidata":"https://www.wikidata.org/wiki/Q1960395","display_name":"Span (engineering)","level":2,"score":0.3248000144958496},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.3239000141620636},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3151000142097473},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.3133000135421753},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.31290000677108765},{"id":"https://openalex.org/C162670838","wikidata":"https://www.wikidata.org/wiki/Q6057295","display_name":"Interval temporal logic","level":3,"score":0.310699999332428},{"id":"https://openalex.org/C2779466056","wikidata":"https://www.wikidata.org/wiki/Q107630651","display_name":"Time point","level":2,"score":0.3084999918937683},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3084000051021576},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.3077999949455261},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2915000021457672},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.2718999981880188},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.2700999975204468},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.26989999413490295},{"id":"https://openalex.org/C77277458","wikidata":"https://www.wikidata.org/wiki/Q1969246","display_name":"Temporal database","level":2,"score":0.2572000026702881}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2607.23951","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2607.23951","pdf_url":"https://arxiv.org/pdf/2607.23951","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,"listed_in":[],"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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2607.23951","doi":"https://doi.org/10.48550/arxiv.2607.23951","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.23951","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,"listed_in":[],"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:2607.23951","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2607.23951","pdf_url":"https://arxiv.org/pdf/2607.23951","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,"listed_in":[],"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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7171531399.pdf","grobid_xml":"https://content.openalex.org/works/W7171531399.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Video":[0],"temporal":[1,91,163,167],"grounding":[2,82],"(VTG)":[3],"aims":[4],"to":[5,80,97,110,160],"localize":[6],"the":[7,53,126,176],"continuous":[8,36,152],"video":[9,123],"interval":[10,23,55,61,96,142,156],"described":[11],"by":[12,83],"a":[13,57,85,98,101,111,122,129,140],"natural-language":[14],"query.":[15],"However,":[16],"current":[17],"VLM-based":[18],"methods":[19],"typically":[20],"produce":[21],"this":[22],"indirectly":[24],"through":[25,145],"two":[26],"endpoint":[27,78,204],"outputs,":[28],"represented":[29],"either":[30],"as":[31],"discrete":[32],"timestamp":[33],"tokens":[34],"or":[35],"boundary":[37],"coordinates.":[38],"These":[39],"formulations":[40],"differ":[41],"in":[42,49,100],"how":[43],"endpoints":[44],"are":[45,67],"encoded,":[46],"but":[47],"not":[48],"what":[50],"is":[51,137,158],"predicted:":[52],"event":[54,182],"remains":[56],"derived":[58],"object,":[59],"while":[60],"validity,":[62],"duration,":[63],"and":[64,114,124,149,189,218],"interval-level":[65],"similarity":[66],"handled":[68],"only":[69],"implicitly.":[70],"We":[71],"propose":[72],"TimePLE,":[73],"which":[74],"reformulates":[75],"VTG":[76,197],"from":[77],"prediction":[79,205],"interval-native":[81],"predicting":[84],"single":[86,130],"joint":[87,141],"distribution":[88],"over":[89],"valid":[90,112],"intervals.":[92,120],"TimePLE":[93,201],"maps":[94],"each":[95],"point":[99,108],"canonical":[102],"position-duration":[103],"square,":[104],"where":[105],"every":[106],"support":[107],"corresponds":[109],"span":[113,171,178],"neighboring":[115],"points":[116],"represent":[117],"geometrically":[118],"similar":[119],"Given":[121],"query,":[125],"VLM":[127],"generates":[128],"latent":[131,177],"<|TIMESPAN|>":[132],"token":[133],"whose":[134],"hidden":[135],"state":[136],"decoded":[138],"into":[139,151],"distribution,":[143],"refined":[144],"duration-aware":[146],"coordinate":[147],"correction,":[148],"converted":[150],"boundaries.":[153],"The":[154],"same":[155],"representation":[157,179],"used":[159],"encode":[161],"input":[162],"anchors,":[164],"aligning":[165],"video-side":[166],"evidence":[168],"with":[169,180,213],"output-side":[170],"prediction.":[172],"To":[173],"reliably":[174],"align":[175],"complete":[181],"intervals,":[183],"we":[184],"curate":[185],"90K-scale":[186],"grounded":[187],"samples":[188],"human-verify":[190],"3K-scale":[191],"benchmark":[192],"annotations.":[193],"Experiments":[194],"across":[195],"four":[196],"benchmarks":[198],"show":[199],"that":[200],"consistently":[202],"outperforms":[203],"baselines,":[206],"achieving":[207],"an":[208],"average":[209],"mIoU":[210],"of":[211],"58.9,":[212],"clear":[214],"gains":[215],"on":[216],"short-duration":[217],"medium-duration":[219],"events.":[220]},"counts_by_year":[],"updated_date":"2026-10-01T08:54:57.152042","created_date":"2026-07-29T00:00:00"}