{"id":"https://openalex.org/W4407186796","doi":"https://doi.org/10.48550/arxiv.2502.02492","title":"VideoJAM: Joint Appearance-Motion Representations for Enhanced Motion Generation in Video Models","display_name":"VideoJAM: Joint Appearance-Motion Representations for Enhanced Motion Generation in Video Models","publication_year":2025,"publication_date":"2025-02-04","ids":{"openalex":"https://openalex.org/W4407186796","doi":"https://doi.org/10.48550/arxiv.2502.02492"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2502.02492","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.02492","pdf_url":"https://arxiv.org/pdf/2502.02492","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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/2502.02492","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020794872","display_name":"Hila Chefer","orcid":"https://orcid.org/0000-0003-1585-8782","observed_orcids":["https://orcid.org/0000-0003-1585-8782"]},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Chefer, Hila","raw_affiliation_strings":["Tel Aviv University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tel Aviv University","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079470269","display_name":"Uriel Singer","orcid":"https://orcid.org/0000-0001-8451-8533","observed_orcids":["https://orcid.org/0000-0001-8451-8533"]},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Singer, Uriel","raw_affiliation_strings":["Tel Aviv University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tel Aviv University","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093286191","display_name":"Amit Zohar","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Zohar, Amit","raw_affiliation_strings":["Tel Aviv University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tel Aviv University","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058252245","display_name":"Yuval Kirstain","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Kirstain, Yuval","raw_affiliation_strings":["Tel Aviv University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tel Aviv University","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038017098","display_name":"Adam Polyak","orcid":"https://orcid.org/0000-0003-2563-2111","observed_orcids":["https://orcid.org/0000-0003-2563-2111"]},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Polyak, Adam","raw_affiliation_strings":["Tel Aviv University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tel Aviv University","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070563684","display_name":"Yaniv Taigman","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Taigman, Yaniv","raw_affiliation_strings":["Tel Aviv University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tel Aviv University","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078102229","display_name":"Lior Wolf","orcid":"https://orcid.org/0000-0001-5578-8892","observed_orcids":["https://orcid.org/0000-0001-5578-8892"]},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Wolf, Lior","raw_affiliation_strings":["Tel Aviv University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tel Aviv University","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040159136","display_name":"Shelly Sheynin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Sheynin, Shelly","raw_affiliation_strings":["Tel Aviv University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tel Aviv University","institution_ids":["https://openalex.org/I16391192"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I16391192"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":78,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","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/T11714","display_name":"Multimodal Machine Learning Applications","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/T11105","display_name":"Advanced Image Processing Techniques","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/generative-video-models","display_name":"generative video models","score":0.9340000152587891},{"id":"https://openalex.org/keywords/motion-coherence","display_name":"motion coherence","score":0.8100000023841858},{"id":"https://openalex.org/keywords/motion-priors","display_name":"motion priors","score":0.7310000061988831},{"id":"https://openalex.org/keywords/motion-prediction","display_name":"motion prediction","score":0.597000002861023},{"id":"https://openalex.org/keywords/video-generation","display_name":"video generation","score":0.6499999761581421},{"id":"https://openalex.org/keywords/visual-quality","display_name":"visual