{"id":"https://openalex.org/W4404783136","doi":"https://doi.org/10.18653/v1/2024.emnlp-main.544","title":"TraveLER: A Modular Multi-LMM Agent Framework for Video Question-Answering","display_name":"TraveLER: A Modular Multi-LMM Agent Framework for Video Question-Answering","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4404783136","doi":"https://doi.org/10.18653/v1/2024.emnlp-main.544"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2024.emnlp-main.544","doi":"https://doi.org/10.18653/v1/2024.emnlp-main.544","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.emnlp-main.544","pdf_url":null,"source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.18653/v1/2024.emnlp-main.544","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101328120","display_name":"Chuyi Shang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chuyi Shang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5094579755","display_name":"Amos You","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Amos You","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020117260","display_name":"Sanjay Subramanian","orcid":"https://orcid.org/0009-0001-1399-9920","observed_orcids":["https://orcid.org/0009-0001-1399-9920"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sanjay Subramanian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029105520","display_name":"Trevor Darrell","orcid":"https://orcid.org/0000-0001-5453-8533","observed_orcids":["https://orcid.org/0000-0001-5453-8533"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Trevor Darrell","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5066997569","display_name":"Roei Herzig","orcid":"https://orcid.org/0000-0002-5451-6059","observed_orcids":["https://orcid.org/0000-0002-5451-6059"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Roei Herzig","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":2.0531,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.91361877,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"9740","last_page":"9766"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9965999722480774,"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":0.9965999722480774,"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":0.00039999998989515007,"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.0003000000142492354,"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/multimodal-large-language-models","display_name":"multimodal large language models","score":0.7429999709129333},{"id":"https://openalex.org/keywords/video-question-answering","display_name":"video question answering","score":0.949999988079071},{"id":"https://openalex.org/keywords/agent-frameworks","display_name":"agent frameworks","score":0.5879999995231628},{"id":"https://openalex.org/keywords/video-understanding","display_name":"video understanding","score":0.49300000071525574}],"concepts":[{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.8248506784439087},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.745235800743103},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6121099591255188},{"id":"https://openalex.org/C2777614354","wikidata":"https://www.wikidata.org/wiki/Q55648394","display_name":"Modular construction","level":3,"score":0.5157421231269836},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.32140591740608215},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.32125890254974365},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.30019837617874146}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2024.emnlp-main.544","doi":"https://doi.org/10.18653/v1/2024.emnlp-main.544","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.emnlp-main.544","pdf_url":null,"source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2404.01476","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2404.01476","pdf_url":"https://arxiv.org/pdf/2404.01476","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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2404.01476","doi":"https://doi.org/10.48550/arxiv.2404.01476","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2404.01476","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2024.emnlp-main.544","doi":"https://doi.org/10.18653/v1/2024.emnlp-main.544","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.emnlp-main.544","pdf_url":null,"source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4390190606","https://openalex.org/W4417521047","https://openalex.org/W4414165806","https://openalex.org/W3217304284","https://openalex.org/W4404781975","https://openalex.org/W7138867579","https://openalex.org/W4415709634","https://openalex.org/W7221366401","https://openalex.org/W4415125283","https://openalex.org/W4416281167"],"abstract_inverted_index":{"Recently,":[0],"image-based":[1],"Large":[2],"Multimodal":[3],"Models":[4],"(LMMs)":[5],"have":[6],"made":[7],"significant":[8],"progress":[9],"in":[10,22,52],"video":[11],"question-answering":[12],"(VideoQA)":[13],"using":[14,94],"a":[15,23,53,73,87,105,110],"frame-wise":[16],"approach":[17,167],"by":[18,86],"leveraging":[19],"large-scale":[20],"pretraining":[21],"zero-shot":[24],"manner.":[25],"Nevertheless,":[26],"these":[27,50],"models":[28],"need":[29,176],"to":[30,59,112,122,136,151,177],"be":[31],"capable":[32],"of":[33,49],"finding":[34],"relevant":[35],"information,":[36,127,146],"extracting":[37],"it,":[38],"and":[39,124,128],"answering":[40],"the":[41,98,115,138,164,175],"question":[42],"simultaneously.":[43],"Currently,":[44],"existing":[45],"methods":[46],"perform":[47],"all":[48],"steps":[51],"single":[54],"pass":[55],"without":[56,174],"being":[57],"able":[58,150],"adapt":[60],"if":[61,131,141],"insufficient":[62],"or":[63],"incorrect":[64],"information":[65,135],"is":[66,133,143,149,184],"collected.":[67],"To":[68],"overcome":[69],"this,":[70],"we":[71,102,161],"introduce":[72],"modular":[74],"multi-LMM":[75],"agent":[76,89],"framework":[77],"based":[78,153],"on":[79,154,170,179],"several":[80,171],"agents":[81],"with":[82],"different":[83],"roles,":[84],"instructed":[85],"Planner":[88],"that":[90,107,163],"updates":[91],"its":[92,155],"instructions":[93],"shared":[95],"feedback":[96],"from":[97],"other":[99],"agents.":[100],"Specifically,":[101],"propose":[103],"TraveLER,":[104],"method":[106,148],"can":[108],"create":[109],"plan":[111],"\"Traverse\"":[113],"through":[114],"video,":[116],"ask":[117],"questions":[118],"about":[119],"individual":[120],"frames":[121],"\"Locate\"":[123],"store":[125],"key":[126],"then":[129],"\"Evaluate\"":[130],"there":[132,142],"enough":[134,145],"answer":[137],"question.":[139],"Finally,":[140],"not":[144],"our":[147],"\"Replan\"":[152],"collected":[156],"knowledge.":[157],"Through":[158],"extensive":[159],"experiments,":[160],"find":[162],"proposed":[165],"TraveLER":[166],"improves":[168],"performance":[169],"VideoQA":[172],"benchmarks":[173],"fine-tune":[178],"specific":[180],"datasets.":[181],"Our":[182],"code":[183],"available":[185],"at":[186],"https://github.com/traveler-framework/TraveLER.":[187]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":5}],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2024-11-28T00:00:00"}