{"id":"https://openalex.org/W4413144301","doi":"https://doi.org/10.1109/cvpr52734.2025.01270","title":"Divot: Diffusion Powers Video Tokenizer for Comprehension and Generation","display_name":"Divot: Diffusion Powers Video Tokenizer for Comprehension and Generation","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413144301","doi":"https://doi.org/10.1109/cvpr52734.2025.01270"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.01270","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.01270","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5062830848","display_name":"Yuying Ge","orcid":"https://orcid.org/0000-0001-5818-2589"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuying Ge","raw_affiliation_strings":["ARC Lab, Tencent PCG"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ARC Lab, Tencent PCG","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101457179","display_name":"Yizhuo Li","orcid":"https://orcid.org/0000-0001-5491-1983"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yizhuo Li","raw_affiliation_strings":["ARC Lab, Tencent PCG"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ARC Lab, Tencent PCG","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047802386","display_name":"Yixiao Ge","orcid":"https://orcid.org/0000-0002-5351-5329"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yixiao Ge","raw_affiliation_strings":["ARC Lab, Tencent PCG"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ARC Lab, Tencent PCG","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102004349","display_name":"Ying Shan","orcid":"https://orcid.org/0000-0001-7673-8325"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Shan","raw_affiliation_strings":["ARC Lab, Tencent PCG"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ARC Lab, Tencent PCG","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2250653659"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"13606","last_page":"13617"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9674000144004822,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9674000144004822,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9555000066757202,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.954200029373169,"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/comprehension","display_name":"Comprehension","score":0.715498149394989},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6583447456359863},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.5349477529525757},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1778547763824463},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.10326483845710754}],"concepts":[{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.715498149394989},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6583447456359863},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5349477529525757},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1778547763824463},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.10326483845710754},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52734.2025.01270","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.01270","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"In":[0,76],"recent":[1],"years,":[2],"there":[3],"has":[4,25,123],"been":[5],"a":[6,41,82,100,114,139,169,184],"significant":[7],"surge":[8],"of":[9,54,113,164],"interest":[10,24],"in":[11,39,203],"unifying":[12],"image":[13],"comprehension":[14,193],"and":[15,51,61,128,157,194,209,213],"generation":[16,159,195],"within":[17],"Large":[18],"Language":[19],"Models":[20,212],"(LLMs).":[21],"This":[22],"growing":[23],"prompted":[26],"us":[27],"to":[28,33,56,72],"explore":[29],"extending":[30],"this":[31,77],"unification":[32],"videos.":[34,211],"The":[35,197],"core":[36],"challenge":[37],"lies":[38],"developing":[40],"versatile":[42],"video":[43,70,74,93,101,107,115,133,179,192,204],"tokenizer":[44,116,122],"that":[45,98,176],"captures":[46],"both":[47],"the":[48,62,88,111,118,121,132,148,162],"spatial":[49,127],"characteristics":[50],"temporal":[52,129],"dynamics":[53],"videos":[55,142],"obtain":[57],"representations":[58,63],"for":[59,91],"LLMs,":[60],"can":[64,104],"be":[65],"further":[66],"decoded":[67],"into":[68],"realistic":[69],"clips":[71,108],"enable":[73],"generation.":[75],"work,":[78],"we":[79,151],"introduce":[80],"Divot,":[81],"Diffusion-Powered":[83],"Video":[84],"Tokenizer,":[85],"which":[86],"leverages":[87],"diffusion":[89,102,134],"process":[90],"self-supervised":[92],"representation":[94],"learning.":[95],"We":[96],"posit":[97],"if":[99],"model":[103,135],"effectively":[105],"de-noise":[106],"by":[109,160],"taking":[110],"features":[112,167],"as":[117,138],"condition,":[119],"then":[120],"successfully":[124],"captured":[125],"robust":[126],"information.":[130],"Additionally,":[131],"inherently":[136],"functions":[137],"de-tokenizer,":[140],"decoding":[141],"from":[143],"their":[144],"representations.":[145],"Building":[146],"upon":[147],"Divot":[149,166],"tokenizer,":[150,180],"present":[152],"Divot-LLM":[153,200],"through":[154],"video-to-text":[155],"auto-regression":[156],"text-to-video":[158],"modeling":[161],"distributions":[163],"continuous-valued":[165],"with":[168,183],"Gaussian":[170],"Mixture":[171],"Model.":[172],"Experimental":[173],"results":[174],"demonstrate":[175],"our":[177],"diffusion-based":[178],"when":[181],"integrated":[182],"pre-trained":[185],"LLM,":[186],"achieves":[187],"competitive":[188],"performance":[189],"across":[190],"various":[191],"benchmarks.":[196],"instruction":[198],"tuned":[199],"also":[201],"excels":[202],"storytelling,":[205],"generating":[206],"interleaved":[207],"narratives":[208],"corresponding":[210],"codes":[214],"are":[215],"available":[216],"at":[217],"https://github.com/TencentARC/Divot.":[218]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}