{"id":"https://openalex.org/W7129109165","doi":"https://doi.org/10.1109/tmm.2026.3664996","title":"Long Video Understanding With Learnable Retrieval in Video-Language Models","display_name":"Long Video Understanding With Learnable Retrieval in Video-Language Models","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7129109165","doi":"https://doi.org/10.1109/tmm.2026.3664996"},"language":null,"primary_location":{"id":"doi:10.1109/tmm.2026.3664996","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3664996","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126077421","display_name":"Jiaqi Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaqi Xu","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0005-4081-736X","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093975902","display_name":"Cuiling Lan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cuiling Lan","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9145-9957","affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126119626","display_name":"Wenxuan Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenxuan Xie","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093975904","display_name":"Xuejin Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuejin Chen","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-0478-7018","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5126083558","display_name":"Yan Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Lu","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5383-6424","affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.18473988,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"28","issue":null,"first_page":"5254","last_page":"5261"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9800999760627747,"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":0.9800999760627747,"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":0.002899999963119626,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.002899999963119626,"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/context","display_name":"Context (archaeology)","score":0.5738999843597412},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5575000047683716},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.4474000036716461},{"id":"https://openalex.org/keywords/video-processing","display_name":"Video processing","score":0.42320001125335693},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.39010000228881836},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.367000013589859},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.3626999855041504}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.896399974822998},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5738999843597412},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5575000047683716},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48590001463890076},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.4474000036716461},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.42320001125335693},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.39010000228881836},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.367000013589859},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3626999855041504},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.35839998722076416},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3529999852180481},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.3513000011444092},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3458999991416931},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.3061000108718872},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.3050000071525574},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.29809999465942383},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.28529998660087585},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.28110000491142273}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2026.3664996","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3664996","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7840346097946167}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1927052826","https://openalex.org/W2969897437","https://openalex.org/W3034425145","https://openalex.org/W3175961224","https://openalex.org/W3181758331","https://openalex.org/W3197457832","https://openalex.org/W3207409917","https://openalex.org/W3217304284","https://openalex.org/W4200631219","https://openalex.org/W4242466979","https://openalex.org/W4292829066","https://openalex.org/W4312246181","https://openalex.org/W4387546363","https://openalex.org/W4388692349","https://openalex.org/W4389519587","https://openalex.org/W4389988129","https://openalex.org/W4390873732","https://openalex.org/W4390889724","https://openalex.org/W4402660133","https://openalex.org/W4402671548","https://openalex.org/W4402702917","https://openalex.org/W4402727142","https://openalex.org/W4402727272","https://openalex.org/W4402754220","https://openalex.org/W4402961760","https://openalex.org/W4403002096","https://openalex.org/W4403791756","https://openalex.org/W4404770348","https://openalex.org/W4404781975","https://openalex.org/W4404784276","https://openalex.org/W4413145669","https://openalex.org/W4415795316","https://openalex.org/W7108068597","https://openalex.org/W7133182950","https://openalex.org/W7133185515","https://openalex.org/W7133193597","https://openalex.org/W7133196460","https://openalex.org/W7133198646","https://openalex.org/W7133211372","https://openalex.org/W7133220561","https://openalex.org/W7133226454"],"related_works":[],"abstract_inverted_index":{"The":[0,39],"remarkable":[1],"natural":[2],"language":[3,11],"understanding,":[4,22],"reasoning,":[5],"and":[6,100,111,136],"generation":[7],"capabilities":[8],"of":[9,42,59,65,130,155,162,184],"large":[10],"models":[12],"(LLMs)":[13],"have":[14],"made":[15],"them":[16],"attractive":[17],"for":[18,32,50,91,121,187],"application":[19],"to":[20,46,71,117,150],"video":[21,24,34,43,73,94,131,177],"utilizing":[23],"tokens":[25,44,55,68,116],"as":[26,119],"contextual":[27],"input.":[28],"However,":[29],"employing":[30],"LLMs":[31,51],"long":[33,93,102,189],"understanding":[35],"presents":[36],"significant":[37],"challenges.":[38],"extensive":[40],"number":[41,129],"leads":[45],"considerable":[47],"computational":[48],"costs":[49],"while":[52],"using":[53],"aggregated":[54],"results":[56,173],"in":[57],"loss":[58],"vision":[60],"details.":[61],"Moreover,":[62],"the":[63,72,107,122,128,152,159,182],"presence":[64],"abundant":[66],"question-irrelevant":[67],"introduces":[69],"noise":[70,134],"reasoning":[74],"process.":[75],"To":[76],"address":[77],"these":[78],"issues,":[79],"we":[80],"introduce":[81],"a":[82,98,101,145,167],"simple":[83],"yet":[84],"effective":[85],"learnable":[86,146],"retrieval-based":[87],"video-language":[88,164],"model":[89,105,165],"(R-VLM)":[90],"efficient":[92,153],"understanding.":[95],"Specifically,":[96],"given":[97],"question":[99,178],"video,":[103],"our":[104,163,185],"identifies":[106],"most":[108],"relevant$K$video":[109],"chunks":[110],"uses":[112],"their":[113],"associated":[114],"visual":[115],"serve":[118],"context":[120],"LLM":[123],"inference.":[124],"This":[125],"effectively":[126],"reduces":[127],"tokens,":[132],"eliminates":[133],"interference,":[135],"enhances":[137],"system":[138],"performance.":[139],"We":[140],"achieve":[141],"this":[142],"by":[143],"incorporating":[144],"lightweight":[147],"MLP":[148],"block":[149],"facilitate":[151],"retrieval":[154],"question-relevant":[156],"chunks,":[157],"through":[158],"end-to-end":[160],"training":[161],"with":[166],"proposed":[168],"soft":[169],"matching":[170],"loss.":[171],"Experimental":[172],"on":[174],"multiple":[175],"zero-shot":[176],"answering":[179],"datasets":[180],"validate":[181],"effectiveness":[183],"framework":[186],"comprehending":[188],"videos.":[190]},"counts_by_year":[],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2026-02-17T00:00:00"}