{"id":"https://openalex.org/W4415961091","doi":"https://doi.org/10.1109/iccv51701.2025.02252","title":"Enrich and Detect: Video Temporal Grounding With Multimodal Llms","display_name":"Enrich and Detect: Video Temporal Grounding With Multimodal Llms","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4415961091","doi":"https://doi.org/10.1109/iccv51701.2025.02252"},"language":null,"primary_location":{"id":"doi:10.1109/iccv51701.2025.02252","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02252","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/2510.17023","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067636415","display_name":"Shraman Pramanick","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shraman Pramanick","raw_affiliation_strings":["FAIR, Meta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FAIR, Meta","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046800804","display_name":"Effrosyni Mavroudi","orcid":"https://orcid.org/0000-0001-7552-8342"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Effrosyni Mavroudi","raw_affiliation_strings":["FAIR, Meta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FAIR, Meta","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100566791","display_name":"Yale Song","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yale Song","raw_affiliation_strings":["FAIR, Meta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FAIR, Meta","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102762707","display_name":"Rama Chellappa","orcid":"https://orcid.org/0000-0002-7638-1650"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rama Chellappa","raw_affiliation_strings":["Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082736347","display_name":"Lorenzo Torresani","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lorenzo Torresani","raw_affiliation_strings":["FAIR, Meta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FAIR, Meta","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018690028","display_name":"Triantafyllos Afouras","orcid":"https://orcid.org/0000-0002-3935-9681"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Triantafyllos Afouras","raw_affiliation_strings":["FAIR, Meta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FAIR, Meta","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4136,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.85481247,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"24297","last_page":"24308"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9783999919891357,"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":0.9783999919891357,"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":0.004800000227987766,"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"}},{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.0031999999191612005,"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/paragraph","display_name":"Paragraph","score":0.6933000087738037},{"id":"https://openalex.org/keywords/ground","display_name":"Ground","score":0.6685000061988831},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.593999981880188},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.46869999170303345},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4603999853134155},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.45170000195503235}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7789000272750854},{"id":"https://openalex.org/C2777206241","wikidata":"https://www.wikidata.org/wiki/Q194431","display_name":"Paragraph","level":2,"score":0.6933000087738037},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.6685000061988831},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.593999981880188},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5485000014305115},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.46869999170303345},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4603999853134155},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.45170000195503235},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43720000982284546},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.32600000500679016},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.3228999972343445},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31189998984336853},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.28859999775886536},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.25519999861717224}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.02252","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02252","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:2510.17023","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.17023","pdf_url":"https://arxiv.org/pdf/2510.17023","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2510.17023","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.17023","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":"pmh:oai:arXiv.org:2510.17023","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.17023","pdf_url":"https://arxiv.org/pdf/2510.17023","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,123],"introduce":[1],"ED-VTG,":[2],"a":[3,40,76,107,163],"method":[4,142],"for":[5,119],"fine-grained":[6],"video":[7,132],"temporal":[8,131,149],"grounding":[9,133,136,150],"utilizing":[10],"multi-modal":[11],"large":[12],"language":[13,35,48],"models.":[14],"Our":[15],"approach":[16],"harnesses":[17],"the":[18,67,90,98,113,117],"capabilities":[19],"of":[20,89,100,116],"multimodal":[21],"LLMs":[22],"to":[23,31,62,158],"jointly":[24],"process":[25],"text":[26],"and":[27,60,96,134,152],"video,":[28],"in":[29,37,64,130,168],"order":[30],"effectively":[32],"localize":[33],"natural":[34],"queries":[36,49,72],"videos":[38],"through":[39],"two-stage":[41],"process.":[42],"Rather":[43],"than":[44],"being":[45],"directly":[46],"grounded,":[47,74],"are":[50,73],"initially":[51],"transformed":[52],"into":[53],"enriched":[54,71,91],"sentences":[55],"that":[56,110,140],"incorporate":[57],"missing":[58],"details":[59],"cues":[61],"aid":[63],"grounding.":[65],"In":[66],"second":[68],"stage,":[69],"these":[70],"using":[75],"lightweight":[77],"decoder,":[78],"which":[79],"specializes":[80],"at":[81],"predicting":[82],"accurate":[83],"boundaries":[84],"conditioned":[85],"on":[86],"contextualized":[87],"representations":[88],"queries.":[92],"To":[93],"mitigate":[94],"noise":[95],"reduce":[97],"impact":[99],"hallucinations,":[101],"our":[102,141],"model":[103],"is":[104,153],"trained":[105],"with":[106],"multiple-instance-learning":[108],"objective":[109],"dynamically":[111],"selects":[112],"optimal":[114],"version":[115],"query":[118],"each":[120],"training":[121],"sample.":[122],"demonstrate":[124],"state-of-the-art":[125],"results":[126],"across":[127],"various":[128],"benchmarks":[129],"paragraph":[135],"settings.":[137],"Experiments":[138],"reveal":[139],"significantly":[143],"outperforms":[144],"all":[145],"previously":[146],"proposed":[147],"LLM-based":[148],"approaches":[151],"either":[154],"superior":[155],"or":[156],"comparable":[157],"specialized":[159],"models,":[160],"while":[161],"maintaining":[162],"clear":[164],"advantage":[165],"against":[166],"them":[167],"zero-shot":[169],"evaluation":[170],"scenarios.":[171]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-22T00:00:00"}