{"id":"https://openalex.org/W4411635563","doi":"https://doi.org/10.1145/3731715.3733417","title":"R <scp>ag</scp> M <scp>e</scp> : Retrieval Augmented Video Generation for Enhanced Motion Realism","display_name":"R <scp>ag</scp> M <scp>e</scp> : Retrieval Augmented Video Generation for Enhanced Motion Realism","publication_year":2025,"publication_date":"2025-06-25","ids":{"openalex":"https://openalex.org/W4411635563","doi":"https://doi.org/10.1145/3731715.3733417"},"language":"en","primary_location":{"id":"doi:10.1145/3731715.3733417","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731715.3733417","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3731715.3733417","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004548591","display_name":"Elia Peruzzo","orcid":"https://orcid.org/0000-0003-0119-3783"},"institutions":[{"id":"https://openalex.org/I193223587","display_name":"University of Trento","ror":"https://ror.org/05trd4x28","country_code":"IT","type":"education","lineage":["https://openalex.org/I193223587"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Elia Peruzzo","raw_affiliation_strings":["University of Trento, Trento, Italy"],"raw_orcid":"https://orcid.org/0000-0003-0119-3783","affiliations":[{"raw_affiliation_string":"University of Trento, Trento, Italy","institution_ids":["https://openalex.org/I193223587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084521327","display_name":"Dejia Xu","orcid":"https://orcid.org/0000-0001-8474-3095"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dejia Xu","raw_affiliation_strings":["University of Texas at Austin, Austin, USA"],"raw_orcid":"https://orcid.org/0000-0001-8474-3095","affiliations":[{"raw_affiliation_string":"University of Texas at Austin, Austin, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046341376","display_name":"Xingqian Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xingqian Xu","raw_affiliation_strings":["Picsart AI Research, Atlanta, USA"],"raw_orcid":"https://orcid.org/0009-0002-7276-5566","affiliations":[{"raw_affiliation_string":"Picsart AI Research, Atlanta, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002072267","display_name":"Humphrey Shi","orcid":"https://orcid.org/0000-0002-2922-5663"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]},{"id":"https://openalex.org/I2800444561","display_name":"Atlanta Technical College","ror":"https://ror.org/01s3vfp47","country_code":"US","type":"education","lineage":["https://openalex.org/I2800444561"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Humphrey Shi","raw_affiliation_strings":["Georgia Tech, Atlanta, USA"],"raw_orcid":"https://orcid.org/0000-0002-2922-5663","affiliations":[{"raw_affiliation_string":"Georgia Tech, Atlanta, USA","institution_ids":["https://openalex.org/I2800444561","https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027171279","display_name":"Nicu Sebe","orcid":"https://orcid.org/0000-0002-6597-7248"},"institutions":[{"id":"https://openalex.org/I193223587","display_name":"University of Trento","ror":"https://ror.org/05trd4x28","country_code":"IT","type":"education","lineage":["https://openalex.org/I193223587"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Nicu Sebe","raw_affiliation_strings":["University of Trento, Trento, Italy"],"raw_orcid":"https://orcid.org/0000-0002-6597-7248","affiliations":[{"raw_affiliation_string":"University of Trento, Trento, Italy","institution_ids":["https://openalex.org/I193223587"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"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":0.1098836,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1081","last_page":"1090"},"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":0.9987999796867371,"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":0.9987999796867371,"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":0.9987000226974487,"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":0.9945999979972839,"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/computer-science","display_name":"Computer science","score":0.5674374103546143},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.4780700206756592},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.24020901322364807}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5674374103546143},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.4780700206756592},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.24020901322364807}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3731715.3733417","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731715.3733417","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:iris.unitn.it:11572/462231","is_oa":false,"landing_page_url":"https://hdl.handle.net/11572/462231","pdf_url":null,"source":{"id":"https://openalex.org/S4306401913","display_name":"Institutional Research Information System (Universit\u00e0 degli Studi di Trento)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I193223587","host_organization_name":"University of Trento","host_organization_lineage":["https://openalex.org/I193223587"],"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":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.1145/3731715.3733417","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731715.3733417","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W3027879771","https://openalex.org/W4285606530","https://openalex.org/W4286980377","https://openalex.org/W4304014690","https://openalex.org/W4312933868","https://openalex.org/W4377864624","https://openalex.org/W4386071957","https://openalex.org/W4386072096","https://openalex.org/W4388778348","https://openalex.org/W4389539288","https://openalex.org/W4390871980","https://openalex.org/W4390874580","https://openalex.org/W4402660110","https://openalex.org/W4402702984","https://openalex.org/W4402713100","https://openalex.org/W4404966213","https://openalex.org/W6801986474","https://openalex.org/W6930322006"],"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":{"Video":[0],"generation":[1,123],"is":[2,144],"experiencing":[3],"a":[4,89,102,118,154],"rapid":[5],"growth,":[6],"driven":[7],"by":[8],"advances":[9],"in":[10,57,66,98],"diffusion":[11,151],"models":[12],"and":[13,18,33,48,71,177,180],"the":[14,29,34,37,60,94,108,115,122,133,139,158,166,186],"development":[15],"of":[16,36,68,96,107,117,137,168,185],"better":[17],"larger":[19],"datasets.":[20],"However,":[21],"producing":[22],"high-quality":[23],"videos":[24,62,127],"remains":[25],"challenging,":[26],"due":[27],"to":[28,105,146,148],"high":[30],"dimensional":[31],"data":[32],"complexity":[35,70],"task.":[38],"Recent":[39],"efforts":[40],"have":[41],"primarily":[42],"focused":[43],"on":[44,157],"enhancing":[45],"visual":[46],"quality":[47],"addressing":[49],"temporal":[50],"inconsistencies,":[51],"such":[52],"as":[53,129],"flickering.":[54],"Despite":[55],"progress":[56],"these":[58],"areas,":[59],"generated":[61,99],"often":[63],"fall":[64],"short":[65],"terms":[67],"motion":[69,97],"physical":[72],"plausibility,":[73],"with":[74,135,161],"many":[75],"outputs":[76],"either":[77],"appearing":[78],"static":[79],"or":[80],"exhibiting":[81],"unrealistic":[82],"motion.":[83],"In":[84],"this":[85],"work,":[86],"we":[87,112,181],"propose":[88],"framework":[90],"aimed":[91],"at":[92],"improving":[93],"realism":[95],"videos,":[100],"exploring":[101],"complementary":[103],"direction":[104],"much":[106],"existing":[109],"literature.":[110],"Specifically,":[111],"advocate":[113],"for":[114],"incorporation":[116],"retrieval":[119],"mechanism":[120],"during":[121],"phase.":[124],"The":[125],"retrieved":[126,159],"act":[128],"grounding":[130],"signals,":[131],"providing":[132],"model":[134,156],"demonstrations":[136],"how":[138],"objects":[140],"move.":[141],"Our":[142],"pipeline":[143],"designed":[145],"apply":[147],"any":[149],"text-to-video":[150],"model,":[152],"conditioning":[153],"pre-trained":[155],"samples":[160],"minimal":[162],"fine-tuning.":[163],"We":[164],"demonstrate":[165],"superiority":[167],"our":[169],"approach":[170],"through":[171],"established":[172],"metrics,":[173],"recently":[174],"proposed":[175],"benchmarks,":[176],"qualitative":[178],"results,":[179],"highlight":[182],"additional":[183],"applications":[184],"framework.":[187],"Code":[188],"available":[189],"at:":[190],"https://github.com/helia95/ragme.":[191]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}