{"id":"https://openalex.org/W4414739831","doi":"https://doi.org/10.1109/iccv51701.2025.02016","title":"DisCo: Towards Distinct and Coherent Visual Encapsulation in Video MLLMs","display_name":"DisCo: Towards Distinct and Coherent Visual Encapsulation in Video MLLMs","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4414739831","doi":"https://doi.org/10.1109/iccv51701.2025.02016"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.02016","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02016","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.10302","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Jiahe Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jiahe Zhao","raw_affiliation_strings":["The University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119809227","display_name":"Rongkun Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Rongkun Zheng","raw_affiliation_strings":["The University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100710570","display_name":"Yibin Wang","orcid":"https://orcid.org/0000-0003-0852-0767"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Wang","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Helin Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Helin Wang","raw_affiliation_strings":["Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078109015","display_name":"Hengshuang Zhao","orcid":"https://orcid.org/0000-0001-8277-2706"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Hengshuang Zhao","raw_affiliation_strings":["The University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"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":0.46821938,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"21710","last_page":"21720"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9916999936103821,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9916999936103821,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9815999865531921,"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/T11408","display_name":"Advanced Optical Imaging Technologies","score":0.9623000025749207,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5651999711990356},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.4975000023841858},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.4948999881744385},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.47450000047683716},{"id":"https://openalex.org/keywords/encapsulation","display_name":"Encapsulation (networking)","score":0.4339999854564667},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.41839998960494995},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.3968000113964081}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7839000225067139},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5651999711990356},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5493000149726868},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.4975000023841858},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.4948999881744385},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.47450000047683716},{"id":"https://openalex.org/C81147070","wikidata":"https://www.wikidata.org/wiki/Q1172449","display_name":"Encapsulation (networking)","level":2,"score":0.4339999854564667},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.41839998960494995},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3968000113964081},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.3856000006198883},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3790999948978424},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3142000138759613},{"id":"https://openalex.org/C105842133","wikidata":"https://www.wikidata.org/wiki/Q1899679","display_name":"Visual communication","level":2,"score":0.3000999987125397},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.2939999997615814},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.28859999775886536},{"id":"https://openalex.org/C2779321571","wikidata":"https://www.wikidata.org/wiki/Q7936605","display_name":"Visual learning","level":2,"score":0.27129998803138733},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.25209999084472656}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.02016","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02016","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.10302","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.10302","pdf_url":"https://arxiv.org/pdf/2507.10302","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":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2507.10302","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.10302","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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.10302","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.10302","pdf_url":"https://arxiv.org/pdf/2507.10302","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":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5058943624","display_name":null,"funder_award_id":"2022ZD0160101","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G5496564920","display_name":null,"funder_award_id":"62422606,62201484","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0],"video":[1,18,86,132,136,143,159],"Multimodal":[2],"Large":[3],"Language":[4],"Models":[5],"(video":[6],"MLLMs),":[7],"the":[8,46,115,170],"visual":[9,72,83,104,129],"encapsulation":[10,73],"process":[11],"plays":[12],"a":[13,70,156],"pivotal":[14],"role":[15],"in":[16,52,109,114],"converting":[17],"contents":[19],"into":[20],"representative":[21],"tokens":[22,84,105,130],"for":[23,32,85,103],"LLM":[24],"input.":[25],"While":[26],"linear":[27],"projectors":[28],"are":[29],"widely":[30],"employed":[31],"encapsulation,":[33],"they":[34],"introduce":[35,68],"semantic":[36,173],"indistinctness":[37],"and":[38,80],"temporal":[39,126],"incoherence":[40],"when":[41],"applied":[42],"to":[43,76,131,169],"videos.":[44],"Conversely,":[45],"structure":[47],"of":[48,128,158,172],"resamplers":[49],"shows":[50],"promise":[51],"tackling":[53],"these":[54],"challenges,":[55],"but":[56],"an":[57],"effective":[58],"solution":[59],"remains":[60],"unexplored.":[61],"Drawing":[62],"inspiration":[63],"from":[64],"resampler":[65],"structures,":[66],"we":[67,146],"DisCo,":[69],"novel":[71],"method":[74],"designed":[75],"yield":[77],"semantically":[78],"distinct":[79],"temporally":[81],"coherent":[82],"MLLMs.":[87],"DisCo":[88,149],"integrates":[89],"two":[90],"key":[91],"components:":[92],"(1)":[93],"A":[94,118],"Visual":[95],"Concept":[96],"Discriminator":[97],"(VCD)":[98],"module,":[99,123],"assigning":[100],"unique":[101],"semantics":[102],"by":[106],"associating":[107],"them":[108],"pair":[110],"with":[111],"discriminative":[112],"concepts":[113],"video.":[116],"(2)":[117],"Temporal":[119],"Focus":[120],"Calibrator":[121],"(TFC)":[122],"ensuring":[124],"consistent":[125],"focus":[127],"elements":[133],"across":[134,155],"every":[135],"frame.":[137],"Through":[138],"extensive":[139],"experiments":[140],"on":[141],"multiple":[142],"MLLM":[144],"frameworks,":[145],"demonstrate":[147],"that":[148],"remarkably":[150],"outperforms":[151],"previous":[152],"state-of-the-art":[153],"methods":[154],"variety":[157],"understanding":[160],"benchmarks,":[161],"while":[162],"also":[163],"achieving":[164],"higher":[165],"token":[166],"efficiency":[167],"thanks":[168],"reduction":[171],"indistinctness.":[174],"The":[175],"code:":[176],"https://github.com/ZJHTerry18/DisCo.":[177]},"counts_by_year":[],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-10-10T00:00:00"}