{"id":"https://openalex.org/W4416035957","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.50","title":"Grounded-VideoLLM: Sharpening Fine-grained Temporal Grounding in Video Large Language Models","display_name":"Grounded-VideoLLM: Sharpening Fine-grained Temporal Grounding in Video Large Language Models","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416035957","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.50"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.50","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.50","pdf_url":"https://aclanthology.org/2025.findings-emnlp.50.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.50.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008475639","display_name":"Haibo Wang","orcid":"https://orcid.org/0000-0002-7514-1719"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haibo Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115593603","display_name":"Zhiyang Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiyang Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084146010","display_name":"Yu Cheng","orcid":"https://orcid.org/0000-0002-4837-3370"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu Cheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114462435","display_name":"Shizhe Diao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shizhe Diao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087777496","display_name":"Yufan Zhou","orcid":"https://orcid.org/0000-0001-7188-3072"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yufan Zhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101488072","display_name":"Yixin Cao","orcid":"https://orcid.org/0000-0002-1632-7812"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yixin Cao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055007304","display_name":"Qifan Wang","orcid":"https://orcid.org/0000-0002-5304-7975"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qifan Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101647216","display_name":"Weifeng Ge","orcid":"https://orcid.org/0000-0002-6258-6225"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weifeng Ge","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101307306","display_name":"Lifu Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lifu Huang","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":true,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"959","last_page":"975"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8306999802589417,"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":0.8306999802589417,"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":0.04450000077486038,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.011500000022351742,"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/sharpening","display_name":"Sharpening","score":0.6603000164031982},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3199999928474426},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.28839999437332153},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.27880001068115234},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.2621999979019165}],"concepts":[{"id":"https://openalex.org/C2781137444","wikidata":"https://www.wikidata.org/wiki/Q237105","display_name":"Sharpening","level":2,"score":0.6603000164031982},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6176000237464905},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5776000022888184},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5206000208854675},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3337000012397766},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3199999928474426},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.29820001125335693},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.28839999437332153},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.27880001068115234},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2621999979019165},{"id":"https://openalex.org/C57654395","wikidata":"https://www.wikidata.org/wiki/Q1097775","display_name":"Compression artifact","level":5,"score":0.26080000400543213}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.50","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.50","pdf_url":"https://aclanthology.org/2025.findings-emnlp.50.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.50","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.50","pdf_url":"https://aclanthology.org/2025.findings-emnlp.50.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416035957.pdf","grobid_xml":"https://content.openalex.org/works/W4416035957.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Despite":[0],"their":[1],"impressive":[2],"performance":[3],"in":[4,16,141],"coarsegrained":[5],"video":[6,43,102,153],"understanding,":[7],"Video":[8],"Large":[9],"Language":[10],"Models":[11],"(Video-LLMs)":[12],"still":[13],"face":[14],"challenges":[15],"fine-grained":[17,142],"temporal":[18,22,47,68,103,112,117],"grounding,":[19],"including":[20],"ineffective":[21],"modeling":[23],"and":[24,39,65,97,111],"inadequate":[25],"timestamp":[26,76],"representations.In":[27],"this":[28],"work,":[29],"we":[30,78],"introduce":[31],"Grounded-VideoLLM,":[32],"a":[33,52,80,107,121,151],"novel":[34],"Video-LLM":[35],"designed":[36],"to":[37,85,100],"perceive":[38],"reason":[40],"over":[41],"specific":[42],"moments":[44],"with":[45,71,124],"finegrained":[46],"precision.Our":[48],"model":[49,89],"features":[50],"(1)":[51],"two-stream":[53],"encoder":[54],"that":[55,134],"explicitly":[56],"captures":[57],"inter-frame":[58],"relationships":[59],"while":[60],"preserving":[61],"intra-frame":[62],"visual":[63],"details":[64],"(2)":[66],"discrete":[67],"tokens":[69],"enriched":[70],"structured":[72],"time":[73],"knowledge":[74],"for":[75],"representation.Besides,":[77],"propose":[79],"multi-stage":[81],"training":[82],"strategy":[83],"tailored":[84],"such":[86],"grounding-specific":[87],"architecture.The":[88],"is":[90],"initially":[91],"trained":[92],"on":[93],"simple":[94],"video-caption":[95],"tasks":[96,144],"progressively":[98],"introduced":[99],"complex":[101],"grounding":[104,143],"tasks,":[105],"ensuring":[106],"smooth":[108],"learning":[109],"curve":[110],"alignment.We":[113],"further":[114],"strengthen":[115],"Grounded-VideoLLM's":[116],"reasoning":[118],"by":[119],"constructing":[120],"VideoQA":[122],"dataset":[123],"grounded":[125],"information":[126],"using":[127],"an":[128],"automated":[129],"annotation":[130],"pipeline.Extensive":[131],"experiments":[132],"demonstrate":[133],"Grounded-VideoLLM":[135],"not":[136],"only":[137],"surpasses":[138],"existing":[139],"models":[140],"but":[145],"also":[146],"exhibits":[147],"strong":[148],"potential":[149],"as":[150],"general":[152],"understanding":[154],"assistant.":[155]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-08T00:00:00"}