{"id":"https://openalex.org/W4404985367","doi":"https://doi.org/10.48550/arxiv.2411.14505","title":"LLaVA-MR: Large Language-and-Vision Assistant for Video Moment Retrieval","display_name":"LLaVA-MR: Large Language-and-Vision Assistant for Video Moment Retrieval","publication_year":2024,"publication_date":"2024-11-21","ids":{"openalex":"https://openalex.org/W4404985367","doi":"https://doi.org/10.48550/arxiv.2411.14505"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2411.14505","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.14505","pdf_url":"https://arxiv.org/pdf/2411.14505","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2411.14505","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112806035","display_name":"Weisheng Lu","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Lu, Weiheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100402609","display_name":"Jian Li","orcid":"https://orcid.org/0000-0003-3439-7539"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Jian","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038784048","display_name":"An Yu\ue00a","orcid":"https://orcid.org/0000-0003-2855-7401"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, An","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012638803","display_name":"Ming\u2010Ching Chang","orcid":"https://orcid.org/0000-0001-9325-5341"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chang, Ming-Ching","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102904447","display_name":"Shengpeng Ji","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ji, Shengpeng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5019003956","display_name":"Min Xia","orcid":"https://orcid.org/0000-0001-8057-9654"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xia, Min","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5112806035"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998000264167786,"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":0.9998000264167786,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9991000294685364,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9984999895095825,"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/moment","display_name":"Moment (physics)","score":0.5800637602806091},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.49300190806388855},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4582895040512085},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3893555998802185},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.201048344373703}],"concepts":[{"id":"https://openalex.org/C179254644","wikidata":"https://www.wikidata.org/wiki/Q13222844","display_name":"Moment (physics)","level":2,"score":0.5800637602806091},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49300190806388855},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4582895040512085},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3893555998802185},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.201048344373703},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2411.14505","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.14505","pdf_url":"https://arxiv.org/pdf/2411.14505","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2411.14505","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2411.14505","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2411.14505","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.14505","pdf_url":"https://arxiv.org/pdf/2411.14505","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4404985367.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Multimodal":[0],"Large":[1,37],"Language":[2],"Models":[3],"(MLLMs)":[4],"are":[5],"widely":[6],"used":[7],"for":[8,40,64,72],"visual":[9,75],"perception,":[10],"understanding,":[11],"and":[12,18,30,49,60,76,79,94,110],"reasoning.":[13],"However,":[14],"long":[15],"video":[16],"processing":[17],"precise":[19],"moment":[20,47],"retrieval":[21,48],"remain":[22],"challenging":[23],"due":[24],"to":[25,84],"LLMs'":[26],"limited":[27],"context":[28,87],"size":[29],"coarse":[31],"frame":[32],"extraction.":[33],"We":[34],"propose":[35],"the":[36,115],"Language-and-Vision":[38],"Assistant":[39],"Moment":[41],"Retrieval":[42],"(LLaVA-MR),":[43],"which":[44],"enables":[45],"accurate":[46],"contextual":[50],"grounding":[51],"in":[52,108,112],"videos":[53],"using":[54],"MLLMs.":[55],"LLaVA-MR":[56,98],"combines":[57],"Dense":[58],"Frame":[59,69],"Time":[61],"Encoding":[62],"(DFTE)":[63],"spatial-temporal":[65],"feature":[66],"extraction,":[67],"Informative":[68],"Selection":[70],"(IFS)":[71],"capturing":[73],"brief":[74],"motion":[77],"patterns,":[78],"Dynamic":[80],"Token":[81],"Compression":[82],"(DTC)":[83],"manage":[85],"LLM":[86],"limitations.":[88],"Evaluations":[89],"on":[90,114],"benchmarks":[91],"like":[92],"Charades-STA":[93],"QVHighlights":[95,116],"demonstrate":[96],"that":[97],"outperforms":[99],"11":[100],"state-of-the-art":[101],"methods,":[102],"achieving":[103],"an":[104],"improvement":[105],"of":[106],"1.82%":[107],"R1@0.5":[109],"1.29%":[111],"mAP@0.5":[113],"dataset.":[117],"Our":[118],"implementation":[119],"will":[120],"be":[121],"open-sourced":[122],"upon":[123],"acceptance.":[124]},"counts_by_year":[],"updated_date":"2026-03-12T08:34:05.389933","created_date":"2025-10-10T00:00:00"}