{"id":"https://openalex.org/W4405088984","doi":"https://doi.org/10.18653/v1/2026.findings-acl.70","title":"TemporalVLM: Video LLMs for Temporal Reasoning in Long Videos","display_name":"TemporalVLM: Video LLMs for Temporal Reasoning in Long Videos","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4405088984","doi":"https://doi.org/10.18653/v1/2026.findings-acl.70"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.70","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.70","pdf_url":null,"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: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.18653/v1/2026.findings-acl.70","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5115021336","display_name":"Fawad Javed Fateh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fawad Javed Fateh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115021337","display_name":"Umer Ahmed","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Umer Ahmed","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Hamza Khan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hamza Khan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011037400","display_name":"M. Zeeshan Zia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zeeshan Zia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5000328580","display_name":"Quoc-Huy Tran","orcid":"https://orcid.org/0000-0003-1396-6544"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Quoc-Huy Tran","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":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00247729,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1427","last_page":"1447"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9905999898910522,"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":0.9905999898910522,"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":0.9829000234603882,"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":0.9588000178337097,"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/computer-science","display_name":"Computer science","score":0.3931042551994324}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3931042551994324}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.70","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.70","pdf_url":null,"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: ACL 2026","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2412.02930","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.02930","pdf_url":"https://arxiv.org/pdf/2412.02930","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":"pmh:oai:arXiv.org:2412.02930","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2412.02930","pdf_url":"https://arxiv.org/pdf/2412.02930","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.2412.02930","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2412.02930","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.70","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.70","pdf_url":null,"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: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"We":[0],"introduce":[1],"TemporalVLM,":[2,91],"a":[3,22,27,74,94],"video":[4,29,47,97,148,151,153,173],"large":[5],"language":[6],"model":[7],"(video":[8],"LLM)":[9],"for":[10,25,81,120],"temporal":[11,61,126,140,150,157],"reasoning":[12,141],"and":[13,35,39,57,114,122,125,142,156],"fine-grained":[14,143],"understanding":[15,144],"in":[16],"long":[17,76,96],"videos.":[18],"Our":[19],"approach":[20],"includes":[21],"visual":[23],"encoder":[24],"mapping":[26],"long-term":[28],"into":[30,48,63,172],"features":[31,70],"which":[32,51],"are":[33,52,71],"time-aware":[34],"contain":[36],"both":[37],"local":[38,65,69],"global":[40,82],"cues.":[41],"It":[42],"first":[43,168],"divides":[44],"an":[45],"input":[46],"short-term":[49,77],"clips,":[50],"jointly":[53],"encoded":[54],"with":[55,112],"timestamps":[56,115],"fused":[58],"across":[59,139],"overlapping":[60],"windows":[62],"time-sensitive":[64],"features.":[66],"Next,":[67],"the":[68,88,167],"passed":[72],"through":[73],"bidirectional":[75],"memory":[78],"(BiLSTM)":[79],"module":[80],"feature":[83],"aggregation.":[84],"Moreover,":[85],"to":[86,169],"facilitate":[87],"evaluation":[89],"of":[90,99,106],"we":[92],"present":[93],"large-scale":[95],"dataset":[98],"industry":[100],"assembly":[101],"processes,":[102],"namely":[103],"IndustryASM,":[104],"consisting":[105],"videos":[107],"recorded":[108],"on":[109],"factory":[110],"floors":[111],"actions":[113],"annotated":[116],"by":[117],"industrial":[118],"engineers":[119],"time":[121],"motion":[123],"studies":[124],"action":[127,158],"segmentation":[128],"evaluation.":[129],"Finally,":[130],"extensive":[131],"experiments":[132],"show":[133],"that":[134],"TemporalVLM":[135],"outperforms":[136],"previous":[137],"methods":[138],"tasks,":[145],"i.e.,":[146],"dense":[147],"captioning,":[149],"grounding,":[152],"highlight":[154],"detection,":[155],"segmentation.":[159],"To":[160],"our":[161,164],"best":[162],"knowledge,":[163],"work":[165],"is":[166],"incorporate":[170],"LSTMs":[171],"LLMs.":[174]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}