{"id":"https://openalex.org/W7160243981","doi":"https://doi.org/10.1109/wacv61042.2026.00413","title":"Learning Compact Video Representations for Efficient Long-form Video Understanding in Large Multimodal Models","display_name":"Learning Compact Video Representations for Efficient Long-form Video Understanding in Large Multimodal Models","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W7160243981","doi":"https://doi.org/10.1109/wacv61042.2026.00413"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00413","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00413","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-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/A5135289150","display_name":"Yuxiao Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuxiao Chen","raw_affiliation_strings":["Amazon AGI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon AGI","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135355698","display_name":"Jue Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jue Wang","raw_affiliation_strings":["Amazon AGI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon AGI","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025539122","display_name":"Zhikang Zhang","orcid":"https://orcid.org/0000-0002-3024-1644"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhikang Zhang","raw_affiliation_strings":["Amazon AGI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon AGI","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054640239","display_name":"Jingru Yi","orcid":"https://orcid.org/0000-0001-9648-9389"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jingru Yi","raw_affiliation_strings":["Amazon AGI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon AGI","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100437225","display_name":"Xu Zhang","orcid":"https://orcid.org/0000-0002-3991-5748"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xu Zhang","raw_affiliation_strings":["Amazon AGI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon AGI","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128342354","display_name":"Yang Zou","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yang Zou","raw_affiliation_strings":["Amazon AGI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon AGI","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135392540","display_name":"Zhaowei Cai","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhaowei Cai","raw_affiliation_strings":["Amazon AGI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon AGI","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135407720","display_name":"Jianbo Yuan","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jianbo Yuan","raw_affiliation_strings":["Amazon AGI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon AGI","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135302323","display_name":"Xinyu Li","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xinyu Li","raw_affiliation_strings":["Amazon AGI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon AGI","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135390276","display_name":"Hao Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hao Yang","raw_affiliation_strings":["Amazon AGI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon AGI","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044605684","display_name":"Davide Modolo","orcid":"https://orcid.org/0000-0002-7625-7748"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Davide Modolo","raw_affiliation_strings":["Amazon AGI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon AGI","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":11,"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":0.68144028,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4242","last_page":"4252"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.36239999532699585,"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":0.36239999532699585,"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":0.12399999797344208,"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/T11448","display_name":"Face recognition and analysis","score":0.09989999979734421,"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/frame","display_name":"Frame (networking)","score":0.3239000141620636},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.3230000138282776},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.32179999351501465},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.29809999465942383},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.27379998564720154}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6678000092506409},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5131999850273132},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3978999853134155},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.3239000141620636},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3230000138282776},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.32179999351501465},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.29809999465942383},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.27070000767707825},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.25529998540878296}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wacv61042.2026.00413","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00413","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W2099614498","https://openalex.org/W2964094654","https://openalex.org/W2964220823","https://openalex.org/W2989322838","https://openalex.org/W3175859344","https://openalex.org/W3175961224","https://openalex.org/W3205786327","https://openalex.org/W4226407477","https://openalex.org/W4312290555","https://openalex.org/W4313038481","https://openalex.org/W4385801014","https://openalex.org/W4386075572","https://openalex.org/W4388979610","https://openalex.org/W4389519526","https://openalex.org/W4402671548","https://openalex.org/W4402702917","https://openalex.org/W4402716120","https://openalex.org/W4402716132","https://openalex.org/W4402727142","https://openalex.org/W4403002096","https://openalex.org/W4403760933","https://openalex.org/W4404781468","https://openalex.org/W4404781975","https://openalex.org/W4404784276","https://openalex.org/W4414404693","https://openalex.org/W4415798317","https://openalex.org/W7108068597","https://openalex.org/W7117320526","https://openalex.org/W7133198646","https://openalex.org/W7133228365"],"related_works":[],"abstract_inverted_index":{"With":[0],"recent":[1],"advancements":[2],"in":[3,155,177],"video":[4,39,89,96,103,129,158,163,183],"backbone":[5],"architectures,":[6],"combined":[7],"with":[8,107],"the":[9,17,34,72,169,179],"remarkable":[10],"achievements":[11],"of":[12,19,24,38,61,75,131,173,181],"large":[13,110],"language":[14,111],"models":[15],"(LLMs),":[16],"analysis":[18],"long-form":[20,88,157],"videos":[21],"spanning":[22],"tens":[23],"minutes":[25],"has":[26],"become":[27],"both":[28,156],"feasible":[29],"and":[30,66,99,123,134,161,171],"increasingly":[31],"prevalent.":[32],"However,":[33],"inherently":[35],"redundant":[36],"nature":[37],"sequences":[40,130],"poses":[41],"significant":[42],"challenges":[43,49],"for":[44,87],"contemporary":[45],"state-of-the-art":[46],"models.":[47],"These":[48,166],"stem":[50],"from":[51,71,128],"two":[52,118],"primary":[53],"aspects:":[54],"1)":[55],"efficiently":[56],"incorporating":[57],"a":[58,83,108],"larger":[59],"number":[60],"frames":[62],"within":[63],"memory":[64],"constraints,":[65],"2)":[67],"extracting":[68],"discriminative":[69,143],"information":[70,127],"vast":[73],"volume":[74],"input":[76],"data.":[77],"In":[78],"this":[79],"paper,":[80],"we":[81],"introduce":[82],"novel":[84],"end-to-end":[85],"schema":[86],"understanding,":[90],"which":[91],"includes":[92],"an":[93,100],"information-density-based":[94],"adaptive":[95],"sampler":[97],"(AVS)":[98],"autoencoder-based":[101],"spatiotemporal":[102],"compressor":[104],"(SVC)":[105],"integrated":[106],"multimodal":[109],"model":[112],"(MLLM).":[113],"Our":[114],"proposed":[115,146],"system":[116],"offers":[117],"major":[119],"advantages:":[120],"it":[121,135],"adaptively":[122],"effectively":[124],"captures":[125],"essential":[126],"varying":[132],"durations,":[133],"achieves":[136],"high":[137],"compression":[138],"rates":[139],"while":[140],"preserving":[141],"crucial":[142],"information.":[144],"The":[145],"framework":[147],"demonstrates":[148],"promising":[149],"performance":[150],"across":[151],"various":[152],"benchmarks,":[153],"excelling":[154],"understanding":[159,164],"tasks":[160],"standard":[162],"benchmarks.":[165],"results":[167],"underscore":[168],"versatility":[170],"efficacy":[172],"our":[174],"approach,":[175],"particularly":[176],"managing":[178],"complexities":[180],"prolonged":[182],"sequences.":[184]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-06T00:00:00"}