{"id":"https://openalex.org/W4417168958","doi":"https://doi.org/10.48550/arxiv.2504.20384","title":"FiLA-Video: Spatio-Temporal Compression for Fine-Grained Long Video Understanding","display_name":"FiLA-Video: Spatio-Temporal Compression for Fine-Grained Long Video Understanding","publication_year":2025,"publication_date":"2025-04-29","ids":{"openalex":"https://openalex.org/W4417168958","doi":"https://doi.org/10.48550/arxiv.2504.20384"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2504.20384","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.20384","pdf_url":"https://arxiv.org/pdf/2504.20384","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2504.20384","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011615039","display_name":"Yanan Guo","orcid":"https://orcid.org/0000-0002-1166-1504"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Guo, Yanan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100732484","display_name":"Wenhui Dong","orcid":"https://orcid.org/0000-0001-5157-8951"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dong, Wenhui","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069575221","display_name":"Jun S. Song","orcid":"https://orcid.org/0000-0002-0422-2175"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song, Jun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102556614","display_name":"Shiding Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Shiding","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100342872","display_name":"Xuan Zhang","orcid":"https://orcid.org/0000-0001-5329-7272"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Xuan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Yang, Hanqing","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Hanqing","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076538539","display_name":"Y. Q. Wang","orcid":"https://orcid.org/0009-0006-7644-7150"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yingbo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101504057","display_name":"Yang Du","orcid":"https://orcid.org/0000-0002-4926-9233"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Du, Yang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Chen, Xianing","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Xianing","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5023147004","display_name":"Bo Zheng","orcid":"https://orcid.org/0000-0002-9299-7682"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng, Bo","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5011615039"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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":0.8141000270843506,"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":0.8141000270843506,"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":0.03519999980926514,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.027899999171495438,"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/data-compression","display_name":"Data compression","score":0.5238000154495239},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.4855000078678131},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.44369998574256897},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.4399000108242035},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.42640000581741333},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.37290000915527344},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3716999888420105},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.3662000000476837},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.36469998955726624}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.857699990272522},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6011999845504761},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.5238000154495239},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.4855000078678131},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.44369998574256897},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.4399000108242035},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.42640000581741333},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4036000072956085},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.37290000915527344},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3716999888420105},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3695000112056732},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.3662000000476837},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.36469998955726624},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.34950000047683716},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.32429999113082886},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.3012000024318695},{"id":"https://openalex.org/C2780139006","wikidata":"https://www.wikidata.org/wiki/Q1493902","display_name":"Key frame","level":3,"score":0.2964000105857849},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.29350000619888306},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.2906999886035919},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.2800000011920929},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2741999924182892},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.265500009059906},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.26089999079704285},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2596000134944916},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.25609999895095825},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.25600001215934753},{"id":"https://openalex.org/C57654395","wikidata":"https://www.wikidata.org/wiki/Q1097775","display_name":"Compression artifact","level":5,"score":0.2549000084400177},{"id":"https://openalex.org/C3261483","wikidata":"https://www.wikidata.org/wiki/Q119565","display_name":"Frame rate","level":2,"score":0.25040000677108765}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2504.20384","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.20384","pdf_url":"https://arxiv.org/pdf/2504.20384","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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.2504.20384","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2504.20384","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2504.20384","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.20384","pdf_url":"https://arxiv.org/pdf/2504.20384","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":{"Recent":[0],"advancements":[1],"in":[2,154],"video":[3,20,34,96],"understanding":[4],"within":[5],"visual":[6],"large":[7,42],"language":[8,43],"models":[9],"(VLLMs)":[10],"have":[11],"led":[12],"to":[13,37,41,50,55,158],"notable":[14],"progress.":[15],"However,":[16],"the":[17],"complexity":[18],"of":[19],"data":[21,134],"and":[22,98,152],"contextual":[23],"processing":[24],"limitations":[25],"still":[26],"hinder":[27],"long-video":[28,132,155],"comprehension.":[29],"A":[30],"common":[31],"approach":[32],"is":[33],"feature":[35],"compression":[36],"reduce":[38],"token":[39],"input":[40],"models,":[44],"yet":[45,130],"many":[46],"methods":[47],"either":[48],"fail":[49],"prioritize":[51],"essential":[52],"features,":[53],"leading":[54],"redundant":[56],"inter-frame":[57],"information,":[58],"or":[59],"introduce":[60,109],"computationally":[61],"expensive":[62],"modules.To":[63],"address":[64],"these":[65],"issues,":[66],"we":[67,108,126],"propose":[68],"FiLA(Fine-grained":[69],"Vision":[70],"Language":[71],"Model)-Video,":[72],"a":[73,78,90,110,119,128],"novel":[74],"framework":[75],"that":[76,147],"leverages":[77],"lightweight":[79],"dynamic-weight":[80],"multi-frame":[81],"fusion":[82],"strategy,":[83,113,136],"which":[84],"adaptively":[85],"integrates":[86],"multiple":[87],"frames":[88,117],"into":[89],"single":[91],"representation":[92],"while":[93],"preserving":[94],"key":[95],"information":[97],"reducing":[99],"computational":[100],"costs.":[101],"To":[102],"enhance":[103],"frame":[104],"selection":[105,112],"for":[106,122],"fusion,":[107],"keyframe":[111],"effectively":[114],"identifying":[115],"informative":[116],"from":[118],"larger":[120],"pool":[121],"improved":[123],"summarization.":[124],"Additionally,":[125],"present":[127],"simple":[129],"effective":[131],"training":[133],"generation":[135],"boosting":[137],"model":[138],"performance":[139],"without":[140],"extensive":[141],"manual":[142],"annotation.":[143],"Experimental":[144],"results":[145],"demonstrate":[146],"FiLA-Video":[148],"achieves":[149],"superior":[150],"efficiency":[151],"accuracy":[153],"comprehension":[156],"compared":[157],"existing":[159],"methods.":[160]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}