{"id":"https://openalex.org/W4415329052","doi":"https://doi.org/10.48550/arxiv.2505.15529","title":"Clapper: Compact Learning and Video Representation in VLMs","display_name":"Clapper: Compact Learning and Video Representation in VLMs","publication_year":2025,"publication_date":"2025-05-21","ids":{"openalex":"https://openalex.org/W4415329052","doi":"https://doi.org/10.48550/arxiv.2505.15529"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2505.15529","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.15529","pdf_url":"https://arxiv.org/pdf/2505.15529","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.15529","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100610017","display_name":"Lingyu Kong","orcid":"https://orcid.org/0000-0002-9471-0278","observed_orcids":["https://orcid.org/0000-0002-9471-0278"]},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kong, Lingyu","raw_affiliation_strings":["University of Chinese Academy of Sciences ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences ,","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100776513","display_name":"Hongzhi Zhang","orcid":"https://orcid.org/0000-0001-8025-346X","observed_orcids":["https://orcid.org/0000-0001-8025-346X","https://orcid.org/0000-0002-9688-7691"]},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Hongzhi","raw_affiliation_strings":["Kuaishou Technology ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuaishou Technology ,","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100639601","display_name":"Jingyuan Zhang","orcid":"https://orcid.org/0000-0001-6644-4673","observed_orcids":["https://orcid.org/0000-0001-6644-4673"]},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Jingyuan","raw_affiliation_strings":["Kuaishou Technology ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuaishou Technology ,","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025205664","display_name":"Jianzhao Huang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huang, Jianzhao","raw_affiliation_strings":["Kuaishou Technology ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuaishou Technology ,","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114182852","display_name":"Kunze Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Kunze","raw_affiliation_strings":["Xi'an Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101947323","display_name":"Qi Wang","orcid":"https://orcid.org/0000-0002-4290-0117","observed_orcids":["https://orcid.org/0000-0002-4290-0117"]},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Qi","raw_affiliation_strings":["Kuaishou Technology ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuaishou Technology ,","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101586840","display_name":"Fuzheng Zhang","orcid":"https://orcid.org/0000-0002-6079-6392","observed_orcids":["https://orcid.org/0000-0002-6079-6392"]},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Fuzheng","raw_affiliation_strings":["Kuaishou Technology ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuaishou Technology ,","institution_ids":["https://openalex.org/I4401726859"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"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":1.0,"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":1.0,"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":0.0,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.0,"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/vision-language-models","display_name":"vision-language models","score":0.9649999737739563},{"id":"https://openalex.org/keywords/long-video-understanding","display_name":"long video understanding","score":0.8510000109672546},{"id":"https://openalex.org/keywords/video-representation","display_name":"video representation","score":0.6899999976158142},{"id":"https://openalex.org/keywords/visual-token-compression","display_name":"visual token compression","score":0.8240000009536743},{"id":"https://openalex.org/keywords/temporal-modeling","display_name":"temporal modeling","score":0.671999990940094},{"id":"https://openalex.org/keywords/video-question-answering","display_name":"video question answering","score":0.6389999985694885},{"id":"https://openalex.org/keywords/compact-modeling","display_name":"compact modeling","score":0.38100001215934753}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.849399983882904},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.6067000031471252},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5735999941825867},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.569100022315979},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.5356000065803528},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4848000109195709},{"id":"https://openalex.org/C106030495","wikidata":"https://www.wikidata.org/wiki/Q1797012","display_name":"Video compression picture types","level":4,"score":0.47200000286102295},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.4706000089645386},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4668000042438507},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.45730000734329224},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.43160000443458557},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.37929999828338623},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.37400001287460327},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.3637999892234802},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.33390000462532043},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.33169999718666077},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3199999928474426},{"id":"https://openalex.org/C160086991","wikidata":"https://www.wikidata.org/wiki/Q5939193","display_name":"Human