{"id":"https://openalex.org/W4404987156","doi":"https://doi.org/10.1109/iccv51701.2025.01897","title":"VideoOrion: Tokenizing Object Dynamics in Videos","display_name":"VideoOrion: Tokenizing Object Dynamics in Videos","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4404987156","doi":"https://doi.org/10.1109/iccv51701.2025.01897"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01897","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01897","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":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2411.16156","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100609931","display_name":"Yicheng Feng","orcid":"https://orcid.org/0000-0002-4652-7794"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yicheng Feng","raw_affiliation_strings":["School of Computer Science, Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005222486","display_name":"Yijiang Li","orcid":"https://orcid.org/0000-0003-0644-7199"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yijiang Li","raw_affiliation_strings":["University of California,San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,San Diego","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101893972","display_name":"Wanpeng Zhang","orcid":"https://orcid.org/0000-0002-7548-5220"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wanpeng Zhang","raw_affiliation_strings":["School of Computer Science, Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Sipeng Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I2803021693","display_name":"Steinbeis Foundation","ror":"https://ror.org/0184gbk60","country_code":"DE","type":"other","lineage":["https://openalex.org/I2803021693"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sipeng Zheng","raw_affiliation_strings":["BeingBeyond"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BeingBeyond","institution_ids":["https://openalex.org/I2803021693"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hao Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Luo","raw_affiliation_strings":["School of Computer Science, Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zihao Yue","orcid":null},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zihao Yue","raw_affiliation_strings":["Renmin University of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Renmin University of China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"last","author":{"id":null,"display_name":"Zongqing Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zongqing Lu","raw_affiliation_strings":["School of Computer Science, Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Peking University","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"20401","last_page":"20412"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9919000267982483,"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9919000267982483,"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/T11017","display_name":"Chaos-based Image/Signal Encryption","score":0.9876999855041504,"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":0.9860000014305115,"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/dynamics","display_name":"Dynamics (music)","score":0.775370717048645},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6759499311447144},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5399671792984009},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.41804319620132446},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37711113691329956},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.25595471262931824}],"concepts":[{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.775370717048645},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6759499311447144},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5399671792984009},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.41804319620132446},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37711113691329956},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.25595471262931824},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01897","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01897","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:2411.16156","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.16156","pdf_url":"https://arxiv.org/pdf/2411.16156","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.2411.16156","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2411.16156","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:2411.16156","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.16156","pdf_url":"https://arxiv.org/pdf/2411.16156","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/G8328019060","display_name":null,"funder_award_id":"62450001","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"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4404987156.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"We":[0],"present":[1],"VideoOrion,":[2],"a":[3,37,43,103],"Video":[4],"Large":[5],"Language":[6],"Model":[7],"(Video-LLM)":[8],"that":[9,70,144],"explicitly":[10],"captures":[11],"the":[12,19,25,56,83,129,153],"key":[13],"semantic":[14,68,113],"information":[15,94],"in":[16,59],"videos":[17],"-":[18],"spatial-temporal":[20,50],"dynamics":[21,35],"of":[22,45,61,121,152],"objects":[23],"throughout":[24],"videos.":[26],"VideoOrion":[27,99,135,145],"employs":[28],"expert":[29],"vision":[30],"models":[31],"to":[32,73,76,81,93,109,136,148],"extract":[33],"object":[34,46,51,119,131,154],"through":[36],"detect-segment-track":[38],"pipeline,":[39],"encoding":[40],"them":[41],"into":[42,67],"set":[44],"tokens":[47,69,89,132],"by":[48],"aggregating":[49,87],"features.":[52],"Our":[53],"method":[54],"addresses":[55],"persistent":[57],"challenge":[58],"Video-LLMs":[60],"efficiently":[62],"compressing":[63],"high-dimensional":[64],"video":[65,85,122,163],"data":[66],"are":[71],"comprehensible":[72],"LLMs.":[74],"Compared":[75],"prior":[77],"methods":[78],"which":[79],"resort":[80],"downsampling":[82],"original":[84],"or":[86],"visual":[88],"using":[90],"resamplers,":[91],"leading":[92],"loss":[95],"and":[96,106,156,166],"entangled":[97],"semantics,":[98],"not":[100],"only":[101],"offers":[102],"more":[104],"natural":[105],"efficient":[107],"way":[108],"derive":[110],"compact,":[111],"disentangled":[112],"representations":[114],"but":[115],"also":[116],"enables":[117],"explicit":[118],"modeling":[120],"content":[123],"with":[124],"minimal":[125],"computational":[126],"cost.":[127],"Moreover,":[128],"introduced":[130],"naturally":[133],"allow":[134],"accomplish":[137],"video-based":[138,167],"referring":[139,168],"tasks.":[140],"Experimental":[141],"results":[142,159],"show":[143],"can":[146],"learn":[147],"make":[149],"good":[150],"use":[151],"tokens,":[155],"achieves":[157],"competitive":[158],"on":[160],"both":[161],"general":[162],"question":[164],"answering":[165],"benchmarks.":[169]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}