{"id":"https://openalex.org/W4414856890","doi":"https://doi.org/10.1109/iccv51701.2025.02039","title":"DisTime: Distribution-Based Time Representation for Video Large Language Models","display_name":"DisTime: Distribution-Based Time Representation for Video Large Language Models","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4414856890","doi":"https://doi.org/10.1109/iccv51701.2025.02039"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.02039","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02039","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":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.24329","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072520602","display_name":"Yingsen Zeng","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yingsen Zeng","raw_affiliation_strings":["Meituan Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meituan Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001354909","display_name":"Zepeng Huang","orcid":"https://orcid.org/0000-0001-9997-649X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zepeng Huang","raw_affiliation_strings":["Meituan Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meituan Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073721922","display_name":"Yuhui Zhong","orcid":"https://orcid.org/0009-0000-8673-618X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yujie Zhong","raw_affiliation_strings":["Meituan Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meituan Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101303327","display_name":"Chengjian Feng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chengjian Feng","raw_affiliation_strings":["Meituan Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meituan Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013797064","display_name":"Jie Hu","orcid":"https://orcid.org/0000-0003-0908-0468"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jie Hu","raw_affiliation_strings":["Meituan Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meituan Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017116858","display_name":"Lin Ma","orcid":"https://orcid.org/0000-0002-7331-6132"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin Ma","raw_affiliation_strings":["Meituan Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meituan Inc","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100355988","display_name":"Yang Liu","orcid":"https://orcid.org/0000-0002-8070-1477"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Liu","raw_affiliation_strings":["Wangxuan Institute of Computer Technology, Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wangxuan Institute of Computer Technology, Peking University","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5072520602"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.24580922,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"21961","last_page":"21971"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9901000261306763,"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":0.9901000261306763,"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":0.982200026512146,"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":0.9458000063896179,"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/timestamp","display_name":"Timestamp","score":0.6851999759674072},{"id":"https://openalex.org/keywords/temporal-database","display_name":"Temporal database","score":0.5874000191688538},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.5622000098228455},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4641000032424927},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.44920000433921814},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4472000002861023},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.43309998512268066},{"id":"https://openalex.org/keywords/conflation","display_name":"Conflation","score":0.4074000120162964},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.4056999981403351},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.40400001406669617}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.816100001335144},{"id":"https://openalex.org/C113954288","wikidata":"https://www.wikidata.org/wiki/Q186885","display_name":"Timestamp","level":2,"score":0.6851999759674072},{"id":"https://openalex.org/C77277458","wikidata":"https://www.wikidata.org/wiki/Q1969246","display_name":"Temporal database","level":2,"score":0.5874000191688538},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.5622000098228455},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5088000297546387},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4641000032424927},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.44920000433921814},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4472000002861023},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.43309998512268066},{"id":"https://openalex.org/C130440534","wikidata":"https://www.wikidata.org/wiki/Q14946528","display_name":"Conflation","level":2,"score":0.4074000120162964},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.4056999981403351},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.40400001406669617},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4000000059604645},{"id":"https://openalex.org/C151406439","wikidata":"https://www.wikidata.org/wiki/Q186588","display_name":"Time series","level":2,"score":0.35899999737739563},{"id":"https://openalex.org/C119666444","wikidata":"https://www.wikidata.org/wiki/Q5977280","display_name":"Temporal resolution","level":2,"score":0.35589998960494995},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3359000086784363},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.31150001287460327},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.3107999861240387},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.30320000648498535},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.3005000054836273},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.2964000105857849},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.29010000824928284},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.28360000252723694},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28279998898506165},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.27709999680519104},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.2728999853134155},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.26739999651908875},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.2653999924659729},{"id":"https://openalex.org/C55689738","wikidata":"https://www.wikidata.org/wiki/Q15963867","display_name":"Discrete time and continuous time","level":2,"score":0.25780001282691956},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.25519999861717224},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.2547999918460846},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.25220000743865967}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.02039","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02039","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:2505.24329","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.24329","pdf_url":"https://arxiv.org/pdf/2505.24329","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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.2505.24329","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.24329","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2505.24329","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.24329","pdf_url":"https://arxiv.org/pdf/2505.24329","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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/G3077714275","display_name":null,"funder_award_id":"62372014","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3701923927","display_name":null,"funder_award_id":"4252040","funder_id":"https://openalex.org/F4320322919","funder_display_name":"Natural Science Foundation of Beijing Municipality"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322919","display_name":"Natural Science Foundation of Beijing Municipality","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Despite":[0],"advances":[1],"in":[2,13,69,120,177,185],"general":[3],"video":[4],"understanding,":[5],"Video":[6,186],"Large":[7],"Language":[8],"Models":[9],"(Video-LLMs)":[10],"face":[11],"challenges":[12],"precise":[14],"temporal":[15,30,44,51,67,80,91,100,117,142],"localization":[16,138],"due":[17],"to":[18,65,76,109,146],"discrete":[19],"time":[20,34,48,111],"representations":[21],"and":[22,83,98,190],"limited":[23],"temporally":[24,156],"aware":[25],"datasets.":[26],"Existing":[27],"methods":[28],"for":[29,113],"expression":[31],"either":[32],"conflate":[33],"with":[35,136,154],"text-based":[36],"numerical":[37],"values,":[38],"add":[39],"a":[40,61,73,78,85,151],"series":[41],"of":[42,134,140,149],"dedicated":[43,141],"tokens,":[45],"or":[46],"regress":[47],"using":[49],"specialized":[50],"grounding":[52],"heads.":[53],"To":[54,115],"address":[55],"these":[56],"issues,":[57],"we":[58,123],"introduce":[59],"DisTime,":[60],"lightweight":[62],"framework":[63],"designed":[64],"enhance":[66],"comprehension":[68],"Video-LLMs.":[70,114],"DisTime":[71,171],"employs":[72],"learnable":[74],"token":[75],"create":[77],"continuous":[79],"embedding":[81],"space":[82],"incorporates":[84],"Distribution-based":[86,104],"Time":[87,105],"Decoder":[88],"that":[89,129,170],"generates":[90],"probability":[92],"distributions,":[93],"effectively":[94],"mitigating":[95],"boundary":[96],"ambiguities":[97],"maintaining":[99,182],"continuity.":[101],"Additionally,":[102],"the":[103,131,137,147],"Encoder":[106],"re-encodes":[107],"timestamps":[108],"provide":[110],"markers":[112],"overcome":[116],"granularity":[118],"limitations":[119],"existing":[121],"datasets,":[122],"propose":[124],"an":[125],"automated":[126],"annotation":[127],"paradigm":[128],"combines":[130],"captioning":[132],"capabilities":[133],"Video-LLMs":[135],"expertise":[139],"models.":[143],"This":[144],"leads":[145],"creation":[148],"InternVid-TG,":[150],"substantial":[152],"dataset":[153],"1.25M":[155],"grounded":[157],"events":[158],"across":[159,175],"179k":[160],"videos,":[161],"surpassing":[162],"ActivityNet-Caption":[163],"by":[164],"55":[165],"times.":[166],"Extensive":[167],"experiments":[168],"demonstrate":[169],"achieves":[172],"state-of-the-art":[173],"performance":[174,184],"benchmarks":[176],"three":[178],"time-sensitive":[179],"tasks":[180],"while":[181],"competitive":[183],"QA":[187],"tasks.":[188],"Code":[189],"data":[191],"are":[192],"released":[193],"at":[194],"https://github.com/josephzpng/DisTime.":[195]},"counts_by_year":[],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-10-10T00:00:00"}