visual system model","level":3,"score":0.3109999895095825},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.3070000112056732},{"id":"https://openalex.org/C57654395","wikidata":"https://www.wikidata.org/wiki/Q1097775","display_name":"Compression artifact","level":5,"score":0.29319998621940613},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.29190000891685486},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2791000008583069},{"id":"https://openalex.org/C3261483","wikidata":"https://www.wikidata.org/wiki/Q119565","display_name":"Frame rate","level":2,"score":0.26820001006126404},{"id":"https://openalex.org/C23431618","wikidata":"https://www.wikidata.org/wiki/Q1404672","display_name":"Multiview Video Coding","level":4,"score":0.2662999927997589}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2505.15529","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.15529","pdf_url":"https://arxiv.org/pdf/2505.15529","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2505.15529","doi":"https://doi.org/10.48550/arxiv.2505.15529","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.15529","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2505.15529","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.15529","pdf_url":"https://arxiv.org/pdf/2505.15529","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415329052.pdf","grobid_xml":"https://content.openalex.org/works/W4415329052.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W4383604278","https://openalex.org/W4396818380","https://openalex.org/W4400024885","https://openalex.org/W4400375159","https://openalex.org/W4401660192","https://openalex.org/W4402670320","https://openalex.org/W4403370767","https://openalex.org/W4403853618","https://openalex.org/W4404304985","https://openalex.org/W4404784276","https://openalex.org/W4405172832","https://openalex.org/W4405425349","https://openalex.org/W4406073438","https://openalex.org/W4406489046","https://openalex.org/W4411113516","https://openalex.org/W4411120590","https://openalex.org/W4413144845","https://openalex.org/W4413146669","https://openalex.org/W7128429593","https://openalex.org/W7166493911"],"related_works":["https://openalex.org/W4403574051","https://openalex.org/W7153349655","https://openalex.org/W4417247495","https://openalex.org/W7154587395","https://openalex.org/W4415935673","https://openalex.org/W7140223168","https://openalex.org/W4404304985","https://openalex.org/W7214768171","https://openalex.org/W7215811224","https://openalex.org/W4413156662"],"abstract_inverted_index":{"Current":[0],"vision-language":[1],"models":[2],"(VLMs)":[3],"have":[4],"demonstrated":[5],"remarkable":[6],"capabilities":[7],"across":[8,27],"diverse":[9],"video":[10,16,78,103,116],"understanding":[11,79],"applications.":[12],"Designing":[13],"VLMs":[14,71],"for":[15,115,125],"inputs":[17],"requires":[18],"effectively":[19],"modeling":[20,97],"the":[21,31,184],"temporal":[22,58],"dimension":[23],"(i.e.":[24],"capturing":[25],"dependencies":[26],"frames)":[28],"and":[29,35,101,118,164],"balancing":[30],"processing":[32],"of":[33,43,52,88,98,141],"short":[34,39,100],"long":[36,47,77,102],"videos.":[37],"Specifically,":[38],"videos":[40,48],"demand":[41],"preservation":[42],"fine-grained":[44],"details,":[45],"whereas":[46],"require":[49],"strategic":[50],"compression":[51,140],"visual":[53,83,91,142,173],"information":[54],"to":[55],"handle":[56],"extensive":[57],"contexts":[59],"efficiently.":[60],"However,":[61],"our":[62,135,154],"empirical":[63],"analysis":[64],"reveals":[65],"a":[66,86,108,112,120],"critical":[67],"limitation:":[68],"most":[69],"existing":[70,130],"suffer":[72],"severe":[73],"performance":[74],"degradation":[75],"in":[76],"tasks":[80],"when":[81],"compressing":[82],"tokens":[84,143,174],"below":[85],"quarter":[87],"their":[89],"original":[90],"tokens.":[92],"To":[93],"enable":[94],"more":[95],"effective":[96],"both":[99],"inputs,":[104],"we":[105,137],"propose":[106],"Clapper,":[107],"method":[109],"that":[110],"utilizes":[111],"slow-fast":[113],"strategy":[114],"representation":[117],"introduces":[119],"novel":[121],"module":[122],"named":[123],"TimePerceiver":[124],"efficient":[126],"temporal-spatial":[127],"encoding":[128],"within":[129],"VLM":[131],"backbones.":[132],"By":[133],"using":[134],"method,":[136],"achieves":[138,157],"13x":[139],"per":[144,175],"frame":[145],"(averaging":[146],"61":[147],"tokens/frame)":[148],"without":[149],"compromising":[150],"QA":[151],"accuracy.":[152],"In":[153],"experiments,":[155],"Clapper":[156],"62.0%":[158],"on":[159,162,166,183],"VideoMME,":[160],"69.8%":[161],"MLVU,":[163],"67.4%":[165],"TempCompass,":[167],"all":[168],"with":[169],"fewer":[170],"than":[171],"6,000":[172],"video.":[176],"The":[177],"code":[178],"will":[179],"be":[180],"publicly":[181],"available":[182],"homepage.":[185]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-19T00:00:00"}