quality","score":0.527999997138977}],"concepts":[{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.722273588180542},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.6945548057556152},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5086811184883118},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5069854259490967},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43185630440711975},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.33616504073143005},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09074798226356506},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2502.02492","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.02492","pdf_url":"https://arxiv.org/pdf/2502.02492","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2502.02492","doi":"https://doi.org/10.48550/arxiv.2502.02492","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2502.02492","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2502.02492","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.02492","pdf_url":"https://arxiv.org/pdf/2502.02492","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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/W4407186796.pdf","grobid_xml":"https://content.openalex.org/works/W4407186796.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W3162926177","https://openalex.org/W4281632497","https://openalex.org/W4288099666","https://openalex.org/W4289785095","https://openalex.org/W4303440777","https://openalex.org/W4304697829","https://openalex.org/W4366456807","https://openalex.org/W4383994075","https://openalex.org/W4385848606","https://openalex.org/W4387164994","https://openalex.org/W4387226755","https://openalex.org/W4387560540","https://openalex.org/W4387636037","https://openalex.org/W4389115686","https://openalex.org/W4391212809","https://openalex.org/W4393148423","https://openalex.org/W4404527320","https://openalex.org/W4406052102"],"related_works":["https://openalex.org/W4416780405","https://openalex.org/W4403794718","https://openalex.org/W4388891147","https://openalex.org/W6910562769","https://openalex.org/W7117166626","https://openalex.org/W3024142718","https://openalex.org/W4402961784","https://openalex.org/W4414975318","https://openalex.org/W7084447107","https://openalex.org/W4414809304"],"abstract_inverted_index":{"Despite":[0],"tremendous":[1],"recent":[2],"progress,":[3],"generative":[4],"video":[5,56,131,193],"models":[6,30,159],"still":[7],"struggle":[8],"to":[9,55,62,81,129,139],"capture":[10],"real-world":[11],"motion,":[12],"dynamics,":[13],"and":[14,87,175,189],"physics.":[15],"We":[16],"show":[17],"that":[18,49,103,173],"this":[19],"limitation":[20],"arises":[21],"from":[22,91],"the":[23,35,60,79,84,105,112,140,146,163,168,186,190],"conventional":[24],"pixel":[25],"reconstruction":[26],"objective,":[27],"which":[28],"biases":[29],"toward":[31,107],"appearance":[32,174],"fidelity":[33],"at":[34],"expense":[36],"of":[37,71,145,167,192],"motion":[38,53,90,109,116,153,176],"coherence.":[39],"To":[40],"address":[41],"this,":[42],"we":[43,77,98],"introduce":[44,99],"VideoJAM,":[45],"a":[46,64,92,101,119],"novel":[47],"framework":[48,125],"instills":[50],"an":[51],"effective":[52],"prior":[54],"generators,":[57],"by":[58,110],"encouraging":[59],"model":[61,132],"learn":[63],"joint":[65],"appearance-motion":[66],"representation.":[67,95],"VideoJAM":[68,148],"is":[69],"composed":[70],"two":[72],"complementary":[73,179],"units.":[74],"During":[75,96],"training,":[76],"extend":[78],"objective":[80],"predict":[82],"both":[83,185],"generated":[85],"pixels":[86],"their":[88],"corresponding":[89],"single":[93],"learned":[94],"inference,":[97],"Inner-Guidance,":[100],"mechanism":[102],"steers":[104],"generation":[106],"coherent":[108],"leveraging":[111],"model's":[113],"own":[114],"evolving":[115],"prediction":[117],"as":[118],"dynamic":[120],"guidance":[121],"signal.":[122],"Notably,":[123],"our":[124],"can":[126,177],"be":[127,178],"applied":[128],"any":[130],"with":[133],"minimal":[134],"adaptations,":[135],"requiring":[136],"no":[137],"modifications":[138],"training":[141],"data":[142],"or":[143],"scaling":[144],"model.":[147],"achieves":[149],"state-of-the-art":[150],"performance":[151],"in":[152],"coherence,":[154],"surpassing":[155],"highly":[156],"competitive":[157],"proprietary":[158],"while":[160],"also":[161],"enhancing":[162],"perceived":[164],"visual":[165,187],"quality":[166,188],"generations.":[169],"These":[170],"findings":[171],"emphasize":[172],"and,":[180],"when":[181],"effectively":[182],"integrated,":[183],"enhance":[184],"coherence":[191],"generation.":[194],"Project":[195],"website:":[196],"https://hila-chefer.github.io/videojam-paper.github.io/":[197]},"counts_by_year":[{"year":2026,"cited_by_count":43},{"year":2025,"cited_by_count":35}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-02-06T00:00:00"}